{"meta":{"query_hash":"532ca883ae4d","filters":{"topic":"Machine Learning and Data Classification"},"cohort_total":559,"direct_labels_cover":1,"predictions_cover":559,"exported":559,"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/532ca883ae4d","api":"https://metacan.xera.ac/api/v1/cohort?topic=Machine+Learning+and+Data+Classification"},"results":[{"id":"W100047375","doi":"10.1007/978-3-642-34413-8_5","title":"Parallel Algorithm Configuration","year":2012,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":74,"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 British Columbia","funders":"","keywords":"Computer science; Solver; Variety (cybernetics); State space; Algorithm; Parallel algorithm; State (computer science); Scale (ratio); Parallel computing; Theoretical computer science; Artificial intelligence; Programming language; Mathematics","score_opus":0.02042844678248977,"score_gpt":0.25912248163027274,"score_spread":0.23869403484778295,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W100047375","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":[0.0000019154322,0.00068901194,0.9883183,0.0012617771,0.0013307396,0.00023985951,0.0000050340973,0.00021633114,0.007937028],"genre_scores_gemma":[0.021857567,0.000123265,0.9747274,0.0011525345,0.0009054587,0.000012520024,0.00006475935,0.00003082222,0.0011256802],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99705696,0.00004690209,0.00042114104,0.0011205504,0.0008149396,0.0005394864],"domain_scores_gemma":[0.99762964,0.00025733325,0.00031399212,0.0014441316,0.000174322,0.00018057616],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00094579504,0.0003898332,0.00033795717,0.0005364028,0.00024644283,0.00053419056,0.0023707638,0.00028428723,0.00005604619],"category_scores_gemma":[0.00007613689,0.00035532838,0.00008082227,0.00036298617,0.00033429806,0.00093987986,0.0005971223,0.00077921996,0.00030290568],"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":[0.0000010667892,0.000014232603,0.00002325868,0.0000095489795,0.0000036098916,0.000007809319,0.0002325829,0.0023916312,0.000043133485,0.05037479,0.000031877895,0.94686645],"study_design_scores_gemma":[0.00023317036,0.00009214827,0.00070626003,0.0001248362,0.000008039309,0.000062143605,8.7414634e-8,0.89579475,0.0002763651,0.072112344,0.029921027,0.00066885445],"about_ca_topic_score_codex":0.000026852838,"about_ca_topic_score_gemma":0.000016261938,"teacher_disagreement_score":0.9461976,"about_ca_system_score_codex":0.0001822672,"about_ca_system_score_gemma":0.00030833308,"threshold_uncertainty_score":0.99988985},"labels":[],"label_agreement":null},{"id":"W114730584","doi":"","title":"An Efficient Approach for Assessing Hyperparameter Importance","year":2014,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":314,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Hyperparameter; Computer science; Hyperparameter optimization; Machine learning; Leverage (statistics); Bayesian optimization; Artificial intelligence; Random forest; Bayesian probability; Support vector machine","score_opus":0.025866910082388676,"score_gpt":0.2989415350621249,"score_spread":0.2730746249797362,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W114730584","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":[0.016587554,0.000006838259,0.9647276,0.00022314704,0.000069815535,0.0001010868,5.2914146e-7,0.00021116191,0.018072287],"genre_scores_gemma":[0.54591817,1.1531345e-7,0.45373267,0.00020703435,0.00003428168,0.000013928372,0.000019798668,0.0000033767062,0.00007062266],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991658,0.000062858155,0.00012731452,0.00036561055,0.00012025538,0.00015819454],"domain_scores_gemma":[0.9990749,0.00008511083,0.000063363135,0.0006731731,0.00004007076,0.00006339457],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006258399,0.0000721844,0.00008166577,0.000040926217,0.0001208108,0.00032339786,0.00049630145,0.00003201737,0.00000390051],"category_scores_gemma":[0.00008978233,0.000056494773,0.000028523127,0.00011330835,0.000014973508,0.00030278048,0.000036547266,0.00006123591,0.000007503562],"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":[0.000005244368,0.0003608505,0.014067409,0.00004111994,0.0000073319884,2.2627246e-7,0.00024949393,0.022223074,0.0026889306,0.5141896,0.0017988122,0.44436792],"study_design_scores_gemma":[0.00011866023,0.000034584446,0.0069666123,0.0000012946064,0.0000018698238,0.000002431863,0.000012971698,0.9871507,0.00013288771,0.00025915453,0.005226442,0.000092341914],"about_ca_topic_score_codex":0.000006570181,"about_ca_topic_score_gemma":4.3614963e-7,"teacher_disagreement_score":0.9649277,"about_ca_system_score_codex":0.000011149193,"about_ca_system_score_gemma":0.00001560333,"threshold_uncertainty_score":0.31185332},"labels":[],"label_agreement":null},{"id":"W133090141","doi":"10.1007/978-3-642-40261-6_23","title":"A Novel Border Identification Algorithm Based on an “Anti-Bayesian” Paradigm","year":2013,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Computer science; Cardinality (data modeling); Identification (biology); Set (abstract data type); Artificial intelligence; Algorithm; Bayesian probability; Position (finance); Field (mathematics); Discriminant; Pattern recognition (psychology); Machine learning; Data mining; Mathematics","score_opus":0.015918963066963825,"score_gpt":0.27286589164829916,"score_spread":0.25694692858133533,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W133090141","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":[0.000025300633,0.00004510989,0.9941994,0.002004568,0.0011645348,0.00046685492,0.000014667862,0.00029790774,0.0017816796],"genre_scores_gemma":[0.12861583,0.000017381397,0.8674688,0.0024577524,0.0005052108,0.000040596766,0.00015748468,0.00006143552,0.0006755192],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9953778,0.00007122497,0.000607664,0.0021413087,0.0012198786,0.0005821399],"domain_scores_gemma":[0.99589103,0.00034153266,0.00047317529,0.0028312926,0.00022398021,0.00023895832],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0011443238,0.00055480836,0.00043055063,0.0010228731,0.000365141,0.0013162531,0.0036351632,0.00034816194,0.00006431312],"category_scores_gemma":[0.00010181685,0.0005103011,0.00009603176,0.0006877392,0.00038637914,0.0011193008,0.0003695456,0.00090658484,0.00023090499],"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":[0.0000019792847,0.00009077233,0.000028412447,0.000019085242,0.0000038728167,0.0000065338504,0.000116561714,0.047672406,0.000244175,0.014074122,0.000025282457,0.9377168],"study_design_scores_gemma":[0.0002537471,0.00019123226,0.0022844917,0.00016219956,0.000006565843,0.000021591724,5.9232278e-8,0.98113066,0.00035563856,0.012185269,0.0028256588,0.00058288453],"about_ca_topic_score_codex":0.0000715507,"about_ca_topic_score_gemma":0.000017207107,"teacher_disagreement_score":0.9371339,"about_ca_system_score_codex":0.00022317487,"about_ca_system_score_gemma":0.000489414,"threshold_uncertainty_score":0.9997349},"labels":[],"label_agreement":null},{"id":"W138034719","doi":"","title":"Constructing new and better evaluation measures for machine learning","year":2007,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":38,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University; University of Ottawa","funders":"","keywords":"Computer science; Machine learning; Artificial intelligence; Measure (data warehouse); Construct (python library); Artificial neural network; Greedy algorithm; Mean squared error; Data mining; Algorithm; Mathematics","score_opus":0.04615306708286241,"score_gpt":0.31401666680242446,"score_spread":0.26786359971956203,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W138034719","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":[0.00821802,0.00012510917,0.9840258,0.0028845137,0.00009053011,0.00013784849,4.2011916e-7,0.00012097211,0.004396837],"genre_scores_gemma":[0.69869536,0.0000031086274,0.3002826,0.00033453098,0.00010475175,0.0000036400984,0.000026272348,0.000005012618,0.00054475246],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99926037,0.000049764505,0.00013635475,0.00022368552,0.00019477234,0.00013508118],"domain_scores_gemma":[0.99942327,0.00021811997,0.00007053569,0.00015028537,0.00007693766,0.000060845054],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019426383,0.0000622315,0.00006309541,0.00006900593,0.00013398615,0.00011702504,0.00013372426,0.000030789204,0.00001652117],"category_scores_gemma":[0.00049269054,0.00005355402,0.000015949161,0.000097269694,0.000014257632,0.00032945606,0.0000468445,0.00009969679,0.000005238767],"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":[0.0000033297124,0.0000025864783,0.02248413,0.0000034514742,0.0000037176248,1.0854322e-7,0.00010392996,0.000019680376,0.0004968246,0.034721717,0.00019966057,0.9419609],"study_design_scores_gemma":[0.0007968988,0.000068307796,0.024434658,0.0000100579,0.000015219112,0.000022689348,0.0001086173,0.92538595,0.0016477671,0.0050810096,0.042258263,0.00017058973],"about_ca_topic_score_codex":0.00010913132,"about_ca_topic_score_gemma":0.000091942755,"teacher_disagreement_score":0.9417903,"about_ca_system_score_codex":0.000021479276,"about_ca_system_score_gemma":0.000032064498,"threshold_uncertainty_score":0.21838696},"labels":[],"label_agreement":null},{"id":"W14214433","doi":"","title":"A fast decision tree learning algorithm","year":2006,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":162,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Computer science; Decision tree; Algorithm; Speedup; Incremental decision tree; Naive Bayes classifier; Tree (set theory); Time complexity; ID3 algorithm; Benchmark (surveying); Machine learning; Artificial intelligence; Decision tree learning; Mathematics","score_opus":0.006777359616075056,"score_gpt":0.23589823220158543,"score_spread":0.22912087258551037,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W14214433","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":[0.0010126181,0.0000373958,0.9508733,0.0005629238,0.0000906634,0.000030900424,4.0412118e-7,0.00035363666,0.047038116],"genre_scores_gemma":[0.26638103,0.0000043624686,0.7216412,0.000096469856,0.00012013389,0.0000050108756,0.00003194531,0.0000067324977,0.011713128],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992128,0.000045497243,0.00013435562,0.00026605226,0.00019709642,0.00014421048],"domain_scores_gemma":[0.99946606,0.000090926405,0.000047894217,0.00032721047,0.000032665783,0.000035213856],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021484148,0.000070682305,0.00006579442,0.000077864745,0.0001312057,0.00017866022,0.00039404535,0.000032780405,0.000040213486],"category_scores_gemma":[0.000042413325,0.000057767862,0.000029092946,0.0002523641,0.000011218973,0.0002966454,0.00010727625,0.00013244776,0.00037715357],"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":[5.848904e-7,0.000019034911,0.0012716075,6.3076783e-7,7.7106785e-7,0.0000021698643,0.000019689303,0.00040035642,0.00015570891,0.028896367,0.0037547115,0.96547836],"study_design_scores_gemma":[0.00017972641,0.000035612862,0.03925005,0.0000051058905,0.0000012239879,0.000011160713,0.00001076019,0.8599198,0.00015336472,0.003351898,0.09697396,0.00010733016],"about_ca_topic_score_codex":0.00023227006,"about_ca_topic_score_gemma":0.00003532636,"teacher_disagreement_score":0.965371,"about_ca_system_score_codex":0.000017153581,"about_ca_system_score_gemma":0.000017885268,"threshold_uncertainty_score":0.4847672},"labels":[],"label_agreement":null},{"id":"W1437335841","doi":"10.1088/1749-4699/8/1/014008","title":"Hyperopt: a Python library for model selection and hyperparameter optimization","year":2015,"lang":"en","type":"article","venue":"Computational Science & Discovery","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":1041,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Rowland Institute at Harvard; Office of the Director; National Science Foundation","keywords":"Bayesian optimization; MNIST database; Computer science; Hyperparameter; Python (programming language); Machine learning; Hyperparameter optimization; Artificial intelligence; Model selection; Algorithm; Support vector machine; Deep learning; Programming language","score_opus":0.03402540472736977,"score_gpt":0.2792169580267524,"score_spread":0.24519155329938264,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1437335841","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":[0.028158434,0.000042164735,0.96923524,0.0015362022,0.00013583469,0.00016434083,0.000010385128,0.00016179943,0.00055560895],"genre_scores_gemma":[0.53777665,0.0000032023931,0.4616437,0.00031460752,0.00003614231,0.00001777911,0.000050183196,0.0000061850124,0.00015155788],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99873877,0.000032486143,0.0001615585,0.0004905974,0.00038364992,0.00019296503],"domain_scores_gemma":[0.99932027,0.00010701026,0.00008886812,0.00017043002,0.00014323255,0.00017019451],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00044365512,0.00009921597,0.0000892916,0.00017191992,0.0002817079,0.00093866786,0.0004203226,0.00003207243,0.0000012718828],"category_scores_gemma":[0.00027038078,0.000089579735,0.000024180783,0.0006191306,0.00012724017,0.0057600555,0.00018456891,0.00006773999,0.0000046965647],"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":[0.0000101663,0.000026150303,0.0005576409,0.000004068712,0.0000014960009,1.2416294e-7,0.00013824,0.911079,0.00011120313,0.08171629,0.000517221,0.005838435],"study_design_scores_gemma":[0.00024500865,0.00006921262,0.0015686813,0.0000065015233,0.000003358917,0.000012056534,0.000016001151,0.9729728,0.000076714845,0.024493812,0.00041555805,0.00012028461],"about_ca_topic_score_codex":0.0000046916575,"about_ca_topic_score_gemma":5.146525e-7,"teacher_disagreement_score":0.5096182,"about_ca_system_score_codex":0.00004855394,"about_ca_system_score_gemma":0.000628821,"threshold_uncertainty_score":0.9051596},"labels":[],"label_agreement":null},{"id":"W1471542436","doi":"10.1016/j.artint.2016.04.003","title":"ASlib: A benchmark library for algorithm selection","year":2016,"lang":"en","type":"article","venue":"Artificial Intelligence","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":213,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Deutsche Forschungsgemeinschaft; Microsoft","keywords":"Computer science; Selection (genetic algorithm); Benchmark (surveying); Exploit; Task (project management); Set (abstract data type); Variety (cybernetics); Data mining; Selection algorithm; Range (aeronautics); Algorithm; Machine learning; Artificial intelligence","score_opus":0.03557090669313157,"score_gpt":0.2896685730587838,"score_spread":0.25409766636565223,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1471542436","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":[0.00044737195,0.00002938727,0.99184793,0.0058845244,0.00036812163,0.0001658798,0.000013701611,0.0004050903,0.00083799567],"genre_scores_gemma":[0.5623511,0.000055587003,0.4345994,0.00048638158,0.0005113457,0.000110128436,0.000030273088,0.000025659905,0.0018301213],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989007,0.00005807035,0.00025066326,0.00040951683,0.00013970886,0.00024130863],"domain_scores_gemma":[0.9991292,0.00030362158,0.000089393216,0.00034090734,0.000059872014,0.00007701524],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025150017,0.000103176346,0.00008998041,0.00009371611,0.00016738655,0.00017523777,0.0005738222,0.00005737556,0.00009852841],"category_scores_gemma":[0.00018132811,0.00007481756,0.00005431535,0.0003639259,0.000041376003,0.0010159276,0.00009440875,0.00006722178,0.00031740163],"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":[0.0000054190177,0.00001888919,0.00010103071,0.0000023921834,0.0000030929175,3.6359455e-7,0.00005350524,0.000005301852,0.0024094472,0.25131747,0.0013626167,0.74472046],"study_design_scores_gemma":[0.00004508579,0.00026516162,0.0006474656,0.000038482416,0.000006659929,0.000010697849,0.000030850246,0.39547384,0.18033926,0.27782172,0.14498769,0.00033308775],"about_ca_topic_score_codex":0.000013045817,"about_ca_topic_score_gemma":0.000006431769,"teacher_disagreement_score":0.7443874,"about_ca_system_score_codex":0.000019475341,"about_ca_system_score_gemma":0.000060299928,"threshold_uncertainty_score":0.40796617},"labels":[],"label_agreement":null},{"id":"W1479807131","doi":"10.7551/mitpress/9780262033589.001.0001","title":"Semi-Supervised Learning","year":2006,"lang":"en","type":"book","venue":"The MIT Press eBooks","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":4308,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Mitacs","keywords":"Computer science; Artificial intelligence; Machine learning; Benchmark (surveying); Field (mathematics); Unsupervised learning; Semi-supervised learning; Graph; Taxonomy (biology); Theoretical computer science; Mathematics","score_opus":0.02696831639417286,"score_gpt":0.24172548049105133,"score_spread":0.21475716409687848,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1479807131","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":[0.0000035681426,0.0005487378,0.06157424,0.00017727443,0.00022115573,0.00024390887,0.000008017809,0.000511959,0.93671113],"genre_scores_gemma":[0.00062357995,0.000012414492,0.00090120226,0.00016731278,0.00041564996,0.000039037797,0.00013882699,0.00004184061,0.99766016],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99812585,0.0002747699,0.00030486376,0.0005548203,0.00043123108,0.000308445],"domain_scores_gemma":[0.9978231,0.000242564,0.0002812413,0.0015224023,0.000068845264,0.000061823506],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047771397,0.00030685772,0.00026560432,0.00007290439,0.00033101803,0.00039713885,0.0023012813,0.00022838822,0.000010685031],"category_scores_gemma":[0.000041209132,0.00022271718,0.00012795503,0.00001860897,0.00009457339,0.00009682404,0.00061221764,0.0011260795,0.0001372754],"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":[0.000011014773,0.00002298664,0.000010905628,0.00014308278,0.000103463346,0.000021819991,0.001306182,0.0009333083,0.00012165557,0.4201052,0.38559994,0.19162045],"study_design_scores_gemma":[0.00013941125,0.000026691154,0.00003722912,0.00007406889,0.000036741032,0.000010268473,0.0000013492555,0.027102819,0.000047617174,0.00287465,0.96938014,0.00026903313],"about_ca_topic_score_codex":0.00021443822,"about_ca_topic_score_gemma":0.000011292586,"teacher_disagreement_score":0.58378017,"about_ca_system_score_codex":0.00006220192,"about_ca_system_score_gemma":0.00014371723,"threshold_uncertainty_score":0.90821433},"labels":[],"label_agreement":null},{"id":"W1485129084","doi":"10.1109/iat.2004.71","title":"Improving modeling of other agents using tentative stereotypes and compactification of observations","year":2004,"lang":"en","type":"article","venue":"IEEE/WIC/ACM International Conference on Intelligent Agent Technology","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Compactification (mathematics); Stereotype (UML); Computer science; k-nearest neighbors algorithm; Econometrics; Social psychology; Artificial intelligence; Psychology; Mathematics","score_opus":0.19175290214898139,"score_gpt":0.3643906421290424,"score_spread":0.172637739980061,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1485129084","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":[0.35819474,0.000026775404,0.63928443,0.0016752928,0.00027830468,0.0001595324,0.000020664149,0.000075989956,0.00028426576],"genre_scores_gemma":[0.948365,0.000058334826,0.051401995,0.000066430104,0.000019631327,0.000014456524,0.000023227713,0.000010617904,0.000040306688],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984977,0.00004740164,0.0005401127,0.00042671623,0.00032494805,0.00016310629],"domain_scores_gemma":[0.99829847,0.00005651595,0.0005068316,0.0006070826,0.00048803937,0.000043046402],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021829514,0.00016883879,0.00021483593,0.0005807852,0.00008074561,0.000056639296,0.0011015622,0.00011810891,0.000027199292],"category_scores_gemma":[0.00025019594,0.00016377287,0.000050005612,0.00034674842,0.00015051114,0.0003136032,0.00021639519,0.00022107313,0.000011188388],"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":[0.000042560143,0.00031656117,0.0049733324,0.00003842867,0.00012253661,0.00000216878,0.0012136912,0.026104668,0.116047256,0.8097863,0.000012127383,0.041340344],"study_design_scores_gemma":[0.00033756497,0.0001655511,0.001332451,0.0001821808,0.000018730476,0.000009489993,0.0006115505,0.9082211,0.06444363,0.024392173,0.0000930362,0.00019250507],"about_ca_topic_score_codex":0.00044908008,"about_ca_topic_score_gemma":0.000026048448,"teacher_disagreement_score":0.88211644,"about_ca_system_score_codex":0.00012428805,"about_ca_system_score_gemma":0.00010303317,"threshold_uncertainty_score":0.6678464},"labels":[],"label_agreement":null},{"id":"W1488125285","doi":"10.1017/cbo9780511921803.013","title":"Two Case Studies","year":2011,"lang":"en","type":"other","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science","score_opus":0.06316710887995561,"score_gpt":0.3412493820496664,"score_spread":0.2780822731697108,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1488125285","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":[3.4955303e-7,0.00090582384,0.116184354,0.00011530181,0.0003164261,0.00004811475,0.0000021561689,0.0005933804,0.8818341],"genre_scores_gemma":[0.0002384523,0.000121915655,0.06646125,0.00013355946,0.00012234153,0.0000071944514,0.0000059617955,0.00005103795,0.9328583],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99945474,0.000040103056,0.00007421304,0.00026999105,0.0000704734,0.000090489746],"domain_scores_gemma":[0.9991673,0.000021348656,0.0000819576,0.000682573,0.000015657604,0.000031114316],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00009731731,0.00010327084,0.0001175022,0.000107783686,0.000031019157,0.00003271719,0.0003703024,0.0000463354,0.00084568025],"category_scores_gemma":[0.000028277245,0.00007579784,0.000022064656,0.00008137469,0.000022779306,0.000047559406,0.00018245364,0.00009358266,0.0014444898],"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":[1.0566431e-7,0.000007689374,0.0000144660125,0.000013318067,0.000022754897,0.00021916235,0.00008943108,6.052564e-8,3.6084896e-7,0.140892,0.82759833,0.03114231],"study_design_scores_gemma":[0.000068290334,0.000011382308,0.00000466308,0.00001843102,0.0000058685973,0.00040733404,0.000023433562,0.00042298404,0.0000028405466,0.0004466501,0.9984616,0.00012653664],"about_ca_topic_score_codex":0.0008008182,"about_ca_topic_score_gemma":0.00043921507,"teacher_disagreement_score":0.17086324,"about_ca_system_score_codex":0.000007024777,"about_ca_system_score_gemma":0.000014444146,"threshold_uncertainty_score":0.999333},"labels":[],"label_agreement":null},{"id":"W1496427819","doi":"10.1007/978-3-540-87481-2_43","title":"A Visualization-Based Exploratory Technique for Classifier Comparison with Respect to Multiple Metrics and Multiple Domains","year":2008,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Classifier (UML); Multitude; Machine learning; Artificial intelligence; Visualization; Data mining; Pattern recognition (psychology)","score_opus":0.03964815951718529,"score_gpt":0.2956787907324393,"score_spread":0.256030631215254,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1496427819","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":[0.00012351987,0.00018988196,0.9970056,0.0005825503,0.00026805737,0.0013939717,0.000024154508,0.00022967544,0.00018260117],"genre_scores_gemma":[0.3089498,0.000018175191,0.68978065,0.0008663158,0.00013490398,0.00010581395,0.000043714666,0.00004459802,0.000056015142],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99643993,0.00007468325,0.0005111357,0.0016458757,0.00082800764,0.00050034706],"domain_scores_gemma":[0.99587035,0.001837554,0.00036039445,0.0012763712,0.00040751178,0.0002478161],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009476901,0.0004897653,0.0005424591,0.001583209,0.00048850843,0.0004307784,0.0015991998,0.00028095796,0.0000019638253],"category_scores_gemma":[0.0007391008,0.00042253584,0.00006782796,0.001325774,0.00042900007,0.00042089337,0.0004561196,0.00052710134,0.0000068096947],"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":[0.0004545639,0.0005381315,0.026613655,0.0005201751,0.00007440159,0.00012311275,0.0069760303,0.30677497,0.004778489,0.027123095,0.0015081703,0.6245152],"study_design_scores_gemma":[0.0007373798,0.00060486374,0.0006467382,0.00026434293,0.000009222294,0.000021571623,8.6804516e-7,0.9768037,0.003966965,0.0013193313,0.014947134,0.0006778603],"about_ca_topic_score_codex":0.000025414423,"about_ca_topic_score_gemma":0.00024626,"teacher_disagreement_score":0.67002875,"about_ca_system_score_codex":0.00026890016,"about_ca_system_score_gemma":0.00058921135,"threshold_uncertainty_score":0.9998226},"labels":[],"label_agreement":null},{"id":"W1504509715","doi":"10.1007/11527770_63","title":"On Understanding and Assessing Feature Selection Bias","year":2005,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Machine Learning and Data Classification","field":"Computer Science","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":"National Research Council Canada; National Research Council Institute for Biodiagnostics","funders":"","keywords":"Feature selection; Selection (genetic algorithm); Computer science; Feature (linguistics); Artificial intelligence; Linguistics; Philosophy","score_opus":0.054350748821586546,"score_gpt":0.2900000794928637,"score_spread":0.23564933067127716,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1504509715","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":[0.000087505745,0.00019094329,0.98876494,0.0029701411,0.0005937722,0.00015719347,0.0000015467721,0.00019291238,0.007041044],"genre_scores_gemma":[0.5784396,0.000081374616,0.41786394,0.001896854,0.0006990275,0.0000041982194,0.000015947959,0.000041513435,0.0009575363],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997346,0.000051854982,0.00024677697,0.0012790511,0.00068536267,0.00039097067],"domain_scores_gemma":[0.9983019,0.0005768786,0.00025734442,0.000667292,0.00007591669,0.00012063088],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0008704478,0.0003675552,0.0002906097,0.0008132001,0.00045358005,0.0013646939,0.001020384,0.00029614122,0.000009319571],"category_scores_gemma":[0.00016077209,0.00032787607,0.00004973708,0.0005024001,0.00026976693,0.0008326453,0.00040646113,0.0011114725,0.000016931692],"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":[0.0000035638716,0.000014644982,0.00015989455,0.000023132543,0.000005641352,0.000011349813,0.000265537,0.013242257,0.00009408049,0.22709219,0.00007431979,0.7590134],"study_design_scores_gemma":[0.00019978397,0.00014203276,0.000807894,0.00041498776,0.0000067670735,0.000093097486,3.5033548e-7,0.8492833,0.00014005313,0.14537251,0.0030263993,0.00051283016],"about_ca_topic_score_codex":0.00000939994,"about_ca_topic_score_gemma":0.000053945016,"teacher_disagreement_score":0.83604103,"about_ca_system_score_codex":0.00054229994,"about_ca_system_score_gemma":0.0002474305,"threshold_uncertainty_score":0.9999173},"labels":[],"label_agreement":null},{"id":"W1510552458","doi":"10.1109/icsmc.2002.1175674","title":"Creative prototype reduction schemes: a taxonomy and ranking","year":2003,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"sort; Computer science; Reduction (mathematics); Taxonomy (biology); Ranking (information retrieval); Data reduction; Artificial intelligence; Class (philosophy); Data mining; Machine learning; Classification scheme; Information retrieval; Mathematics","score_opus":0.03177822263767262,"score_gpt":0.2586923945165637,"score_spread":0.22691417187889107,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1510552458","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":[0.0060798493,0.000055603145,0.92395556,0.0003894471,0.00005356831,0.00032823952,1.4854187e-7,0.00012919551,0.06900842],"genre_scores_gemma":[0.781526,0.00000939262,0.21709956,0.000045252837,0.000017897617,0.00011420515,0.0000023904686,0.0000027671033,0.0011825134],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9995018,0.00006723468,0.000074168245,0.00021120613,0.000066132176,0.00007946245],"domain_scores_gemma":[0.9996764,0.000014974557,0.000039108203,0.00020774567,0.000030683696,0.000031055803],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000222852,0.000051583775,0.000049419617,0.000043134358,0.00009326613,0.00009528267,0.000097038486,0.000021465532,0.000034897475],"category_scores_gemma":[0.00008306079,0.000042671985,0.000009045889,0.00014789785,0.000019621659,0.0003412008,0.000024138635,0.00006848919,0.000022034017],"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":[0.000006224007,0.000030601528,0.00230653,0.000012067613,0.000008428881,6.0471484e-7,0.000324697,0.0000061826872,0.001316199,0.85441864,0.00045397453,0.14111587],"study_design_scores_gemma":[0.0007757676,0.00022689541,0.0076714065,0.000035496105,0.00000841811,0.00010063324,0.00033016765,0.0335987,0.010883182,0.0070865597,0.9389225,0.00036023973],"about_ca_topic_score_codex":0.000023611492,"about_ca_topic_score_gemma":8.292039e-7,"teacher_disagreement_score":0.9384686,"about_ca_system_score_codex":0.000010575326,"about_ca_system_score_gemma":0.000026828691,"threshold_uncertainty_score":0.1740113},"labels":[],"label_agreement":null},{"id":"W1513988862","doi":"10.1007/978-3-642-13672-6_45","title":"Supervised Learning with Minimal Effort","year":2010,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Machine Learning and Data Classification","field":"Computer Science","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":"Western University","funders":"","keywords":"Computer science; Simple (philosophy); Artificial intelligence; Exploit; Machine learning; Process (computing); Instance-based learning; Supervised learning; Active learning (machine learning); Artificial neural network","score_opus":0.0123272612070977,"score_gpt":0.23582155513398081,"score_spread":0.2234942939268831,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1513988862","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":[0.0005851623,0.000090801695,0.98983544,0.0009946726,0.0006715334,0.0002376044,0.0000018985216,0.00029790736,0.0072849845],"genre_scores_gemma":[0.2555539,0.0000227741,0.7418968,0.00069477403,0.0005059781,0.000011500918,0.000036325007,0.00005214538,0.0012258084],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99639714,0.000033713397,0.00038138518,0.0015984477,0.0009944594,0.00059485337],"domain_scores_gemma":[0.9975,0.00030910072,0.00027780814,0.0015092664,0.00020940433,0.00019443064],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009207889,0.00048780697,0.00042535618,0.00065729214,0.00041357675,0.0007204031,0.003088766,0.0003543851,0.000042830867],"category_scores_gemma":[0.00010791409,0.0003932196,0.0000789639,0.00051252707,0.00062379224,0.0006308921,0.0008570589,0.0022298137,0.00009278903],"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":[0.000016789973,0.000031840107,0.0018891218,0.000045155342,0.000011869206,0.00009419725,0.00080753566,0.010585335,0.000939273,0.019058885,0.000008628867,0.96651137],"study_design_scores_gemma":[0.00067888305,0.0007275611,0.0037615886,0.0004086414,0.000017629365,0.00026396278,3.508573e-7,0.9437873,0.0017373948,0.017829515,0.029371614,0.0014155923],"about_ca_topic_score_codex":0.000032112428,"about_ca_topic_score_gemma":0.000109618864,"teacher_disagreement_score":0.96509576,"about_ca_system_score_codex":0.00010445714,"about_ca_system_score_gemma":0.00053352653,"threshold_uncertainty_score":0.99985194},"labels":[],"label_agreement":null},{"id":"W1518470882","doi":"10.1007/978-3-642-15552-9_42","title":"Optimizing Complex Loss Functions in Structured Prediction","year":2010,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Segmentation; Solver; Piecewise linear function; Artificial intelligence; Piecewise; Algorithm; Simple (philosophy); Image segmentation; Pattern recognition (psychology); Mathematical optimization; Mathematics","score_opus":0.02164440741970232,"score_gpt":0.2540126322396124,"score_spread":0.2323682248199101,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1518470882","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":[0.00020884295,0.000089832705,0.99269146,0.0011463948,0.002244776,0.00031269673,0.00002418139,0.0002525969,0.0030292384],"genre_scores_gemma":[0.38015538,0.000023873048,0.6180179,0.00061758613,0.00062682456,0.000015262849,0.0001351143,0.000038067916,0.00036997482],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9965051,0.000054231466,0.00057259353,0.0015461766,0.00077838294,0.000543526],"domain_scores_gemma":[0.99748427,0.00027219034,0.00030968254,0.0016124469,0.00016977383,0.0001516268],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008413621,0.00043929718,0.0004090863,0.001176276,0.00035035392,0.0005760556,0.0024279903,0.0004451593,0.000059287577],"category_scores_gemma":[0.00013611553,0.00042098717,0.000087138724,0.0007736565,0.0005290717,0.000758113,0.00081849913,0.0019346357,0.00004736987],"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":[0.000013910016,0.000057718575,0.0016699344,0.00005362577,0.000012083878,0.00006606994,0.0014054425,0.12815548,0.0031088802,0.026019212,0.000047200974,0.83939046],"study_design_scores_gemma":[0.00041017297,0.000109377914,0.009398947,0.0001821514,0.0000072022394,0.000104977895,3.3457724e-7,0.9343295,0.00027609858,0.0453418,0.009253235,0.000586183],"about_ca_topic_score_codex":0.00006255614,"about_ca_topic_score_gemma":0.00054795574,"teacher_disagreement_score":0.83880424,"about_ca_system_score_codex":0.000262603,"about_ca_system_score_gemma":0.00036757218,"threshold_uncertainty_score":0.99982417},"labels":[],"label_agreement":null},{"id":"W152303868","doi":"10.1007/978-3-642-21043-3_19","title":"Instance Selection in Semi-supervised Learning","year":2011,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Machine Learning and Data Classification","field":"Computer Science","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 New Brunswick","funders":"","keywords":"Computer science; Classifier (UML); Artificial intelligence; Machine learning; Labeled data; Training set; Naive Bayes classifier; Pattern recognition (psychology); Bayes classifier; Semi-supervised learning; Co-training; Support vector machine","score_opus":0.020887687691478484,"score_gpt":0.24282444718845428,"score_spread":0.2219367594969758,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W152303868","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":[0.0003303189,0.0002756844,0.9867071,0.00035425386,0.00058874337,0.00024135088,0.0000011292846,0.0002582402,0.011243173],"genre_scores_gemma":[0.7411157,0.00018781773,0.2560344,0.00066702085,0.00037177507,0.000020109952,0.000020083404,0.000055737008,0.0015273639],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9965343,0.00009618239,0.0005216365,0.0015800094,0.0006808391,0.0005870717],"domain_scores_gemma":[0.99838096,0.00025193655,0.00030275545,0.00078324426,0.00015735086,0.00012376766],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001188033,0.00043441547,0.0004177812,0.0011222943,0.0002424303,0.00036962135,0.0023903616,0.00033471858,0.000038686685],"category_scores_gemma":[0.00019599784,0.0004303424,0.00007425261,0.0010677265,0.00026917201,0.0008826692,0.00068490766,0.0017338546,0.00008822178],"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":[0.000008702386,0.00003298296,0.0029775451,0.00003701338,0.0000043294167,0.00002878723,0.0013946146,0.032838494,0.00034153534,0.028488588,0.000009350184,0.93383807],"study_design_scores_gemma":[0.0003295971,0.00017610147,0.004667238,0.00040667146,0.0000038736457,0.000046982936,2.5834066e-7,0.93656915,0.00039914,0.050758492,0.005940908,0.00070160977],"about_ca_topic_score_codex":0.00012375675,"about_ca_topic_score_gemma":0.00035755668,"teacher_disagreement_score":0.93313646,"about_ca_system_score_codex":0.00035613845,"about_ca_system_score_gemma":0.0004243737,"threshold_uncertainty_score":0.9998148},"labels":[],"label_agreement":null},{"id":"W1527945204","doi":"10.1007/978-3-642-03348-3_22","title":"Instance Selection by Border Sampling in Multi-class Domains","year":2009,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Machine Learning and Data Classification","field":"Computer Science","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":"Health Canada; University of Ottawa","funders":"","keywords":"Computer science; Redundancy (engineering); Artificial intelligence; Machine learning; Training set; Selection (genetic algorithm); Class (philosophy); Sampling (signal processing); Binary classification; Binary number; Noise (video); Sample (material); Pattern recognition (psychology); Data mining; Naive Bayes classifier; Support vector machine; Mathematics; Computer vision","score_opus":0.02292200055169073,"score_gpt":0.2952974681570974,"score_spread":0.27237546760540665,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1527945204","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":[0.00013814779,0.00047559786,0.9949104,0.0013561681,0.00059761066,0.00031372765,0.000006717095,0.00022227183,0.0019793443],"genre_scores_gemma":[0.14980093,0.00018356563,0.8456711,0.0025638097,0.00027909482,0.00001684181,0.00005748521,0.000049842733,0.0013773387],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9961548,0.000067869274,0.00058092794,0.0017512852,0.00077947415,0.0006656334],"domain_scores_gemma":[0.99802303,0.00028830694,0.00033975733,0.001056382,0.00015673123,0.00013577928],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010284155,0.00048821364,0.00044547697,0.0008918422,0.00026977752,0.0005629831,0.0023749592,0.00036542476,0.00001187329],"category_scores_gemma":[0.00016651199,0.00048444147,0.000073481104,0.0011271796,0.00026502472,0.00081262505,0.00043372114,0.0013405593,0.000032465367],"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":[0.0000056984736,0.000065532506,0.0003391428,0.000019168248,0.0000035992884,0.00001196801,0.0003844771,0.038193457,0.00063372904,0.00937715,0.000042455264,0.9509236],"study_design_scores_gemma":[0.0005156035,0.00012640656,0.0017965699,0.000303576,0.000003534448,0.000032392203,1.8112227e-7,0.95112246,0.00031281187,0.017217932,0.027852092,0.0007164113],"about_ca_topic_score_codex":0.00008397364,"about_ca_topic_score_gemma":0.0006027391,"teacher_disagreement_score":0.95020723,"about_ca_system_score_codex":0.00053465413,"about_ca_system_score_gemma":0.000383937,"threshold_uncertainty_score":0.99976075},"labels":[],"label_agreement":null},{"id":"W1530482069","doi":"","title":"Improving observation-based modeling of other agents using tentative stereotyping and compactification through kd-tree structuring","year":2006,"lang":"en","type":"article","venue":"Web Intelligence and Agent Systems An International Journal","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Compactification (mathematics); k-nearest neighbors algorithm; Stereotype (UML); Structuring; Computer science; Nearest neighbor search; Algorithm; Mathematics; Pattern recognition (psychology); Artificial intelligence; Pure mathematics","score_opus":0.10385676790376214,"score_gpt":0.3328703702894823,"score_spread":0.22901360238572016,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1530482069","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":[0.41778812,0.000117872405,0.5815763,0.00006836921,0.000305862,0.0000662452,0.0000065040354,0.000016273249,0.000054473723],"genre_scores_gemma":[0.9728741,0.000035171415,0.026789898,0.00005118335,0.00020309194,0.0000026748542,0.000016905487,0.000009340554,0.000017613054],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99850965,0.00012353303,0.0005524559,0.00028167316,0.0003934204,0.00013926961],"domain_scores_gemma":[0.99883354,0.000054710697,0.00055710546,0.00018073819,0.00031786558,0.000056050143],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004345322,0.00013309502,0.00014662974,0.00017278397,0.00020476659,0.00057074387,0.000417617,0.00004411897,0.000006248996],"category_scores_gemma":[0.000036899262,0.00011866013,0.00003623194,0.000107016254,0.000038871494,0.001374574,0.000060492934,0.00015934785,0.000001082747],"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":[0.00004714706,0.0001329267,0.09354431,0.000093888586,0.000105204366,0.000011986603,0.0020261288,0.771874,0.028977105,0.04973741,0.000011602389,0.053438265],"study_design_scores_gemma":[0.00014289707,0.000029265448,0.0071490584,0.00020381561,0.000009548818,0.000056256824,0.00053002994,0.9900874,0.0009757064,0.00062449754,0.00006954361,0.00012196502],"about_ca_topic_score_codex":0.0018107216,"about_ca_topic_score_gemma":0.000028466542,"teacher_disagreement_score":0.555086,"about_ca_system_score_codex":0.00008308024,"about_ca_system_score_gemma":0.000068720154,"threshold_uncertainty_score":0.5503696},"labels":[],"label_agreement":null},{"id":"W1548053363","doi":"10.1007/3-540-46502-2_9","title":"Parallel Predictor Generation","year":2002,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Machine Learning and Data Classification","field":"Computer Science","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":"Queen's University","funders":"","keywords":"Computer science; Training set; Range (aeronautics); Regression; Set (abstract data type); Data mining; Machine learning; Artificial intelligence; Data set; Statistics; Mathematics","score_opus":0.02959770801902471,"score_gpt":0.24951881216591523,"score_spread":0.21992110414689053,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1548053363","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":[0.000018547598,0.00035249468,0.9886104,0.0015879621,0.0014010601,0.00023746416,0.000005447546,0.00023937221,0.0075472393],"genre_scores_gemma":[0.08223833,0.00022102878,0.9094788,0.001896366,0.0020110002,0.000021273658,0.00008093352,0.000049435348,0.004002871],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9968268,0.000042875956,0.00042439334,0.001402674,0.00086855283,0.00043469275],"domain_scores_gemma":[0.9976917,0.00016124573,0.00026726048,0.001582241,0.00015079843,0.0001467783],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00061404274,0.0003784251,0.00031265372,0.00056116463,0.00025690327,0.0006292012,0.0025200197,0.00027305802,0.00006418444],"category_scores_gemma":[0.00010925087,0.00034558025,0.00008080797,0.00037859753,0.00028550284,0.0006650518,0.00065016805,0.0007139613,0.00019037917],"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":[0.0000017310912,0.000028551452,0.00010501801,0.000019246578,0.0000068989625,0.000027594691,0.00038673647,0.034625936,0.00013976396,0.07593908,0.0003948072,0.8883246],"study_design_scores_gemma":[0.00016327992,0.000089563684,0.0002924353,0.000073487194,0.000004251804,0.000031712,1.6123364e-8,0.9604045,0.0000841633,0.025744379,0.012719564,0.0003926557],"about_ca_topic_score_codex":0.0000140953325,"about_ca_topic_score_gemma":0.000025622629,"teacher_disagreement_score":0.92577857,"about_ca_system_score_codex":0.0001923308,"about_ca_system_score_gemma":0.0002013896,"threshold_uncertainty_score":0.9998996},"labels":[],"label_agreement":null},{"id":"W1551753208","doi":"10.1007/978-3-642-13208-7_61","title":"Using Feature Selection Approaches to Find the Dependent Features","year":2010,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":8,"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 Windsor","funders":"","keywords":"Computer science; Feature selection; Selection (genetic algorithm); Artificial intelligence; Feature (linguistics); Pattern recognition (psychology)","score_opus":0.06967491408382005,"score_gpt":0.27316246559877755,"score_spread":0.2034875515149575,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1551753208","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":[0.0001737777,0.00019816343,0.9894569,0.0064789876,0.001380244,0.00045828221,0.000004852113,0.00014322388,0.0017055647],"genre_scores_gemma":[0.12587336,0.000011031264,0.8688386,0.0020292208,0.0011369942,0.000015966878,0.000015750667,0.000043712113,0.0020353799],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9966579,0.00007110742,0.0002807744,0.0014899719,0.0009689979,0.0005312233],"domain_scores_gemma":[0.9976265,0.00030709637,0.0002553639,0.0015197902,0.0001318695,0.00015941306],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0011786243,0.0004561987,0.00031676877,0.00058604457,0.00071291,0.0011485431,0.0035246497,0.00045950836,0.000010387586],"category_scores_gemma":[0.00016782142,0.00032276477,0.00009258195,0.00074503396,0.0003057129,0.00042942056,0.0011289029,0.0022651628,0.00003233279],"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":[0.000009972521,0.000028991537,0.0001628724,0.000027693535,0.000014335047,0.000012244584,0.0013280698,0.0886968,0.0034998797,0.037477717,0.00009309859,0.86864835],"study_design_scores_gemma":[0.00023633408,0.00017768868,0.0046403753,0.00023148979,0.000025801346,0.00047240683,6.8927034e-7,0.92082566,0.0054247277,0.05308654,0.013728115,0.0011501828],"about_ca_topic_score_codex":0.00006750059,"about_ca_topic_score_gemma":0.00040233426,"teacher_disagreement_score":0.86749816,"about_ca_system_score_codex":0.0002142558,"about_ca_system_score_gemma":0.00042384877,"threshold_uncertainty_score":0.99992245},"labels":[],"label_agreement":null},{"id":"W1561259622","doi":"10.1007/11871842_62","title":"Right of Inference: Nearest Rectangle Learning Revisited","year":2006,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Machine Learning and Data Classification","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":"Simon Fraser University","funders":"","keywords":"Rectangle; Inference; Benchmark (surveying); Class (philosophy); Artificial intelligence; Computer science; Machine learning; Pattern recognition (psychology); Decision tree; Mathematics; Geography; Cartography; Geometry","score_opus":0.013525339371429823,"score_gpt":0.2584907581373493,"score_spread":0.24496541876591946,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1561259622","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":[0.00009687331,0.00043362667,0.9797069,0.0004285261,0.00044664356,0.00020008069,0.0000057756893,0.00019075922,0.018490808],"genre_scores_gemma":[0.65558004,0.000112284004,0.34067467,0.00037251718,0.00055332074,0.000008419659,0.00012511776,0.000053317282,0.0025203296],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9966832,0.00009191266,0.00062693167,0.001247662,0.0009014608,0.0004488736],"domain_scores_gemma":[0.9969586,0.00064180384,0.0005941016,0.0013836174,0.0003162966,0.00010555727],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010311516,0.00039989638,0.0005219603,0.0008276074,0.00024453754,0.00037578846,0.002644898,0.00029817343,0.00004182123],"category_scores_gemma":[0.00038675638,0.0003591171,0.00010733866,0.00088142796,0.0004746084,0.0005007404,0.00086738745,0.0011698107,0.000048789265],"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":[0.0000074331356,0.000050006543,0.0021747868,0.00012185135,0.000010672659,0.00005159736,0.00040308904,0.06915992,0.000531793,0.06168378,0.00018055254,0.8656245],"study_design_scores_gemma":[0.0003117312,0.00030887086,0.0031098335,0.0010137645,0.000013746655,0.00003448893,1.3441283e-7,0.9168166,0.0011162503,0.050746758,0.025670333,0.00085749396],"about_ca_topic_score_codex":0.0000849732,"about_ca_topic_score_gemma":0.000036231402,"teacher_disagreement_score":0.864767,"about_ca_system_score_codex":0.00016301457,"about_ca_system_score_gemma":0.00037395657,"threshold_uncertainty_score":0.9998861},"labels":[],"label_agreement":null},{"id":"W1585078559","doi":"10.1109/ccis.2014.7175758","title":"Building diverse and optimized ensembles of gradient boosted trees for high-dimensional data","year":2014,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","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":"University of Waterloo","funders":"","keywords":"Computer science; Boosting (machine learning); Computation; Gradient boosting; Artificial intelligence; Machine learning; Ensemble learning; Tree (set theory); Feature selection; Big data; Reduction (mathematics); Cloud computing; Decision tree; Data mining; Random forest; Algorithm","score_opus":0.03842223823157406,"score_gpt":0.2849758958860554,"score_spread":0.2465536576544813,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1585078559","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":[0.058753233,0.000028744931,0.9399147,0.0009110285,0.00009116136,0.000094273215,0.000022896444,0.00006056882,0.00012340442],"genre_scores_gemma":[0.52268904,0.000003706587,0.47708488,0.000054486092,0.000015555055,0.0000024027518,0.000072761664,0.0000023173993,0.000074824406],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999291,0.0000514919,0.0001373863,0.0003088239,0.000113867696,0.00009743259],"domain_scores_gemma":[0.9989162,0.0002860358,0.000083572224,0.00062701287,0.000042940752,0.000044222485],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000434608,0.000064377025,0.00011525177,0.00005729558,0.00008207193,0.00004177599,0.000481608,0.000022767135,0.0000055003966],"category_scores_gemma":[0.00019890236,0.000050145358,0.00001315865,0.00006649608,0.00002921782,0.00026123616,0.00043651173,0.000032626205,0.0000014923604],"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":[0.00006108875,0.00008707232,0.00074993307,0.000038768478,0.00003121251,4.6207012e-7,0.00011096928,0.0013614476,0.013779178,0.71632826,0.00665573,0.26079586],"study_design_scores_gemma":[0.0008353087,0.00008083676,0.006013995,0.000013034879,0.00001108465,0.0000026513135,0.00000793383,0.9851517,0.0012820911,0.0018714925,0.0046440572,0.00008581441],"about_ca_topic_score_codex":0.00012756037,"about_ca_topic_score_gemma":0.000017850694,"teacher_disagreement_score":0.9837903,"about_ca_system_score_codex":0.0000040918085,"about_ca_system_score_gemma":0.000011447571,"threshold_uncertainty_score":0.20448683},"labels":[],"label_agreement":null},{"id":"W1589919686","doi":"","title":"Does Unlabeled Data Provably Help? Worst-case Analysis of the Sample Complexity of Semi-Supervised Learning.","year":2008,"lang":"en","type":"article","venue":"Conference on Learning Theory","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":108,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Sample complexity; Computer science; Semi-supervised learning; Homogeneous; Distribution (mathematics); Artificial intelligence; Conjecture; Sample (material); Class (philosophy); Labeled data; Supervised learning; Machine learning; Pattern recognition (psychology); Mathematics; Artificial neural network; Discrete mathematics; Combinatorics","score_opus":0.10947263266089535,"score_gpt":0.3005835196592879,"score_spread":0.19111088699839257,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1589919686","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":[0.60353523,0.000062335515,0.3912469,0.0013244121,0.00022695119,0.00035587294,0.00011559616,0.00030445616,0.0028282048],"genre_scores_gemma":[0.99329215,0.000056849694,0.005183752,0.0000630356,0.000025813406,0.000008339051,0.00022925781,0.000014699273,0.0011260922],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9962797,0.0016518782,0.00052282016,0.00074815605,0.00049976434,0.00029765035],"domain_scores_gemma":[0.9950982,0.0013067942,0.00067249726,0.002539643,0.00029163982,0.00009123523],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020334017,0.00023669821,0.0005220857,0.0003124982,0.00055214285,0.000068019384,0.0025889603,0.000101691956,0.00023507405],"category_scores_gemma":[0.0034434176,0.00014212269,0.00015433393,0.0016103238,0.00064816576,0.00033173995,0.0009704476,0.0007906125,0.000015297213],"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":[0.00028441023,0.0006297041,0.26838067,0.00016717121,0.0010545278,0.00005502323,0.009647001,0.018214641,0.0054311864,0.6018642,0.0002038829,0.09406758],"study_design_scores_gemma":[0.00053434394,0.0002254615,0.067984015,0.0001015096,0.0002736543,0.00003210279,0.0008228603,0.9206918,0.0008382852,0.0056510908,0.002489695,0.00035519945],"about_ca_topic_score_codex":0.00037131627,"about_ca_topic_score_gemma":0.00006921801,"teacher_disagreement_score":0.90247715,"about_ca_system_score_codex":0.000026949649,"about_ca_system_score_gemma":0.00022255968,"threshold_uncertainty_score":0.57955956},"labels":[],"label_agreement":null},{"id":"W1623534659","doi":"10.1186/s40537-015-0021-4","title":"Meta-MapReduce for scalable data mining","year":2015,"lang":"en","type":"article","venue":"Journal Of Big Data","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; Dalhousie University","funders":"","keywords":"Computer science; Scalability; Big data; AdaBoost; Machine learning; Node (physics); Programming paradigm; Cloud computing; Artificial intelligence; Data mining; Database; Programming language; Operating system; Support vector machine","score_opus":0.6436468009513665,"score_gpt":0.3948568341215879,"score_spread":0.2487899668297786,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1623534659","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":[0.00064095034,0.0013962283,0.9891389,0.0067795245,0.0011390737,0.000065528155,0.00033874984,0.000024147079,0.000476882],"genre_scores_gemma":[0.09742723,0.00006890715,0.8990729,0.00037807095,0.0013848353,0.000002344654,0.0010993093,0.000015064154,0.00055136933],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987145,0.00009397454,0.0003736098,0.00030873032,0.00035942343,0.00014972982],"domain_scores_gemma":[0.9959646,0.000196579,0.00046057635,0.0030052331,0.00021268181,0.00016033613],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0037175529,0.000083217135,0.00023165019,0.00010149809,0.00006249354,0.000255979,0.006078374,0.00003282447,0.000004188959],"category_scores_gemma":[0.0015733702,0.000060435952,0.000036078898,0.00019607916,0.000015541416,0.0022884936,0.0016116712,0.00014108088,0.0000137457355],"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":[0.000029612029,0.00009486675,0.00030786364,0.00001900053,0.00039894143,0.000010414199,0.00017387293,0.00010305227,0.00019261532,0.00072811765,0.6457739,0.35216776],"study_design_scores_gemma":[0.00049293274,0.00010814917,0.00021247288,0.000016751876,0.0003094492,0.00012481534,0.00005063772,0.21550053,0.00007421103,0.00046065362,0.78254974,0.00009965597],"about_ca_topic_score_codex":0.000019128816,"about_ca_topic_score_gemma":0.000008452446,"teacher_disagreement_score":0.3520681,"about_ca_system_score_codex":0.000016109721,"about_ca_system_score_gemma":0.000311215,"threshold_uncertainty_score":0.9992992},"labels":[],"label_agreement":null},{"id":"W1771347991","doi":"10.1007/978-3-540-85502-6_32","title":"Forgetting Reinforced Cases","year":2008,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":12,"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 Laval","funders":"","keywords":"Forgetting; Computer science; Bounding overwatch; Reinforcement learning; Case-based reasoning; Artificial intelligence; Value (mathematics); Base (topology); Machine learning; Mathematics","score_opus":0.02403337914753786,"score_gpt":0.25850201668115597,"score_spread":0.2344686375336181,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1771347991","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":[0.000058950674,0.0003318125,0.98823977,0.00094857253,0.0009216339,0.00021488324,0.0000035350267,0.0002950763,0.008985794],"genre_scores_gemma":[0.18793619,0.00026591658,0.80408496,0.0026476588,0.0009725643,0.000013829562,0.000051287545,0.00006341236,0.003964206],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9967274,0.000031790838,0.00049203716,0.0013297431,0.00085835374,0.0005606448],"domain_scores_gemma":[0.99698126,0.0006139182,0.0003569618,0.0017121297,0.00017858903,0.00015712794],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006641633,0.00042150708,0.00038681543,0.0007097323,0.00043687868,0.00042879322,0.0029343797,0.0002515921,0.00001604638],"category_scores_gemma":[0.00038619337,0.0003872123,0.00010783534,0.00051080197,0.00043091393,0.0007451604,0.0010724828,0.0008584749,0.00009791642],"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":[0.0000034694824,0.000007333142,0.00006325589,0.000028438746,0.0000057765283,0.00022220246,0.00059560896,0.021232974,0.00008586841,0.03128571,0.00018176979,0.9462876],"study_design_scores_gemma":[0.00021057008,0.00015421434,0.00023063523,0.0002643784,0.000004785943,0.00062525895,1.0792835e-7,0.96711826,0.0005415762,0.0083388295,0.02177348,0.0007378827],"about_ca_topic_score_codex":0.000047997415,"about_ca_topic_score_gemma":0.000025818303,"teacher_disagreement_score":0.9458853,"about_ca_system_score_codex":0.00019483225,"about_ca_system_score_gemma":0.00047825338,"threshold_uncertainty_score":0.99985796},"labels":[],"label_agreement":null},{"id":"W1798702550","doi":"10.48550/arxiv.1502.05700","title":"Scalable Bayesian Optimization Using Deep Neural Networks","year":2015,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":440,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada; Office of Science; National Energy Research Scientific Computing Center; Canadian Institute for Advanced Research; FAS Division of Science, Harvard University; U.S. Department of Energy; Harvard University; National Science Foundation","keywords":"Computer science; Bayesian optimization; Hyperparameter; Artificial intelligence; Artificial neural network; Convolutional neural network; Machine learning; Gaussian process; Global Positioning System; Deep learning; Benchmark (surveying); Optimization problem; Scalability; Surrogate model; Scale (ratio); Gaussian; Algorithm","score_opus":0.07416914068091068,"score_gpt":0.2071218247056708,"score_spread":0.13295268402476013,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1798702550","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":[0.00499872,0.00007977828,0.9922126,0.00010194484,0.0006255783,0.00016208633,0.000003665801,0.0003161442,0.0014994643],"genre_scores_gemma":[0.96826375,0.000036091515,0.031026307,0.000068170084,0.00012916436,3.9790945e-7,0.00012960895,0.000018537317,0.00032797307],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982349,0.00025051844,0.0001811435,0.0009339853,0.00009110034,0.00030831783],"domain_scores_gemma":[0.9980234,0.000043955635,0.00029631975,0.0012310237,0.00020528358,0.00020004637],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00035069138,0.0002464372,0.00023086938,0.00020773165,0.00019801565,0.0002762661,0.0013989942,0.00027909453,0.000023684923],"category_scores_gemma":[0.000051751245,0.00029076682,0.00009093125,0.0006251398,0.00005628445,0.00059969485,0.0013741492,0.00059412257,0.000015127969],"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":[0.0000085015745,0.000027026485,0.0024311172,0.000014845637,0.000015554415,0.0000311177,0.000047442703,0.98519415,0.0000010042919,0.010814682,0.000109709224,0.0013048294],"study_design_scores_gemma":[0.00021568399,0.000018430865,0.0002102396,0.000023103283,0.00003794356,0.000005740778,0.000017528411,0.996922,0.0000011185416,0.002138042,0.000110272376,0.00029988706],"about_ca_topic_score_codex":0.00024559838,"about_ca_topic_score_gemma":0.00002274833,"teacher_disagreement_score":0.963265,"about_ca_system_score_codex":0.00022880136,"about_ca_system_score_gemma":0.00011886417,"threshold_uncertainty_score":0.99995446},"labels":[],"label_agreement":null},{"id":"W1821814192","doi":"10.1007/978-3-642-31295-3_2","title":"Optimal “Anti-Bayesian” Parametric Pattern Classification for the Exponential Family Using Order Statistics Criteria","year":2012,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Mahalanobis distance; Exponential family; Computer science; Bayesian probability; Parametric statistics; Artificial intelligence; Order statistic; Algorithm; Bayes' theorem; Pattern recognition (psychology); Statistics; Mathematics; Machine learning","score_opus":0.05307906058183555,"score_gpt":0.3118320624366386,"score_spread":0.25875300185480304,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1821814192","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":[0.000120901605,0.00063293445,0.99520564,0.00066375505,0.0024806676,0.0006453581,0.00006341317,0.00011141098,0.00007589759],"genre_scores_gemma":[0.28932613,0.00007691864,0.7089954,0.0006053995,0.0007802805,0.000026184975,0.0000823101,0.000042072126,0.00006531735],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9964285,0.000085848726,0.0006243762,0.001257565,0.0009024415,0.00070128083],"domain_scores_gemma":[0.9958323,0.001374856,0.00055113947,0.0016527993,0.00044393694,0.00014495423],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0014681941,0.0004814522,0.00041409303,0.00068177877,0.00061024306,0.001069587,0.0028873004,0.00028799483,0.000023637811],"category_scores_gemma":[0.00030636883,0.00037925655,0.000098280056,0.000780914,0.0004823108,0.0006637209,0.0006792065,0.0006982977,0.000026501491],"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":[0.0000070353544,0.000042166692,0.00017469563,0.00005233352,0.000017945425,0.000004442227,0.0003514783,0.04295522,0.000514498,0.010049785,0.00009396696,0.9457364],"study_design_scores_gemma":[0.00021701002,0.00007141986,0.0024591375,0.00007640285,0.00003431325,0.000025742727,6.1051077e-7,0.9889943,0.00009083706,0.004441158,0.0031193953,0.00046964813],"about_ca_topic_score_codex":0.000070532165,"about_ca_topic_score_gemma":0.000013730416,"teacher_disagreement_score":0.9460391,"about_ca_system_score_codex":0.00021829896,"about_ca_system_score_gemma":0.00044062504,"threshold_uncertainty_score":0.9999674},"labels":[],"label_agreement":null},{"id":"W1832226433","doi":"10.1007/3-540-45486-1_29","title":"Typical Example Selection for Learning Classifiers","year":2000,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Mahalanobis distance; Computer science; Artificial intelligence; Set (abstract data type); Selection (genetic algorithm); Machine learning; Gaussian; Training set; Measure (data warehouse); Pattern recognition (psychology); Labeled data; Data mining","score_opus":0.027766386641199577,"score_gpt":0.26584179621263876,"score_spread":0.2380754095714392,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1832226433","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":[0.00006507555,0.00010810246,0.99303687,0.0007632407,0.0007094984,0.00035146222,0.0000028656013,0.00031183884,0.0046510287],"genre_scores_gemma":[0.17052385,0.00010234324,0.8236011,0.0011744746,0.0012066325,0.00005053802,0.00009509787,0.00007866877,0.0031672688],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99683607,0.00005742835,0.00041440545,0.0015288378,0.00058954756,0.00057369523],"domain_scores_gemma":[0.9980836,0.0005952316,0.00024020184,0.00076971756,0.00016034293,0.00015092317],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00090810924,0.00038451434,0.00036690608,0.0006390386,0.00048372598,0.00056356826,0.0018087308,0.00034836205,0.0000507083],"category_scores_gemma":[0.0001734452,0.00036924888,0.0001200727,0.0005010386,0.00029674638,0.0005048576,0.000312777,0.0010897905,0.000072020935],"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":[0.000018178976,0.000015637223,0.000199577,0.000020373805,0.0000061369446,0.0000025101842,0.0002234607,0.019976046,0.00009236763,0.043893002,0.00006021309,0.9354925],"study_design_scores_gemma":[0.00023346645,0.00023639464,0.0004899762,0.00009433827,0.000007211197,0.000032423606,1.09287164e-7,0.8389398,0.00015225688,0.08056507,0.07879814,0.0004508003],"about_ca_topic_score_codex":0.000048120804,"about_ca_topic_score_gemma":0.000072068884,"teacher_disagreement_score":0.9350417,"about_ca_system_score_codex":0.000257075,"about_ca_system_score_gemma":0.00041243478,"threshold_uncertainty_score":0.99987596},"labels":[],"label_agreement":null},{"id":"W184141742","doi":"","title":"Adaptive error-correcting output codes","year":2013,"lang":"en","type":"article","venue":"International Joint Conference on Artificial Intelligence","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Computer science; Artificial intelligence; Machine learning; Multiclass classification; Class (philosophy); Generalization; Subspace topology; Binary number; Set (abstract data type); External Data Representation; Pattern recognition (psychology); Support vector machine; Mathematics","score_opus":0.1593352712391407,"score_gpt":0.33395722350649226,"score_spread":0.17462195226735155,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W184141742","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":[0.008267308,0.000008309931,0.9389206,0.011240985,0.0015793056,0.00023734506,0.000008236283,0.00030089705,0.039436992],"genre_scores_gemma":[0.9825305,0.000012479347,0.015556529,0.0006387217,0.00019286602,0.00006880655,0.000022237755,0.00001133476,0.00096655695],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978172,0.00012525788,0.0005363565,0.0006455019,0.00056634756,0.00030931845],"domain_scores_gemma":[0.99825925,0.00020412714,0.00026743644,0.00053386285,0.0005998994,0.00013544598],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003706691,0.00022284144,0.00018780967,0.00025642035,0.00017840054,0.00075053837,0.0013078467,0.0000809169,0.0007337134],"category_scores_gemma":[0.00053692824,0.00020592035,0.000087030414,0.0002488883,0.00010213374,0.00083146384,0.00024772988,0.00040055113,0.0051930747],"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":[0.000007869997,0.000056515863,0.00008927961,0.0000014716504,0.00001326764,0.0000034667132,0.00035398276,0.00042031612,0.0013561873,0.5057963,0.000358707,0.4915426],"study_design_scores_gemma":[0.000027909848,0.00014826268,0.0022839066,0.00008114432,0.000003106529,0.000018606816,0.0006908451,0.8683043,0.016382033,0.11078622,0.00095787214,0.000315768],"about_ca_topic_score_codex":0.0006021186,"about_ca_topic_score_gemma":0.00006427063,"teacher_disagreement_score":0.97426313,"about_ca_system_score_codex":0.00009953812,"about_ca_system_score_gemma":0.00009725622,"threshold_uncertainty_score":0.9955815},"labels":[],"label_agreement":null},{"id":"W1842879116","doi":"10.1007/978-3-540-24677-0_111","title":"Boosting with Data Generation: Improving the Classification of Hard to Learn Examples","year":2004,"lang":"en","type":"book","venue":"Lecture notes in computer science","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":18,"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":"Boosting (machine learning); Computer science; Artificial intelligence; Machine learning; Training set; Artificial neural network; Decision tree; Ensemble learning; Gradient boosting; Data mining; Pattern recognition (psychology); Algorithm; Random forest","score_opus":0.06730520912970453,"score_gpt":0.2824679243042869,"score_spread":0.21516271517458238,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1842879116","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":[0.0002695229,0.00016643055,0.9951374,0.003017242,0.00046010702,0.00042950394,0.000014380953,0.000099613884,0.0004058321],"genre_scores_gemma":[0.12790327,0.00000936364,0.86968094,0.000869719,0.0007968767,0.000018685338,0.00020498033,0.000028968218,0.00048719568],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9963873,0.00011381441,0.0004837422,0.001645391,0.0009758597,0.00039388082],"domain_scores_gemma":[0.9947912,0.00046615087,0.00050174334,0.0038555935,0.0002859456,0.00009934274],"candidate_categories":["open_science"],"consensus_categories":[],"category_scores_codex":[0.0020166642,0.00031031657,0.00030643216,0.00039559617,0.0004049556,0.00071524427,0.00627789,0.00013652892,0.000002779395],"category_scores_gemma":[0.0005456816,0.00021264979,0.00003158504,0.0012395583,0.00040648135,0.0008311318,0.0017702363,0.00065975095,0.00001130403],"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":[0.0000047385747,0.00002550329,0.00025372615,0.000058871665,0.000007292982,0.000004550896,0.0012999605,0.10239333,0.0030709072,0.0048292065,0.00015149289,0.8879004],"study_design_scores_gemma":[0.00016039347,0.00016785336,0.0046648444,0.00027117695,0.000011190784,0.00003321721,9.65747e-7,0.98720336,0.00063840445,0.0015123874,0.0049836193,0.000352584],"about_ca_topic_score_codex":0.00013818144,"about_ca_topic_score_gemma":0.0002622593,"teacher_disagreement_score":0.88754785,"about_ca_system_score_codex":0.00038400156,"about_ca_system_score_gemma":0.00304898,"threshold_uncertainty_score":0.9990986},"labels":[],"label_agreement":null},{"id":"W1848549407","doi":"10.1080/00207721.2015.1074762","title":"MSEBAG: a dynamic classifier ensemble generation based on ‘minimum-sufficient ensemble' and bagging","year":2015,"lang":"en","type":"article","venue":"International Journal of Systems Science","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Ensemble learning; Classifier (UML); Inference; Artificial intelligence; Computer science; Machine learning; Random forest; Random subspace method; Fitness function; Variance (accounting); Selection (genetic algorithm); Algorithm; Mathematics; Genetic algorithm","score_opus":0.041985045890793805,"score_gpt":0.30700317551227824,"score_spread":0.2650181296214844,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1848549407","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":[0.1905861,0.00017018209,0.79728425,0.0033358987,0.0054448457,0.00009726187,0.000002575058,0.000034424273,0.003044455],"genre_scores_gemma":[0.99264675,0.000010028005,0.006670008,0.0002087124,0.0003190113,0.0000031056252,0.0000026696491,0.0000054027005,0.00013428541],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997235,0.00012130846,0.00047905766,0.00032510248,0.0016474102,0.00019212865],"domain_scores_gemma":[0.99767303,0.000117071,0.0005468266,0.00030253883,0.0011381311,0.00022241149],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028037177,0.00011757482,0.00014843317,0.0006374801,0.0001420611,0.00086785865,0.0012626849,0.000039895604,0.0000013253039],"category_scores_gemma":[0.0006037073,0.00009486518,0.0000400997,0.0003925852,0.00012488311,0.0010353159,0.00012161773,0.00019702391,0.000017764058],"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":[0.00020814824,0.00078547146,0.009738148,0.000051707073,0.00008557513,0.000341238,0.005473109,0.2889504,0.36128867,0.19470172,0.008236419,0.13013938],"study_design_scores_gemma":[0.00047528755,0.00021269807,0.0021825144,0.00010944931,0.0000036167942,0.00029054945,0.00018578919,0.9920413,0.0007146202,0.00011247113,0.003562042,0.0001096706],"about_ca_topic_score_codex":0.000029160934,"about_ca_topic_score_gemma":0.000004676168,"teacher_disagreement_score":0.80206066,"about_ca_system_score_codex":0.0003328215,"about_ca_system_score_gemma":0.00058834086,"threshold_uncertainty_score":0.8368781},"labels":[],"label_agreement":null},{"id":"W195714529","doi":"10.1007/978-3-642-23199-5_8","title":"Granular Instances Selection for Fuzzy Modeling","year":2011,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Machine Learning and Data Classification","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 Alberta","funders":"","keywords":"Computer science; Granularity; Feature selection; Data mining; Selection (genetic algorithm); Particle swarm optimization; Granular computing; Fuzzy logic; Artificial intelligence; Task (project management); Machine learning; Rough set","score_opus":0.03361113244121725,"score_gpt":0.26160741342491217,"score_spread":0.22799628098369493,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W195714529","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":[0.00003761436,0.0003679811,0.99316865,0.00040023893,0.0011107329,0.0003865985,0.000005090094,0.00023755406,0.004285523],"genre_scores_gemma":[0.24587373,0.000092445356,0.75240064,0.0006048445,0.0005497557,0.000033035878,0.000028444849,0.000039572646,0.00037753454],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971184,0.000029018527,0.00042809607,0.0013970955,0.00054483407,0.00048256962],"domain_scores_gemma":[0.99824977,0.00018131989,0.00025833963,0.0009125881,0.00028814582,0.000109819375],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00096257316,0.0003779568,0.00035292603,0.00066192937,0.00037793667,0.00040659218,0.0022375444,0.0002629599,0.0000069067996],"category_scores_gemma":[0.00011000605,0.00035009472,0.000110149245,0.0004374937,0.00019786097,0.0007667454,0.0003861935,0.0005887459,0.000022181255],"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":[0.000009540995,0.000018751889,0.0000819659,0.000046867164,0.0000047664525,0.0000023510622,0.0004476005,0.07204303,0.00008443253,0.14791422,0.000015252687,0.7793312],"study_design_scores_gemma":[0.00012613929,0.000097619006,0.000020403546,0.000106148116,0.000005317133,0.000013151562,5.5218425e-8,0.71328264,0.000153965,0.28355202,0.0023343647,0.00030817653],"about_ca_topic_score_codex":0.00006046322,"about_ca_topic_score_gemma":0.0001463108,"teacher_disagreement_score":0.77902305,"about_ca_system_score_codex":0.00016774783,"about_ca_system_score_gemma":0.0003476467,"threshold_uncertainty_score":0.9998951},"labels":[],"label_agreement":null},{"id":"W1963759559","doi":"10.1145/2463372.2463438","title":"Ordered racing protocols for automatically configuring algorithms for scaling performance","year":2013,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Scaling; Algorithm; Mathematics","score_opus":0.046626573319035976,"score_gpt":0.3256492104166988,"score_spread":0.27902263709766284,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1963759559","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":[0.0029566197,0.0000024782294,0.9819711,0.0013030983,0.000060199705,0.011734062,0.000001910999,0.0003909834,0.0015795513],"genre_scores_gemma":[0.14434493,4.742704e-7,0.8273812,0.000219856,0.00008727473,0.026964718,0.000018564098,0.00001254289,0.0009704318],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998954,0.000021728549,0.00028064253,0.0003229567,0.00013610878,0.00028457207],"domain_scores_gemma":[0.9989865,0.00023798873,0.00010430014,0.000409426,0.00018937362,0.0000724207],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046379303,0.000108823864,0.000136613,0.000058258,0.00025019087,0.00041156224,0.0005064844,0.000047936388,0.000030101806],"category_scores_gemma":[0.00017970696,0.000088880806,0.000045866524,0.00011371973,0.000016353986,0.0007159133,0.000068371206,0.000071973445,0.000060043098],"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":[0.000009119745,0.000060369384,0.00047952513,0.00042160976,0.000014387745,9.317321e-8,0.00032731498,0.00054591295,0.00412287,0.050239734,0.0015552958,0.9422238],"study_design_scores_gemma":[0.0005237671,0.00011729311,0.0025205363,0.00005745951,0.00000226502,0.0000024497567,0.000016971608,0.98543394,0.0031195688,0.0010830334,0.00698093,0.0001418145],"about_ca_topic_score_codex":0.000019158953,"about_ca_topic_score_gemma":7.872181e-7,"teacher_disagreement_score":0.984888,"about_ca_system_score_codex":0.00002014134,"about_ca_system_score_gemma":0.00004982956,"threshold_uncertainty_score":0.3968704},"labels":[],"label_agreement":null},{"id":"W1982508511","doi":"10.1016/j.patcog.2013.04.019","title":"Order statistics-based parametric classification for multi-dimensional distributions","year":2013,"lang":"en","type":"article","venue":"Pattern Recognition","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Order statistic; Statistics; Parametric statistics; Nonparametric statistics; Computer science; Pattern recognition (psychology); Artificial intelligence; Mathematics; Data mining","score_opus":0.08668302126302689,"score_gpt":0.31638709072313853,"score_spread":0.22970406946011163,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1982508511","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":[0.0083827935,0.000011643715,0.98848796,0.0016209196,0.00021573674,0.00052011485,0.0005430197,0.00017569972,0.00004213642],"genre_scores_gemma":[0.5842195,0.0000026666519,0.40798292,0.0003819483,0.000049130464,0.00052502967,0.0067716865,0.000010638892,0.0000564495],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99883956,0.000099215395,0.00026328219,0.0003904216,0.0001904256,0.00021707507],"domain_scores_gemma":[0.9985056,0.00034124492,0.0001752118,0.00033942953,0.00055028277,0.00008822195],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002200537,0.00012360238,0.00010233311,0.0001646024,0.00021341343,0.00021090651,0.00023858713,0.000070070724,0.0001579596],"category_scores_gemma":[0.00047782023,0.0001192693,0.000039385566,0.0004071158,0.000029082608,0.00038314465,0.00003105957,0.00012039939,0.0009904694],"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":[0.000003938003,0.00025978457,0.004151959,0.00003675022,0.000010546959,3.644914e-7,0.000018738567,0.000058825764,0.0007371837,0.0009937703,0.0053213723,0.9884068],"study_design_scores_gemma":[0.00054160436,0.00005745705,0.13096856,0.000015091922,0.000011195694,0.0000019141123,0.0000055469236,0.86488515,0.0003486811,0.0019363608,0.0010663392,0.00016209079],"about_ca_topic_score_codex":0.00013179918,"about_ca_topic_score_gemma":0.000016991788,"teacher_disagreement_score":0.98824465,"about_ca_system_score_codex":0.000056586432,"about_ca_system_score_gemma":0.00005895633,"threshold_uncertainty_score":0.9997874},"labels":[],"label_agreement":null},{"id":"W1982723861","doi":"10.1145/2746539.2746580","title":"Preserving Statistical Validity in Adaptive Data Analysis","year":2015,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":265,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"National Science Foundation","keywords":"Spurious relationship; Computer science; Statistical inference; Statistical hypothesis testing; Inference; Data mining; Machine learning; Statistical analysis; Data collection; Data science; Artificial intelligence; Statistics; Mathematics","score_opus":0.3190507828462666,"score_gpt":0.3803631002506314,"score_spread":0.061312317404364824,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1982723861","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":[0.0010647151,0.000010320769,0.98783004,0.00075145613,0.000036395504,0.00003450806,0.000024097886,0.00007049568,0.010177954],"genre_scores_gemma":[0.7261399,0.0000012791772,0.27332947,0.000054704684,0.000015087963,0.0000019141457,0.00021685254,0.0000015540193,0.00023925773],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989426,0.00020619128,0.00013333754,0.00038001707,0.00022030558,0.00011756412],"domain_scores_gemma":[0.9983107,0.00017578396,0.00003617435,0.0013473907,0.00003948847,0.00009045967],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010599537,0.000050618786,0.0001002531,0.00012230387,0.00002194668,0.000101690384,0.0013016247,0.000021901387,0.00003868562],"category_scores_gemma":[0.00060237275,0.000042489617,0.000009477505,0.0007255284,0.000013574518,0.00060833764,0.00085901516,0.00010062919,0.000058612044],"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":[0.000023981323,0.0002504971,0.32960317,0.00000860834,0.00011523028,0.000031371073,0.000926205,0.005580692,0.000015678823,0.55967075,0.046606187,0.057167638],"study_design_scores_gemma":[0.00008398129,0.000017415208,0.11619357,9.408558e-7,0.00001333386,4.6649825e-7,0.000032742362,0.8787134,0.0000030754218,0.0024382053,0.0024494666,0.000053356638],"about_ca_topic_score_codex":0.001592023,"about_ca_topic_score_gemma":0.00095834077,"teacher_disagreement_score":0.87313277,"about_ca_system_score_codex":0.000023698021,"about_ca_system_score_gemma":0.00006127205,"threshold_uncertainty_score":0.24187642},"labels":[],"label_agreement":null},{"id":"W1986622224","doi":"10.1037/0003-066x.59.1.51","title":"On (Not) Trimming One's Toenails With a Bazooka.","year":2004,"lang":"en","type":"letter","venue":"American Psychologist","topic":"Machine Learning and Data Classification","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":"York University","funders":"","keywords":"Trimming; Psychology; Engineering","score_opus":0.026543522030433746,"score_gpt":0.28916580016889615,"score_spread":0.2626222781384624,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1986622224","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0002941315,0.00003541995,0.23032036,0.7503313,0.0003555072,0.00027212373,0.000026111977,0.00059155613,0.017773528],"genre_scores_gemma":[0.034712903,0.000036123754,0.034953907,0.92662627,0.0009741747,0.00009391409,0.00036798316,0.00006656502,0.0021681404],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99671644,0.00024846537,0.000344508,0.0014352876,0.00064648077,0.00060884375],"domain_scores_gemma":[0.996431,0.00029682505,0.0006737382,0.0024411143,0.00006383485,0.00009347501],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002599977,0.0004595626,0.0005401094,0.00029462075,0.00017561683,0.00042735925,0.002051136,0.0002452925,0.000031380016],"category_scores_gemma":[0.000109468725,0.00037206608,0.000114897455,0.00074049673,0.00056993053,0.0002355799,0.00011426371,0.0022794202,0.0006562568],"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":[0.000059947502,0.00013094729,0.0000648066,0.00003075245,0.000068867535,0.00034557463,0.00012761579,0.0000615717,0.000023018147,0.006278317,0.8510959,0.14171265],"study_design_scores_gemma":[0.00071112084,0.0018256911,0.0038159888,0.00020468209,0.00003099762,0.0000841307,0.00002373753,0.00014961384,0.000024416477,0.0009842966,0.99127585,0.0008694641],"about_ca_topic_score_codex":0.0007625243,"about_ca_topic_score_gemma":0.000011996795,"teacher_disagreement_score":0.19536646,"about_ca_system_score_codex":0.00017588973,"about_ca_system_score_gemma":0.00018525698,"threshold_uncertainty_score":0.9998731},"labels":[],"label_agreement":null},{"id":"W1987455112","doi":"10.1016/j.jbi.2011.04.004","title":"Class proximity measures – Dissimilarity-based classification and display of high-dimensional data","year":2011,"lang":"en","type":"article","venue":"Journal of Biomedical Informatics","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"BC Cancer Agency; National Research Council Canada; National Research Council Institute for Biodiagnostics","funders":"","keywords":"Computer science; Class (philosophy); Visualization; Pattern recognition (psychology); Artificial intelligence; Construct (python library); Feature (linguistics); Data mining","score_opus":0.08143006026382793,"score_gpt":0.29179282426798153,"score_spread":0.2103627640041536,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1987455112","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":[0.045374606,0.00008847725,0.9510991,0.002743869,0.00028188323,0.000092059796,0.000068549285,0.000023727764,0.00022774252],"genre_scores_gemma":[0.81642294,0.000048549624,0.18317701,0.00020051078,0.00004196691,7.316332e-7,0.00010067303,0.0000035045136,0.000004137522],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979886,0.00009401442,0.0009248107,0.0000991917,0.0007623087,0.00013106632],"domain_scores_gemma":[0.99773073,0.00017251617,0.0010177552,0.00064096955,0.00023754226,0.00020048437],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017684394,0.00010060622,0.00023264966,0.00020706568,0.00007053327,0.000050405386,0.001065457,0.0001017953,0.00001202352],"category_scores_gemma":[0.00063491,0.000069486574,0.000035640332,0.00025774137,0.00018429144,0.0012529305,0.00025925107,0.00031846325,0.0000035929424],"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":[0.0005323013,0.0031723417,0.027584735,0.0013674597,0.00038917823,0.000036070996,0.0071533467,0.00008531674,0.0041093775,0.16757521,0.05087823,0.73711646],"study_design_scores_gemma":[0.0010261014,0.00047573494,0.09629269,0.00018366743,0.00006252629,0.00010086023,0.00012538598,0.8810183,0.0004933747,0.0024994584,0.017531084,0.00019085941],"about_ca_topic_score_codex":0.000017679604,"about_ca_topic_score_gemma":0.000001957163,"teacher_disagreement_score":0.8809329,"about_ca_system_score_codex":0.000020116257,"about_ca_system_score_gemma":0.0002430476,"threshold_uncertainty_score":0.28335804},"labels":[],"label_agreement":null},{"id":"W2001325299","doi":"10.1109/bigdata.2013.6691741","title":"Meta-learning for large scale machine learning with MapReduce","year":2013,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University; University of Ottawa","funders":"","keywords":"Computer science; Scalability; AdaBoost; Machine learning; Big data; Artificial intelligence; Node (physics); Programming paradigm; Data mining; Support vector machine; Database; Programming language","score_opus":0.02920715133756604,"score_gpt":0.25330946025166,"score_spread":0.22410230891409397,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2001325299","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":[0.0050012283,0.0001412882,0.9836307,0.0033070005,0.00005245959,0.0003164017,0.0000019260756,0.0005645687,0.0069844103],"genre_scores_gemma":[0.7630239,0.000009428812,0.21118541,0.00030619936,0.000050991897,0.00021924582,0.00008140156,0.000021743735,0.02510167],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99861544,0.0001407742,0.00018858552,0.0004770781,0.00021986938,0.00035827243],"domain_scores_gemma":[0.99902153,0.00018040852,0.00012800768,0.0004301884,0.00012814194,0.000111737674],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005343405,0.00016819601,0.0002254207,0.00009150398,0.00036838412,0.00035193784,0.0005377434,0.000048539077,0.00042240255],"category_scores_gemma":[0.00009675502,0.000112221285,0.00008778251,0.00025652352,0.000016419513,0.00073681056,0.00015056193,0.00032067145,0.0002966633],"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":[0.0001294067,0.0011756646,0.14126647,0.00043399693,0.0030522333,0.000010873871,0.009256218,0.029571958,0.01458997,0.4001076,0.025630806,0.3747748],"study_design_scores_gemma":[0.00047930816,0.00022618925,0.0049206624,0.0000056236663,0.00009638902,0.000011923524,0.00011834509,0.8598445,0.00051103556,0.00035031434,0.13319378,0.000241919],"about_ca_topic_score_codex":0.00020621212,"about_ca_topic_score_gemma":0.000037597136,"teacher_disagreement_score":0.83027256,"about_ca_system_score_codex":0.000015173981,"about_ca_system_score_gemma":0.00002740086,"threshold_uncertainty_score":0.46250117},"labels":[],"label_agreement":null},{"id":"W2002035275","doi":"10.1145/2594413.2594424","title":"Understanding the empirical hardness of <i>NP</i> -complete problems","year":2014,"lang":"en","type":"article","venue":"Communications of the ACM","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":48,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Mathematics","score_opus":0.4601499494803349,"score_gpt":0.3555965632417745,"score_spread":0.10455338623856036,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2002035275","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":[0.0024621787,0.00028919193,0.60799253,0.37510246,0.00021253183,0.0002992609,0.000010772272,0.000086939544,0.0135441255],"genre_scores_gemma":[0.9539348,0.00003466801,0.04562157,0.00031529408,0.000008988581,0.0000117366435,0.000006472312,0.000004433417,0.00006203166],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9988641,0.000504813,0.00024218918,0.000119379874,0.0001792842,0.000090194735],"domain_scores_gemma":[0.9718997,0.00075601996,0.0002674218,0.02698587,0.00007178663,0.000019222734],"candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.00094432733,0.00006085875,0.000105590196,0.00003573031,0.000352764,0.000040813306,0.032127712,0.000026958649,0.0000018969866],"category_scores_gemma":[0.003556714,0.00003537694,0.00006351848,0.00039503534,0.00030224829,0.00011926001,0.011647106,0.00019590433,0.000007371608],"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":[0.0000032279193,0.00014866749,0.016022442,0.000043971493,0.000032220334,9.8309085e-9,0.0034359887,0.00072036346,0.0035468207,0.9361096,0.03642715,0.003509514],"study_design_scores_gemma":[0.00036090333,0.000056022946,0.04257151,0.00011045895,0.000033566626,0.000008025187,0.0002730969,0.19936551,0.00048732414,0.5860921,0.17046325,0.00017821051],"about_ca_topic_score_codex":0.00003796352,"about_ca_topic_score_gemma":0.000024536348,"teacher_disagreement_score":0.95147264,"about_ca_system_score_codex":0.000023157378,"about_ca_system_score_gemma":0.00003304708,"threshold_uncertainty_score":0.99634653},"labels":[],"label_agreement":null},{"id":"W2007908724","doi":"10.1016/j.compchemeng.2008.10.013","title":"Image quality in image classification: Design and construction of an image quality database","year":2008,"lang":"en","type":"article","venue":"Computers & Chemical Engineering","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Artificial intelligence; Image quality; Computer science; Image (mathematics); Process (computing); Contextual image classification; Quality (philosophy); Pattern recognition (psychology); Computer vision; Data mining; Database","score_opus":0.03961991861048538,"score_gpt":0.2924812261176871,"score_spread":0.25286130750720176,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2007908724","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":[0.25784594,0.000027882317,0.7415452,0.00019556466,0.00008290816,0.000099861,0.000007285888,0.00015559461,0.00003976393],"genre_scores_gemma":[0.35233855,0.000013163844,0.647521,0.000018283072,0.000035391928,0.0000072457424,0.000056871602,0.000008248711,0.000001243379],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983209,0.00016524682,0.0005234114,0.00053229474,0.00023484296,0.00022333398],"domain_scores_gemma":[0.99855876,0.0003196789,0.00016676389,0.0007296019,0.0000831649,0.00014202736],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007607131,0.00017759833,0.00027987701,0.00013110504,0.000052216004,0.00007031951,0.00050300895,0.0000755733,0.0000031590491],"category_scores_gemma":[0.00026778347,0.00019446341,0.000038724884,0.00035624404,0.00016917144,0.0010458303,0.00020266941,0.00028726432,0.000003978197],"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":[0.000020796582,0.000108852044,0.00048199572,0.00015740278,0.0000086801865,0.000012563062,0.0003878538,0.0003528495,0.978537,0.009470554,0.00006922438,0.0103922235],"study_design_scores_gemma":[0.00053544587,0.000022418626,0.027234832,0.000040898638,0.0000033311069,0.00006447114,0.000020069525,0.9292253,0.042389862,0.00013622509,0.0000693626,0.00025776224],"about_ca_topic_score_codex":0.000062365776,"about_ca_topic_score_gemma":3.539058e-7,"teacher_disagreement_score":0.93614715,"about_ca_system_score_codex":0.000057840272,"about_ca_system_score_gemma":0.000043640026,"threshold_uncertainty_score":0.7929988},"labels":[],"label_agreement":null},{"id":"W2014504390","doi":"10.1007/s10844-012-0224-5","title":"Iterative classification for multiple target attributes","year":2012,"lang":"en","type":"article","venue":"Journal of Intelligent Information Systems","topic":"Machine Learning and Data Classification","field":"Computer Science","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":"National Research Council Canada","funders":"","keywords":"Computer science; Exploit; Machine learning; Artificial intelligence; Data mining; Scheme (mathematics); Computation; Artificial neural network; Decision tree; Algorithm","score_opus":0.054814601534027445,"score_gpt":0.29749545444652475,"score_spread":0.2426808529124973,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2014504390","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":[0.0015067809,0.00036071194,0.99500227,0.00051838433,0.0016637862,0.00025970058,0.000019533883,0.000034146906,0.0006346647],"genre_scores_gemma":[0.97354907,0.000036448288,0.025775345,0.000107860964,0.00034317264,0.00002261888,0.000083094405,0.000003887163,0.000078514946],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983804,0.00009794887,0.00094746734,0.000056522764,0.00033371738,0.00018389603],"domain_scores_gemma":[0.9972092,0.00030018648,0.0012915443,0.00022845276,0.0008510348,0.00011960143],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016631404,0.00010055604,0.00017771486,0.00026667822,0.00011341079,0.00032945175,0.00042087358,0.00006247268,0.0000043874643],"category_scores_gemma":[0.0006431617,0.000076891294,0.00009350731,0.00020880676,0.00001216712,0.0053533106,0.000031131403,0.0001368876,0.00009702784],"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":[0.00020597033,0.00043844123,0.076669335,0.000600361,0.0002510385,5.736701e-7,0.028636362,0.013163874,0.0020892927,0.67740124,0.06573294,0.13481054],"study_design_scores_gemma":[0.0003160738,0.00013384686,0.00576332,0.00006311303,0.000008247586,0.000068434216,0.0012169257,0.31276932,0.0019350084,0.00008787079,0.67750734,0.00013048976],"about_ca_topic_score_codex":0.000004883428,"about_ca_topic_score_gemma":1.280255e-7,"teacher_disagreement_score":0.97204226,"about_ca_system_score_codex":0.000111681686,"about_ca_system_score_gemma":0.000057135625,"threshold_uncertainty_score":0.38810208},"labels":[],"label_agreement":null},{"id":"W2014830929","doi":"10.1109/icsmc.2011.6083986","title":"Feature and instance selection via cooperative PSO","year":2011,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Universiti Teknikal Malaysia Melaka; Ministry of Higher Education, Malaysia","keywords":"Feature selection; Computer science; Particle swarm optimization; Curse of dimensionality; Dimensionality reduction; Data mining; Artificial intelligence; Machine learning; Selection (genetic algorithm); Feature (linguistics)","score_opus":0.01850900527507319,"score_gpt":0.23147861639288628,"score_spread":0.2129696111178131,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2014830929","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":[0.0051687486,0.000044567092,0.9667211,0.0010532029,0.000059761205,0.00004756067,3.5633002e-7,0.00014853002,0.026756179],"genre_scores_gemma":[0.9062445,0.000013898208,0.09033304,0.0002833919,0.000017496366,0.000004181701,0.000002950281,0.0000023331097,0.00309818],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996218,0.000034519344,0.000037876976,0.00018295458,0.00005421863,0.000068634276],"domain_scores_gemma":[0.999753,0.00001083802,0.000024185643,0.00013910365,0.00004156237,0.000031287174],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008087139,0.000047985115,0.000041134375,0.000027952745,0.00008879303,0.00004831807,0.0001301176,0.000029157709,0.000021211461],"category_scores_gemma":[0.00001674171,0.000037259375,0.000005701955,0.0001696834,0.00001555875,0.00035955495,0.00003947408,0.000091870555,0.00002894722],"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":[0.000015499429,0.00006875524,0.02031266,0.000011177229,0.000014097116,0.0000023634177,0.0030325388,0.000009038176,0.005241092,0.67055374,0.011517896,0.28922114],"study_design_scores_gemma":[0.00056474586,0.00037133906,0.41685843,0.000016865615,0.000007489825,0.00009128729,0.0000890698,0.46364337,0.011918749,0.0038067685,0.10217957,0.00045230763],"about_ca_topic_score_codex":0.00004834043,"about_ca_topic_score_gemma":0.000058787675,"teacher_disagreement_score":0.9010758,"about_ca_system_score_codex":0.000007418425,"about_ca_system_score_gemma":0.00001219616,"threshold_uncertainty_score":0.15193933},"labels":[],"label_agreement":null},{"id":"W2015688842","doi":"10.1080/09528130903010295","title":"Warning: statistical benchmarking is addictive. Kicking the habit in machine learning","year":2009,"lang":"en","type":"article","venue":"Journal of Experimental & Theoretical Artificial Intelligence","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; National Research Council Canada","funders":"","keywords":"Benchmarking; Computer science; Addiction; Set (abstract data type); Habit; Machine learning; Test (biology); Artificial intelligence; Measure (data warehouse); Psychology; Data mining; Social psychology; Psychiatry; Management","score_opus":0.02424670070729992,"score_gpt":0.3166015831447657,"score_spread":0.2923548824374658,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2015688842","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":[0.04075523,0.0006506664,0.9502326,0.005781055,0.00035803346,0.00013396723,0.0000026738926,0.00004226702,0.0020434968],"genre_scores_gemma":[0.98401403,0.000034142002,0.015137446,0.0005791128,0.00021044919,0.000002420632,0.0000034883365,0.00000899907,0.000009881352],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973153,0.00047062885,0.0008691084,0.00032939218,0.0006490539,0.0003665079],"domain_scores_gemma":[0.9983812,0.00069133117,0.00036396788,0.00029481188,0.000116140545,0.00015255464],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016778684,0.00020038281,0.0002806414,0.00017240309,0.00026484593,0.0002981327,0.0010135147,0.00008272116,0.00042731024],"category_scores_gemma":[0.0006561424,0.00013898892,0.000112173184,0.0004407742,0.00035225978,0.00042254067,0.0001559327,0.0011319929,0.000041089585],"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":[0.00009188477,0.00018493575,0.00031399704,0.0000015499759,0.000008653268,0.00005499535,0.0029900523,0.0004102418,0.009732835,0.8472567,0.00003398388,0.13892017],"study_design_scores_gemma":[0.000115365794,0.0015978892,0.0014053156,0.00013143131,0.000014870342,0.00021167927,0.0013151336,0.6883076,0.10178018,0.20366324,0.0011377127,0.00031959944],"about_ca_topic_score_codex":0.000018487108,"about_ca_topic_score_gemma":0.0000019681522,"teacher_disagreement_score":0.9432588,"about_ca_system_score_codex":0.000110561436,"about_ca_system_score_gemma":0.00006359275,"threshold_uncertainty_score":0.5667804},"labels":[],"label_agreement":null},{"id":"W2015738394","doi":"10.1007/s10799-012-0135-8","title":"A comparative analysis of classification algorithms in data mining for accuracy, speed and robustness","year":2012,"lang":"en","type":"article","venue":"Information Technology and Management","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":52,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"PricewaterhouseCoopers (Canada)","funders":"","keywords":"Computer science; Robustness (evolution); Data mining; Classifier (UML); Scalability; Principal component analysis; Machine learning; Artificial intelligence; Statistical classification; Execution time; Pattern recognition (psychology); Database","score_opus":0.06475445140591805,"score_gpt":0.3373495764834195,"score_spread":0.27259512507750144,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2015738394","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":[0.04006977,0.00009225014,0.95762146,0.001210426,0.000036861304,0.0002818416,0.00001696284,0.00006000581,0.00061042875],"genre_scores_gemma":[0.8890077,0.0000876998,0.110494256,0.000032972264,0.0000030835863,0.000027610491,0.0003323686,7.854849e-7,0.000013548977],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99944437,0.00001667658,0.00024798882,0.00012005198,0.00006709826,0.00010383294],"domain_scores_gemma":[0.99926305,0.00006363005,0.0002049206,0.0004163719,0.000034286688,0.000017760894],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004995712,0.00005734403,0.00013691642,0.0011039282,0.000053403728,0.000035409787,0.00032856868,0.00005201355,8.731511e-7],"category_scores_gemma":[0.00004947784,0.000054263746,0.000008319351,0.0010100545,0.000046216104,0.001685714,0.00031162446,0.000046604648,8.5513e-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":[0.000011023775,0.00005136699,0.017180264,0.00010351349,0.0001818731,7.995103e-8,0.0015896092,0.00047705887,0.00001777515,0.42066193,0.00029856642,0.55942696],"study_design_scores_gemma":[0.00025287384,0.00001295036,0.13667424,0.000008744313,0.00006641498,7.793248e-7,0.0013379934,0.85338366,0.000035091354,0.00015299398,0.008014617,0.000059661288],"about_ca_topic_score_codex":0.000005687492,"about_ca_topic_score_gemma":0.000008590066,"teacher_disagreement_score":0.8529066,"about_ca_system_score_codex":0.000010642656,"about_ca_system_score_gemma":0.000004505727,"threshold_uncertainty_score":0.22128114},"labels":[],"label_agreement":null},{"id":"W202723009","doi":"10.1007/978-3-540-39935-3_15","title":"Adaptive Training for Combining Classifier Ensembles","year":2004,"lang":"en","type":"book-chapter","venue":"Studies in fuzziness and soft computing","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Classifier (UML); Computer science; Random subspace method; Training set; Machine learning; Artificial intelligence; Ensemble learning; Pattern recognition (psychology); Test set; Cascading classifiers","score_opus":0.15100949490505436,"score_gpt":0.3393871998367348,"score_spread":0.18837770493168046,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W202723009","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":[0.00048208216,0.011514762,0.83353204,0.0015728816,0.0024622711,0.0010097091,0.000031897183,0.000542547,0.14885183],"genre_scores_gemma":[0.90565,0.0010365051,0.07832987,0.00040812735,0.0008042987,0.000053895244,0.00007419618,0.00010835365,0.013534767],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9979549,0.00003595767,0.0005464152,0.0008398131,0.00022718268,0.0003957555],"domain_scores_gemma":[0.997977,0.0009931525,0.00038901798,0.00038515008,0.00019098575,0.0000646959],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00070695154,0.000411868,0.00073561154,0.00024189349,0.00048308072,0.00012878384,0.00045715264,0.00019499971,0.0000016116035],"category_scores_gemma":[0.0002452955,0.00038954624,0.00009960196,0.0000868978,0.00021755422,0.00016885821,0.00060529186,0.00049123226,0.0000034062366],"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":[0.000012830397,0.0000101758205,0.00006708674,0.00020825258,0.00009399731,0.000015504744,0.006414839,0.00057090796,0.0000027401927,0.75438833,0.00015997134,0.23805533],"study_design_scores_gemma":[0.00446168,0.0007064686,0.0018615687,0.008712056,0.00015898666,0.000086638,0.0061800913,0.3023428,0.0000068246122,0.61647004,0.05607233,0.0029405153],"about_ca_topic_score_codex":0.0000120899385,"about_ca_topic_score_gemma":0.000023769191,"teacher_disagreement_score":0.90516794,"about_ca_system_score_codex":0.000116486925,"about_ca_system_score_gemma":0.00012123578,"threshold_uncertainty_score":0.99985564},"labels":[],"label_agreement":null},{"id":"W2028307124","doi":"10.1016/j.patcog.2012.07.004","title":"The fundamental theory of optimal “Anti-Bayesian” parametric pattern classification using order statistics criteria","year":2012,"lang":"en","type":"article","venue":"Pattern Recognition","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Mahalanobis distance; Bayesian probability; Mathematics; Classifier (UML); Pattern recognition (psychology); Parametric statistics; Artificial intelligence; Order statistic; Bayesian statistics; Exponential family; Algorithm; Naive Bayes classifier; Bayes' theorem; Computer science; Statistics; Bayesian inference; Support vector machine","score_opus":0.07559781138873717,"score_gpt":0.32272291304852674,"score_spread":0.24712510165978957,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2028307124","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":[0.15268914,0.00009227038,0.84613407,0.00015956337,0.00048529953,0.00015862996,0.00010863902,0.00005582518,0.00011655989],"genre_scores_gemma":[0.9695327,0.00005126127,0.029749213,0.00012832746,0.00014198905,0.000021819795,0.000340189,0.000016321483,0.000018126015],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998209,0.00047472064,0.0004002825,0.0002682773,0.00032388722,0.0003238537],"domain_scores_gemma":[0.9983907,0.00048719958,0.00038890346,0.0004675639,0.00018242926,0.00008324001],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011017419,0.0001522126,0.00014209992,0.00014633244,0.00026735337,0.0002019072,0.00039038292,0.00007035259,0.0000947521],"category_scores_gemma":[0.00022690462,0.00012282899,0.00004170108,0.000408648,0.00008108393,0.00059427693,0.00010596753,0.0001814689,0.00010918199],"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":[0.000008654921,0.00014040581,0.046295132,0.000037751182,0.000023783656,6.262614e-7,0.00040802098,0.000017987282,0.0014822175,0.0006125451,0.00016781507,0.95080507],"study_design_scores_gemma":[0.00049710803,0.000105894476,0.3798532,0.000071799666,0.00007012806,0.00004268448,0.00046557665,0.61399716,0.0019174013,0.0016846046,0.0008931078,0.0004013458],"about_ca_topic_score_codex":0.000061989216,"about_ca_topic_score_gemma":0.000004047131,"teacher_disagreement_score":0.9504037,"about_ca_system_score_codex":0.000057366717,"about_ca_system_score_gemma":0.000033567678,"threshold_uncertainty_score":0.5008821},"labels":[],"label_agreement":null},{"id":"W2029320154","doi":"10.1007/s10732-014-9275-9","title":"Analysing differences between algorithm configurations through ablation","year":2015,"lang":"en","type":"article","venue":"Journal of Heuristics","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":113,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Compute Canada","keywords":"Computer science; Satisfiability; Algorithm; Integer programming","score_opus":0.08233675307823943,"score_gpt":0.3237777667160881,"score_spread":0.24144101363784867,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2029320154","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":[0.007254543,0.000116644034,0.9902336,0.0011548724,0.00027683703,0.00002102387,0.000004893236,0.000020086418,0.00091750635],"genre_scores_gemma":[0.7697024,0.000021757129,0.22984412,0.000040223058,0.00032553996,2.1279085e-7,0.000010392967,0.000002910328,0.000052472566],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99894834,0.00011546877,0.00038755973,0.00009242033,0.00036428357,0.00009191238],"domain_scores_gemma":[0.99865764,0.0001612358,0.00048552177,0.00019541853,0.00040977157,0.0000904344],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004904272,0.00006699231,0.00016257906,0.00009338115,0.00008539103,0.00018110106,0.00036648088,0.000036532456,0.000003750974],"category_scores_gemma":[0.00045080425,0.000052839692,0.00004186761,0.00024625368,0.000023749224,0.0005489103,0.000033692297,0.00019464213,0.000012392758],"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":[0.000016536089,0.0002866023,0.13988344,0.00003179324,0.00028878512,0.0000805415,0.009856646,0.003548621,0.00043903053,0.0794975,0.021234939,0.74483556],"study_design_scores_gemma":[0.00095700653,0.0005387223,0.26917848,0.00007646184,0.00018342536,0.00014459559,0.00046114108,0.6300559,0.00028177924,0.056090593,0.041675787,0.0003561105],"about_ca_topic_score_codex":0.000016371569,"about_ca_topic_score_gemma":0.0000012840356,"teacher_disagreement_score":0.76244783,"about_ca_system_score_codex":0.000035535162,"about_ca_system_score_gemma":0.00012580627,"threshold_uncertainty_score":0.21547401},"labels":[],"label_agreement":null},{"id":"W203732173","doi":"10.1007/978-3-319-09584-4_6","title":"Evaluating Instance Generators by Configuration","year":2014,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Machine Learning and Data Classification","field":"Computer Science","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":"University of Waterloo; University of British Columbia","funders":"","keywords":"Benchmark (surveying); Generator (circuit theory); Metric (unit); Computer science; Solver; Satisfiability; Set (abstract data type); Development (topology); Boolean satisfiability problem; Theoretical computer science; Artificial intelligence; Algorithm; Programming language; Mathematics; Power (physics); Engineering","score_opus":0.029301859252895888,"score_gpt":0.2975607159534128,"score_spread":0.2682588567005169,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W203732173","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":[0.00010624648,0.0003811768,0.9921875,0.0010794117,0.0011122756,0.0002467908,0.000005652065,0.00019702264,0.0046838955],"genre_scores_gemma":[0.3031137,0.00006698651,0.69107056,0.0032232746,0.0008177691,0.000022311102,0.000117649644,0.00005523446,0.0015125066],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99639326,0.00009563969,0.00051554124,0.0014912377,0.0010630185,0.00044127976],"domain_scores_gemma":[0.99735075,0.00035478975,0.0004499721,0.0014546362,0.00025395598,0.00013589146],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001688484,0.00040350595,0.0003631933,0.00041098357,0.0003367311,0.0007186673,0.002403392,0.00025532977,0.000024498217],"category_scores_gemma":[0.00028015336,0.0003791172,0.00006483372,0.0004308331,0.0003157593,0.00049549236,0.00045142343,0.0007269916,0.000094789946],"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":[0.0000018461556,0.0000074514496,0.00002929817,0.000017084152,0.000003277053,0.0000029477108,0.00017814731,0.012957349,0.0014471675,0.046022154,0.00014951719,0.9391838],"study_design_scores_gemma":[0.00020795004,0.00015549092,0.00007095592,0.00015661247,0.000004908538,0.000013801036,5.530328e-8,0.9576136,0.0025104403,0.025734799,0.013009472,0.0005219212],"about_ca_topic_score_codex":0.000019961688,"about_ca_topic_score_gemma":0.00002705653,"teacher_disagreement_score":0.94465625,"about_ca_system_score_codex":0.00022809414,"about_ca_system_score_gemma":0.00039153663,"threshold_uncertainty_score":0.99986607},"labels":[],"label_agreement":null},{"id":"W2042053856","doi":"10.1016/j.patcog.2008.03.027","title":"A dynamic overproduce-and-choose strategy for the selection of classifier ensembles","year":2008,"lang":"en","type":"article","venue":"Pattern Recognition","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":152,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Defence Research and Development Canada; Quest University Canada; École de Technologie Supérieure","funders":"","keywords":"Classifier (UML); Computer science; Artificial intelligence; Selection (genetic algorithm); Machine learning; Population; Pattern recognition (psychology)","score_opus":0.05774142430184379,"score_gpt":0.28443365329260833,"score_spread":0.22669222899076455,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2042053856","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":[0.27585638,0.00008699008,0.7227053,0.000779262,0.00011176758,0.00021854942,0.000018618315,0.000060501978,0.00016260151],"genre_scores_gemma":[0.9966234,0.00018551695,0.0028432242,0.00009966787,0.000040450526,0.000054503562,0.000062828265,0.000006586544,0.00008385467],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99930364,0.000061664185,0.00016157073,0.0002475722,0.00011429261,0.000111249305],"domain_scores_gemma":[0.9993647,0.000186758,0.00012877713,0.00019606219,0.00009953366,0.000024208828],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022282338,0.00007737285,0.00008176827,0.000059384907,0.00018011013,0.00003732959,0.00014505598,0.000041432497,0.000012226972],"category_scores_gemma":[0.00007133473,0.000058614994,0.000034859888,0.0001285072,0.00003410119,0.00023298299,0.000028286679,0.000093595416,0.000013751002],"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":[0.000012134994,0.00003642717,0.0038875025,0.00003102371,0.0000132663035,3.4190253e-7,0.0001843792,0.00004061252,0.0024128666,0.00009990422,0.00023612005,0.99304545],"study_design_scores_gemma":[0.00046545203,0.00017505631,0.3561128,0.000034092613,0.000024588118,0.000082392464,0.000048116086,0.63681465,0.0030706336,0.0018701112,0.0011373957,0.00016471789],"about_ca_topic_score_codex":0.000081393955,"about_ca_topic_score_gemma":0.00004186776,"teacher_disagreement_score":0.9928807,"about_ca_system_score_codex":0.000015241676,"about_ca_system_score_gemma":0.00002870615,"threshold_uncertainty_score":0.23902501},"labels":[],"label_agreement":null},{"id":"W2047003964","doi":"10.1145/2076450.2076469","title":"Programming by optimization","year":2012,"lang":"en","type":"article","venue":"Communications of the ACM","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":226,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Programming language","score_opus":0.03999092086229857,"score_gpt":0.3033604240854069,"score_spread":0.26336950322310837,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2047003964","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":[0.0018655031,0.004298829,0.8148117,0.16902472,0.00030460328,0.00038725417,0.000008490614,0.0002708913,0.009027991],"genre_scores_gemma":[0.42678306,0.000058780744,0.57296604,0.000064748296,0.0000068963823,0.000012821443,0.00001939208,0.0000025959728,0.000085656815],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99948555,0.00014705298,0.000121292935,0.00006366988,0.00009163431,0.00009080237],"domain_scores_gemma":[0.9776353,0.0001221344,0.00012827042,0.02204347,0.000045255936,0.000025547002],"candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.00035036614,0.000039245166,0.000044076787,0.000022960367,0.0001944725,0.000032760778,0.021642193,0.000021599117,0.0000028404063],"category_scores_gemma":[0.0029292265,0.000029211982,0.000026452308,0.00027780497,0.00006412171,0.00033897444,0.010388285,0.00009686417,0.0000103661905],"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":[0.0000037074674,0.0010986443,0.08322302,0.00003849051,0.00005128481,1.2077052e-8,0.0037367728,0.00296482,0.0040175673,0.40279934,0.15675895,0.34530738],"study_design_scores_gemma":[0.00028466916,0.00002749331,0.025294917,0.00004779175,0.000027869031,0.0000070015517,0.00012896306,0.20091106,0.0023798577,0.007438128,0.7631907,0.00026156002],"about_ca_topic_score_codex":0.000021136315,"about_ca_topic_score_gemma":0.0000011641989,"teacher_disagreement_score":0.6064317,"about_ca_system_score_codex":0.000012982675,"about_ca_system_score_gemma":0.000013234546,"threshold_uncertainty_score":0.9976155},"labels":[],"label_agreement":null},{"id":"W2055649902","doi":"10.1142/s0218001407005752","title":"COEVOLUTION OF NEAREST NEIGHBOR CLASSIFIERS","year":2007,"lang":"en","type":"article","venue":"International Journal of Pattern Recognition and Artificial Intelligence","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":21,"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 Laval","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Classifier (UML); Computer science; Genetic programming; Artificial intelligence; Normalization (sociology); Machine learning; k-nearest neighbors algorithm; Large margin nearest neighbor; Pattern recognition (psychology); Random subspace method; Data mining","score_opus":0.08270104479482547,"score_gpt":0.33036680928443013,"score_spread":0.24766576448960465,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2055649902","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":[0.121630676,0.00005890669,0.8755341,0.0014223984,0.00092935114,0.00003678236,0.000011519996,0.000013436501,0.00036282558],"genre_scores_gemma":[0.99345356,0.000115549825,0.005945592,0.00020093172,0.00025472417,5.45567e-7,0.000014079321,0.00000428035,0.000010753035],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99861145,0.000057865014,0.0006660174,0.00014281448,0.00040667245,0.000115177114],"domain_scores_gemma":[0.9983563,0.00018812426,0.0005816953,0.000105113075,0.00068229734,0.00008649636],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008903251,0.0000825226,0.00012002311,0.00030034062,0.000043443553,0.000101253536,0.00045237024,0.000052299976,0.00005993807],"category_scores_gemma":[0.00024783963,0.000075494194,0.00006558419,0.00014991514,0.000082275066,0.0004860724,0.000062353734,0.0001874327,0.000032024695],"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":[0.00004975003,0.000067048604,0.0025445658,0.00000588283,0.000025383064,0.000019578138,0.00033822603,0.000018363298,0.005329909,0.0047013406,0.000041184183,0.9868588],"study_design_scores_gemma":[0.0010030195,0.0020069685,0.18437085,0.0013289091,0.0001151377,0.0016477769,0.0045153587,0.17193024,0.39875293,0.22095287,0.012028852,0.001347097],"about_ca_topic_score_codex":0.00004799427,"about_ca_topic_score_gemma":0.000035130553,"teacher_disagreement_score":0.98551166,"about_ca_system_score_codex":0.000034864956,"about_ca_system_score_gemma":0.000041805542,"threshold_uncertainty_score":0.30785638},"labels":[],"label_agreement":null},{"id":"W2058115154","doi":"10.1145/1553374.1553519","title":"Optimal reverse prediction","year":2009,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Supervised learning; Artificial intelligence; Computer science; Machine learning; Cluster analysis; Semi-supervised learning; Graph; Regression; Unsupervised learning; Unification; Simple (philosophy); Principal component analysis; Pattern recognition (psychology); Artificial neural network; Mathematics; Statistics; Theoretical computer science","score_opus":0.011990057309124006,"score_gpt":0.24655622877591687,"score_spread":0.23456617146679287,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2058115154","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":[0.0021685779,0.000010476732,0.94090086,0.0052930987,0.00008432369,0.000027717266,5.568916e-7,0.0003339085,0.051180504],"genre_scores_gemma":[0.81478727,0.000010378257,0.18159042,0.0009264148,0.00006091466,0.0000011951191,0.000012881721,0.0000012189644,0.0026092832],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996314,0.000017570606,0.0000621485,0.00013749153,0.00008395417,0.00006743014],"domain_scores_gemma":[0.999652,0.000007887547,0.00001904408,0.0002749258,0.000015430307,0.00003069619],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000109305365,0.0000321322,0.000027895987,0.00003004445,0.00004643172,0.000054711047,0.00021028846,0.000018146753,0.000027912174],"category_scores_gemma":[0.00002234979,0.000026964315,0.000012508526,0.0001116263,0.0000040323425,0.0003220167,0.000018764444,0.00005239508,0.00014638029],"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":[0.0000039710662,0.00006897347,0.0006855559,0.0000017340436,0.000002582025,0.000003021499,0.00025127272,0.0009765114,0.0021719728,0.3473792,0.06441708,0.58403814],"study_design_scores_gemma":[0.00020798059,0.00017050222,0.08096777,0.0000044664707,0.0000022326074,0.000017193186,0.000017553702,0.68777835,0.00049982977,0.0013629451,0.22886562,0.000105528066],"about_ca_topic_score_codex":0.000007634949,"about_ca_topic_score_gemma":3.1759606e-7,"teacher_disagreement_score":0.81261873,"about_ca_system_score_codex":0.000008220736,"about_ca_system_score_gemma":0.0000092074215,"threshold_uncertainty_score":0.18814713},"labels":[],"label_agreement":null},{"id":"W2070077913","doi":"10.1016/j.patcog.2013.02.006","title":"“Anti-Bayesian” parametric pattern classification using order statistics criteria for some members of the exponential family","year":2013,"lang":"en","type":"article","venue":"Pattern Recognition","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Exponential family; Natural exponential family; Mathematics; Parametric statistics; Order statistic; Bayesian probability; Statistics; Bayes' theorem; Gaussian; Gamma distribution; Exponential function; Exponential distribution; Nonparametric statistics; Applied mathematics; Pattern recognition (psychology); Artificial intelligence; Computer science; Mathematical analysis; Physics","score_opus":0.07341635214590447,"score_gpt":0.30940229934133545,"score_spread":0.23598594719543098,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2070077913","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":[0.252508,0.000015300191,0.7458639,0.00040627783,0.00054752326,0.00044888418,0.00013440603,0.000046738813,0.00002891956],"genre_scores_gemma":[0.9673369,0.00001571643,0.031645827,0.0003736293,0.00012413244,0.00010733708,0.0003596893,0.000019023573,0.000017763186],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984086,0.00021966608,0.00043666203,0.00038789448,0.00030993318,0.00023722199],"domain_scores_gemma":[0.9984171,0.00021736002,0.00044236574,0.00052384526,0.00034364668,0.00005570194],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031869704,0.00015577055,0.00017782651,0.00017353323,0.00017010033,0.00021305104,0.00047904334,0.0000753109,0.00008689367],"category_scores_gemma":[0.00020908206,0.00012929758,0.00006743522,0.00040372153,0.00005104889,0.00066185533,0.00009405468,0.00013600661,0.00005852369],"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":[0.0000050621984,0.00015526557,0.010882021,0.0001716713,0.00003244398,4.6386813e-7,0.00023757467,0.0000931093,0.022825057,0.00021710449,0.0014889436,0.96389127],"study_design_scores_gemma":[0.0004432556,0.000050396946,0.15059079,0.00006382465,0.00003995969,0.0000055368464,0.00006839508,0.8427759,0.0023952178,0.0031772978,0.00016980829,0.00021960709],"about_ca_topic_score_codex":0.0006097956,"about_ca_topic_score_gemma":0.000011072948,"teacher_disagreement_score":0.9636717,"about_ca_system_score_codex":0.000044681645,"about_ca_system_score_gemma":0.00004858934,"threshold_uncertainty_score":0.5272602},"labels":[],"label_agreement":null},{"id":"W2073116371","doi":"10.1109/grc.2005.1547387","title":"Evaluation and automatic selection of methods for handling missing data","year":2005,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Missing data; Computer science; Data mining; Data set; Set (abstract data type); Training set; Artificial intelligence; Selection (genetic algorithm); Machine learning","score_opus":0.15198978496978563,"score_gpt":0.4706624978544997,"score_spread":0.3186727128847141,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2073116371","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":[0.0015937645,0.00015391133,0.9963894,0.0012353105,0.000034175373,0.00013246699,8.20231e-7,0.00006646795,0.00039368263],"genre_scores_gemma":[0.1443133,0.0000044268936,0.85556006,0.00003065717,0.000027556485,0.0000050924905,0.000023142438,0.0000020489194,0.00003372286],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993287,0.00017054088,0.00014140588,0.00019997098,0.00009976696,0.000059617585],"domain_scores_gemma":[0.9992315,0.00022605014,0.00008658607,0.00033063468,0.000105805986,0.000019407466],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0037915355,0.000037557336,0.00006287388,0.000054271546,0.0000760398,0.000067795016,0.00022816984,0.00002056052,0.000011430898],"category_scores_gemma":[0.0007786173,0.00003257977,0.000007266403,0.000113056885,0.000008042339,0.0005339227,0.0000767376,0.000029976321,9.1945634e-7],"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":[5.188397e-7,0.000008620795,0.00008434928,0.000013863356,0.00000419329,1.1584123e-9,0.000067747795,0.00011794135,0.0048058573,0.002263465,0.00012183207,0.99251163],"study_design_scores_gemma":[0.00015774847,0.000018711431,0.002007686,0.0000099577,0.000020073678,0.0000023984535,0.000005925249,0.9894005,0.002827676,0.000957307,0.0045537516,0.000038232738],"about_ca_topic_score_codex":0.00001507784,"about_ca_topic_score_gemma":0.000008415238,"teacher_disagreement_score":0.99247336,"about_ca_system_score_codex":0.000015321384,"about_ca_system_score_gemma":0.000052204825,"threshold_uncertainty_score":0.13285644},"labels":[],"label_agreement":null},{"id":"W2092353981","doi":"10.1007/s10044-003-0191-0","title":"A brief taxonomy and ranking of creative prototype reduction schemes","year":2003,"lang":"en","type":"article","venue":"Pattern Analysis and Applications","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":93,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Computer science; sort; Ranking (information retrieval); Reduction (mathematics); Taxonomy (biology); Set (abstract data type); Data reduction; Artificial intelligence; Class (philosophy); Machine learning; Data mining; Pattern recognition (psychology); Information retrieval; Mathematics","score_opus":0.020255414103223807,"score_gpt":0.2641137965063549,"score_spread":0.2438583824031311,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2092353981","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":[0.012462382,0.00013089963,0.985604,0.00019269112,0.000003087445,0.00026958462,0.000003665085,0.000021590226,0.0013121049],"genre_scores_gemma":[0.9871511,0.000058027636,0.012326886,0.000019966714,0.00001097035,0.00034735922,0.000019145242,0.0000021325511,0.00006442167],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99942297,0.00005161445,0.00014288789,0.00025044222,0.00007012237,0.00006195241],"domain_scores_gemma":[0.9994854,0.000023231703,0.00012370963,0.00028036116,0.000052810898,0.00003451736],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017822208,0.000057839825,0.00011729762,0.00012788776,0.00010927941,0.00005881875,0.000093349634,0.000020454245,0.000013899711],"category_scores_gemma":[0.0000138639725,0.000052417712,0.00003096321,0.0005751369,0.000040923424,0.00011569213,0.000027403717,0.00004961284,0.0000017888586],"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":[0.00000241212,0.000095957,0.15121584,0.0000379984,0.00025212293,1.02171306e-7,0.0003149908,0.000036360823,0.0022786523,0.11053375,0.000024293819,0.7352075],"study_design_scores_gemma":[0.0011598384,0.00017128423,0.56719446,0.00005254282,0.0012323504,0.000028063398,0.0006240052,0.1213181,0.019485507,0.006902289,0.28102988,0.0008016918],"about_ca_topic_score_codex":0.0001362164,"about_ca_topic_score_gemma":0.000010945281,"teacher_disagreement_score":0.9746887,"about_ca_system_score_codex":0.0000050087124,"about_ca_system_score_gemma":0.000010899738,"threshold_uncertainty_score":0.21375322},"labels":[],"label_agreement":null},{"id":"W2095705004","doi":"","title":"Dropout: a simple way to prevent neural networks from overfitting","year":2014,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":34279,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Overfitting; Dropout (neural networks); Computer science; Artificial intelligence; Artificial neural network; Machine learning; Benchmark (surveying); Deep neural networks; Regularization (linguistics)","score_opus":0.01136010837867235,"score_gpt":0.2537860031689929,"score_spread":0.24242589479032056,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2095705004","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":[0.04197765,0.000010713208,0.9524139,0.0022327355,0.00021186334,0.0000717718,0.0000011253903,0.00023055033,0.002849664],"genre_scores_gemma":[0.96606034,7.2783985e-7,0.031893015,0.00147494,0.00021224504,0.000006763363,0.000026612266,0.0000059270124,0.00031940662],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990335,0.00011207053,0.00015669844,0.00035042193,0.00014784609,0.0001994529],"domain_scores_gemma":[0.99901533,0.00016706706,0.000055340326,0.0006269014,0.000023033712,0.000112347065],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029802907,0.000086398104,0.000092606795,0.00003306788,0.000103777005,0.00018897612,0.0005670101,0.0000321088,0.000057314297],"category_scores_gemma":[0.00014348002,0.000071799135,0.000030141846,0.00017198506,0.000006499203,0.00020282791,0.00027820747,0.00011922409,0.00011671192],"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":[0.000004311024,0.00006573375,0.0105181625,0.0000033807883,0.000008493594,0.0000010869654,0.0003257093,0.020894054,0.00037545376,0.08239655,0.0077229924,0.87768406],"study_design_scores_gemma":[0.000072224786,0.000039163584,0.020765599,0.0000037902132,0.0000017778335,5.4351017e-7,0.0000066507478,0.9529493,0.00009504422,0.0011862388,0.024780577,0.000099108154],"about_ca_topic_score_codex":0.00051635195,"about_ca_topic_score_gemma":0.00005901926,"teacher_disagreement_score":0.93205523,"about_ca_system_score_codex":0.000014815014,"about_ca_system_score_gemma":0.000005036547,"threshold_uncertainty_score":0.29278836},"labels":[],"label_agreement":null},{"id":"W2100168598","doi":"10.1145/1281192.1281261","title":"Partial example acquisition in cost-sensitive learning","year":2007,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Computer science; Incremental learning; Data acquisition; Machine learning; Labeled data; Set (abstract data type); Artificial intelligence; Ideal (ethics); Training set; Data mining; Data set","score_opus":0.025971686922589093,"score_gpt":0.28757487387020764,"score_spread":0.2616031869476185,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2100168598","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":[0.053750288,0.00000679764,0.9289637,0.00049815996,0.00009011851,0.00008280566,2.2809958e-7,0.00017780838,0.016430063],"genre_scores_gemma":[0.9860157,0.0000027942685,0.013205671,0.00024464264,0.00005724183,0.0000035397225,0.000025188288,0.0000036365595,0.00044159996],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9991265,0.00009298816,0.00015848175,0.0002618257,0.00014500243,0.00021519802],"domain_scores_gemma":[0.99948424,0.0001592451,0.000051594317,0.00021648084,0.000034477656,0.000053970776],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010035951,0.000063922686,0.00006907592,0.00011546265,0.00007660485,0.00007262728,0.00017227168,0.00004088241,0.000030427136],"category_scores_gemma":[0.00007216653,0.000060725815,0.000017149985,0.0002989796,0.000015201569,0.00033286808,0.0000759067,0.00018011856,0.00016106557],"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":[0.00003651568,0.0001059708,0.052460663,0.000006672074,0.000005429616,0.000054685257,0.0022457198,0.0014615692,0.008159721,0.2991745,0.00041656522,0.635872],"study_design_scores_gemma":[0.0005931971,0.000101971484,0.6334998,0.000015865895,0.0000021012136,0.000020692973,0.000304227,0.30901113,0.009549876,0.0006263288,0.046014555,0.00026025996],"about_ca_topic_score_codex":0.0005132163,"about_ca_topic_score_gemma":0.00013813394,"teacher_disagreement_score":0.9322654,"about_ca_system_score_codex":0.00003876698,"about_ca_system_score_gemma":0.000016839047,"threshold_uncertainty_score":0.24763268},"labels":[],"label_agreement":null},{"id":"W2100527225","doi":"10.1007/978-3-540-74958-5_73","title":"Roulette Sampling for Cost-Sensitive Learning","year":2007,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Activity-based costing; Roulette; Computer science; Sampling (signal processing); Preprocessor; Sample (material); Artificial intelligence; Machine learning; Rejection sampling; Data mining; Mathematics","score_opus":0.04985687444367841,"score_gpt":0.3132162319413482,"score_spread":0.26335935749766975,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2100527225","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":[0.000017276074,0.00014090205,0.9927886,0.0011863445,0.0011273683,0.0005952908,0.0000073339984,0.00027566598,0.0038612066],"genre_scores_gemma":[0.044043902,0.000035611214,0.9515912,0.0023143776,0.0009718925,0.000020457752,0.00007445359,0.00005625324,0.0008918742],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99632514,0.000044836754,0.0004987202,0.001638223,0.00075116777,0.00074189657],"domain_scores_gemma":[0.9965326,0.001491468,0.00040496883,0.0010413656,0.00036193308,0.00016763422],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0021915643,0.00045983927,0.00044772506,0.0008585204,0.00050947693,0.0006238346,0.0020032274,0.00033258606,0.000006154215],"category_scores_gemma":[0.00049033144,0.00044766458,0.0001380918,0.00047943374,0.00036177397,0.0005157169,0.0007401371,0.0013039331,0.000047438127],"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":[0.000008352076,0.000009768413,0.000044743723,0.000026040727,0.0000070400506,0.000015504087,0.0003851201,0.037542485,0.00016645607,0.038460396,0.000013330796,0.9233208],"study_design_scores_gemma":[0.0003265039,0.0001859397,0.0003580311,0.00028889385,0.000010379231,0.000057493635,3.66515e-7,0.9162138,0.00066276354,0.030128011,0.051025122,0.0007426686],"about_ca_topic_score_codex":0.000021696278,"about_ca_topic_score_gemma":0.000046960613,"teacher_disagreement_score":0.9225781,"about_ca_system_score_codex":0.00029653538,"about_ca_system_score_gemma":0.00031630497,"threshold_uncertainty_score":0.9997975},"labels":[],"label_agreement":null},{"id":"W2101865757","doi":"10.1504/ijica.2012.050053","title":"Improving a dynamic ensemble selection method based on oracle information","year":2012,"lang":"en","type":"article","venue":"International Journal of Innovative Computing and Applications","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure; Université du Québec à Montréal","funders":"","keywords":"Computer science; Oracle; NIST; Classifier (UML); Artificial intelligence; k-nearest neighbors algorithm; Ensemble learning; Cluster analysis; Data mining; Pattern recognition (psychology); Nearest neighbour; Selection (genetic algorithm); Machine learning; Natural language processing","score_opus":0.011105246708907918,"score_gpt":0.3288613490625342,"score_spread":0.3177561023536263,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2101865757","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":[0.004419584,0.000024977877,0.99294066,0.0014996879,0.00021718201,0.00008476288,0.0000033601827,0.000043989334,0.000765788],"genre_scores_gemma":[0.7514259,0.0000028200996,0.24792093,0.00046128608,0.000156444,0.0000049815694,0.000016211312,0.0000033769218,0.0000080385225],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989877,0.00007950992,0.00040287388,0.00010193018,0.00030530724,0.00012270792],"domain_scores_gemma":[0.9978095,0.0002418751,0.0006865225,0.000118246906,0.0010888327,0.000054984994],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009807511,0.00008885621,0.000098680015,0.00039657758,0.00013824285,0.00017744978,0.0003759373,0.00003639495,0.000002607693],"category_scores_gemma":[0.0002090428,0.00007960856,0.000028490094,0.000586178,0.000018504219,0.00095435703,0.00007313904,0.0002504349,0.0000105642575],"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":[0.000013123871,0.00009490434,0.003219941,0.0000070103033,0.000022634711,1.8378022e-7,0.00027217093,0.0026428397,0.0016939667,0.07198942,0.00011181455,0.919932],"study_design_scores_gemma":[0.000444469,0.0000893847,0.029340995,0.00004123026,0.000005082077,0.00007940156,0.00008267615,0.94842035,0.0011420621,0.00070305576,0.019525541,0.00012577094],"about_ca_topic_score_codex":0.000009977353,"about_ca_topic_score_gemma":3.8938717e-7,"teacher_disagreement_score":0.9457775,"about_ca_system_score_codex":0.00009267704,"about_ca_system_score_gemma":0.000075420736,"threshold_uncertainty_score":0.32463428},"labels":[],"label_agreement":null},{"id":"W2102539288","doi":"10.1145/2487575.2487629","title":"Auto-WEKA","year":2013,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":1321,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Hyperparameter; Machine learning; Computer science; MNIST database; Artificial intelligence; Hyperparameter optimization; Bayesian optimization; Classifier (UML); Feature selection; Data mining; Artificial neural network; Support vector machine","score_opus":0.010311523931344213,"score_gpt":0.22755372459307321,"score_spread":0.217242200661729,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2102539288","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":[0.0014958548,0.000008186629,0.8134656,0.007009239,0.00007786651,0.00003832611,7.564475e-8,0.00029958182,0.17760529],"genre_scores_gemma":[0.86058396,0.000002226434,0.11190275,0.0009462579,0.000032008316,0.000012985725,0.0000039167,0.0000023329546,0.026513573],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99966216,0.00001711405,0.00005320073,0.00012211227,0.0000693413,0.00007607154],"domain_scores_gemma":[0.99956745,0.00002006533,0.000015885798,0.00034016508,0.000021009908,0.00003540153],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00006153078,0.000030202214,0.000027236629,0.000023356184,0.000028357192,0.00013475855,0.00033922508,0.000013681655,0.00038243827],"category_scores_gemma":[0.000023074525,0.000022512462,0.000010192167,0.00009195808,0.000006239531,0.00037184704,0.00006999714,0.000042542197,0.0042062034],"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":[7.1023926e-8,0.000013423052,0.0016667835,0.0000015221434,0.0000013814163,2.5418163e-7,0.00006687733,0.000005428991,0.0010437114,0.38571432,0.035354175,0.57613206],"study_design_scores_gemma":[0.0000777832,0.000019220071,0.14532667,0.0000016115506,5.132972e-7,0.0000040928367,0.000008660517,0.5324925,0.00027950524,0.0044667916,0.31722796,0.00009470364],"about_ca_topic_score_codex":0.00010477952,"about_ca_topic_score_gemma":0.0000016435596,"teacher_disagreement_score":0.8590881,"about_ca_system_score_codex":0.000004458535,"about_ca_system_score_gemma":0.000008782587,"threshold_uncertainty_score":0.99656916},"labels":[],"label_agreement":null},{"id":"W2107103101","doi":"","title":"Predicting accurate probabilities with a ranking loss.","year":2012,"lang":"en","type":"article","venue":"PubMed","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Ranking (information retrieval); Computer science; Machine learning; Artificial intelligence; Isotonic regression; Logistic regression; Set (abstract data type); Regression; Parametric statistics; Data mining; Statistics; Mathematics","score_opus":0.02706841915597657,"score_gpt":0.22155332398817842,"score_spread":0.19448490483220185,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2107103101","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":[0.5660138,0.00037517952,0.40391946,0.003671964,0.00057055685,0.0010109491,0.0000040789246,0.0010796301,0.023354374],"genre_scores_gemma":[0.99336535,0.0000025147172,0.005558905,0.00008740175,0.00014015415,0.00052411587,0.000004704686,0.0000059002505,0.00031095557],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9990981,0.0000688309,0.00011134473,0.00018074883,0.00017902009,0.00036194228],"domain_scores_gemma":[0.99935734,0.000081905084,0.00008185668,0.00035414746,0.000031008105,0.000093764495],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006843463,0.00007546512,0.00007176186,0.00004563871,0.00010937278,0.00014493268,0.0003239177,0.000023359446,0.000002630656],"category_scores_gemma":[0.0001655634,0.000055658475,0.000015303583,0.00019683542,0.000030853316,0.0010191413,0.000093374685,0.00011111525,0.000012412112],"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":[0.000010702798,0.000048299462,0.6400174,0.00003394717,0.000014557469,0.0000011364573,0.0015801854,0.00007396164,0.0000045034185,0.034711946,0.00012613965,0.3233772],"study_design_scores_gemma":[0.00022425926,0.000010798806,0.98219436,0.000008348465,0.000005949384,0.000026052088,0.000041916224,0.006801461,0.00009543134,0.0003639232,0.010100309,0.00012719788],"about_ca_topic_score_codex":0.000026218417,"about_ca_topic_score_gemma":0.000005032998,"teacher_disagreement_score":0.42735156,"about_ca_system_score_codex":0.000027249023,"about_ca_system_score_gemma":0.000015028748,"threshold_uncertainty_score":0.22696868},"labels":[],"label_agreement":null},{"id":"W2107975633","doi":"10.1109/coginf.2006.365686","title":"Reducing Cognitive Overload by Meta-Learning Assisted Algorithm Selection","year":2006,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"","keywords":"Computer science; Reduct; Meta learning (computer science); Rough set; Machine learning; Ranking (information retrieval); Process (computing); Feature selection; Data mining; Reduction (mathematics); Artificial intelligence; Information overload; Algorithm; Cognitive load; Set (abstract data type); Cognition","score_opus":0.018530123870357598,"score_gpt":0.26149941496955814,"score_spread":0.24296929109920054,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2107975633","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":[0.0017634016,0.00013551701,0.97723496,0.00054945005,0.000087888904,0.00008293247,0.000004372612,0.00056908926,0.019572387],"genre_scores_gemma":[0.8576499,0.000009644942,0.12225035,0.00019026885,0.0001275429,0.00003655483,0.0002738666,0.000015872392,0.019445984],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986538,0.00021039917,0.0002099716,0.0004519019,0.00025887025,0.00021504129],"domain_scores_gemma":[0.99938244,0.00014688056,0.00014109112,0.00017235875,0.000109662804,0.000047547932],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003894742,0.00013443838,0.00016074412,0.00009436845,0.0002695911,0.00026031854,0.00022259107,0.00006252228,0.0001274617],"category_scores_gemma":[0.00009834794,0.00011505688,0.00007549074,0.0004932344,0.000019380179,0.00052873633,0.000066898414,0.0002717523,0.000086363456],"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":[0.000005812459,0.00020550667,0.0016962561,0.000009925515,0.00025311823,0.000003841493,0.00013709228,0.0005619965,0.011216519,0.010727405,0.026418304,0.9487642],"study_design_scores_gemma":[0.0005338587,0.0001501704,0.025338085,0.000014375595,0.00022714295,0.00005400281,0.00007030768,0.90923953,0.010084946,0.00043142613,0.053410467,0.0004456926],"about_ca_topic_score_codex":0.0015285064,"about_ca_topic_score_gemma":0.000014683001,"teacher_disagreement_score":0.94831854,"about_ca_system_score_codex":0.000041557792,"about_ca_system_score_gemma":0.000030480565,"threshold_uncertainty_score":0.46918833},"labels":[],"label_agreement":null},{"id":"W2112364454","doi":"10.25080/majora-14bd3278-006","title":"Hyperopt-Sklearn: Automatic Hyperparameter Configuration for Scikit-Learn","year":2014,"lang":"en","type":"article","venue":"Proceedings of the Python in Science Conferences","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":298,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"MNIST database; Hyperparameter; Computer science; Artificial intelligence; Preprocessor; Machine learning; Benchmarking; Classifier (UML); Support vector machine; Pattern recognition (psychology); Data mining; Deep learning","score_opus":0.024583413551202186,"score_gpt":0.27673620596396115,"score_spread":0.25215279241275895,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2112364454","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":[0.92285174,0.000021996444,0.05064991,0.0076362253,0.0005931001,0.0006038392,0.0000017917183,0.000162175,0.017479198],"genre_scores_gemma":[0.9755748,0.000004943371,0.024048705,0.0001409146,0.00003248458,0.000047397654,6.8302126e-7,0.0000042125953,0.00014588238],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99822706,0.000027187107,0.00039110673,0.00049783074,0.0005466033,0.00031022626],"domain_scores_gemma":[0.99853337,0.00022971406,0.0003929795,0.00029518083,0.0004678353,0.00008091439],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027662013,0.00012823957,0.00019897713,0.00024801676,0.00034630435,0.0005214636,0.0023982555,0.00005091596,0.000011758244],"category_scores_gemma":[0.0036705579,0.00008663438,0.000053160868,0.0010689647,0.0005671994,0.0011606831,0.00024164753,0.00015609906,0.000008355416],"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":[0.0000093535555,0.000070112554,0.028859515,0.00012740272,0.000003856459,2.7128364e-8,0.0035152542,0.000079274185,0.047381338,0.7142948,0.00020294708,0.20545615],"study_design_scores_gemma":[0.0004114364,0.00021172047,0.08197734,0.00016268896,0.000009170723,0.0000065885783,0.00081455114,0.8525357,0.026130227,0.0320619,0.005417144,0.00026153558],"about_ca_topic_score_codex":0.000056320372,"about_ca_topic_score_gemma":0.000007758607,"teacher_disagreement_score":0.85245645,"about_ca_system_score_codex":0.00003361907,"about_ca_system_score_gemma":0.00025761462,"threshold_uncertainty_score":0.50284857},"labels":[],"label_agreement":null},{"id":"W2113145584","doi":"","title":"Multi-Task Bayesian Optimization","year":2013,"lang":"en","type":"article","venue":"Digital Access to Scholarship at Harvard (DASH) (Harvard University)","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":452,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Defense Advanced Research Projects Agency","keywords":"Bayesian optimization; Hyperparameter; Computer science; Gaussian process; Machine learning; Bayesian probability; Artificial intelligence; Task (project management); Gaussian","score_opus":0.02370578556113782,"score_gpt":0.2429140372040699,"score_spread":0.2192082516429321,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2113145584","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":[0.039142147,0.0000051302854,0.9363591,0.0013381601,0.00032148388,0.00078672817,0.000094018724,0.0009317293,0.021021476],"genre_scores_gemma":[0.9427283,0.000021823995,0.04517494,0.0009412361,0.00008059952,0.000013606734,0.00038697498,0.000047128226,0.010605398],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.997226,0.00017797582,0.00033637663,0.0010890355,0.0005477737,0.0006228571],"domain_scores_gemma":[0.9973358,0.000120156474,0.00023369183,0.0012522218,0.00040714818,0.00065097224],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.00024704833,0.00037954678,0.00030442013,0.00077021535,0.00056874024,0.0047595464,0.003684237,0.00018897546,0.0007069896],"category_scores_gemma":[0.00040751556,0.00041371217,0.00015742712,0.001785575,0.00007251638,0.017928284,0.002149191,0.00042977094,0.011119201],"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":[0.00031242947,0.0018018044,0.60737514,0.00024606762,0.00044704814,0.00039781997,0.0016026532,0.06974005,0.0056510638,0.03902546,0.027564984,0.2458355],"study_design_scores_gemma":[0.0013879191,0.00015021853,0.20404401,0.00008863234,0.00003438215,0.000025261455,0.0000593938,0.11836573,0.0005619449,0.00023873681,0.6738371,0.0012066266],"about_ca_topic_score_codex":0.00007968314,"about_ca_topic_score_gemma":0.000032552653,"teacher_disagreement_score":0.90358615,"about_ca_system_score_codex":0.00038145747,"about_ca_system_score_gemma":0.00010334892,"threshold_uncertainty_score":0.9998315},"labels":[],"label_agreement":null},{"id":"W2113635748","doi":"","title":"Quickly Boosting Decision Trees - Pruning Underachieving Features Early","year":2013,"lang":"en","type":"article","venue":"CaltechAUTHORS (California Institute of Technology)","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":123,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Army Research Office; Natural Sciences and Engineering Research Council of Canada; Office of Naval Research; Multidisciplinary University Research Initiative; Gordon and Betty Moore Foundation; National Aeronautics and Space Administration","keywords":"Boosting (machine learning); Computer science; Exploit; Machine learning; Artificial intelligence; Decision tree; Gradient boosting; Pruning; Classifier (UML); Training set; Random forest","score_opus":0.011343138029806726,"score_gpt":0.24745450426567872,"score_spread":0.236111366235872,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2113635748","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":[0.32418355,0.00037242039,0.66758746,0.004680851,0.0004551506,0.00036711284,0.000010885681,0.00122001,0.0011225818],"genre_scores_gemma":[0.74857014,0.000029385124,0.25109965,0.00008023319,0.000041365663,0.000047639645,0.000015709515,0.000018707959,0.0000971751],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99772453,0.000046020923,0.0006287515,0.00070535776,0.00039271906,0.00050264533],"domain_scores_gemma":[0.99783087,0.00010556586,0.0004295918,0.0012865824,0.00020698202,0.00014040174],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00051258405,0.00029832643,0.00038638277,0.0009209096,0.0004296978,0.00021010441,0.001841768,0.00042735087,0.000017616472],"category_scores_gemma":[0.0013954984,0.0002638687,0.00010622675,0.0014572018,0.00031114084,0.0010487675,0.00073732616,0.00080468156,0.00024378975],"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":[0.00000940289,0.00008245546,0.010984378,0.00005029484,0.000029655725,0.000012272676,0.00013211177,0.00053466315,0.017016858,0.18536876,0.0010583942,0.7847208],"study_design_scores_gemma":[0.0030591462,0.0013491584,0.2026611,0.0026213196,0.00013671565,0.00047283492,0.00065589056,0.2345501,0.0507776,0.23832142,0.26202467,0.003370041],"about_ca_topic_score_codex":0.00027407228,"about_ca_topic_score_gemma":0.000036669404,"teacher_disagreement_score":0.78135073,"about_ca_system_score_codex":0.000077348785,"about_ca_system_score_gemma":0.00009722253,"threshold_uncertainty_score":0.99998134},"labels":[],"label_agreement":null},{"id":"W2116283693","doi":"10.1109/tsmcb.2004.824524","title":"Enhancing Prototype Reduction Schemes With Recursion: A Method Applicable for “Large” Data Sets","year":2004,"lang":"en","type":"article","venue":"IEEE Transactions on Systems Man and Cybernetics Part B (Cybernetics)","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":42,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Reduction (mathematics); Recursion (computer science); Computer science; Data reduction; Algorithm; Data mining; Mathematics","score_opus":0.03595339579860602,"score_gpt":0.3036403519203792,"score_spread":0.2676869561217732,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2116283693","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":[0.0024482945,0.00028618448,0.99324423,0.00077772717,0.0005842885,0.0017762819,0.000114625676,0.0002778683,0.0004905049],"genre_scores_gemma":[0.8288547,0.000227508,0.16722119,0.00009006362,0.00021022283,0.0007902514,0.000120355406,0.000067145826,0.002418593],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9972173,0.00016138966,0.0005176026,0.0011629205,0.00045227795,0.00048853434],"domain_scores_gemma":[0.99750483,0.00011995927,0.0002637637,0.0017092867,0.00017537035,0.00022681172],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00093508326,0.00034680762,0.0003658983,0.0001737062,0.00047293777,0.00041074783,0.000780527,0.00018586493,0.000009482504],"category_scores_gemma":[0.0000140367,0.00030987558,0.00005695511,0.0004117443,0.000064814994,0.00041751727,0.00002165447,0.0003798064,0.000046967925],"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":[0.002174159,0.005890884,0.00019709094,0.004159069,0.0017680736,0.00005920825,0.011628027,0.1175235,0.031030135,0.38004965,0.008451786,0.43706843],"study_design_scores_gemma":[0.006684262,0.0033562947,0.00019402048,0.001360145,0.0004164422,0.0007508879,0.0011124699,0.3373946,0.04917622,0.0026625607,0.5948194,0.0020726826],"about_ca_topic_score_codex":0.00018867933,"about_ca_topic_score_gemma":0.000118466516,"teacher_disagreement_score":0.82640636,"about_ca_system_score_codex":0.00008296744,"about_ca_system_score_gemma":0.0001345835,"threshold_uncertainty_score":0.9999353},"labels":[],"label_agreement":null},{"id":"W2118437143","doi":"10.1007/978-3-319-03680-9_42","title":"Ultimate Order Statistics-Based Prototype Reduction Schemes","year":2013,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Computer science; Naive Bayes classifier; Parametric statistics; Artificial intelligence; Machine learning; Classifier (UML); Data mining; Pattern recognition (psychology); Bayes' theorem; Algorithm; Bayesian probability; Support vector machine; Statistics; Mathematics","score_opus":0.017386322631367704,"score_gpt":0.2692044193975189,"score_spread":0.2518180967661512,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2118437143","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":[0.00002033721,0.00010372745,0.99476737,0.001186942,0.0010226304,0.0007279177,0.000013258879,0.00026319758,0.0018946134],"genre_scores_gemma":[0.01778194,0.00001372635,0.9805179,0.00044070918,0.00028060493,0.00005149188,0.00007609468,0.00003329227,0.00080422836],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9967947,0.000049630235,0.00045055762,0.0013901095,0.0008256588,0.00048936],"domain_scores_gemma":[0.9972795,0.00020281914,0.00036266333,0.0015027631,0.0005081622,0.00014408257],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006360414,0.00042649693,0.0003457097,0.0006166718,0.000276988,0.00076030265,0.0020797756,0.00024648634,0.00012905446],"category_scores_gemma":[0.00020608911,0.00037961922,0.000050213162,0.0005701922,0.0004649434,0.0006349592,0.00043199744,0.00079360325,0.00036449087],"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":[0.0000072362627,0.000030114164,0.000026866694,0.000068743786,0.0000059021527,0.000009755944,0.00013161449,0.014914878,0.00025452062,0.047833294,0.00012675917,0.9365903],"study_design_scores_gemma":[0.00021360411,0.00018249024,0.00019978,0.00019209404,0.000005884451,0.000030045265,5.858198e-8,0.9412204,0.0007012957,0.04746756,0.0092755575,0.00051123364],"about_ca_topic_score_codex":0.000053965017,"about_ca_topic_score_gemma":0.000013131353,"teacher_disagreement_score":0.9360791,"about_ca_system_score_codex":0.00019538675,"about_ca_system_score_gemma":0.0006950058,"threshold_uncertainty_score":0.9998656},"labels":[],"label_agreement":null},{"id":"W2120501001","doi":"","title":"Lifelong Machine Learning Systems: Beyond Learning Algorithms","year":2013,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":292,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Acadia University","funders":"","keywords":"Computer science; Lifelong learning; Listing (finance); Artificial intelligence; Field (mathematics); Task (project management); Machine learning; Remainder; Key (lock); Position paper; Psychology; Engineering","score_opus":0.012633824492797771,"score_gpt":0.23234648508530595,"score_spread":0.21971266059250819,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2120501001","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":[0.005278739,0.0005911687,0.94970423,0.0027355242,0.0004817153,0.00027660117,8.2812505e-7,0.0014432643,0.03948791],"genre_scores_gemma":[0.9294171,0.00006625811,0.040925324,0.00028073025,0.00021618369,0.0000704875,0.00007832713,0.00002678548,0.028918846],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99807316,0.00032121912,0.00032849048,0.00052964245,0.00036693606,0.00038057216],"domain_scores_gemma":[0.9987991,0.00019325604,0.00017704949,0.00052391656,0.00013351158,0.0001731891],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005961136,0.00019346138,0.00020190697,0.00016462727,0.00040480765,0.0008449987,0.0007761957,0.0000861591,0.00020665376],"category_scores_gemma":[0.00027258156,0.00016151516,0.000053986565,0.000407137,0.000029426828,0.0010825298,0.0002976034,0.00064020633,0.0020891428],"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":[0.000003918486,0.00013432614,0.07660656,0.00010786594,0.00007657265,0.00001886606,0.001483384,0.020406986,0.0023814514,0.14184645,0.009486262,0.7474474],"study_design_scores_gemma":[0.00018224049,0.00007728177,0.007963277,0.000014477002,0.000003628364,0.000027382206,0.00012068239,0.91232187,0.000059912112,0.00016924283,0.078835614,0.00022442339],"about_ca_topic_score_codex":0.001836736,"about_ca_topic_score_gemma":0.000007924457,"teacher_disagreement_score":0.9241383,"about_ca_system_score_codex":0.00003870386,"about_ca_system_score_gemma":0.000034978115,"threshold_uncertainty_score":0.99868786},"labels":[],"label_agreement":null},{"id":"W2122135337","doi":"10.1016/j.patcog.2007.03.006","title":"On using prototype reduction schemes to optimize dissimilarity-based classification","year":2007,"lang":"en","type":"article","venue":"Pattern Recognition","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Pattern recognition (psychology); Artificial intelligence; Classifier (UML); Discriminant; Computer science; Naive Bayes classifier; Set (abstract data type); Computation; Linear discriminant analysis; Machine learning; Data mining; Support vector machine; Algorithm","score_opus":0.08314667445788243,"score_gpt":0.33239786844005564,"score_spread":0.2492511939821732,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2122135337","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":[0.15149973,0.0000032695416,0.84543097,0.0012168438,0.00028221228,0.0005013267,0.000009044508,0.00021672508,0.000839854],"genre_scores_gemma":[0.89824325,0.0000010917818,0.10084262,0.00044908008,0.0001372985,0.000058866088,0.00023345213,0.000015034788,0.00001929598],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99855334,0.00010694033,0.00028018426,0.0005070254,0.0003060942,0.00024643223],"domain_scores_gemma":[0.9990093,0.00008093863,0.00016351684,0.00047270113,0.00014978483,0.00012377511],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007583075,0.0001470583,0.00010692669,0.00029291573,0.000197004,0.0001598773,0.00027185233,0.000091412294,0.000046447756],"category_scores_gemma":[0.00015501409,0.00014871477,0.000045070592,0.00044344564,0.000018348175,0.00036033863,0.000036118385,0.00020872544,0.00025324995],"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":[0.00012135967,0.00022454193,0.0014704645,0.000041148982,0.000008201437,0.0000047543667,0.00015410704,0.00039367023,0.015487417,0.00075687916,0.00016175486,0.9811757],"study_design_scores_gemma":[0.0014942669,0.0008970923,0.07634715,0.0004869675,0.000042215972,0.00006439552,0.000112739275,0.8367103,0.07474377,0.004292978,0.0037094394,0.0010987044],"about_ca_topic_score_codex":0.000036153593,"about_ca_topic_score_gemma":0.0000041933486,"teacher_disagreement_score":0.98007697,"about_ca_system_score_codex":0.00012103931,"about_ca_system_score_gemma":0.000039858864,"threshold_uncertainty_score":0.6064412},"labels":[],"label_agreement":null},{"id":"W2122352257","doi":"10.1109/icpr.2014.221","title":"On Meta-learning for Dynamic Ensemble Selection","year":2014,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Classifier (UML); Training set; Ensemble learning; Pattern recognition (psychology); Cascading classifiers; Feature selection","score_opus":0.02146099593270745,"score_gpt":0.2790567691335513,"score_spread":0.25759577320084387,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2122352257","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":[0.001367484,0.000005986919,0.98638415,0.0014159195,0.00008260085,0.00007655894,1.5077052e-7,0.0003015031,0.010365642],"genre_scores_gemma":[0.9211322,0.0000013393516,0.07285101,0.00031358906,0.000021576501,0.00003196996,0.0000133211,0.000005756089,0.0056292373],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993311,0.00009273008,0.00009149972,0.00025825482,0.000101387086,0.0001249946],"domain_scores_gemma":[0.9993895,0.00026885752,0.000054722368,0.00021452171,0.000039964925,0.000032418542],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004569344,0.00006963171,0.00009482624,0.00006607634,0.0001579389,0.00009813198,0.00021665164,0.000030297768,0.000025946689],"category_scores_gemma":[0.00027713252,0.000053306405,0.0000584374,0.0001339355,0.00000484407,0.0001550443,0.000026242868,0.00010259267,0.000105813306],"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":[0.0000063957727,0.000028658736,0.00009317852,0.00000931221,0.00004536925,4.029336e-8,0.000048804082,0.0066498853,0.0021996568,0.782661,0.0017165771,0.20654109],"study_design_scores_gemma":[0.000114453185,0.00017950068,0.00080468354,0.000001195865,0.0000218881,0.0000015759232,0.0000021947649,0.94180477,0.00049846194,0.0069507584,0.049548224,0.00007231044],"about_ca_topic_score_codex":0.00001668626,"about_ca_topic_score_gemma":0.00001659796,"teacher_disagreement_score":0.93515486,"about_ca_system_score_codex":0.000016624886,"about_ca_system_score_gemma":0.000009557614,"threshold_uncertainty_score":0.21737722},"labels":[],"label_agreement":null},{"id":"W2125381833","doi":"10.1109/cmpsac.1979.762465","title":"Some new algorithms and software implementation methods for pattern recognition research","year":2005,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Software; Interpreter; Software system; Algorithm; Software development; Data mining; Artificial intelligence; Machine learning; Programming language","score_opus":0.17592168448828957,"score_gpt":0.4991944641069069,"score_spread":0.32327277961861733,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2125381833","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":[0.0004541521,0.00016535369,0.9904767,0.008393944,0.000067261055,0.00023240023,0.0000062348213,0.00012655617,0.00007737534],"genre_scores_gemma":[0.00273245,0.00007208826,0.99579746,0.0003976619,0.0003586624,0.000045462493,0.000129419,0.0000063445104,0.00046043465],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990125,0.00020076083,0.00014699236,0.00031031083,0.00013859759,0.00019085077],"domain_scores_gemma":[0.99917215,0.00037058647,0.000041887062,0.00023496474,0.00009968515,0.00008072273],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001592626,0.0000597621,0.000062480656,0.00012087016,0.00017105468,0.00020076902,0.00020848453,0.0000342943,0.000049924016],"category_scores_gemma":[0.0001453867,0.00005384954,0.000017299979,0.00016191279,0.0000137794705,0.0007463605,0.0001014759,0.00010137896,0.00003957653],"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":[0.0000013332514,0.000008808184,0.00016867039,0.000006581805,0.0000028467568,6.0110494e-8,0.00022452009,9.35576e-7,0.00020750167,0.0017426006,0.0032761085,0.99436],"study_design_scores_gemma":[0.0020250846,0.0004664132,0.018642135,0.000024706593,0.000014197261,0.000025267795,0.0003558986,0.5147909,0.011253629,0.093154095,0.35878983,0.0004578275],"about_ca_topic_score_codex":0.0002891283,"about_ca_topic_score_gemma":0.00004963708,"teacher_disagreement_score":0.9939022,"about_ca_system_score_codex":0.000029388451,"about_ca_system_score_gemma":0.000045516794,"threshold_uncertainty_score":0.21959205},"labels":[],"label_agreement":null},{"id":"W2125592902","doi":"10.1613/jair.1509","title":"Learning From Labeled And Unlabeled Data: An Empirical Study Across Techniques And Domains","year":2005,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence Research","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":97,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Labeled data; Semi-supervised learning; Relevance (law); Independence (probability theory); Selection (genetic algorithm); Empirical research; Bivariate analysis; Process (computing); Selection bias","score_opus":0.2839496994906822,"score_gpt":0.524008033142466,"score_spread":0.2400583336517838,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2125592902","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":[0.91874206,0.00031259173,0.07779205,0.0028402314,0.000049982194,0.00016873509,0.0000044503163,0.00004600145,0.000043903616],"genre_scores_gemma":[0.9709637,0.00032377528,0.028138937,0.000026018397,0.0004920706,0.0000030749038,0.000006676139,0.000009830418,0.000035930138],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99658436,0.0011041767,0.000601707,0.00049725437,0.0008395939,0.00037291404],"domain_scores_gemma":[0.9976065,0.00076932,0.00021226912,0.00069767324,0.00046347498,0.00025074268],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008206872,0.00012146596,0.0002443503,0.00024695942,0.00052514434,0.0008792608,0.0013967603,0.00008331259,0.000013393298],"category_scores_gemma":[0.0011297979,0.00009840656,0.000019660507,0.000552252,0.00021457131,0.0016913981,0.0009282492,0.0012439161,0.000015334941],"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":[0.0000959222,0.00047899576,0.017674217,0.000004650558,0.00002506583,0.000057716825,0.007070971,0.000048683978,0.004432799,0.0008270133,0.00009016633,0.9691938],"study_design_scores_gemma":[0.00058389746,0.009978671,0.038079116,0.00018106551,0.000046471272,0.00040188912,0.03539537,0.828493,0.027718116,0.016828086,0.041469652,0.0008246821],"about_ca_topic_score_codex":0.00021818209,"about_ca_topic_score_gemma":0.0003532617,"teacher_disagreement_score":0.9683691,"about_ca_system_score_codex":0.00005180987,"about_ca_system_score_gemma":0.00012434376,"threshold_uncertainty_score":0.8478733},"labels":[],"label_agreement":null},{"id":"W2125943921","doi":"10.1145/1401890.1401965","title":"Get another label? improving data quality and data mining using multiple, noisy labelers","year":2008,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":1114,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; National Science Foundation","keywords":"Computer science; Quality (philosophy); Sequence labeling; Set (abstract data type); Crowdsourcing; Artificial intelligence; Imperfect; Focus (optics); Machine learning; Outsourcing; Labeled data; Data quality; Data mining; Task (project management); Engineering","score_opus":0.3107738534872337,"score_gpt":0.38542256523394575,"score_spread":0.07464871174671206,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2125943921","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":[0.17313373,0.000172531,0.82411677,0.0012566163,0.00012836141,0.0001122892,0.0001209972,0.00026129695,0.0006974303],"genre_scores_gemma":[0.4296047,0.000025541309,0.5690429,0.0005633169,0.00006582499,9.757795e-7,0.0003798271,0.0000125170445,0.00030434786],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99812233,0.00016271684,0.0002812086,0.00094256084,0.00024675461,0.0002444426],"domain_scores_gemma":[0.9958273,0.00025147374,0.00016123189,0.0036456808,0.00004007361,0.00007423348],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011445722,0.00013542287,0.00015716787,0.000067219684,0.00032030404,0.00018040556,0.0023609877,0.000055254735,0.000011788924],"category_scores_gemma":[0.0006510016,0.00011936708,0.0000075420207,0.00023027457,0.000076049524,0.0018863579,0.0028744265,0.00014370221,0.000012058757],"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":[0.000021311667,0.00018566535,0.34402758,0.00009520839,0.00005125175,0.000024242861,0.0014046746,0.00006588954,0.016666472,0.0026938647,0.007980296,0.62678355],"study_design_scores_gemma":[0.0004142925,0.000010493948,0.030393872,0.000008936322,0.00000555634,0.00003126034,0.000050875453,0.96029127,0.000044715605,0.000009382456,0.008549623,0.0001897479],"about_ca_topic_score_codex":0.0022444394,"about_ca_topic_score_gemma":0.00023637102,"teacher_disagreement_score":0.96022534,"about_ca_system_score_codex":0.000018177514,"about_ca_system_score_gemma":0.00008865914,"threshold_uncertainty_score":0.48676485},"labels":[],"label_agreement":null},{"id":"W2126238368","doi":"10.1007/978-1-4757-3359-4_13","title":"Learning via Prototype Generation and Filtering","year":2001,"lang":"en","type":"book-chapter","venue":"","topic":"Machine Learning and Data Classification","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":"Western University","funders":"","keywords":"Computer science; Artificial intelligence; Noise reduction; Reduction (mathematics); Machine learning; Noise (video); Data mining; Pattern recognition (psychology); Algorithm; Mathematics; Image (mathematics)","score_opus":0.03113332019009729,"score_gpt":0.24534275016471915,"score_spread":0.21420942997462186,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2126238368","genre_codex":"methods","genre_gemma":"other","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":[0.000012797035,0.000074007265,0.52085423,0.00026117408,0.000074072355,0.00015817497,3.796961e-7,0.00018577189,0.4783794],"genre_scores_gemma":[0.0089143,0.00031774596,0.034172084,0.0001652087,0.00041666807,0.000027603712,0.00016251155,0.000034768414,0.9557891],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991266,0.000020644615,0.00016660028,0.00041956446,0.00015515379,0.00011145159],"domain_scores_gemma":[0.9994132,0.000020728221,0.000120441124,0.00035030907,0.000041911302,0.000053424366],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016933067,0.00015987168,0.00012871884,0.00009928958,0.00013933949,0.00020904448,0.00022907867,0.00013067672,0.00017730649],"category_scores_gemma":[0.00001757935,0.00014800628,0.000025550804,0.000023650802,0.000017892327,0.00023055545,0.00016455441,0.00032686538,0.00014341816],"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":[0.0000024066464,0.0000038713224,0.00006628652,0.000025617874,0.000011849795,0.0000072069784,0.00009299057,0.00008612376,0.00080317806,0.3733059,0.0006120287,0.62498254],"study_design_scores_gemma":[0.000081695354,0.00014052195,0.00011880801,0.00003189899,0.000006229013,0.00004363578,8.932803e-7,0.2508689,0.000046340534,0.0026933078,0.7457066,0.00026117728],"about_ca_topic_score_codex":0.000019754494,"about_ca_topic_score_gemma":0.00001074132,"teacher_disagreement_score":0.7450946,"about_ca_system_score_codex":0.000020034859,"about_ca_system_score_gemma":0.00001985827,"threshold_uncertainty_score":0.6035521},"labels":[],"label_agreement":null},{"id":"W2126443908","doi":"","title":"Bayesian Comparison of Machine Learning Algorithms on Single and Multiple Datasets","year":2012,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Computer science; Sign test; Machine learning; Wilcoxon signed-rank test; Algorithm; Bayesian probability; Key (lock); Artificial intelligence; Set (abstract data type); Test data; Bayesian network; Mathematics; Statistics; Mann–Whitney U test","score_opus":0.03976322648787854,"score_gpt":0.3023984921882241,"score_spread":0.26263526570034557,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2126443908","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":[0.014363412,0.00031562572,0.9813527,0.00051218073,0.0001414519,0.0000889789,0.000032642638,0.00016325277,0.0030297707],"genre_scores_gemma":[0.94853073,0.000004914464,0.051024947,0.000056635374,0.000031693464,0.0000011161238,0.00023110908,0.0000050858534,0.0001137908],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991657,0.00010116216,0.0001742581,0.00019843999,0.00016491016,0.00019552806],"domain_scores_gemma":[0.9992272,0.00019134789,0.00010848574,0.00036157036,0.000014676335,0.00009666545],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034794124,0.00008816005,0.00013107024,0.00007328689,0.00010761773,0.000047910005,0.0002498835,0.000033955635,0.000020252088],"category_scores_gemma":[0.00016034284,0.00007272844,0.000015278374,0.00012882988,0.000026947262,0.00035963353,0.0001714655,0.00016280814,0.000024679419],"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":[0.000013610944,0.0006486824,0.44938993,0.000032466887,0.0000151542135,5.9068554e-7,0.0011633316,0.00042427285,0.0046164156,0.015672745,0.0019392815,0.5260835],"study_design_scores_gemma":[0.00025901344,0.00017247516,0.03050174,0.000010949107,0.0000040776604,0.000004256282,0.000051331983,0.9282109,0.0050490387,0.000026400283,0.035589185,0.00012059908],"about_ca_topic_score_codex":0.00015523456,"about_ca_topic_score_gemma":0.000013874784,"teacher_disagreement_score":0.9341673,"about_ca_system_score_codex":0.000009718973,"about_ca_system_score_gemma":0.0000050745602,"threshold_uncertainty_score":0.296578},"labels":[],"label_agreement":null},{"id":"W2128309607","doi":"10.1088/1749-4699/8/1/014007","title":"SkData: data sets and algorithm evaluation protocols in Python","year":2015,"lang":"en","type":"article","venue":"Computational Science & Discovery","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Rowland Institute at Harvard; National Science Foundation","keywords":"Python (programming language); Computer science; Upload; Parsing; Scripting language; Benchmark (surveying); Algorithm; Set (abstract data type); Data structure; On the fly; Data mining; Programming language; Theoretical computer science; World Wide Web; Operating system","score_opus":0.15672703877176145,"score_gpt":0.42337798945473637,"score_spread":0.26665095068297495,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2128309607","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":[0.013376285,0.00008207884,0.98092544,0.0017696383,0.0002128978,0.0024544836,0.00005255088,0.00007565498,0.0010509836],"genre_scores_gemma":[0.7427831,0.0000033019614,0.25551006,0.000292782,0.000085570944,0.0004426405,0.0008203692,0.000008162324,0.000053969037],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997382,0.00014823028,0.00023963579,0.0007937814,0.001215315,0.00022103224],"domain_scores_gemma":[0.9986321,0.00010820149,0.00012058491,0.0007881738,0.00021752252,0.00013344207],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004455702,0.0001022208,0.000103542945,0.0002157304,0.0001431673,0.00093777705,0.0015560692,0.000027140966,0.0000023441953],"category_scores_gemma":[0.00073066645,0.00009217568,0.000008374013,0.0009912348,0.00021751788,0.0071984353,0.0010406737,0.000119813696,0.000026484899],"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":[0.000010813844,0.00019010011,0.011586297,0.000014342908,0.0000036487918,0.0000067160877,0.00085160387,0.04004339,0.000104089646,0.04354638,0.0026057642,0.90103686],"study_design_scores_gemma":[0.0003920565,0.000035235345,0.11351438,0.000022922464,0.0000017446565,0.000013642643,0.000040242867,0.8645036,0.000008662435,0.019652607,0.0017057026,0.00010917503],"about_ca_topic_score_codex":0.000086154934,"about_ca_topic_score_gemma":0.00002074495,"teacher_disagreement_score":0.90092766,"about_ca_system_score_codex":0.00014228301,"about_ca_system_score_gemma":0.0011704161,"threshold_uncertainty_score":0.9043006},"labels":[],"label_agreement":null},{"id":"W2129718951","doi":"10.1109/wits.1994.513862","title":"Nonparametric classifier design using vector quantization","year":2002,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Nonparametric statistics; Vector quantization; Computer science; Classifier (UML); Artificial intelligence; Pattern recognition (psychology); Machine learning; Support vector machine; Quantization (signal processing); Data mining; Algorithm; Mathematics; Statistics","score_opus":0.12849650664400786,"score_gpt":0.2882021818433756,"score_spread":0.15970567519936774,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2129718951","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":[0.0011033803,0.00007280956,0.992329,0.00067326525,0.00017811003,0.00008305007,3.0852397e-7,0.00024112307,0.005318938],"genre_scores_gemma":[0.63720995,0.000014270479,0.3614745,0.0001646214,0.000037746075,0.000002657484,0.0000025953673,0.000005750719,0.0010878707],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991004,0.00012544577,0.00014922784,0.0002768727,0.0001907691,0.00015729459],"domain_scores_gemma":[0.99925834,0.00012023134,0.00007314783,0.00044367992,0.000048982347,0.000055626584],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023840994,0.00008078328,0.00007682395,0.00019086753,0.000121629506,0.00019500667,0.00037896074,0.00004814996,0.00018685914],"category_scores_gemma":[0.00017305576,0.00007018643,0.000024406905,0.001004409,0.000014657717,0.0004893829,0.00005494434,0.00009019211,0.0004024644],"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":[0.000007564804,0.0004155364,0.008040299,0.000029720395,0.00003361281,0.000012373701,0.0007104695,0.019891933,0.019876922,0.49689358,0.022849064,0.43123892],"study_design_scores_gemma":[0.00009637602,0.000027026144,0.0032700372,0.0000032705295,0.000002915846,0.000009506448,0.0000038026997,0.99153155,0.00039451124,0.00018798343,0.004371565,0.00010145343],"about_ca_topic_score_codex":0.000029408004,"about_ca_topic_score_gemma":9.400095e-7,"teacher_disagreement_score":0.97163963,"about_ca_system_score_codex":0.000033476135,"about_ca_system_score_gemma":0.000012750126,"threshold_uncertainty_score":0.51729995},"labels":[],"label_agreement":null},{"id":"W2130969489","doi":"10.1109/icdm.2002.1184010","title":"ESRS: a case selection algorithm using extended similarity-based rough sets","year":2003,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","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":"University of Regina","funders":"","keywords":"Similarity (geometry); Rough set; Computer science; Selection (genetic algorithm); Data mining; Set (abstract data type); Algorithm; Data set; Artificial intelligence; Function (biology); Noise (video); Pattern recognition (psychology); Case-based reasoning; Image (mathematics)","score_opus":0.0348741007945133,"score_gpt":0.3076157898431524,"score_spread":0.2727416890486391,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2130969489","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":[0.0043754745,0.000018432074,0.9925136,0.0003180386,0.00014640254,0.00010114886,0.0000026250837,0.00032296282,0.0022013152],"genre_scores_gemma":[0.3596506,6.6802465e-7,0.63977575,0.00038639523,0.000020174683,0.0000050134117,0.000011941953,0.000007066722,0.00014236617],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99877167,0.00023977098,0.00017316663,0.00040331,0.00018829734,0.00022379863],"domain_scores_gemma":[0.9992594,0.00006613577,0.00007958184,0.00042468475,0.00008513152,0.00008503188],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045092424,0.00012233798,0.00010078562,0.00010870002,0.00027617352,0.00020791632,0.00019378416,0.00006825052,0.000055414068],"category_scores_gemma":[0.00011087989,0.00011438622,0.000039640672,0.0005441029,0.000018021821,0.00047024948,0.00003057198,0.00018015917,0.000027399528],"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":[0.000012953769,0.0008115816,0.0031283572,0.00006550691,0.00005446257,0.0009783084,0.00062096136,0.021280512,0.002760445,0.14071697,0.0026961502,0.8268738],"study_design_scores_gemma":[0.0002781538,0.000042518554,0.00025406884,0.000005333881,0.0000069568664,0.0010096736,0.000016828446,0.98824936,0.0015349663,0.0008463626,0.0075987754,0.00015702672],"about_ca_topic_score_codex":0.0003442515,"about_ca_topic_score_gemma":0.000040395887,"teacher_disagreement_score":0.96696883,"about_ca_system_score_codex":0.00006609726,"about_ca_system_score_gemma":0.00013257375,"threshold_uncertainty_score":0.46645346},"labels":[],"label_agreement":null},{"id":"W2134511703","doi":"10.1109/ccece.1998.685647","title":"A reliable composite classification strategy","year":2002,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Classifier (UML); Weighting; Computer science; A priori and a posteriori; Artificial intelligence; Pattern recognition (psychology); Quadratic classifier; Data mining; Classification scheme; Linear classifier; Machine learning; Random subspace method; Test data; Training set","score_opus":0.05029839216280017,"score_gpt":0.26470132508952754,"score_spread":0.21440293292672735,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2134511703","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":[0.002754621,0.00010944563,0.6682616,0.0056024636,0.00010828821,0.00008020314,8.227432e-7,0.0005561406,0.32252643],"genre_scores_gemma":[0.95884216,0.000035201934,0.030810634,0.00030162875,0.00003139301,0.000008255632,0.000012775581,0.000004287304,0.009953648],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99927676,0.00003617708,0.00013701982,0.00026535545,0.00014714386,0.00013755247],"domain_scores_gemma":[0.9992429,0.000027965256,0.000056187226,0.00057519844,0.00003990141,0.000057846293],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00012844414,0.000067677014,0.00006128818,0.000058583002,0.000109576285,0.00019398324,0.00046286915,0.000035713863,0.00022472134],"category_scores_gemma":[0.000014551636,0.000058614893,0.00002103278,0.00027023826,0.00001509446,0.00045223403,0.000050951792,0.000100294594,0.0013634769],"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":[0.0000012669118,0.00012060254,0.0032385166,0.000007814853,0.0000057021507,0.0000021783758,0.00014438167,0.000205017,0.0060233125,0.73505837,0.03775007,0.2174428],"study_design_scores_gemma":[0.00012043436,0.000033201028,0.028295854,0.0000033995314,0.0000016288745,0.000008120967,0.000011724677,0.9032419,0.00021854116,0.000963432,0.06699946,0.00010234094],"about_ca_topic_score_codex":0.000038373837,"about_ca_topic_score_gemma":0.0000029636378,"teacher_disagreement_score":0.9560875,"about_ca_system_score_codex":0.000017562377,"about_ca_system_score_gemma":0.000006437677,"threshold_uncertainty_score":0.9994141},"labels":[],"label_agreement":null},{"id":"W2140027094","doi":"10.1142/s0218195905001622","title":"GEOMETRIC PROXIMITY GRAPHS FOR IMPROVING NEAREST NEIGHBOR METHODS IN INSTANCE-BASED LEARNING AND DATA MINING","year":2005,"lang":"en","type":"article","venue":"International Journal of Computational Geometry & Applications","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":88,"is_retracted":false,"has_abstract":true,"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; Voronoi diagram; Classification rule; Computer science; Data mining; Decision rule; Pattern recognition (psychology); Artificial intelligence; Rule induction; Classifier (UML); Large margin nearest neighbor; Nearest neighbor graph; Mathematics","score_opus":0.036824472942890776,"score_gpt":0.38571561570188495,"score_spread":0.3488911427589942,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2140027094","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":[0.0041126767,0.00068444316,0.9910625,0.003456051,0.00013849488,0.00033611606,0.00004312153,0.000043199605,0.00012335142],"genre_scores_gemma":[0.37242565,0.000022489114,0.62688565,0.00017108064,0.00025433485,0.000053663447,0.00015894999,0.000009846135,0.000018319315],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99783206,0.00013886623,0.0007890661,0.00045119136,0.00058997853,0.00019885441],"domain_scores_gemma":[0.9962611,0.0016116506,0.0008291798,0.00031734566,0.00086573086,0.000114954666],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002052382,0.00015699396,0.00022851027,0.001572563,0.0001707303,0.00034087323,0.0016755295,0.00006859376,0.000009461567],"category_scores_gemma":[0.00078188116,0.00016000216,0.00007126693,0.0013525399,0.0000616155,0.0013409414,0.00029641626,0.0003620399,0.0000032787193],"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":[0.000033689474,0.00018614925,0.010333155,0.000027559121,0.000044102817,0.0000016546384,0.00005885643,0.058050957,0.00016475505,0.014893604,0.00008714048,0.9161184],"study_design_scores_gemma":[0.001431338,0.000094964045,0.033727482,0.00003980418,0.000022045058,0.000066563975,0.0000461927,0.84265286,0.00009352048,0.0071488763,0.11444968,0.0002266786],"about_ca_topic_score_codex":0.000010328816,"about_ca_topic_score_gemma":0.0000064847886,"teacher_disagreement_score":0.9158917,"about_ca_system_score_codex":0.00013333581,"about_ca_system_score_gemma":0.0003027564,"threshold_uncertainty_score":0.6524699},"labels":[],"label_agreement":null},{"id":"W2152625064","doi":"10.1109/icmla.2010.26","title":"How Dependencies Affect the Capability of Several Feature Selection Approaches to Extract the Key Features","year":2010,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Support vector machine; Feature selection; Computer science; Dependency (UML); Artificial intelligence; Machine learning; Feature (linguistics); Selection (genetic algorithm); Data mining; Pattern recognition (psychology)","score_opus":0.0408361604749496,"score_gpt":0.24603651218432576,"score_spread":0.20520035170937617,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2152625064","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":[0.31089938,0.00007416045,0.5312591,0.14961322,0.0005781951,0.0007603796,0.000006848974,0.0002969965,0.006511739],"genre_scores_gemma":[0.973242,0.0000011493917,0.023625221,0.00019555906,0.00010065543,0.000023069328,0.000004597424,0.0000043472996,0.0028034048],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99894404,0.00021629083,0.00008082706,0.0003050668,0.00029086389,0.00016289974],"domain_scores_gemma":[0.9987142,0.00030065767,0.00008083754,0.0008014516,0.00005810327,0.00004471509],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009678687,0.000113897564,0.00009572206,0.000037564525,0.00027624163,0.000360438,0.0009833114,0.00008502951,0.000008162006],"category_scores_gemma":[0.00041065167,0.000052290845,0.000060777587,0.00035781658,0.0000711952,0.00033597703,0.00013916337,0.00059096504,0.000005268748],"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":[0.00007667188,0.0003217609,0.045506474,0.00009572275,0.00009270169,0.0000011501759,0.012638465,0.0020463222,0.06693509,0.5232137,0.052568726,0.29650325],"study_design_scores_gemma":[0.00011871867,0.00010617985,0.8922033,0.000004750562,0.000013996434,0.0000686909,0.0003428075,0.06292334,0.013288635,0.001243364,0.029485686,0.00020054622],"about_ca_topic_score_codex":0.00023232422,"about_ca_topic_score_gemma":0.0018320113,"teacher_disagreement_score":0.8466968,"about_ca_system_score_codex":0.000012799827,"about_ca_system_score_gemma":0.00004813531,"threshold_uncertainty_score":0.3475712},"labels":[],"label_agreement":null},{"id":"W2156273182","doi":"10.1109/icmlc.2002.1175377","title":"Coverage-performance curves for classification in datasets with a typical data","year":2003,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Support vector machine; Scheme (mathematics); Function (biology); Pattern recognition (psychology); Contextual image classification; Fraction (chemistry); Data mining; Artificial intelligence; Machine learning; Image (mathematics); Mathematics","score_opus":0.06627517136276553,"score_gpt":0.30927984058270364,"score_spread":0.2430046692199381,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2156273182","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":[0.0029773384,0.00008727268,0.9920537,0.0018225166,0.000050487695,0.0002654561,0.00009139308,0.00007929334,0.0025725747],"genre_scores_gemma":[0.9084014,0.00016126108,0.08748348,0.0006883176,0.000014525226,0.000047929527,0.0029734059,0.0000068417567,0.00022282016],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99905837,0.00006658857,0.0001543613,0.00043182055,0.0001376661,0.00015118807],"domain_scores_gemma":[0.9983531,0.00010656266,0.00006040029,0.001413774,0.000026015432,0.00004011842],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00058407505,0.00007695786,0.00008813937,0.000053497384,0.000059081707,0.00007282185,0.0008574987,0.000027816222,0.000014171653],"category_scores_gemma":[0.00021068136,0.00005809756,0.000006035381,0.00027303825,0.000019791856,0.0009655472,0.00008168385,0.00009460809,0.00002961364],"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":[0.00021566237,0.0005445169,0.0949107,0.00043398148,0.00002370715,0.0000038362828,0.0001091369,0.00021542123,0.0004565074,0.591578,0.10960397,0.20190458],"study_design_scores_gemma":[0.0007034425,0.000108784814,0.15381308,0.000074158655,0.0000052695614,0.000014208375,0.000009252078,0.57908416,0.0001234313,0.000244823,0.26562756,0.00019182256],"about_ca_topic_score_codex":0.00000974196,"about_ca_topic_score_gemma":0.000047290763,"teacher_disagreement_score":0.90542406,"about_ca_system_score_codex":0.00001604696,"about_ca_system_score_gemma":0.00007857124,"threshold_uncertainty_score":0.23691499},"labels":[],"label_agreement":null},{"id":"W2157568408","doi":"10.1109/cec.2015.7256933","title":"ADR-Miner: An ant-based data reduction algorithm for classification","year":2015,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brandon University","funders":"","keywords":"Computer science; Ant colony optimization algorithms; Feature selection; Artificial intelligence; Data mining; Machine learning; Wilcoxon signed-rank test; Classifier (UML); Benchmark (surveying); Statistical classification; Mathematics","score_opus":0.2093254066562986,"score_gpt":0.3709180458314412,"score_spread":0.16159263917514263,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2157568408","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":[0.0002782633,0.000022994293,0.99356014,0.0038916555,0.00044201067,0.00020862036,0.00003978605,0.0003961466,0.0011603823],"genre_scores_gemma":[0.105858356,0.000003164049,0.88898915,0.00019239963,0.00035895355,0.000042141743,0.0036933494,0.000012655189,0.0008498177],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99866647,0.00010053527,0.00020246256,0.0006235929,0.00023931937,0.00016765183],"domain_scores_gemma":[0.99747163,0.000045253244,0.00011926189,0.0020100325,0.00019705037,0.00015675054],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000984982,0.00010115632,0.00009248197,0.0000995416,0.0001065027,0.00021542968,0.0012786079,0.00006154542,0.000005974596],"category_scores_gemma":[0.00016644617,0.0000895032,0.000018028939,0.00025416838,0.000027089325,0.0014470371,0.000115298615,0.000082438,0.000049110222],"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":[0.0000075116945,0.00012113519,0.0000820246,0.000005112234,0.000003729676,2.5071677e-7,0.00007232544,0.00007483302,0.0014653946,0.017485496,0.025785625,0.95489657],"study_design_scores_gemma":[0.0003894437,0.00012457195,0.00081353233,0.0000029377995,0.0000058233622,0.0000060521525,0.00008412622,0.9124513,0.00035529665,0.00050310063,0.08514284,0.000120955934],"about_ca_topic_score_codex":0.000104916006,"about_ca_topic_score_gemma":0.000012508593,"teacher_disagreement_score":0.95477563,"about_ca_system_score_codex":0.000043624448,"about_ca_system_score_gemma":0.00018669915,"threshold_uncertainty_score":0.36498347},"labels":[],"label_agreement":null},{"id":"W2158026689","doi":"10.1109/ijcnn.2006.247280","title":"Multi-view ANNs for Multi-relational Classification","year":2006,"lang":"en","type":"article","venue":"The 2006 IEEE International Joint Conference on Neural Network Proceedings","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Artificial neural network; Relation (database); Artificial intelligence; Relational database; Exploit; Bridging (networking); Construct (python library); Machine learning; Statistical relational learning; Data mining","score_opus":0.14638829148945168,"score_gpt":0.32609371611177446,"score_spread":0.17970542462232278,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2158026689","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":[0.0151946265,0.00009397858,0.9393938,0.034619,0.0022546854,0.0010719359,0.000062875064,0.00052707794,0.0067819813],"genre_scores_gemma":[0.9320907,0.000037349502,0.06216084,0.0010377605,0.0011465413,0.00022193529,0.00018074455,0.000023438844,0.0031006667],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99794364,0.00004191068,0.00053276704,0.0006107041,0.00049937895,0.00037157547],"domain_scores_gemma":[0.9983886,0.00013158619,0.00046575122,0.00028167953,0.000664317,0.00006809711],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006213231,0.00026175528,0.00019400548,0.00011765041,0.00039446208,0.00046974496,0.0011621525,0.000100996585,0.000027336484],"category_scores_gemma":[0.00011399549,0.00019833402,0.00012618504,0.00028731045,0.00009806544,0.000652942,0.0000969326,0.00035941132,0.00011139413],"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":[0.000050889386,0.00022609622,0.0029589883,0.0000183532,0.000030703213,8.790798e-7,0.00010988715,0.007613396,0.0049063656,0.9337408,0.03256079,0.017782854],"study_design_scores_gemma":[0.00058522576,0.000063984764,0.061852135,0.00006103585,0.000010051971,0.000014444141,0.0000148892805,0.9163963,0.00014310278,0.0038190198,0.01681356,0.00022623884],"about_ca_topic_score_codex":0.00005558648,"about_ca_topic_score_gemma":0.000027575832,"teacher_disagreement_score":0.9299218,"about_ca_system_score_codex":0.00009401293,"about_ca_system_score_gemma":0.00005923281,"threshold_uncertainty_score":0.8087827},"labels":[],"label_agreement":null},{"id":"W2158404716","doi":"10.1109/icdm.2010.66","title":"An Extensive Empirical Study on Semi-supervised Learning","year":2010,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Artificial intelligence; Machine learning; Computer science; Semi-supervised learning; Labeled data; Classifier (UML); Co-training; Supervised learning; Support vector machine; Pattern recognition (psychology); Artificial neural network","score_opus":0.03378477896116197,"score_gpt":0.34268529002015397,"score_spread":0.30890051105899197,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2158404716","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":[0.90048033,0.000001330057,0.08683702,0.0016771517,0.00024282032,0.0001434389,3.1204476e-7,0.000517618,0.010099966],"genre_scores_gemma":[0.9916,3.849746e-7,0.007010623,0.0006625221,0.00009343167,0.000009657544,0.0000097564,0.000007822526,0.0006058475],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9987438,0.00020435297,0.0001382907,0.00048026044,0.00026016452,0.00017318032],"domain_scores_gemma":[0.99874264,0.00012375526,0.00004459878,0.0008790314,0.000085207255,0.00012478302],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004303153,0.00010807351,0.00010309155,0.00008511581,0.00019891666,0.00021779953,0.0006688692,0.000052964962,0.00007833451],"category_scores_gemma":[0.00022694198,0.00008448784,0.000025092353,0.00022128121,0.000018734363,0.00032042316,0.00009890263,0.00060636306,0.00035249657],"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":[0.00003053576,0.002134586,0.7261697,0.000005209502,0.000024666233,0.000046551548,0.009404097,0.00057487836,0.045441486,0.03492414,0.0023564138,0.17888774],"study_design_scores_gemma":[0.0004824815,0.0010905509,0.64275354,0.000002571616,0.000004711793,0.000010269339,0.00087069784,0.34524077,0.000419717,0.00029586538,0.008586552,0.00024226574],"about_ca_topic_score_codex":0.000045868263,"about_ca_topic_score_gemma":0.000029256367,"teacher_disagreement_score":0.3446659,"about_ca_system_score_codex":0.0000074022923,"about_ca_system_score_gemma":0.000029971843,"threshold_uncertainty_score":0.45307478},"labels":[],"label_agreement":null},{"id":"W2164092299","doi":"10.1287/opre.1060.0360","title":"Classification and Regression via Integer Optimization","year":2007,"lang":"en","type":"article","venue":"Operations Research","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":116,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Integer (computer science); Regression; Integer programming; Regression analysis; Computer science; Optimization problem; Mathematics; Mathematical optimization; Data mining; Artificial intelligence; Statistics; Machine learning","score_opus":0.08721332552102332,"score_gpt":0.41979486974373104,"score_spread":0.3325815442227077,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2164092299","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":[0.007286594,0.00007085413,0.9819533,0.0041813334,0.00007294472,0.00018375972,8.6178227e-7,0.000089071276,0.0061612343],"genre_scores_gemma":[0.8714819,0.00008611541,0.12682006,0.000044833625,0.00006854746,0.000022627912,0.00006801185,0.000007263478,0.0014006458],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99854326,0.0002376077,0.00020121333,0.0003614417,0.00041980585,0.0002366733],"domain_scores_gemma":[0.9987633,0.00016437918,0.000020211326,0.0005445896,0.00040013783,0.00010738899],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027523355,0.000072027084,0.00006378913,0.00036541704,0.00065392273,0.0004083216,0.00036450275,0.000075106545,0.000038031303],"category_scores_gemma":[0.00040735747,0.00005942348,0.00001216683,0.00079833815,0.000085363405,0.0007308076,0.00017156565,0.000325952,0.00008409562],"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":[0.000022343276,0.00020524717,0.0052865054,0.000023474933,0.000010740942,0.0000049760747,0.0015006186,0.018301308,0.03272191,0.45462927,0.0019995386,0.48529407],"study_design_scores_gemma":[0.00011707641,0.000057082405,0.022650817,0.000013431574,8.97644e-7,0.000007967102,0.0001081066,0.97106487,0.00038071375,0.00018763576,0.005335159,0.00007622088],"about_ca_topic_score_codex":0.00010173797,"about_ca_topic_score_gemma":0.00010935005,"teacher_disagreement_score":0.95276356,"about_ca_system_score_codex":0.0000630334,"about_ca_system_score_gemma":0.00006246378,"threshold_uncertainty_score":0.5029511},"labels":[],"label_agreement":null},{"id":"W2164921999","doi":"10.1162/089976600300015178","title":"Boosting Neural Networks","year":2000,"lang":"en","type":"article","venue":"Neural Computation","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":303,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Boosting (machine learning); AdaBoost; Computer science; Artificial intelligence; Artificial neural network; Machine learning; Resampling; Weighting; Decision tree; Gradient boosting; Overfitting; Benchmark (surveying); Pattern recognition (psychology); Random forest; Classifier (UML)","score_opus":0.018898372840297543,"score_gpt":0.26795922063793065,"score_spread":0.2490608477976331,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2164921999","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":[0.21779022,0.000078098565,0.77563614,0.0020492545,0.00032168132,0.00010630833,6.463726e-7,0.00056012976,0.0034575132],"genre_scores_gemma":[0.99159515,0.0000040617406,0.0073618675,0.00063133927,0.00014231355,0.0000041154717,0.000052477342,0.000007116707,0.00020157752],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990367,0.00012265693,0.00018332482,0.00029806624,0.0001694215,0.00018977212],"domain_scores_gemma":[0.99951,0.00010197148,0.00006917019,0.00022283847,0.000037025922,0.000059030997],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014013943,0.00009837489,0.000082358885,0.000048000427,0.00019009972,0.0002231553,0.00032186173,0.000037336093,0.000036951435],"category_scores_gemma":[0.00002566202,0.000094323885,0.00003408912,0.00029732022,0.00001592471,0.0005476798,0.00004422616,0.00018587995,0.0000764053],"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":[0.000003190552,0.000008525633,0.0005844014,0.0000018975736,0.0000011455833,0.0000027564272,0.000059998325,0.33338872,0.000033198783,0.0007324801,0.00033550055,0.6648482],"study_design_scores_gemma":[0.00014060477,0.00004535497,0.028747506,0.000003544451,0.000002049038,0.000022635579,0.0000024901904,0.96937215,0.0000090929625,0.00026977822,0.0012856714,0.00009914214],"about_ca_topic_score_codex":0.000030380128,"about_ca_topic_score_gemma":0.000002586887,"teacher_disagreement_score":0.7738049,"about_ca_system_score_codex":0.00001601032,"about_ca_system_score_gemma":0.0000072475705,"threshold_uncertainty_score":0.38464165},"labels":[],"label_agreement":null},{"id":"W2167102385","doi":"10.1109/icmla.2009.25","title":"A New Method for Learning Decision Trees from Rules","year":2009,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":62,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Incremental decision tree; ID3 algorithm; Decision tree; Computer science; Decision tree learning; Machine learning; Data mining; Decision stump; Artificial intelligence; Decision rule; Tree (set theory); Influence diagram; Decision engineering; Set (abstract data type); Alternating decision tree; Business decision mapping; Decision support system; Mathematics","score_opus":0.023266911573950496,"score_gpt":0.3396877144381064,"score_spread":0.3164208028641559,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2167102385","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":[0.000761766,0.00007471827,0.9925386,0.0032235084,0.000074232055,0.000067305744,0.0000013458325,0.00026978433,0.0029887597],"genre_scores_gemma":[0.024941185,0.000007216467,0.9723988,0.00034763894,0.000099209494,0.0000023113723,0.000033327,0.0000032850028,0.0021669837],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992447,0.000057456426,0.00013255939,0.00030920512,0.00013121986,0.00012484688],"domain_scores_gemma":[0.9989879,0.00052465487,0.0000564342,0.00033215713,0.000026827693,0.000071990245],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002921331,0.00007479687,0.00009626333,0.00005820224,0.00010983684,0.00018836334,0.00045643788,0.000039943516,0.000047257876],"category_scores_gemma":[0.000294064,0.000059212984,0.00004571941,0.00011136337,0.000002431615,0.00027835282,0.00004427076,0.00009131211,0.00007830882],"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":[0.000007049625,0.000008564395,0.00014475068,2.994059e-7,0.0000019903378,2.2072166e-7,0.000107337495,0.00024711416,0.0010767679,0.06010562,0.0045867837,0.9337135],"study_design_scores_gemma":[0.00037756143,0.0001380942,0.037192885,0.0000111895315,0.000004804878,0.0000014940713,0.000015874244,0.7082962,0.00064081827,0.09468732,0.15850821,0.00012552782],"about_ca_topic_score_codex":0.0002512437,"about_ca_topic_score_gemma":0.00002783094,"teacher_disagreement_score":0.93358797,"about_ca_system_score_codex":0.000010269002,"about_ca_system_score_gemma":0.000030405661,"threshold_uncertainty_score":0.24146354},"labels":[],"label_agreement":null},{"id":"W2167265457","doi":"10.1016/j.patcog.2005.07.012","title":"Prototype reduction schemes applicable for non-stationary data sets","year":2005,"lang":"en","type":"article","venue":"Pattern Recognition","topic":"Machine Learning and Data Classification","field":"Computer Science","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":"Carleton University","funders":"","keywords":"Computer science; Computation; Data reduction; Algorithm; Reduction (mathematics); Data set; Data mining; Invariant (physics); Set (abstract data type); Feature (linguistics); Pattern recognition (psychology); Artificial intelligence; Mathematics","score_opus":0.07605574288734746,"score_gpt":0.3279922523063894,"score_spread":0.25193650941904194,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2167265457","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":[0.0090877265,0.000021317044,0.9857668,0.003206509,0.00014504082,0.0008335146,0.00014403487,0.00018107718,0.0006139723],"genre_scores_gemma":[0.7230462,0.000031915955,0.2652726,0.00038906376,0.0005557014,0.00078332366,0.009720409,0.000019691306,0.00018113981],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990024,0.000035566427,0.00018624584,0.000473407,0.00014738273,0.00015499076],"domain_scores_gemma":[0.99904275,0.000045664405,0.00012050098,0.0006435215,0.00010350988,0.00004408333],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034602336,0.00009218755,0.00007730083,0.000074154654,0.0001440852,0.00011315654,0.00048191694,0.000049935796,0.00003756528],"category_scores_gemma":[0.000046733247,0.00009410682,0.000020795262,0.00013635628,0.000013038532,0.0011397596,0.00011404088,0.00009595833,0.0003998491],"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":[0.00001096429,0.00006099985,0.0002375668,0.000037016765,0.0000061931064,1.4735454e-7,0.000066853274,0.000010581624,0.0009172107,0.000061122904,0.0038185017,0.99477285],"study_design_scores_gemma":[0.0007010187,0.00013735995,0.0047387024,0.00005795727,0.00001778229,0.000028962568,0.000032505886,0.831528,0.004716514,0.0025223086,0.15520959,0.00030928006],"about_ca_topic_score_codex":0.000020291285,"about_ca_topic_score_gemma":0.0000070704955,"teacher_disagreement_score":0.99446356,"about_ca_system_score_codex":0.000027595037,"about_ca_system_score_gemma":0.000033027438,"threshold_uncertainty_score":0.5139385},"labels":[],"label_agreement":null},{"id":"W2178220322","doi":"10.4018/jcini.2008070107","title":"Reducing Cognitive Overload by Meta-Learning Assisted Algorithm Selection","year":2008,"lang":"en","type":"article","venue":"International Journal of Cognitive Informatics and Natural Intelligence","topic":"Machine Learning and Data Classification","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":"University of Regina","funders":"","keywords":"Computer science; Meta learning (computer science); Machine learning; Data mining; Reduct; Rough set; Ranking (information retrieval); Feature selection; Process (computing); Information overload; Cognitive load; Artificial intelligence; Reduction (mathematics); Algorithm; Cognition","score_opus":0.029834904279658556,"score_gpt":0.30661382679123056,"score_spread":0.276778922511572,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2178220322","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":[0.04443339,0.0009879785,0.95302397,0.00026432477,0.0005241312,0.0000796392,0.000018251414,0.000034815042,0.0006335053],"genre_scores_gemma":[0.9746284,0.0012045514,0.02347558,0.00031596186,0.000104103776,0.0000034864815,0.000043990505,0.0000059885547,0.00021795415],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99819934,0.00010718329,0.0007249551,0.00013058523,0.00067882234,0.00015909834],"domain_scores_gemma":[0.99636513,0.00069010595,0.00091168564,0.00005328338,0.0018823901,0.00009742009],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005348092,0.00016703196,0.00024873295,0.00029752558,0.00019521461,0.00022697037,0.00045507553,0.000064902,0.000030409552],"category_scores_gemma":[0.0010373017,0.00013197694,0.00013070474,0.0002692665,0.00010362223,0.0018176497,0.00012577514,0.000714992,0.000013162504],"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":[0.00007753933,0.0000727323,0.000724037,0.000009307706,0.0010976916,0.000032446937,0.0034189478,0.000113445676,0.00029867672,0.0007947351,0.00035483923,0.9930056],"study_design_scores_gemma":[0.0013491723,0.0010657504,0.013442442,0.00068575545,0.0005358029,0.008653774,0.0033184313,0.93208885,0.030701185,0.0010157652,0.006305418,0.0008376804],"about_ca_topic_score_codex":0.000027784228,"about_ca_topic_score_gemma":8.502945e-7,"teacher_disagreement_score":0.99216795,"about_ca_system_score_codex":0.0000533975,"about_ca_system_score_gemma":0.0000872071,"threshold_uncertainty_score":0.5381864},"labels":[],"label_agreement":null},{"id":"W2186489521","doi":"","title":"Unsupervised and Transfer Learning Challenge: a Deep Learning Approach","year":2011,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":147,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Transfer of learning; Artificial intelligence; Computer science; Unsupervised learning; Machine learning; Deep learning; Classifier (UML); Competitive learning; Semi-supervised learning; Task (project management)","score_opus":0.0682199232260771,"score_gpt":0.27585786633346404,"score_spread":0.20763794310738692,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2186489521","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":[0.045805752,0.00034404232,0.68026674,0.0020917878,0.00034231294,0.00026783123,0.0000032075463,0.0010388391,0.2698395],"genre_scores_gemma":[0.9862804,0.0005298889,0.010840925,0.00013475915,0.00009749596,0.00003988918,0.00012802261,0.00003608911,0.0019125326],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99715424,0.0005618029,0.00039660707,0.0009030992,0.0005834399,0.0004008299],"domain_scores_gemma":[0.99898803,0.00013604281,0.00014955757,0.0003325549,0.00020738639,0.00018641134],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00077486504,0.00035293621,0.000288451,0.00037103632,0.00046186257,0.00036831183,0.0010747812,0.00014705723,0.0004336042],"category_scores_gemma":[0.00034596745,0.000335998,0.00009186747,0.0002487408,0.00008940664,0.0006760344,0.00026845405,0.001887527,0.0001337852],"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":[0.00013261013,0.00027770153,0.03456064,0.000046567624,0.00011664683,0.000029889601,0.011220337,0.005042204,0.0011375237,0.6160211,0.0000068806703,0.3314079],"study_design_scores_gemma":[0.0008469226,0.00047786618,0.014396212,0.000055538865,0.000013642693,0.00004396171,0.000521393,0.97175664,0.000077721415,0.0013413602,0.0100187715,0.00044996353],"about_ca_topic_score_codex":0.00020913212,"about_ca_topic_score_gemma":0.000018280902,"teacher_disagreement_score":0.96671444,"about_ca_system_score_codex":0.00004985772,"about_ca_system_score_gemma":0.000044134566,"threshold_uncertainty_score":0.9999092},"labels":[],"label_agreement":null},{"id":"W2232010405","doi":"","title":"Access to Unlabeled Data can Speed up Prediction Time","year":2011,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"MNIST database; Computer science; Classifier (UML); Labeled data; Artificial intelligence; Machine learning; Semi-supervised learning; Training set; Pattern recognition (psychology); Supervised learning; Data mining; Deep learning; Artificial neural network","score_opus":0.14076852122230335,"score_gpt":0.31807727150794335,"score_spread":0.17730875028564,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2232010405","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":[0.014231657,0.00000766842,0.9028136,0.0051284493,0.0007119155,0.0003138449,0.000084084444,0.000970122,0.07573864],"genre_scores_gemma":[0.90028876,0.0000069308494,0.07607961,0.0020935643,0.0001932593,0.000009337288,0.0008144529,0.000018270563,0.020495798],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99907017,0.000050720533,0.00013622163,0.00043403558,0.0001631116,0.00014572425],"domain_scores_gemma":[0.9981478,0.000020558571,0.000045400404,0.0016342988,0.000044370456,0.00010758959],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000305541,0.00007315118,0.00007091768,0.00008295177,0.00007460086,0.00018981894,0.0024937417,0.000030183715,0.0003113302],"category_scores_gemma":[0.00009644359,0.00006172719,0.000008976864,0.0003282039,0.000009744886,0.00096990616,0.0010001983,0.0000770047,0.00073473173],"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":[0.00004435641,0.00025200742,0.04002887,0.000022147487,0.00005339479,0.000007898973,0.0025252535,0.000060302908,0.006201117,0.044444196,0.45254904,0.4538114],"study_design_scores_gemma":[0.0003519943,0.00011564466,0.2890738,0.000012683018,0.000011788016,0.000009520612,0.000012734913,0.64852977,0.0020581086,0.0005748785,0.058993638,0.00025541423],"about_ca_topic_score_codex":0.00070554554,"about_ca_topic_score_gemma":0.000073937445,"teacher_disagreement_score":0.88605714,"about_ca_system_score_codex":0.000015775177,"about_ca_system_score_gemma":0.000042023432,"threshold_uncertainty_score":0.9443735},"labels":[],"label_agreement":null},{"id":"W2249161032","doi":"10.1109/icdm.2015.127","title":"Ensemble Kernel Mean Matching","year":2015,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Kernel (algebra); Benchmark (surveying); Matching (statistics); Partition (number theory); Kernel density estimation; Quadratic equation; Algorithm; Variable kernel density estimation; Test data; Computer science; Mathematics; Kernel method; Statistics; Artificial intelligence; Support vector machine; Combinatorics","score_opus":0.04327612217669094,"score_gpt":0.28258200522827776,"score_spread":0.23930588305158682,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2249161032","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":[0.0068497453,0.000016659147,0.8756363,0.0019710227,0.000140623,0.000025469413,1.6510003e-7,0.00027576234,0.11508429],"genre_scores_gemma":[0.892685,0.0000010580081,0.10257006,0.00038435106,0.00004185327,0.000002172542,0.000004631532,0.0000031891632,0.004307688],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994484,0.000039885166,0.000078583165,0.00017367661,0.00015508631,0.00010435486],"domain_scores_gemma":[0.99941945,0.00002344727,0.000029038834,0.00040273412,0.00003416797,0.00009117863],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003362002,0.000046949048,0.0000469088,0.000033177505,0.000041182127,0.00012770269,0.0004097638,0.000018783869,0.000010078833],"category_scores_gemma":[0.000036732687,0.00003793035,0.000013338877,0.00011330637,0.0000061851747,0.00032679236,0.0001232212,0.000068193185,0.0006037216],"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":[0.0000020948848,0.0000351211,0.0013963238,0.0000040190066,0.000004195244,0.000004215404,0.0022368266,0.0003176051,0.0009019846,0.85562396,0.019228984,0.1202447],"study_design_scores_gemma":[0.0008623511,0.00013727362,0.010991648,0.000015682783,0.000005823351,0.000068620124,0.00062919426,0.53196424,0.0023453303,0.12870997,0.32372987,0.00053997285],"about_ca_topic_score_codex":0.00021853707,"about_ca_topic_score_gemma":0.000026049458,"teacher_disagreement_score":0.88583523,"about_ca_system_score_codex":0.000015296866,"about_ca_system_score_gemma":0.00003307337,"threshold_uncertainty_score":0.77598214},"labels":[],"label_agreement":null},{"id":"W2257410811","doi":"10.1145/3365672","title":"A New Smooth Approximation to the Zero One Loss with a Probabilistic Interpretation","year":2019,"lang":"en","type":"preprint","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Hinge loss; Algorithm; Computer science; Probabilistic logic; Maxima and minima; Artificial intelligence; Mathematics; Benchmark (surveying); Mathematical optimization; Machine learning; Pattern recognition (psychology); Support vector machine","score_opus":0.04480686181851787,"score_gpt":0.29227264341833536,"score_spread":0.2474657815998175,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2257410811","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":[0.00093433744,0.00014212125,0.9888692,0.0045040334,0.0012872105,0.0013871726,0.0021757896,0.00023489713,0.0004652418],"genre_scores_gemma":[0.83079356,0.00006072625,0.15743405,0.00027864357,0.00029090562,0.00028548852,0.009030242,0.000061182574,0.0017651916],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99676436,0.00030442406,0.00045259207,0.001712724,0.00048008777,0.00028580945],"domain_scores_gemma":[0.98912203,0.00058334286,0.00028546425,0.0096945325,0.00017845693,0.00013615491],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.00046095715,0.0004188118,0.000379028,0.00022670158,0.00022435997,0.0012554944,0.006803858,0.00018822083,0.00003136076],"category_scores_gemma":[0.0003629158,0.00030823261,0.000085581705,0.00054083986,0.000050545896,0.0016375467,0.00076448807,0.0010007573,0.0006361347],"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":[0.00053991645,0.0011664821,0.0001980154,0.00043416207,0.00050473784,0.0000028455177,0.009378181,0.1168347,0.0000756471,0.004556789,0.008698326,0.8576102],"study_design_scores_gemma":[0.0014017521,0.00055215805,0.009106469,0.0023730258,0.00063517713,0.0000064011842,0.00016676915,0.92506737,0.00026666006,0.0217589,0.037090816,0.0015744811],"about_ca_topic_score_codex":0.00094172196,"about_ca_topic_score_gemma":0.0014147349,"teacher_disagreement_score":0.8560357,"about_ca_system_score_codex":0.00018099057,"about_ca_system_score_gemma":0.00075720565,"threshold_uncertainty_score":0.999937},"labels":[],"label_agreement":null},{"id":"W2269550524","doi":"10.1007/978-3-319-24486-0_16","title":"Information Preserving Dimensionality Reduction","year":2015,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Dimensionality reduction; Computer science; Preprocessor; Task (project management); Curse of dimensionality; Machine learning; Reduction (mathematics); Artificial intelligence; Data pre-processing; Dimension (graph theory); Focus (optics); Data mining; Mathematics; Engineering","score_opus":0.029874116344784638,"score_gpt":0.27396011552098143,"score_spread":0.24408599917619678,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2269550524","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":[0.000039033283,0.0001880276,0.9850732,0.0018453243,0.0015052537,0.00022423564,0.0000049418995,0.00020908698,0.010910913],"genre_scores_gemma":[0.27163061,0.00006235637,0.72426707,0.0010286757,0.0011227671,0.000021802469,0.0002485977,0.000039161543,0.0015789736],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974007,0.00005097813,0.00045982696,0.00064650184,0.0011089452,0.00033301764],"domain_scores_gemma":[0.99748945,0.00012991414,0.000364574,0.0014087635,0.000457801,0.00014949891],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001651225,0.0002894351,0.00025882426,0.0005963806,0.00024283913,0.000574189,0.0020518368,0.00022319125,0.000019794896],"category_scores_gemma":[0.00027447444,0.0002653746,0.0000549144,0.00045443935,0.00023822152,0.0025672775,0.0011739559,0.00067032845,0.00013135611],"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":[0.0000055182127,0.000013839037,0.000030498217,0.00003452805,0.0000045820066,0.0000031496284,0.00071115454,0.034691256,0.00006291739,0.078149974,0.00043120515,0.8858614],"study_design_scores_gemma":[0.00020575807,0.00008977406,0.00049341645,0.00019150652,0.000005336938,0.00007430755,4.0542054e-7,0.73380417,0.00015847493,0.22774647,0.0367414,0.00048900023],"about_ca_topic_score_codex":0.00006195485,"about_ca_topic_score_gemma":0.00001260405,"teacher_disagreement_score":0.8853724,"about_ca_system_score_codex":0.00032973234,"about_ca_system_score_gemma":0.0005491947,"threshold_uncertainty_score":0.99997985},"labels":[],"label_agreement":null},{"id":"W2273239185","doi":"10.1017/cbo9780511550881.016","title":"LOCATING CORBA OBJECTS FROM JAVA","year":2000,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Common Object Request Broker Architecture; Computer science; Java; Programming language","score_opus":0.020200161848057556,"score_gpt":0.1956678469942692,"score_spread":0.17546768514621164,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2273239185","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":[0.000042154366,0.00014905655,0.022775855,0.000038267488,0.000227756,0.00018268648,0.00016556628,0.00041466716,0.976004],"genre_scores_gemma":[0.007092058,0.00007831607,0.002401709,0.00012993936,0.00016601916,4.6181407e-7,0.0002945097,0.000030657284,0.98980635],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.998341,0.00006635605,0.00019629278,0.00082218257,0.00031699764,0.0002571383],"domain_scores_gemma":[0.99802613,0.000124623,0.00027837377,0.0013151146,0.000089848276,0.00016590058],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000094845665,0.00033291968,0.000310295,0.00015954796,0.00025799187,0.00016369497,0.0015538551,0.00030038497,0.0000123839845],"category_scores_gemma":[0.000013799889,0.0004017783,0.00012873531,0.000014452581,0.00010762171,0.00021842578,0.00053830096,0.00060797995,0.00015219531],"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":[0.00001761366,0.0000071560034,0.0000033218255,0.00002066377,0.000046341727,0.00012902172,0.00014334633,0.000008138242,0.000035054818,0.9543555,0.012484299,0.032749556],"study_design_scores_gemma":[0.0003218792,0.00003251753,0.00007307694,0.00012957536,0.00006395945,0.000008723341,0.000011152919,0.005081474,0.000097431264,0.00008686918,0.9936223,0.0004710495],"about_ca_topic_score_codex":0.00085011055,"about_ca_topic_score_gemma":0.000007268975,"teacher_disagreement_score":0.981138,"about_ca_system_score_codex":0.00013179492,"about_ca_system_score_gemma":0.00014233352,"threshold_uncertainty_score":0.9998434},"labels":[],"label_agreement":null},{"id":"W2294059674","doi":"","title":"Maxout Networks","year":2013,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":607,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"MNIST database; Dropout (neural networks); Leverage (statistics); Computer science; Benchmark (surveying); Artificial intelligence; Machine learning; Set (abstract data type); Deep learning","score_opus":0.007273672343883744,"score_gpt":0.2085233568947044,"score_spread":0.20124968455082065,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2294059674","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":[0.0007664722,0.000017136881,0.94400895,0.003077148,0.000090848065,0.000038170172,3.1278894e-8,0.0002064066,0.05179484],"genre_scores_gemma":[0.9434403,0.000004511243,0.049744688,0.0008242345,0.000044092973,0.000010462838,0.000003904785,0.0000019817273,0.0059258],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99966145,0.000018598055,0.000055126304,0.00012048446,0.000055932356,0.0000884363],"domain_scores_gemma":[0.9995741,0.000022076507,0.000016871558,0.00033028013,0.000019565729,0.000037069618],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00006521659,0.00003189796,0.000028596705,0.000017930977,0.000037330068,0.0001452662,0.0003311286,0.0000174853,0.00025446372],"category_scores_gemma":[0.000013192654,0.000023915794,0.000010621179,0.000092944916,0.0000060528364,0.00031150508,0.00007419897,0.000054252505,0.0014159748],"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":[1.4096693e-7,0.0000134616,0.0051689385,0.000001142512,0.0000021101398,3.66276e-7,0.00003418587,0.0003341975,0.00008550367,0.36692882,0.041959796,0.58547133],"study_design_scores_gemma":[0.000035613633,0.000007879897,0.07401251,8.739018e-7,2.8614656e-7,0.0000019754348,0.0000032054081,0.88787234,0.000014826543,0.0012741233,0.036728933,0.000047423717],"about_ca_topic_score_codex":0.00010876929,"about_ca_topic_score_gemma":0.0000019357437,"teacher_disagreement_score":0.94267386,"about_ca_system_score_codex":0.0000038036303,"about_ca_system_score_gemma":0.0000047380345,"threshold_uncertainty_score":0.9993615},"labels":[],"label_agreement":null},{"id":"W2296059279","doi":"10.1609/aaai.v29i1.9375","title":"Efficient Benchmarking of Hyperparameter Optimizers via Surrogates","year":2015,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":113,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Deutsche Forschungsgemeinschaft","keywords":"Hyperparameter; Hyperparameter optimization; Machine learning; Computer science; Artificial intelligence; Benchmarking; Regression; Algorithm; Support vector machine; Mathematics; Statistics","score_opus":0.09360323200453574,"score_gpt":0.298169570383572,"score_spread":0.20456633837903626,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2296059279","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":[0.6821634,0.000051678937,0.28832746,0.004196588,0.001030259,0.0005544879,0.0000075636167,0.00016297566,0.0235056],"genre_scores_gemma":[0.97952783,0.0000060932903,0.020302651,0.00005251898,0.000035725945,0.0000101281,0.0000010046356,0.00000758482,0.00005646035],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982487,0.000031950018,0.000512542,0.00040733747,0.00055377843,0.00024567838],"domain_scores_gemma":[0.9981665,0.00012481622,0.0005020026,0.00037436772,0.00072671357,0.0001055996],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009358811,0.0001703651,0.00024356817,0.00013932279,0.000091339476,0.0001238778,0.0016600931,0.0000694512,0.000021012884],"category_scores_gemma":[0.00065304025,0.00012446979,0.00009405311,0.0006010922,0.00023973243,0.00016780783,0.00035553845,0.00023079767,0.00004351112],"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":[0.00011314485,0.0002629792,0.0017916053,0.00006091316,0.000025417507,3.1292348e-7,0.0036500972,0.007772421,0.044904243,0.79401577,0.00015639482,0.1472467],"study_design_scores_gemma":[0.000035580586,0.00020104623,0.0003123296,0.000114671966,0.000010381383,0.000003686107,0.000383082,0.76912755,0.20973013,0.019865999,0.000061496554,0.00015401571],"about_ca_topic_score_codex":0.00009363394,"about_ca_topic_score_gemma":0.0000040124287,"teacher_disagreement_score":0.7741498,"about_ca_system_score_codex":0.000037377285,"about_ca_system_score_gemma":0.00009373601,"threshold_uncertainty_score":0.50757307},"labels":[],"label_agreement":null},{"id":"W2296519941","doi":"","title":"Algorithm Runtime Prediction: Methods & Evaluation (Extended Abstract) .","year":2015,"lang":"en","type":"article","venue":"International Joint Conference on Artificial Intelligence","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Parameterized complexity; Generalization; Variety (cybernetics); Range (aeronautics); Machine learning; Function (biology); Theoretical computer science; Algorithm; Artificial intelligence; Mathematics","score_opus":0.2681916611656205,"score_gpt":0.43264301858162785,"score_spread":0.16445135741600736,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2296519941","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":[0.00043962305,0.000028274497,0.9565379,0.0069845137,0.0031217712,0.0002606417,0.000028203862,0.00028657741,0.032312475],"genre_scores_gemma":[0.72182304,0.000028834766,0.2765426,0.0003952766,0.00047013105,0.00009085424,0.0001591731,0.000014921432,0.000475142],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9966967,0.00031273303,0.0007045674,0.00072833383,0.0012880034,0.00026964964],"domain_scores_gemma":[0.99717796,0.00014222335,0.0003206203,0.00069387775,0.0014397582,0.00022555095],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0029767833,0.00023105173,0.00019718353,0.00031168546,0.00013076665,0.0006038336,0.0011924235,0.000113425405,0.00056803174],"category_scores_gemma":[0.0011825362,0.00022215869,0.000088181674,0.00032738436,0.000097508484,0.0008525073,0.00020420048,0.00039231076,0.0014494521],"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":[0.000013732694,0.000101954465,0.000010356962,0.0000013300329,0.000019006378,0.0000038341755,0.0003244117,0.0006216734,0.0014693579,0.25424862,0.0003083937,0.7428773],"study_design_scores_gemma":[0.0000666844,0.00012955698,0.001479823,0.00003408179,0.00000911847,0.000017653241,0.00021344954,0.8051662,0.011247325,0.17668328,0.004755273,0.00019759116],"about_ca_topic_score_codex":0.000102512065,"about_ca_topic_score_gemma":0.000013371724,"teacher_disagreement_score":0.8045445,"about_ca_system_score_codex":0.00025197858,"about_ca_system_score_gemma":0.0003925968,"threshold_uncertainty_score":0.999328},"labels":[],"label_agreement":null},{"id":"W2303463411","doi":"10.1007/s10836-016-5577-1","title":"Exemplar-based Failure Triage for Regression Design Debugging","year":2016,"lang":"en","type":"article","venue":"Journal of Electronic Testing","topic":"Machine Learning and Data Classification","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 Toronto","funders":"","keywords":"Debugging; Computer science; Metric (unit); Triage; Flexibility (engineering); Process (computing); Reliability engineering; Data mining; Engineering; Programming language; Mathematics","score_opus":0.05114569072665122,"score_gpt":0.2914108569765113,"score_spread":0.2402651662498601,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2303463411","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":[0.004333054,0.00024068895,0.9882252,0.0068949177,0.00008792771,0.0000993737,4.4632066e-7,0.00007338981,0.000044969158],"genre_scores_gemma":[0.7337514,0.0000015847332,0.2659965,0.00006887845,0.00011701066,0.0000044027615,4.4926148e-7,0.0000091917245,0.000050558425],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99873817,0.00016200016,0.0003595089,0.0001740501,0.00021912873,0.00034713547],"domain_scores_gemma":[0.9969754,0.0018104581,0.00067299,0.0002482615,0.000222423,0.000070472],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019580284,0.000104324514,0.00016469271,0.00014928673,0.00016128564,0.000087821965,0.00055533927,0.000045812045,0.000003939205],"category_scores_gemma":[0.0034483108,0.00006089995,0.000072696785,0.0002419917,0.000010081066,0.00046834286,0.000028943992,0.0002112809,0.0000028250456],"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":[0.00014192834,0.00008267257,0.0021443162,0.000033109074,0.000033945547,0.000016673304,0.00009239998,0.0026522116,0.19675851,0.010143494,0.0054025664,0.7824982],"study_design_scores_gemma":[0.0073495377,0.0038488735,0.0029957748,0.0018758576,0.00009141905,0.0006907676,0.00002578541,0.8615492,0.04038938,0.030894604,0.04962106,0.0006677459],"about_ca_topic_score_codex":0.0000013644319,"about_ca_topic_score_gemma":0.0000012106076,"teacher_disagreement_score":0.858897,"about_ca_system_score_codex":0.00013692761,"about_ca_system_score_gemma":0.0005355097,"threshold_uncertainty_score":0.41281992},"labels":[],"label_agreement":null},{"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":"W2368447518","doi":"","title":"A Comparative Study of Cost-Sensitive Classifiers","year":2007,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Artificial intelligence; Machine learning; Thresholding; Computer science; Categorization; Cost estimate; Engineering","score_opus":0.055664227147126044,"score_gpt":0.344623921275251,"score_spread":0.28895969412812494,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2368447518","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":[0.25498858,0.0000036812223,0.688708,0.00014918747,0.00007931754,0.00024624262,7.844317e-7,0.00008505319,0.055739153],"genre_scores_gemma":[0.9904793,4.8829406e-7,0.009021755,0.00006680348,0.0000134887605,0.000003393698,0.0000034209445,0.0000020223333,0.00040934197],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9991415,0.0000874524,0.00020031772,0.00023088003,0.00020545957,0.00013437693],"domain_scores_gemma":[0.99914587,0.0001919677,0.00010791874,0.0003866566,0.00010955837,0.000058048125],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000541727,0.000071015624,0.00014127837,0.00010401752,0.00006024909,0.000027974651,0.00030221627,0.000023622031,0.0000072488137],"category_scores_gemma":[0.000033339573,0.000058053676,0.000019548725,0.0003450838,0.000033287106,0.00018312012,0.0000901549,0.00010707532,0.00004307213],"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":[0.0002319121,0.0044209496,0.049922604,0.000023797204,0.00024780238,0.000070256865,0.09506904,0.0005964254,0.014017711,0.53432333,0.010431796,0.29064435],"study_design_scores_gemma":[0.001582125,0.0011078886,0.86062443,0.0000113958,0.000015895494,0.000011970393,0.026737524,0.091634616,0.0117503535,0.00032615408,0.00587813,0.00031952068],"about_ca_topic_score_codex":0.0001536294,"about_ca_topic_score_gemma":0.00021751014,"teacher_disagreement_score":0.81070185,"about_ca_system_score_codex":0.000019649582,"about_ca_system_score_gemma":0.0000223201,"threshold_uncertainty_score":0.23673603},"labels":[],"label_agreement":null},{"id":"W2398865566","doi":"","title":"AutoFolio: Algorithm Configuration for Algorithm Selection.","year":2015,"lang":"en","type":"article","venue":"National Conference on Artificial Intelligence","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Folio; Algorithm; Benchmark (surveying); Computer science; Selection (genetic algorithm); Parameterized complexity; Set (abstract data type); Hyperparameter; State (computer science); Weighted Majority Algorithm; Variety (cybernetics); Machine learning; Artificial intelligence; Artificial neural network; Wake-sleep algorithm","score_opus":0.17037899944649626,"score_gpt":0.3755070636843442,"score_spread":0.20512806423784796,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2398865566","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":[0.000039399176,0.000014124314,0.9857579,0.004540468,0.00052599114,0.0003795029,0.000041304036,0.0002528507,0.008448466],"genre_scores_gemma":[0.4274206,0.000013060454,0.5682419,0.0011199679,0.00062616484,0.00037786824,0.0003792068,0.000022035192,0.001799193],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978758,0.00011543797,0.000424778,0.0005462086,0.000770197,0.0002675748],"domain_scores_gemma":[0.99708724,0.0002357275,0.0001913835,0.00023478207,0.0020734298,0.0001774279],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000837479,0.00018171866,0.00015579289,0.00024178888,0.00023756697,0.0005254003,0.00061213336,0.00011462151,0.00010886493],"category_scores_gemma":[0.0007841315,0.00017958375,0.000057078603,0.0005303937,0.00006310288,0.0007036471,0.00004815837,0.00021902157,0.0011791028],"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":[0.0000051096204,0.000041459654,0.0000020929565,0.0000014484895,0.000004761306,2.0692353e-7,0.000083823084,0.00047361868,0.00021561746,0.5078351,0.0014997851,0.489837],"study_design_scores_gemma":[0.000046985246,0.00018108425,0.0000857777,0.000008601192,0.0000026151538,0.0000046864548,0.00007706311,0.7813656,0.0065081427,0.20291379,0.008633219,0.00017244562],"about_ca_topic_score_codex":0.00007157496,"about_ca_topic_score_gemma":0.000013581114,"teacher_disagreement_score":0.78089195,"about_ca_system_score_codex":0.00016984287,"about_ca_system_score_gemma":0.0006116724,"threshold_uncertainty_score":0.9995986},"labels":[],"label_agreement":null},{"id":"W2403271036","doi":"","title":"Surrogate benchmarks for hyperparameter optimization","year":2014,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Hyperparameter; Hyperparameter optimization; Machine learning; Computer science; Artificial intelligence; Range (aeronautics); Set (abstract data type); Regression; Mathematics; Support vector machine; Statistics; Engineering","score_opus":0.010266512753067189,"score_gpt":0.23796649307342893,"score_spread":0.22769998032036173,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2403271036","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":[0.00038970335,0.0000037934506,0.97940123,0.001841384,0.00013375646,0.00008112281,7.521397e-7,0.000112240814,0.018036002],"genre_scores_gemma":[0.36567736,0.0000018786699,0.63315904,0.00040546156,0.00003876638,0.000017012226,0.00007906212,0.0000034278064,0.00061798265],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99948454,0.000040633175,0.00009386339,0.0002035843,0.000072336516,0.00010505803],"domain_scores_gemma":[0.99938697,0.00014748846,0.000039779803,0.0003435087,0.00004667136,0.000035556277],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031648303,0.000051536754,0.00005628403,0.00003994545,0.000071627575,0.000112747985,0.00028969353,0.000028958886,0.000047050686],"category_scores_gemma":[0.00017188056,0.0000422969,0.000025274758,0.00009128254,0.000008466226,0.00025588402,0.000042488566,0.00003595056,0.000023377774],"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":[0.0000065730515,0.000046587706,0.0013631785,0.000016742857,0.000007540698,9.122822e-8,0.00010514273,0.06053102,0.00019188602,0.6700201,0.008681272,0.25902984],"study_design_scores_gemma":[0.00014470161,0.00003881399,0.00056258333,0.0000016419775,0.0000016466214,9.4012904e-7,0.0000017522343,0.9582135,0.00014220938,0.001214326,0.039615452,0.000062447376],"about_ca_topic_score_codex":0.000010511929,"about_ca_topic_score_gemma":0.0000021528256,"teacher_disagreement_score":0.8976825,"about_ca_system_score_codex":0.000006350312,"about_ca_system_score_gemma":0.000008552311,"threshold_uncertainty_score":0.17248175},"labels":[],"label_agreement":null},{"id":"W2409550820","doi":"10.48550/arxiv.1605.08803","title":"Density Estimation Using Real NVP","year":2016,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":793,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Latent variable; Inference; Computer science; Artificial intelligence; Unsupervised learning; Sampling (signal processing); Machine learning; Probabilistic logic; Computation; Set (abstract data type); Bayesian inference; Latent variable model; Bayesian probability; Algorithm","score_opus":0.09837519305503026,"score_gpt":0.2189231448305726,"score_spread":0.12054795177554234,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2409550820","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":[0.20130233,0.00000604287,0.7952811,0.00014573295,0.00033647017,0.000099039105,0.00000795521,0.00026851892,0.0025527931],"genre_scores_gemma":[0.9870773,0.00004869158,0.012045583,0.000028527844,0.00007909149,2.1872772e-7,0.000036693196,0.000010073119,0.0006738522],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985068,0.00017801645,0.00014673568,0.0008640297,0.00008696132,0.00021744522],"domain_scores_gemma":[0.9981106,0.000077648685,0.00028805868,0.001294873,0.00012016291,0.0001086359],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028103325,0.00019661828,0.00019103031,0.00018536783,0.00018907676,0.00012636429,0.0010946086,0.00021114577,0.000012439583],"category_scores_gemma":[0.0000624854,0.00019936355,0.000093209244,0.00025823212,0.000059823007,0.00047266242,0.0012707249,0.00033868375,0.00012702098],"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":[0.000029511715,0.00008308622,0.017846888,0.000099161785,0.000064126056,0.00014063407,0.00021455134,0.19294956,0.00057384797,0.7729112,0.00040461286,0.014682818],"study_design_scores_gemma":[0.00016926974,0.000011774173,0.00906796,0.00006751225,0.00002867969,0.0000047287417,0.0000054248426,0.9454781,0.00008122806,0.044665173,0.00017566734,0.00024451094],"about_ca_topic_score_codex":0.00039253102,"about_ca_topic_score_gemma":0.000023170618,"teacher_disagreement_score":0.78577495,"about_ca_system_score_codex":0.000238562,"about_ca_system_score_gemma":0.00017607464,"threshold_uncertainty_score":0.81298095},"labels":[],"label_agreement":null},{"id":"W2419301257","doi":"","title":"Designing a framework of intelligent information processing for dentistry administration data.","year":2005,"lang":"en","type":"article","venue":"PubMed","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Data warehouse; Online analytical processing; Schema (genetic algorithms); Raw data; SQL; Table (database); Data science; Database; Data mining; Information retrieval","score_opus":0.06559912867304556,"score_gpt":0.31165191077018084,"score_spread":0.24605278209713527,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2419301257","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":[0.0010051993,0.00006170383,0.9972103,0.00092125655,0.000093516384,0.00032299795,0.000011416136,0.00007036441,0.0003032101],"genre_scores_gemma":[0.70270085,0.000003914045,0.29680258,0.00007463531,0.000059830218,0.00018085624,0.0001528617,0.0000021119079,0.00002239763],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99927586,0.000022365171,0.00026273358,0.00015179896,0.00015047201,0.00013679345],"domain_scores_gemma":[0.9991305,0.00008523393,0.00022710928,0.0004380234,0.00007645833,0.000042669264],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00058656494,0.000055884982,0.000066134104,0.00006418657,0.00007130415,0.00019421405,0.0005907883,0.00004595929,0.0000011826249],"category_scores_gemma":[0.00055470044,0.000054905417,0.000015002815,0.00016456188,0.000013500266,0.002058637,0.000095045296,0.00007578296,0.0000057223197],"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":[0.000008339435,0.000020549194,0.00025195372,0.000050136725,0.0000030664455,5.855856e-8,0.00018001994,0.000104728315,0.000014237476,0.006084664,0.00025829824,0.99302393],"study_design_scores_gemma":[0.00042902835,0.00006024692,0.06338317,0.000080203965,0.000030718726,0.00002361313,0.000133883,0.80430424,0.015427555,0.0035979813,0.11218683,0.00034254076],"about_ca_topic_score_codex":0.0000025230363,"about_ca_topic_score_gemma":0.0000027834546,"teacher_disagreement_score":0.9926814,"about_ca_system_score_codex":0.00002337275,"about_ca_system_score_gemma":0.000053159838,"threshold_uncertainty_score":0.22389778},"labels":[],"label_agreement":null},{"id":"W2468194642","doi":"10.1007/s00521-016-2458-6","title":"Prototype selection for dynamic classifier and ensemble selection","year":2016,"lang":"en","type":"article","venue":"Neural Computing and Applications","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":39,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure","funders":"Natural Sciences and Engineering Research Council of Canada; Conselho Nacional de Desenvolvimento Científico e Tecnológico; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Classifier (UML); Artificial intelligence; Machine learning; Pattern recognition (psychology); Data mining","score_opus":0.01601551121461373,"score_gpt":0.290738541293404,"score_spread":0.27472303007879023,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2468194642","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":[0.040819064,0.00003586986,0.9556685,0.0025080552,0.000031122163,0.0005390034,0.0000022935426,0.00023602332,0.00016007562],"genre_scores_gemma":[0.9756862,0.000013953826,0.02370082,0.000079960744,0.00007716766,0.0001662587,0.000006633921,0.0000071709323,0.00026186273],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999255,0.0000364561,0.0001294629,0.00036967197,0.000063886604,0.00014551415],"domain_scores_gemma":[0.99949294,0.00016160787,0.000080200836,0.00014117401,0.00007063882,0.00005341977],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015871576,0.00008445529,0.00007521983,0.000058354344,0.0004043525,0.000105657244,0.00011633496,0.00004394394,8.278169e-7],"category_scores_gemma":[0.000030197072,0.00006357395,0.000016703574,0.00019348267,0.00002952472,0.00016442646,0.00005117956,0.000073325806,0.0000054022694],"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":[0.000007745064,0.000020942905,0.0039745993,0.000022664999,0.000004527656,1.9821771e-8,0.000038100563,0.00003089778,0.025613887,0.049138043,0.00016289749,0.9209857],"study_design_scores_gemma":[0.0003770539,0.00017478075,0.034444787,0.000017855806,0.0000089838495,0.000038629423,0.0000072197117,0.9289529,0.00074378995,0.0048730997,0.030193519,0.00016739719],"about_ca_topic_score_codex":0.000009024549,"about_ca_topic_score_gemma":0.000011924744,"teacher_disagreement_score":0.9348671,"about_ca_system_score_codex":0.00001944471,"about_ca_system_score_gemma":0.000016427728,"threshold_uncertainty_score":0.31099933},"labels":[],"label_agreement":null},{"id":"W2470642288","doi":"10.1007/s10618-016-0475-9","title":"Ensembles of label noise filters: a ranking approach","year":2016,"lang":"en","type":"article","venue":"Data Mining and Knowledge Discovery","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"Fundação de Amparo à Pesquisa do Estado de São Paulo","keywords":"Computer science; Noise (video); Machine learning; Artificial intelligence; Filter (signal processing); Ranking (information retrieval); Ensemble learning; Process (computing); Data mining; Noise measurement; Pattern recognition (psychology); Noise reduction","score_opus":0.06737345868108362,"score_gpt":0.3006821942314548,"score_spread":0.23330873555037118,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2470642288","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":[0.14643703,0.0018619576,0.8425545,0.00039487137,0.0002651059,0.00011576029,0.0004257874,0.00012750404,0.007817499],"genre_scores_gemma":[0.9428765,0.00015273037,0.055371672,0.000027552996,0.00008980041,0.0000072518596,0.00031198605,0.000010432092,0.0011520482],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988655,0.00009532072,0.00021403328,0.0005279133,0.000120995726,0.00017627457],"domain_scores_gemma":[0.99826,0.00026897693,0.00012076961,0.0012634534,0.000035413697,0.000051350045],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005679463,0.00012022727,0.0001745506,0.000099629084,0.00008955009,0.00015443063,0.0010285354,0.000044286524,0.0000020841721],"category_scores_gemma":[0.00028183317,0.000079323,0.000018686247,0.00018032499,0.00007917074,0.0016577402,0.0009278987,0.000051914223,0.000009952495],"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":[0.000032885007,0.0002127229,0.0063665383,0.00014885969,0.00003723384,0.0000021089818,0.002336855,6.7864823e-7,0.00847051,0.015572524,0.0066754576,0.9601436],"study_design_scores_gemma":[0.013339987,0.0011482375,0.071731135,0.0042963354,0.00030403055,0.00023475692,0.003959037,0.70636064,0.009054681,0.0022194686,0.18381281,0.0035389059],"about_ca_topic_score_codex":0.000020448288,"about_ca_topic_score_gemma":0.000011003462,"teacher_disagreement_score":0.9566047,"about_ca_system_score_codex":0.000008394629,"about_ca_system_score_gemma":0.00006609001,"threshold_uncertainty_score":0.32346982},"labels":[],"label_agreement":null},{"id":"W2475602767","doi":"10.25080/majora-8b375195-004","title":"SkData: Data Sets and Algorithm Evaluation Protocols in Python","year":2013,"lang":"en","type":"article","venue":"Proceedings of the Python in Science Conferences","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":94,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Rowland Institute at Harvard; National Science Foundation","keywords":"Python (programming language); Computer science; Upload; Parsing; Benchmark (surveying); Scripting language; Algorithm; Set (abstract data type); Data mining; Data set; Programming language; Theoretical computer science; Information retrieval; Artificial intelligence; World Wide Web","score_opus":0.08828722234852654,"score_gpt":0.36836448869067395,"score_spread":0.2800772663421474,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2475602767","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":[0.9401301,0.00015949257,0.010589862,0.015530917,0.00053195097,0.019473664,0.00003120963,0.0001735315,0.013379275],"genre_scores_gemma":[0.9719181,0.000014748678,0.02697645,0.000042773492,0.000014917652,0.0010063673,0.0000039750166,0.0000029646008,0.000019691712],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99772644,0.000042399213,0.0003938225,0.00071116077,0.0008542337,0.0002719186],"domain_scores_gemma":[0.9985355,0.00007950728,0.00032851467,0.0005684296,0.00042666408,0.000061369414],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005335463,0.0001165277,0.00015970219,0.00028147543,0.0001399571,0.0006830572,0.003919029,0.000044654902,0.000011889194],"category_scores_gemma":[0.0016275094,0.00007965659,0.000010498296,0.0015152865,0.00046827464,0.004205823,0.0015524654,0.00020158583,0.000006009427],"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":[0.0000027553751,0.00007844544,0.1982958,0.000059343893,0.0000015823825,9.7713084e-8,0.0018071297,0.000010351099,0.007377317,0.018208612,0.00030064615,0.7738579],"study_design_scores_gemma":[0.00021496211,0.00003357032,0.3685924,0.00015650522,0.000001946725,0.000004121652,0.00035000787,0.61509097,0.0014355166,0.013619043,0.00039630034,0.00010465797],"about_ca_topic_score_codex":0.0006747979,"about_ca_topic_score_gemma":0.00005403582,"teacher_disagreement_score":0.7737532,"about_ca_system_score_codex":0.000045077613,"about_ca_system_score_gemma":0.00037951005,"threshold_uncertainty_score":0.7282597},"labels":[],"label_agreement":null},{"id":"W2487356762","doi":"10.1017/cbo9781107298019.026","title":"Feature Selection and Generation","year":2014,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Selection (genetic algorithm); Computer science; Feature selection; Feature (linguistics); Content (measure theory); Information retrieval; Artificial intelligence; Mathematics","score_opus":0.019359246537704072,"score_gpt":0.19639241947063357,"score_spread":0.1770331729329295,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2487356762","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":[0.000025578636,0.00005586018,0.2376071,0.00016640927,0.00013190319,0.00011354106,0.000013792423,0.00016989319,0.7617159],"genre_scores_gemma":[0.0015166276,0.000058289927,0.0025382661,0.00006944495,0.00019863812,3.0924016e-7,0.00010103925,0.00001289177,0.9955045],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991532,0.000048122158,0.00006458455,0.00046992864,0.0001502353,0.00011395489],"domain_scores_gemma":[0.9992637,0.000025210838,0.00014842827,0.000390382,0.00008990408,0.00008236517],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001031956,0.00017897836,0.00015325983,0.00012321632,0.00021438985,0.00012969898,0.00034218837,0.00024692932,5.3758305e-7],"category_scores_gemma":[0.000008602746,0.00020457494,0.00004490515,0.000007749548,0.000038965343,0.000120975834,0.00021409428,0.0003466657,0.000008028185],"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":[0.0000038057194,0.0000011647437,0.0000027775006,0.000018021263,0.00001507805,0.000004883716,0.000013081149,0.0000037932552,0.00014749636,0.93580145,0.047888074,0.01610036],"study_design_scores_gemma":[0.00015477205,0.000034355904,0.000057055506,0.000022765516,0.000031771655,0.000019357438,7.921878e-7,0.03189535,0.0000883937,0.000006641557,0.9674831,0.00020565548],"about_ca_topic_score_codex":0.000026966587,"about_ca_topic_score_gemma":0.0000039868983,"teacher_disagreement_score":0.93579483,"about_ca_system_score_codex":0.00006477796,"about_ca_system_score_gemma":0.0000389267,"threshold_uncertainty_score":0.8342324},"labels":[],"label_agreement":null},{"id":"W2490023472","doi":"10.5555/2946645.3007063","title":"Are random forests truly the best classifiers","year":2016,"lang":"en","type":"article","venue":"Journal of Machine Learning Research","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":135,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Genomics; University of Toronto","funders":"","keywords":"Random forest; Support vector machine; Random subspace method; Artificial intelligence; Machine learning; Computer science; Classifier (UML); Artificial neural network; Pattern recognition (psychology); Data mining","score_opus":0.08091568562646898,"score_gpt":0.37147970277836134,"score_spread":0.2905640171518924,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2490023472","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":[0.24702424,0.0028308132,0.56105477,0.18177529,0.0010155776,0.00044868494,0.0000066870066,0.00015379647,0.0056901365],"genre_scores_gemma":[0.99373513,0.00031644502,0.0012418138,0.00009478956,0.00038783002,0.0000061359615,9.166591e-7,0.000018598286,0.0041983156],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9950869,0.0021231894,0.00051665306,0.00028543404,0.0014877634,0.0005000231],"domain_scores_gemma":[0.9945799,0.0030918678,0.00076108595,0.0006452409,0.00071030686,0.00021156885],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.009731015,0.00014750316,0.00027251072,0.00047092236,0.0006662366,0.0003689397,0.0021730466,0.000087710694,0.00005798731],"category_scores_gemma":[0.008756197,0.00006847439,0.00016108903,0.0007111454,0.00022837555,0.0006363401,0.00036904513,0.0019067033,0.00020663849],"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":[0.00045575906,0.0001871516,0.42674804,0.000035232257,0.00010180802,0.00018527395,0.00070252345,0.0007787752,0.0033136802,0.007901537,0.012763452,0.5468268],"study_design_scores_gemma":[0.006458111,0.0014441638,0.35885665,0.0006174521,0.000030177001,0.0007393955,0.0006161663,0.0545474,0.0005055121,0.0067100474,0.56905216,0.00042275796],"about_ca_topic_score_codex":0.000047924495,"about_ca_topic_score_gemma":0.00004838485,"teacher_disagreement_score":0.7467109,"about_ca_system_score_codex":0.00011571961,"about_ca_system_score_gemma":0.0001851734,"threshold_uncertainty_score":0.9995935},"labels":[],"label_agreement":null},{"id":"W2548122763","doi":"10.14778/2994509.2994514","title":"ActiveClean","year":2016,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":244,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"MNIST database; Computer science; Context (archaeology); Support vector machine; Data mining; Convergence (economics); Process (computing); Class (philosophy); Iterative and incremental development; Machine learning; Artificial intelligence; Deep learning","score_opus":0.009115700324434017,"score_gpt":0.2121947867126384,"score_spread":0.20307908638820438,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2548122763","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":[0.35625824,0.00024428862,0.27719334,0.15244272,0.0018138462,0.0013919857,0.000014805551,0.0009568534,0.20968392],"genre_scores_gemma":[0.98823136,0.000015588701,0.01057301,0.00009126191,0.000027976917,0.000012272708,9.592381e-8,0.000003741714,0.0010447019],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.999399,0.000006654332,0.00011725924,0.00018284912,0.00017663343,0.0001175978],"domain_scores_gemma":[0.9995267,0.000035164914,0.0001479358,0.00018745528,0.00007123804,0.000031500836],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024550143,0.00006172685,0.00006522557,0.000034179924,0.00006358518,0.000034275752,0.00091081834,0.000017557079,0.0000105892395],"category_scores_gemma":[0.00012363808,0.00002905918,0.0000414636,0.00014897944,0.000036198537,0.0003022806,0.00032721367,0.000047177637,0.000026465435],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000050923313,0.00004358792,0.005162852,0.000012705832,0.000010724554,3.3015958e-8,0.00024853944,2.9720874e-7,0.34996387,0.3406787,0.0026924536,0.30118114],"study_design_scores_gemma":[0.00063869683,0.00010652409,0.076522864,0.00012768761,0.000011149107,0.000010785298,0.00007034253,0.00087337213,0.8030983,0.023660831,0.09468397,0.0001954392],"about_ca_topic_score_codex":0.000009090244,"about_ca_topic_score_gemma":2.7925827e-7,"teacher_disagreement_score":0.6319731,"about_ca_system_score_codex":0.000033861215,"about_ca_system_score_gemma":0.0000116041465,"threshold_uncertainty_score":0.16925423},"labels":[],"label_agreement":null},{"id":"W2560655418","doi":"10.1142/s0219622017500055","title":"Rule Extraction from Decision Trees Ensembles: New Algorithms Based on Heuristic Search and Sparse Group Lasso Methods","year":2016,"lang":"en","type":"article","venue":"International Journal of Information Technology & Decision Making","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":61,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Lasso (programming language); Decision tree; Heuristic; Set (abstract data type); Computer science; Tree (set theory); Algorithm; Random forest; Artificial intelligence; Mathematics; Machine learning; Combinatorics","score_opus":0.02190308660357549,"score_gpt":0.36546215625865525,"score_spread":0.34355906965507976,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2560655418","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":[0.026094124,0.00008231157,0.9688673,0.0036202346,0.0009985992,0.00007024994,0.000010928854,0.00009797126,0.0001582995],"genre_scores_gemma":[0.477042,0.00008767423,0.5225652,0.00020369857,0.00008117775,0.000001615034,0.0000051441175,0.000004810682,0.000008694755],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976519,0.00012126472,0.000903303,0.00022275768,0.0009320525,0.00016873996],"domain_scores_gemma":[0.99605805,0.0021369355,0.00075627514,0.00039769465,0.0005616986,0.00008935939],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014473948,0.00016076729,0.0002154652,0.0018150843,0.000118388794,0.00034395818,0.0011961167,0.0001940934,0.00005600126],"category_scores_gemma":[0.0027698225,0.0001124496,0.000079689205,0.00037741632,0.000057383462,0.0023744854,0.00023219966,0.00037094677,0.00007539663],"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":[0.00016679315,0.000033109034,0.001122539,0.0000010796853,0.000022473345,0.000014524992,0.000074811265,0.0009038907,0.0012802237,0.0055424,0.00037339854,0.99046475],"study_design_scores_gemma":[0.005625854,0.0007978589,0.081743516,0.0023015945,0.000039427716,0.0008989057,0.00028418584,0.6649096,0.008991316,0.18298027,0.05084946,0.00057802914],"about_ca_topic_score_codex":0.000015401454,"about_ca_topic_score_gemma":0.000004757864,"teacher_disagreement_score":0.9898867,"about_ca_system_score_codex":0.00018309352,"about_ca_system_score_gemma":0.000112701695,"threshold_uncertainty_score":0.45855618},"labels":[],"label_agreement":null},{"id":"W2562164287","doi":"10.22360/summersim.2016.scsc.051","title":"Adaptive Parametric Tuning of Glucose-Insulin Kinetics Models Using Multilayer Perceptrons","year":2016,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Perceptron; Computer science; Parametric statistics; Artificial intelligence; Parametric model; Machine learning; Insulin; Multilayer perceptron; Multivariate statistics; Artificial neural network; Mathematics; Statistics; Internal medicine; Medicine","score_opus":0.0727862520461929,"score_gpt":0.2871506089030788,"score_spread":0.2143643568568859,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2562164287","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":[0.061711326,0.0000751645,0.9361347,0.00025764262,0.00006337613,0.000071826835,0.000004729056,0.00009970017,0.0015815337],"genre_scores_gemma":[0.72222084,0.000020541296,0.27753797,0.000036784037,0.000016670154,0.0000011292324,0.0000011364698,0.00000602821,0.00015892045],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99893856,0.00009108824,0.00023788762,0.00030974383,0.0002293182,0.00019337996],"domain_scores_gemma":[0.99890095,0.00022289887,0.000133367,0.0005555982,0.00011696723,0.00007020857],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021233487,0.00010674533,0.00013890138,0.00020568905,0.00005396142,0.000034013945,0.00049680605,0.000054037184,0.000038092512],"category_scores_gemma":[0.00013768228,0.000070578906,0.00004618219,0.00046102828,0.000045851506,0.00046865843,0.0001825204,0.000079201076,0.00003001418],"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":[0.000028627888,0.0003046964,0.0016340021,0.000017227989,0.000037735288,0.0000032075693,0.001187613,0.034325324,0.23624794,0.13569218,0.00024868918,0.5902728],"study_design_scores_gemma":[0.00026828557,0.00007696235,0.0023624285,0.000024806997,0.0000059858476,0.0000035695225,0.000049610684,0.99136126,0.004564378,0.00095843314,0.00020602679,0.00011827142],"about_ca_topic_score_codex":0.00014087025,"about_ca_topic_score_gemma":0.000005789735,"teacher_disagreement_score":0.9570359,"about_ca_system_score_codex":0.000046150504,"about_ca_system_score_gemma":0.000038643288,"threshold_uncertainty_score":0.2878124},"labels":[],"label_agreement":null},{"id":"W2596318830","doi":"","title":"META-DES.Oracle","year":2017,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":50,"is_retracted":false,"has_abstract":true,"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; Classifier (UML); Artificial intelligence; Oracle; Machine learning; Data mining; Pattern recognition (psychology)","score_opus":0.24570438381189721,"score_gpt":0.22246788189858857,"score_spread":0.023236501913308644,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2596318830","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":[0.07537265,0.000041438016,0.891268,0.00054612686,0.00013861211,0.00005628151,0.000002939841,0.00021326011,0.032360666],"genre_scores_gemma":[0.9902174,0.000030210214,0.0028338064,0.00005509978,0.000022049577,2.1889608e-7,0.0000025306883,0.000004225897,0.006834474],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992871,0.00005712317,0.00006172162,0.0003903168,0.00004351102,0.00016022063],"domain_scores_gemma":[0.9981884,0.00003564052,0.00013139834,0.0015037096,0.000052958952,0.00008790833],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022911813,0.00008602291,0.00011430107,0.00005478508,0.00067238125,0.0002310907,0.001595821,0.00003724862,0.00005737602],"category_scores_gemma":[0.00007145093,0.00008290842,0.00008858569,0.00012285922,0.0001104035,0.001191354,0.0003624982,0.000108154745,0.00037236165],"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":[0.0000067076394,0.00005033466,0.013634233,0.0000076279207,0.00015885296,0.000077641336,0.000107447864,0.0014164633,0.00010855331,0.97438115,0.00038242666,0.009668558],"study_design_scores_gemma":[0.00078675925,0.00009141458,0.17081884,0.000010430623,0.0003916474,0.00001145232,0.000045226345,0.7110426,0.00036329866,0.071377985,0.044573676,0.00048670697],"about_ca_topic_score_codex":0.00019992808,"about_ca_topic_score_gemma":0.000039659,"teacher_disagreement_score":0.91484475,"about_ca_system_score_codex":0.000027832933,"about_ca_system_score_gemma":0.000025958063,"threshold_uncertainty_score":0.5171481},"labels":[],"label_agreement":null},{"id":"W2604867865","doi":"10.1007/s10994-017-5683-z","title":"Efficient benchmarking of algorithm configurators via model-based surrogates","year":2017,"lang":"en","type":"article","venue":"Machine Learning","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":47,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Deutsche Forschungsgemeinschaft","keywords":"Benchmarking; Computer science; Surrogate model; Range (aeronautics); Algorithm; Set (abstract data type); Configurator; Hyperparameter; Mathematical optimization; Machine learning; Artificial intelligence; Mathematics; Engineering","score_opus":0.013987542445136907,"score_gpt":0.2622762930874399,"score_spread":0.24828875064230296,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2604867865","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":[0.02380304,0.00007116527,0.97153425,0.0006062008,0.00019640845,0.00009690036,0.0000060910897,0.00018242488,0.0035034872],"genre_scores_gemma":[0.9123327,0.000003834147,0.08738801,0.000041290194,0.000048365182,0.000006747804,0.00003988406,0.0000151843615,0.00012398769],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984225,0.00015991664,0.0003113005,0.00045565542,0.0003610006,0.00028962785],"domain_scores_gemma":[0.9980095,0.00014080042,0.00057567225,0.0010625181,0.00011258385,0.00009894643],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00087905984,0.00018838508,0.0002460587,0.00015117561,0.00082046574,0.0002732738,0.0012242185,0.000072119255,0.000023437518],"category_scores_gemma":[0.00033586973,0.00017471696,0.000091750975,0.00012619195,0.00010274594,0.00016600726,0.00027170812,0.00037937853,0.000020234444],"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":[0.000006069941,0.00006474873,0.025225258,0.00003167851,0.000013517537,0.000004390442,0.00025589406,0.5704937,0.0019982238,0.0029589667,0.00001662835,0.39893094],"study_design_scores_gemma":[0.00037339426,0.00006995167,0.012488086,0.000038700382,0.000008352923,0.0000029297632,0.0000051068755,0.9844541,0.0012620593,0.00012980944,0.000982986,0.0001844997],"about_ca_topic_score_codex":0.0003406058,"about_ca_topic_score_gemma":0.000015986381,"teacher_disagreement_score":0.88852966,"about_ca_system_score_codex":0.000028768405,"about_ca_system_score_gemma":0.00006879822,"threshold_uncertainty_score":0.71247506},"labels":[],"label_agreement":null},{"id":"W261086132","doi":"10.1007/978-3-319-00969-8_2","title":"Classification of Multi-dimensional Distributions Using Order Statistics Criteria","year":2013,"lang":"en","type":"book-chapter","venue":"Advances in intelligent systems and computing","topic":"Machine Learning and Data Classification","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":"Carleton University","funders":"","keywords":"Statistics; Order statistic; Order (exchange); Mathematics; Statistical physics; Physics; Economics","score_opus":0.04886508300545819,"score_gpt":0.33222040194581504,"score_spread":0.2833553189403568,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W261086132","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":[0.00018045699,0.0055630854,0.98981047,0.000023560939,0.00075469556,0.0002829886,0.000092252994,0.000043243697,0.0032492618],"genre_scores_gemma":[0.50695723,0.0016087322,0.47723603,0.00003809066,0.00032768276,0.00002161306,0.00085529673,0.000074726224,0.012880604],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981862,0.00007131721,0.00080613216,0.00049574644,0.0002497507,0.0001909062],"domain_scores_gemma":[0.99821967,0.000261495,0.00071146217,0.0004278917,0.00031692593,0.00006257594],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003343039,0.00024031625,0.00037676207,0.00017615136,0.00013244296,0.000117238465,0.00033199042,0.00014109914,0.000018815772],"category_scores_gemma":[0.00008229621,0.00023101029,0.000033585795,0.00009242403,0.00009563136,0.00028334348,0.0002116974,0.00028032335,0.000017865455],"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":[0.0000026757666,0.000037371174,0.00042766318,0.00030757562,0.000019022364,0.0000029105756,0.00013988152,0.0077830614,0.00013093236,0.9265729,0.00010232352,0.064473644],"study_design_scores_gemma":[0.00009371502,0.000029553365,0.00048660988,0.0007389578,0.000011313689,0.000019477238,0.000031264146,0.97284824,0.000009595896,0.0028416752,0.022648633,0.00024098314],"about_ca_topic_score_codex":0.0001399738,"about_ca_topic_score_gemma":0.000015038963,"teacher_disagreement_score":0.9650652,"about_ca_system_score_codex":0.00008616393,"about_ca_system_score_gemma":0.00006340996,"threshold_uncertainty_score":0.94203264},"labels":[],"label_agreement":null},{"id":"W2613634265","doi":"","title":"Scaling learning algorithms towards AI","year":2007,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":930,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Artificial intelligence; Computer science; Machine learning; Kernel (algebra); Curse of dimensionality; Kernel method; Algorithm; Support vector machine; Mathematics","score_opus":0.01827361657636038,"score_gpt":0.3036296303033375,"score_spread":0.2853560137269771,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2613634265","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":[0.0016411629,0.000028577939,0.9483253,0.0017842054,0.00017447861,0.000030582876,1.1855568e-7,0.00045707411,0.047558505],"genre_scores_gemma":[0.80172855,0.0000067832852,0.19323464,0.0007531186,0.00012906306,0.0000013838388,0.000009617074,0.000006489879,0.0041303854],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991101,0.000037591326,0.00015404918,0.0002613638,0.00021318912,0.00022372224],"domain_scores_gemma":[0.9994458,0.00007421422,0.000045699115,0.00030060092,0.000051681585,0.00008202123],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010339298,0.00007256208,0.000068620604,0.00008913867,0.00014970954,0.00015883967,0.0004269732,0.000042319498,0.00004157996],"category_scores_gemma":[0.00015908534,0.00006208622,0.000029348703,0.0002910499,0.000014734048,0.0003431106,0.00013230566,0.00025096512,0.00020279115],"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":[0.0000010457716,0.000012559297,0.0013978767,0.0000025299926,0.0000025325471,0.0000042251886,0.000190144,0.00014334857,0.00032163708,0.04962149,0.0003015993,0.948001],"study_design_scores_gemma":[0.0002165352,0.000053140055,0.044516318,0.000009782725,0.0000027154417,0.000023632552,0.000094842915,0.68885595,0.0042266003,0.000982984,0.26078197,0.00023554417],"about_ca_topic_score_codex":0.00012267189,"about_ca_topic_score_gemma":0.000005975241,"teacher_disagreement_score":0.94776547,"about_ca_system_score_codex":0.000021331743,"about_ca_system_score_gemma":0.000026526388,"threshold_uncertainty_score":0.26065376},"labels":[],"label_agreement":null},{"id":"W2616741364","doi":"10.5555/2946645.2946655","title":"Herded gibbs sampling","year":2016,"lang":"en","type":"article","venue":"UvA-DARE (University of Amsterdam)","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; Simon Fraser University","funders":"","keywords":"Gibbs sampling; Graphical model; Computer science; Convergence (economics); Probabilistic logic; Inference; Artificial intelligence; Algorithm; Bayesian probability","score_opus":0.02241718206315677,"score_gpt":0.21998522404234386,"score_spread":0.1975680419791871,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2616741364","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":[0.0631376,0.000027007049,0.9232199,0.0063331723,0.00015174391,0.00006873346,0.000018359447,0.00018723536,0.0068562417],"genre_scores_gemma":[0.953958,0.000022621389,0.042030737,0.00007565556,0.000030500722,1.07124514e-7,0.000010197801,0.000005659996,0.0038665573],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99917746,0.000065799424,0.00008720386,0.00030989156,0.00019010356,0.00016953901],"domain_scores_gemma":[0.9990107,0.00010020085,0.00012855924,0.00059844746,0.0000827741,0.00007930843],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017874136,0.00008653027,0.00013003373,0.00011464505,0.00016235502,0.000028467646,0.0008728634,0.000053924483,0.00014497146],"category_scores_gemma":[0.000038965205,0.00007865035,0.000063551306,0.000207884,0.000072705596,0.0006039439,0.00032116956,0.00007219359,0.00021393532],"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":[0.000051330895,0.00010534177,0.012690525,0.000057324523,0.000049579092,0.000024679077,0.0023724772,0.00002215187,0.019608876,0.061076928,0.0054648374,0.89847594],"study_design_scores_gemma":[0.0029416622,0.00034773862,0.41918474,0.0003468564,0.000040086834,0.0000313791,0.0012549321,0.0072699925,0.0009840592,0.0042928346,0.5624882,0.00081749796],"about_ca_topic_score_codex":0.00019887653,"about_ca_topic_score_gemma":0.000054004195,"teacher_disagreement_score":0.89765847,"about_ca_system_score_codex":0.00003909091,"about_ca_system_score_gemma":0.00004775985,"threshold_uncertainty_score":0.3207268},"labels":[],"label_agreement":null},{"id":"W2621841016","doi":"10.1016/j.sigpro.2017.05.030","title":"LMAE: A large margin Auto-Encoders for classification","year":2017,"lang":"en","type":"article","venue":"Signal Processing","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"China University of Petroleum, Beijing; National Natural Science Foundation of China; Canadian Institute for Advanced Research","keywords":"Softmax function; MNIST database; Encoder; Pattern recognition (psychology); Computer science; Artificial intelligence; Classifier (UML); Discriminative model; Margin (machine learning); Artificial neural network; Feature learning; Deep learning; Autoencoder; Algorithm; Machine learning","score_opus":0.048342974523918676,"score_gpt":0.33014132792545486,"score_spread":0.2817983534015362,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2621841016","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":[0.0006001952,0.00010592693,0.98985726,0.004701591,0.000106675776,0.0001720712,0.000006545629,0.00020527958,0.004244431],"genre_scores_gemma":[0.95012814,0.0000035832707,0.048785932,0.00018186079,0.00012927859,0.00005077637,0.000030847004,0.000011629704,0.00067797484],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998848,0.00003717271,0.00018886689,0.00043227067,0.00020991938,0.00028376584],"domain_scores_gemma":[0.9987513,0.000052375653,0.00034366388,0.0006530613,0.00012792984,0.00007166366],"candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00068771874,0.00011580334,0.000114711045,0.00007026997,0.0014183169,0.0011523962,0.0011171945,0.00006855019,0.00000978836],"category_scores_gemma":[0.00018646994,0.000107535685,0.000046397417,0.00008249648,0.000049950082,0.0013588484,0.00012959103,0.0001460056,0.000035047608],"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":[0.00001590966,0.00006606204,0.0024325438,0.00012380333,0.0000066469174,0.0000014411556,0.00050047575,0.000021167092,0.0077993236,0.048095882,0.0015533556,0.9393834],"study_design_scores_gemma":[0.0003836874,0.00003110251,0.01612448,0.000052810617,0.000006861659,0.0000034051716,0.000057408317,0.9424575,0.00032480183,0.004744879,0.03565149,0.00016156709],"about_ca_topic_score_codex":0.000012701434,"about_ca_topic_score_gemma":0.000005386656,"teacher_disagreement_score":0.9495279,"about_ca_system_score_codex":0.000034612556,"about_ca_system_score_gemma":0.0001458634,"threshold_uncertainty_score":0.9998845},"labels":[],"label_agreement":null},{"id":"W2625799632","doi":"10.11591/ijece.v7.i5.pp2855-2862","title":"A Novel Optimization towards Higher Reliability in Predictive Modelling towards Code Reusability","year":2017,"lang":"en","type":"article","venue":"International Journal of Electrical and Computer Engineering (IJECE)","topic":"Machine Learning and Data Classification","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":false,"ca_institutions":"Horizon College and Seminary","funders":"","keywords":"Reusability; Computer science; Code (set theory); Reliability (semiconductor); Software; Reliability engineering; Software quality; Software engineering; Software development; Programming language; Engineering","score_opus":0.01865396465607451,"score_gpt":0.26191261022758305,"score_spread":0.24325864557150856,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2625799632","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":[0.0159277,0.00007260117,0.9803397,0.00265834,0.0008016055,0.000059503447,0.000004401891,0.000037322647,0.00009882385],"genre_scores_gemma":[0.74356365,0.00006747475,0.25598162,0.000050678966,0.00030883885,0.000002181053,0.0000031429965,0.00000632971,0.000016057178],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986067,0.00003838413,0.00046068666,0.00028156317,0.00044246318,0.00017024417],"domain_scores_gemma":[0.9988062,0.000095632895,0.0002977409,0.00032574675,0.0003743897,0.000100340694],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006380667,0.00013681625,0.00021327513,0.00019786046,0.00007118027,0.000375599,0.0011821089,0.00007830248,0.000003871694],"category_scores_gemma":[0.00023786207,0.00011970248,0.00007036822,0.00011312481,0.000030095009,0.0008210575,0.00026860574,0.00041933407,6.792158e-7],"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":[0.000041371884,0.00014142747,0.001820831,0.000008057587,0.00003500474,0.000012702103,0.00011399459,0.94670606,0.00008017142,0.0042409967,0.000036057863,0.04676331],"study_design_scores_gemma":[0.0005194866,0.00011243093,0.07388706,0.000050174673,0.0000052668397,0.000057332803,5.5816656e-7,0.92374533,0.00005485109,0.0005187152,0.0009396847,0.00010908917],"about_ca_topic_score_codex":0.000091675276,"about_ca_topic_score_gemma":0.0000011342847,"teacher_disagreement_score":0.727636,"about_ca_system_score_codex":0.00016233674,"about_ca_system_score_gemma":0.000087426335,"threshold_uncertainty_score":0.48813257},"labels":[],"label_agreement":null},{"id":"W2626480082","doi":"","title":"Unsupervised Learning Beyond Conventional Settings","year":2017,"lang":"en","type":"article","venue":"eScholarship (California Digital Library)","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Library science; Management; Artificial intelligence; Computer science; Economics","score_opus":0.014808238663775721,"score_gpt":0.23425262135142277,"score_spread":0.21944438268764704,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2626480082","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":[0.34379002,0.0004942415,0.14233254,0.050279357,0.0012542997,0.00080711575,0.0016074689,0.0046871263,0.45474786],"genre_scores_gemma":[0.9848776,0.000009590888,0.008544701,0.0006884066,0.00017089315,0.000014359633,0.00096473366,0.00003814428,0.004691599],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9980884,0.00010613405,0.000339378,0.0006293337,0.0004404003,0.00039635805],"domain_scores_gemma":[0.9980665,0.00012956346,0.00032532105,0.0011662636,0.000049043538,0.00026331467],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00035036282,0.00023596385,0.0001966002,0.00012276741,0.0010842172,0.008510841,0.0023244724,0.0001161747,0.000261772],"category_scores_gemma":[0.0008674008,0.00022539837,0.00014146304,0.0001563994,0.00011773998,0.0108741205,0.0009554453,0.00066113885,0.003759609],"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":[0.000040713563,0.00019452015,0.65361017,0.000073090276,0.000052003743,0.000054193708,0.000059597336,0.000026178344,0.0003790068,0.19242652,0.009656966,0.14342704],"study_design_scores_gemma":[0.0007725034,0.00007595176,0.11500472,0.00006938541,0.000007760195,0.000024624609,0.000014105653,0.010486011,0.0006276487,0.02876644,0.8436459,0.0005049982],"about_ca_topic_score_codex":0.000003107016,"about_ca_topic_score_gemma":2.8217886e-7,"teacher_disagreement_score":0.8339889,"about_ca_system_score_codex":0.00001831766,"about_ca_system_score_gemma":0.00009870831,"threshold_uncertainty_score":0.9970161},"labels":[],"label_agreement":null},{"id":"W2731604420","doi":"","title":"An automatically configured algorithm selector","year":2015,"lang":"en","type":"article","venue":"publish.UP (University of Potsdam)","topic":"Machine Learning and Data Classification","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":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Benchmark (surveying); Computer science; Parameterized complexity; Set (abstract data type); Algorithm; Exploit; Selection (genetic algorithm); Range (aeronautics); Variety (cybernetics); Hyperparameter; State (computer science); Heuristics; Suite; Machine learning; Artificial intelligence","score_opus":0.02201071534214741,"score_gpt":0.23169485039133003,"score_spread":0.20968413504918262,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2731604420","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":[0.008763549,0.00001881513,0.9734474,0.0037073398,0.00027677335,0.000102172955,0.000021038528,0.00043171257,0.013231209],"genre_scores_gemma":[0.6861113,0.0000035191945,0.31055015,0.00014847885,0.00007703297,4.21522e-7,0.00017406142,0.000010725016,0.0029243368],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986259,0.0002610907,0.00011776674,0.00036278783,0.00040533437,0.00022717548],"domain_scores_gemma":[0.998361,0.000047505444,0.00015152211,0.0007156925,0.00039009022,0.0003342247],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00088160846,0.000105928964,0.00017414159,0.00019502209,0.00012613021,0.0002347634,0.0015252681,0.000091866146,0.00009271033],"category_scores_gemma":[0.00015578969,0.00012294826,0.000047585218,0.00054864824,0.00008400008,0.0024688845,0.00017838617,0.0001678198,0.000113612296],"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":[0.000019844772,0.00042326716,0.001774478,0.000038743885,0.00007049762,0.000031258554,0.008728315,0.00007674156,0.0011297266,0.14595728,0.061368603,0.78038126],"study_design_scores_gemma":[0.0011842176,0.00026869486,0.06086128,0.000011589986,0.0000199353,0.000015997752,0.0013140638,0.87046754,0.00006943266,0.002301105,0.0631868,0.0002993313],"about_ca_topic_score_codex":0.00058820995,"about_ca_topic_score_gemma":0.0000557527,"teacher_disagreement_score":0.87039083,"about_ca_system_score_codex":0.000055827513,"about_ca_system_score_gemma":0.00026186593,"threshold_uncertainty_score":0.50136846},"labels":[],"label_agreement":null},{"id":"W2733116932","doi":"10.1109/ipdpsw.2017.108","title":"Use of Synthetic Benchmarks for Machine-Learning-Based Performance Auto-Tuning","year":2017,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Benchmark (surveying); Computer science; Metric (unit); Kernel (algebra); Machine learning; Artificial intelligence; Set (abstract data type); Training set; Synthetic data; Measure (data warehouse); Data mining; Mathematics","score_opus":0.04647344824440519,"score_gpt":0.2757702257285831,"score_spread":0.22929677748417793,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2733116932","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":[0.030873552,0.000014319462,0.9637299,0.0017018161,0.00016418539,0.00016547515,0.000006064533,0.0001331102,0.003211569],"genre_scores_gemma":[0.92858315,0.000006977653,0.07004356,0.00006551866,0.000017730103,0.000015668162,0.00004159622,0.000007647307,0.001218176],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990951,0.00005344057,0.00019851097,0.00029925516,0.00016627122,0.00018742395],"domain_scores_gemma":[0.99812126,0.00028358318,0.00031434683,0.0011310293,0.00009267561,0.0000570998],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047011668,0.00010789365,0.00014309621,0.00008391015,0.0005405283,0.00032476682,0.000985301,0.000050380102,0.00004352505],"category_scores_gemma":[0.0008100183,0.00009084629,0.00006101672,0.00005360058,0.00006400297,0.0007292589,0.00015664738,0.00015336221,0.000011982699],"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":[0.00009579559,0.00024640927,0.34045014,0.00041136984,0.000048295668,0.0000027389644,0.00044782742,0.030521305,0.00429241,0.08279041,0.0021277675,0.5385655],"study_design_scores_gemma":[0.00019840631,0.00011207096,0.038407665,0.000036024183,0.0000058258806,0.0000013400577,0.000002073781,0.9345036,0.0015139617,0.000057079877,0.025050215,0.000111747126],"about_ca_topic_score_codex":0.00012763763,"about_ca_topic_score_gemma":0.000014611532,"teacher_disagreement_score":0.9039823,"about_ca_system_score_codex":0.000013540258,"about_ca_system_score_gemma":0.00005567604,"threshold_uncertainty_score":0.4157361},"labels":[],"label_agreement":null},{"id":"W2735519117","doi":"10.1109/ijcnn.2017.7966180","title":"Impact of biased mislabeling on learning with deep networks","year":2017,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Deep learning; Artificial intelligence","score_opus":0.02057108413079788,"score_gpt":0.30288368549235495,"score_spread":0.28231260136155706,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2735519117","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":[0.14603797,0.0000130306635,0.8414992,0.0002435303,0.000039391984,0.000043796033,2.0929062e-7,0.00009159233,0.012031289],"genre_scores_gemma":[0.9871619,0.0000056948543,0.012417546,0.000022423012,0.000029342333,0.0000014956743,0.0000053794324,0.0000052337086,0.00035099345],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99937093,0.000046234287,0.00009965582,0.00020828482,0.00013520909,0.00013967433],"domain_scores_gemma":[0.9988064,0.000084544205,0.00020596888,0.0008037223,0.000050866336,0.00004850363],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024308443,0.00007860881,0.000097491844,0.00004670101,0.00028702847,0.00020509007,0.0006364023,0.00003121407,0.000020509315],"category_scores_gemma":[0.00016523142,0.000051000257,0.000036194862,0.00006495919,0.000029888004,0.00026145673,0.000076920776,0.00017862552,0.000015063396],"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":[0.00005737984,0.00009403091,0.3277348,0.000008652284,0.00004922788,0.0000060771285,0.00025794253,0.30726293,0.000573215,0.014365212,0.00021424114,0.3493763],"study_design_scores_gemma":[0.00021220531,0.00027736017,0.23948362,0.00002072065,0.000002324074,0.0000019008581,0.0000042440224,0.75973666,0.00005888504,0.000023423021,0.000113491595,0.00006516186],"about_ca_topic_score_codex":0.00030976298,"about_ca_topic_score_gemma":0.000022236096,"teacher_disagreement_score":0.84112394,"about_ca_system_score_codex":0.00001395932,"about_ca_system_score_gemma":0.000025905809,"threshold_uncertainty_score":0.22076198},"labels":[],"label_agreement":null},{"id":"W2736021185","doi":"10.1109/ijcnn.2017.7966355","title":"Analyzing different prototype selection techniques for dynamic classifier and ensemble selection","year":2017,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Classifier (UML); Selection (genetic algorithm); Pattern recognition (psychology); Cross-validation; Feature selection; Ensemble learning; Statistical classification; Test data","score_opus":0.020999742830638834,"score_gpt":0.3089039620734993,"score_spread":0.28790421924286047,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2736021185","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":[0.019805321,0.000009446694,0.9764351,0.0012744993,0.000063106105,0.00049249455,7.0595337e-7,0.00030815875,0.001611149],"genre_scores_gemma":[0.92718315,0.000017372107,0.0712699,0.000025484334,0.000040164323,0.00016153733,0.000007740521,0.0000071036916,0.0012875489],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99927133,0.00003382251,0.00012120747,0.00034489494,0.0000796494,0.00014908651],"domain_scores_gemma":[0.9993731,0.000033992925,0.00013824437,0.00033314366,0.000079135505,0.00004241961],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023329702,0.00009684701,0.000100068675,0.00008866762,0.00068081904,0.0005262454,0.00027918603,0.000064284955,0.0000040339332],"category_scores_gemma":[0.000096182135,0.000078210236,0.000027063912,0.00006058476,0.000022293485,0.00052781,0.00008047247,0.00010746686,0.0000033151543],"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":[0.000038600247,0.00006506734,0.04628577,0.00006285356,0.00002228064,1.7630624e-7,0.00006938331,0.0000043406794,0.05781014,0.05675049,0.0006090806,0.8382818],"study_design_scores_gemma":[0.00019913822,0.00030540777,0.17858547,0.000019923791,0.000011272914,0.000010290724,0.000005194062,0.7947985,0.015869197,0.0039182277,0.0060964325,0.0001809347],"about_ca_topic_score_codex":0.00006482322,"about_ca_topic_score_gemma":0.00022123777,"teacher_disagreement_score":0.90737784,"about_ca_system_score_codex":0.000042159056,"about_ca_system_score_gemma":0.000019906634,"threshold_uncertainty_score":0.52363783},"labels":[],"label_agreement":null},{"id":"W2740333758","doi":"10.24963/ijcai.2017/352","title":"Learning Feature Engineering for Classification","year":2017,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":282,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Feature engineering; Feature (linguistics); Computer science; Feature selection; Artificial intelligence; Feature vector; Machine learning; Transformation (genetics); Aggregate (composite); Set (abstract data type); Artificial neural network; Process (computing); Data mining; Pattern recognition (psychology); Deep learning","score_opus":0.027018368044959964,"score_gpt":0.28717921808170016,"score_spread":0.2601608500367402,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2740333758","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":[0.0009845926,0.000011787689,0.9837308,0.007907567,0.00019417674,0.00008834281,5.891434e-7,0.00026794535,0.006814227],"genre_scores_gemma":[0.8461817,0.000005801857,0.14771827,0.000046136585,0.00010180566,0.000027553799,0.000019171035,0.0000065063186,0.0058930973],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99950165,0.000010486667,0.00006527717,0.00022187829,0.00007987792,0.000120832294],"domain_scores_gemma":[0.99907976,0.000055863824,0.000099174795,0.00068065425,0.000046316007,0.000038215323],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024003639,0.00006130656,0.00005702361,0.000036885074,0.00045999888,0.0005168868,0.000729124,0.000044623164,0.000003149786],"category_scores_gemma":[0.0005196166,0.00005447027,0.000029730632,0.000029330024,0.0000089399455,0.00051416486,0.00008482633,0.00012452452,0.000028751318],"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":[0.000003666841,0.00001667678,0.0066918544,0.000026885502,0.000009090489,4.91289e-7,0.00015282066,0.00041122315,0.012601665,0.66970974,0.004622946,0.30575296],"study_design_scores_gemma":[0.00011393094,0.000023104594,0.08381814,0.000005083786,0.0000015715998,0.0000015284947,0.0000075505413,0.755563,0.00028820278,0.00018268093,0.15992099,0.00007422988],"about_ca_topic_score_codex":0.00001080798,"about_ca_topic_score_gemma":0.0000023683965,"teacher_disagreement_score":0.8451971,"about_ca_system_score_codex":0.00001306865,"about_ca_system_score_gemma":0.000013672282,"threshold_uncertainty_score":0.49843514},"labels":[],"label_agreement":null},{"id":"W2741208098","doi":"10.24963/ijcai.2017/715","title":"AutoFolio: An Automatically Configured Algorithm Selector (Extended Abstract)","year":2017,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Exploit; Speedup; Algorithm; Set (abstract data type); Range (aeronautics); Construct (python library); State (computer science); Selection (genetic algorithm); Artificial intelligence; Parallel computing","score_opus":0.021928581663939496,"score_gpt":0.31250986490256605,"score_spread":0.29058128323862653,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2741208098","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":[0.004307791,0.000009234913,0.8998245,0.003982131,0.0003450621,0.00015283862,0.0000072244684,0.0011309254,0.0902403],"genre_scores_gemma":[0.68160003,0.000002693267,0.3153877,0.00027449947,0.000102457205,0.000010957936,0.00002971271,0.000009865334,0.0025820688],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99873084,0.000048796694,0.00022071603,0.00044391965,0.00028315047,0.0002725635],"domain_scores_gemma":[0.9975582,0.000049867012,0.00019090691,0.0019116893,0.0001003648,0.00018896969],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00042049086,0.00013491353,0.00014563832,0.000061411905,0.00054624846,0.0012521856,0.0018832601,0.00007994239,0.00023851708],"category_scores_gemma":[0.0002266483,0.00011251176,0.000039436887,0.00006196708,0.00006250665,0.0012448037,0.00015825925,0.00018533513,0.00044760742],"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":[0.0000019166046,0.0001212035,0.00018518973,0.000007351316,0.000013104439,0.000011567045,0.00013221055,0.0000032272862,0.0017223664,0.20360105,0.001594729,0.79260606],"study_design_scores_gemma":[0.00022497449,0.00006217653,0.34929702,0.0000056916333,0.000003524289,0.000012289515,0.000005314012,0.63756144,0.0005856258,0.002559971,0.0095219575,0.00016001593],"about_ca_topic_score_codex":0.00024270857,"about_ca_topic_score_gemma":0.000034411674,"teacher_disagreement_score":0.7924461,"about_ca_system_score_codex":0.000020243247,"about_ca_system_score_gemma":0.00010435586,"threshold_uncertainty_score":0.9997846},"labels":[],"label_agreement":null},{"id":"W2752489699","doi":"10.1016/j.neucom.2017.08.045","title":"The convergence of linear classifiers on large sparse data","year":2017,"lang":"en","type":"article","venue":"Neurocomputing","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"National Key Research and Development Program of China; Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Computer science; Missing data; Machine learning; Scalability; Artificial intelligence; Data mining; Naive Bayes classifier; Convergence (economics); Pattern recognition (psychology); Support vector machine","score_opus":0.09670514964902502,"score_gpt":0.35116571579618383,"score_spread":0.25446056614715884,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2752489699","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":[0.17270696,0.00011055635,0.78156644,0.017356485,0.003630656,0.00054126116,0.000047936657,0.00048291055,0.02355678],"genre_scores_gemma":[0.9943035,0.000020708494,0.005182523,0.00021301434,0.00012868873,0.0000011375724,0.000009775381,0.0000069701787,0.00013363546],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987324,0.000110691886,0.00021934822,0.00043714026,0.0002670839,0.00023332136],"domain_scores_gemma":[0.9955426,0.00032750732,0.00040582236,0.00362064,0.000051705763,0.000051718744],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.00077919645,0.00009274136,0.00010364671,0.000027654825,0.0013572009,0.000250645,0.004616518,0.000030825304,0.000002495032],"category_scores_gemma":[0.0009350607,0.00006745803,0.00002640167,0.00007215942,0.00007712771,0.00032168548,0.0015917853,0.0002558851,0.00005127146],"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":[0.000041420608,0.00030217847,0.05037177,0.000075024705,0.000046911882,0.000033445955,0.00064109603,0.0011167347,0.004017738,0.32179594,0.0121038575,0.6094539],"study_design_scores_gemma":[0.00016169519,0.000040138508,0.051142134,0.00002392691,0.0000029106561,0.0000026023115,0.0000113677215,0.89409876,0.00045220158,0.000106044085,0.053883687,0.00007454911],"about_ca_topic_score_codex":0.000020535757,"about_ca_topic_score_gemma":0.000006317909,"teacher_disagreement_score":0.892982,"about_ca_system_score_codex":0.0000059264253,"about_ca_system_score_gemma":0.000041832973,"threshold_uncertainty_score":0.9999429},"labels":[],"label_agreement":null},{"id":"W2766935108","doi":"10.1007/978-3-319-69404-7_17","title":"An Experimental Study of Adaptive Capping in irace","year":2017,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":31,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; Belgian Federal Science Policy Office; Fonds De La Recherche Scientifique - FNRS","keywords":"Iterated function; Computer science; Minimisation (clinical trials); Running time; Algorithm; Physics; Discrete mathematics; Mathematics; Mathematical analysis; Statistics","score_opus":0.038389840693019886,"score_gpt":0.31140437355246336,"score_spread":0.2730145328594435,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2766935108","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":[0.010237187,0.00019116972,0.98641276,0.00008838641,0.00057376554,0.00043950547,0.0000025248669,0.0000639402,0.0019907835],"genre_scores_gemma":[0.93120724,0.000004200995,0.0685117,0.00007151878,0.00010656824,0.000008813924,0.000003888919,0.0000141409755,0.00007194078],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970994,0.000086351596,0.00044218995,0.0013086993,0.00072530564,0.0003380501],"domain_scores_gemma":[0.99699044,0.00016781979,0.00047729514,0.0021580493,0.00011060246,0.00009580835],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000962088,0.00032390983,0.00043394064,0.0007099799,0.00022065765,0.00034235054,0.0039281095,0.00015533055,0.000006121062],"category_scores_gemma":[0.00006991911,0.0003074333,0.00004317495,0.0002010284,0.0003391081,0.0009244419,0.0009013267,0.0006503634,0.000008087773],"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":[0.000041016636,0.0013236785,0.0032775195,0.000038732454,0.000018476183,0.00018079953,0.029891023,0.07737489,0.0033735367,0.024952022,0.00000711601,0.8595212],"study_design_scores_gemma":[0.0007129009,0.0017846638,0.0057296846,0.00034619894,0.000004950546,0.000020357009,0.00001323757,0.9814195,0.0018541691,0.0073252814,0.00014655068,0.00064248743],"about_ca_topic_score_codex":0.00035347103,"about_ca_topic_score_gemma":0.00047470175,"teacher_disagreement_score":0.92097,"about_ca_system_score_codex":0.00018087217,"about_ca_system_score_gemma":0.00025585122,"threshold_uncertainty_score":0.9999378},"labels":[],"label_agreement":null},{"id":"W2782221847","doi":"10.4018/978-1-60566-026-4.ch368","title":"Knowledge Combination vs. Meta-Learning","year":2009,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Computer science; Knowledge base; Meta learning (computer science); Context (archaeology); Machine learning; Artificial intelligence; Process (computing); Network topology; Focus (optics); Knowledge space; Knowledge management; Engineering","score_opus":0.03513283776578537,"score_gpt":0.27895763042125166,"score_spread":0.24382479265546628,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2782221847","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":[0.000002366895,0.00078321004,0.029133003,0.00049176795,0.0003302371,0.00020014189,0.0000124825065,0.0006152306,0.96843153],"genre_scores_gemma":[0.15547769,0.000026483145,0.008216762,0.000787064,0.00034527117,0.000028802457,0.00009141274,0.000056117904,0.8349704],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9980287,0.00010095399,0.0004014433,0.0007572254,0.00041935133,0.0002923553],"domain_scores_gemma":[0.9983007,0.000067791094,0.00039426898,0.0009057968,0.00018422052,0.0001472596],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00038329783,0.00042844182,0.00053945795,0.00012927006,0.00022230479,0.00033118136,0.0010860902,0.00034937428,0.00003695386],"category_scores_gemma":[0.00006348572,0.00040167157,0.0003070047,0.00004627478,0.00004817151,0.00016830038,0.00028090415,0.00064646103,0.0008981262],"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":[0.000003896346,0.000013767132,0.0000043601744,0.000013535509,0.00012527767,0.00000846028,0.000049187067,0.000007661633,0.0000028680618,0.8610016,0.0023445748,0.13642476],"study_design_scores_gemma":[0.00024640365,0.00018699122,0.00020430099,0.000049404473,0.00028011054,0.000028201184,0.0000012432298,0.0034288545,0.0000082775405,0.3298691,0.66524786,0.0004492581],"about_ca_topic_score_codex":0.000027002898,"about_ca_topic_score_gemma":0.000021602149,"teacher_disagreement_score":0.6629033,"about_ca_system_score_codex":0.00019254237,"about_ca_system_score_gemma":0.00016251995,"threshold_uncertainty_score":0.9998798},"labels":[],"label_agreement":null},{"id":"W2783053205","doi":"10.1007/978-3-319-74180-2_11","title":"Consistent Subset Problem with Two Labels","year":2018,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University; University of Alberta","funders":"","keywords":"Computer science; NP-complete; Algorithm; Artificial intelligence; Theoretical computer science; Computational complexity theory","score_opus":0.018788604069248413,"score_gpt":0.25517506529034256,"score_spread":0.23638646122109414,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2783053205","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":[0.000093513285,0.0001548498,0.98671806,0.0015975148,0.0005353932,0.00036848703,0.00000898466,0.0002434776,0.0102797495],"genre_scores_gemma":[0.086274296,0.000026540054,0.90952295,0.0018627251,0.0005408592,0.00001889753,0.00004331099,0.000047680067,0.0016627318],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9962621,0.000054010558,0.0004222102,0.0016899809,0.0009903123,0.00058142724],"domain_scores_gemma":[0.9968987,0.00028545188,0.00037000506,0.0019052175,0.00035686712,0.00018377526],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009800672,0.00047825085,0.00042436345,0.00054303044,0.00029434505,0.0007449984,0.00297632,0.0001790648,0.00005549114],"category_scores_gemma":[0.000054752065,0.00036940994,0.00006514035,0.0005818865,0.00096490065,0.00055152015,0.0009201695,0.00073831016,0.0001903931],"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":[0.00002099426,0.00007094045,0.0006495933,0.0000903767,0.000032880507,0.00012330753,0.001462357,0.009264268,0.00017416892,0.10494298,0.00035457857,0.8828136],"study_design_scores_gemma":[0.0014480208,0.0013213813,0.00091786485,0.0014179689,0.00003865954,0.00053658884,4.934169e-7,0.72592634,0.0011940129,0.21282795,0.052101582,0.002269127],"about_ca_topic_score_codex":0.000041568182,"about_ca_topic_score_gemma":0.00022934141,"teacher_disagreement_score":0.8805444,"about_ca_system_score_codex":0.00018749856,"about_ca_system_score_gemma":0.0006108452,"threshold_uncertainty_score":0.9998758},"labels":[],"label_agreement":null},{"id":"W2783872167","doi":"","title":"Classification algorithms and how to distribute them","year":2017,"lang":"en","type":"article","venue":"Computer Science and Software Engineering","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"IBM (Canada); Queen's University","funders":"","keywords":"Computer science; Rewriting; Algorithm; Statistical classification; IBM; Classifier (UML); Categorization; Big data; Plug-in; SPARK (programming language); Machine learning; Artificial intelligence; Data mining; Programming language","score_opus":0.026365219785234494,"score_gpt":0.24992841857342418,"score_spread":0.2235631987881897,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2783872167","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":[0.026572734,0.0000272386,0.9693784,0.003381819,0.0003515103,0.00007542771,0.0000026378025,0.00019411973,0.00001612997],"genre_scores_gemma":[0.6534959,0.0000112015005,0.34630123,0.00007251595,0.00008294556,0.000006702823,0.0000022218828,0.000003890271,0.00002337653],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998911,0.00001004327,0.00007560255,0.00049885473,0.00026896555,0.00023550565],"domain_scores_gemma":[0.9987542,0.00007088174,0.00005964137,0.0008029485,0.0001121066,0.00020020832],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00071864354,0.000110335954,0.00009936124,0.00009083514,0.0007135949,0.0021192243,0.0010965004,0.000029252456,3.2880754e-7],"category_scores_gemma":[0.0006466269,0.00010014466,0.000011569916,0.0001904936,0.000108384615,0.001336425,0.00074577035,0.00010235439,0.000006825473],"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":[6.155846e-7,0.000008289576,0.014350869,0.00001855862,0.0000032460753,0.0000037246907,0.0003537872,0.00017201714,0.00069930236,0.018013937,0.0003274218,0.96604824],"study_design_scores_gemma":[0.00006401632,0.000020574438,0.36782792,0.00001897521,0.0000012525826,0.000016907861,0.0000030784943,0.6252393,0.00011503962,0.000059193648,0.006508594,0.00012513484],"about_ca_topic_score_codex":0.000006485401,"about_ca_topic_score_gemma":5.536542e-7,"teacher_disagreement_score":0.9659231,"about_ca_system_score_codex":0.000028977744,"about_ca_system_score_gemma":0.000040303694,"threshold_uncertainty_score":0.9989167},"labels":[],"label_agreement":null},{"id":"W2784015834","doi":"10.1109/icmla.2017.000-8","title":"Histogram-Based Asymmetric Relabeling for Learning from Only Positive and Unlabeled Data","year":2017,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Histogram; Computer science; Artificial intelligence; Pattern recognition (psychology); Feature (linguistics); Labeled data; Machine learning; Data mining; Image (mathematics)","score_opus":0.06177677766417026,"score_gpt":0.31585390658256174,"score_spread":0.25407712891839146,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2784015834","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":[0.0071558016,0.0002117588,0.98557276,0.0039208033,0.00014802317,0.00015077193,0.00003269296,0.00017106562,0.002636301],"genre_scores_gemma":[0.7440076,0.000015351194,0.25446767,0.00024840646,0.000053301002,0.000005690981,0.0005297731,0.000009521686,0.0006627087],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988328,0.00007541107,0.00015484702,0.00060827745,0.00015104405,0.00017760592],"domain_scores_gemma":[0.99742275,0.00057741057,0.00022000639,0.001635736,0.000079186204,0.000064898275],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005695917,0.00010692658,0.00013511769,0.0001070298,0.00085698784,0.0007125846,0.0015541802,0.00005726588,0.0000052850546],"category_scores_gemma":[0.0017563395,0.00009669118,0.000020334155,0.00010443353,0.000044311408,0.00076523813,0.000533609,0.00018678002,0.000022306693],"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":[0.000021644506,0.000051579686,0.02887576,0.000011824497,0.000024967332,0.0000029687592,0.0000922996,0.00006642752,0.00045595417,0.020453561,0.0016224063,0.9483206],"study_design_scores_gemma":[0.0007992061,0.00007069616,0.05572785,0.000022896565,0.00001987756,0.0000017443022,0.000011937039,0.9105282,0.00014093339,0.0004952437,0.032010283,0.00017116504],"about_ca_topic_score_codex":0.001233293,"about_ca_topic_score_gemma":0.00011521378,"teacher_disagreement_score":0.94814944,"about_ca_system_score_codex":0.00002287297,"about_ca_system_score_gemma":0.000076768636,"threshold_uncertainty_score":0.68714696},"labels":[],"label_agreement":null},{"id":"W2786295418","doi":"","title":"LEAP: Learning Embeddings for Adaptive Pace","year":2018,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"MNIST database; Computer science; Embedding; Convolutional neural network; Artificial intelligence; Feature learning; Deep learning; Classifier (UML); Artificial neural network; Representation (politics); Pattern recognition (psychology); Machine learning; Algorithm","score_opus":0.02455115179818511,"score_gpt":0.29300162512261263,"score_spread":0.2684504733244275,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2786295418","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":[0.0014550762,0.000010653004,0.96617234,0.0014965197,0.0001372165,0.00008906489,6.246299e-7,0.00032441696,0.030314067],"genre_scores_gemma":[0.7753327,0.000001993166,0.21105415,0.00029421708,0.00017001477,0.000015359941,0.000006949807,0.000006644967,0.013117988],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992928,0.000039216862,0.00009481941,0.00029232993,0.00010548752,0.00017534816],"domain_scores_gemma":[0.9993826,0.00011847476,0.00006292935,0.00027205897,0.00011432173,0.000049622115],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003172904,0.000071174545,0.00006965213,0.000049556562,0.00022745444,0.00011978268,0.00037690386,0.00003410182,0.000040701318],"category_scores_gemma":[0.00019471253,0.000060388258,0.00003063233,0.0001623888,0.00003827396,0.00032585577,0.00010308362,0.00009731404,0.00027070986],"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":[0.000023856453,0.000025957346,0.0008191804,0.0000066905923,0.000011551105,4.579734e-7,0.0012565146,0.000059641676,0.0016687647,0.7624679,0.0173655,0.21629398],"study_design_scores_gemma":[0.00019918731,0.00035552008,0.0020393054,0.000006835372,0.000002728752,0.0000035380838,0.000114051574,0.6515125,0.001510344,0.0016593412,0.34246385,0.00013280482],"about_ca_topic_score_codex":0.000032493685,"about_ca_topic_score_gemma":0.000010392886,"teacher_disagreement_score":0.7738776,"about_ca_system_score_codex":0.00001541164,"about_ca_system_score_gemma":0.000024301076,"threshold_uncertainty_score":0.3479518},"labels":[],"label_agreement":null},{"id":"W2786708967","doi":"10.1109/icm.2017.8268827","title":"Hardware accelerators for the K-nearest neighbor algorithm using high level synthesis","year":2017,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph","funders":"","keywords":"Computer science; k-nearest neighbors algorithm; High-level synthesis; Ranging; Algorithm; Parallel computing; Field-programmable gate array; Artificial intelligence; Embedded system","score_opus":0.13102813405229222,"score_gpt":0.33295004480778073,"score_spread":0.20192191075548852,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2786708967","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":[0.0010085971,0.00002368653,0.99181163,0.0057273936,0.000459138,0.0001727496,0.000046539033,0.00010487031,0.00064538734],"genre_scores_gemma":[0.6174531,0.00001071022,0.38089356,0.00025013884,0.00026478802,0.000050343217,0.000007431636,0.000013361771,0.0010565429],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991353,0.00003632024,0.00013478857,0.00032008265,0.00017050638,0.00020297826],"domain_scores_gemma":[0.9978381,0.0003911721,0.0001568188,0.0014675768,0.00009202612,0.00005432771],"candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00037510894,0.00010902311,0.00010775217,0.000034717294,0.0015249774,0.0012450921,0.0018480287,0.000047527523,0.000039814862],"category_scores_gemma":[0.00054107193,0.000069026784,0.000055324625,0.00005587058,0.00005280167,0.0006660925,0.00029619044,0.00009584594,0.000032446373],"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":[0.0000027969877,0.000022440756,0.0011855387,0.000008768035,0.00002315685,0.0000012673772,0.00006495132,0.00009541936,0.0002242286,0.04127412,0.0025022172,0.9545951],"study_design_scores_gemma":[0.00014519531,0.000015357022,0.06802779,0.000013132551,0.000016196866,0.0000040187124,0.000025023633,0.8999281,0.0019335678,0.00048656447,0.029251972,0.00015312115],"about_ca_topic_score_codex":0.0009941051,"about_ca_topic_score_gemma":0.00004147413,"teacher_disagreement_score":0.95444196,"about_ca_system_score_codex":0.000024275032,"about_ca_system_score_gemma":0.000062955536,"threshold_uncertainty_score":0.9997917},"labels":[],"label_agreement":null},{"id":"W2788320705","doi":"","title":"Machine learning: Supervised methods, SVM and kNN","year":2018,"lang":"fr","type":"preprint","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada's Michael Smith Genome Sciences Centre","funders":"","keywords":"Support vector machine; Machine learning; Artificial intelligence; Random forest; Logistic regression; Supervised learning; Context (archaeology); Computer science; Pattern recognition (psychology); Set (abstract data type); Artificial neural network; Biology","score_opus":0.03162811474333381,"score_gpt":0.28229620491469254,"score_spread":0.2506680901713587,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2788320705","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":[0.0062396284,0.0055828607,0.88132566,0.046492845,0.0006583141,0.0004907396,0.000059763734,0.00053548353,0.058614686],"genre_scores_gemma":[0.12451993,0.004937148,0.79451454,0.0002841108,0.00012754723,0.000081684644,0.00141718,0.0001021681,0.07401568],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9673991,0.028261341,0.00094589096,0.002046046,0.000634674,0.00071291695],"domain_scores_gemma":[0.9877689,0.003986633,0.00095260295,0.0039591156,0.0028059345,0.0005268183],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.019224789,0.00069895387,0.0007138298,0.00031597374,0.001202687,0.0017959416,0.002934507,0.0005710683,0.00050783035],"category_scores_gemma":[0.0069930353,0.0007541268,0.00025279546,0.0008047794,0.00083249377,0.00056346593,0.004485357,0.0019081427,0.00033662692],"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":[0.0000150053265,0.00042849724,0.00828987,0.00024197847,0.00009798796,0.000005829642,0.011537916,0.000046287176,0.0020680085,0.47826004,0.0009798605,0.49802873],"study_design_scores_gemma":[0.00061008736,0.0000020921366,0.015242581,0.001038124,0.000073735384,0.000052495154,0.00006431302,0.5827935,0.00490495,0.007120211,0.3874019,0.0006960193],"about_ca_topic_score_codex":0.004810594,"about_ca_topic_score_gemma":0.0009416902,"teacher_disagreement_score":0.58274716,"about_ca_system_score_codex":0.00013716913,"about_ca_system_score_gemma":0.00041946876,"threshold_uncertainty_score":0.999491},"labels":[],"label_agreement":null},{"id":"W2790266074","doi":"10.1016/j.neucom.2017.11.071","title":"Bayesian optimization on graph-structured search spaces: Optimizing deep multimodal fusion architectures","year":2018,"lang":"en","type":"article","venue":"Neurocomputing","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Institute for Advanced Research; University of Guelph","funders":"Air Force Research Laboratory; Defense Advanced Research Projects Agency; Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada; Canada Foundation for Innovation; Agence Nationale de la Recherche; Nvidia","keywords":"Computer science; Artificial intelligence; Hyperparameter; Bayesian optimization; Testbed; Machine learning; Deep learning; Hyperparameter optimization; Gesture; Graph; Fuse (electrical); Optimization problem; Pattern recognition (psychology); Theoretical computer science; Support vector machine; Algorithm","score_opus":0.013866380034235933,"score_gpt":0.26521397946677305,"score_spread":0.2513475994325371,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2790266074","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":[0.041077673,0.000013804357,0.9551997,0.0008607162,0.0004251373,0.00022662642,0.0000011675794,0.0005204652,0.0016746891],"genre_scores_gemma":[0.66085565,0.00000230282,0.3383748,0.00040184156,0.0003161267,0.0000028497523,0.000014011983,0.00001883573,0.000013594791],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976926,0.00031681557,0.00028275265,0.0008052708,0.00045240772,0.0004501755],"domain_scores_gemma":[0.99864686,0.00021113471,0.00016121608,0.00072007783,0.000118028285,0.00014265864],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036698327,0.00023926827,0.00017480472,0.00034420614,0.00071623357,0.00043472493,0.0008769971,0.00009160909,0.0000214061],"category_scores_gemma":[0.00014843764,0.00021696692,0.00007029556,0.0006731489,0.00008169884,0.00016322214,0.00036852184,0.00045908822,0.000029103603],"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":[0.000019518584,0.00002963943,0.00064509857,0.000013088605,0.000005370957,0.0000062097756,0.0011062124,0.8363371,0.0016306823,0.0012435436,0.00003613993,0.1589274],"study_design_scores_gemma":[0.00033333714,0.000217874,0.0047035804,0.000038414324,0.0000036305469,0.000025489502,0.000026123023,0.9924097,0.001569359,0.00016883339,0.00029174416,0.00021190874],"about_ca_topic_score_codex":0.000049580685,"about_ca_topic_score_gemma":0.00000990407,"teacher_disagreement_score":0.619778,"about_ca_system_score_codex":0.000030328769,"about_ca_system_score_gemma":0.000034498447,"threshold_uncertainty_score":0.8847654},"labels":[],"label_agreement":null},{"id":"W2794553059","doi":"","title":"CREAM: new feature selection approach for epigenomic profiles of cells","year":2018,"lang":"en","type":"article","venue":"Research in Computational Molecular Biology","topic":"Machine Learning and Data Classification","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":"Princess Margaret Cancer Centre; University of Toronto","funders":"","keywords":"Epigenomics; Computer science; Feature selection; Selection (genetic algorithm); Feature (linguistics); Artificial intelligence; Chemistry; DNA methylation","score_opus":0.06525411104604177,"score_gpt":0.40573548124093245,"score_spread":0.34048137019489066,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2794553059","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":[0.008873304,0.00009461246,0.98837215,0.0016311612,0.000055538963,0.0003656698,0.000009701624,0.000025389994,0.0005724971],"genre_scores_gemma":[0.5813724,0.0000026474693,0.41827407,0.000035148667,0.0000798808,0.000027340191,0.0001358488,0.0000050929343,0.000067598805],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985446,0.00041594356,0.00017538141,0.00040563795,0.00019000907,0.00026847367],"domain_scores_gemma":[0.9989743,0.0003282235,0.00007160388,0.00020335134,0.00036123305,0.00006123976],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010120684,0.000076105534,0.00012324334,0.00035464528,0.00009550385,0.000034751956,0.0005010422,0.000106233005,0.0000040274167],"category_scores_gemma":[0.00015905514,0.00007181693,0.0000359718,0.00062860217,0.00014312382,0.00006557744,0.00013075725,0.00021074474,0.000011651859],"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":[0.000099593766,0.00027976336,0.0021866634,0.00009673714,0.000035001274,0.0000012571943,0.00022412893,0.01835744,0.2004019,0.7264879,0.0032824127,0.048547223],"study_design_scores_gemma":[0.0005251777,0.000803529,0.004579793,0.000013010507,0.0000017195182,0.000007905074,0.000012249802,0.8246678,0.02114475,0.14430961,0.0038113275,0.00012308435],"about_ca_topic_score_codex":0.00010901657,"about_ca_topic_score_gemma":0.000004602645,"teacher_disagreement_score":0.8063104,"about_ca_system_score_codex":0.00006022775,"about_ca_system_score_gemma":0.0003556956,"threshold_uncertainty_score":0.29286095},"labels":[],"label_agreement":null},{"id":"W2796067775","doi":"10.24963/ijcai.2018/312","title":"Generative Adversarial Positive-Unlabelled Learning","year":2018,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":67,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"Japan Society for the Promotion of Science; National Natural Science Foundation of China","keywords":"Overfitting; Artificial intelligence; Computer science; Discriminative model; Generative grammar; Machine learning; Binary classification; Classifier (UML); Decision boundary; Binary number; Artificial neural network; Labeled data; Task (project management); Generative model; Deep learning; Adversarial system; Support vector machine; Mathematics","score_opus":0.01149179187381857,"score_gpt":0.2589441306130028,"score_spread":0.24745233873918424,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2796067775","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":[0.0050191465,0.000010084586,0.9054526,0.0022739258,0.00029564503,0.000056995665,5.677573e-7,0.00026530682,0.08662572],"genre_scores_gemma":[0.9010416,0.0000035610542,0.09033634,0.000490479,0.00040976045,0.0000038058015,0.00001954386,0.0000053390354,0.0076895584],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99914896,0.00014734756,0.00010660056,0.00029720107,0.00014588129,0.00015400659],"domain_scores_gemma":[0.9994451,0.00006298676,0.00005516374,0.00027687167,0.00010458172,0.000055303797],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00023240673,0.00007847809,0.00007383858,0.000055590273,0.00029700142,0.00013130289,0.00036669415,0.00003699957,0.00016916057],"category_scores_gemma":[0.000120431985,0.000065577886,0.000024043373,0.00021557182,0.000049411738,0.0003407225,0.00015679983,0.00013709598,0.0008191926],"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":[0.00003482982,0.0000831153,0.0034006992,0.000003188264,0.00004015033,0.000006474104,0.003279822,0.00014333919,0.019752637,0.7839876,0.010139044,0.17912911],"study_design_scores_gemma":[0.0009599238,0.0005976216,0.01700599,0.000010488141,0.000008402156,0.00001401276,0.00009196101,0.8355391,0.015891012,0.001728092,0.12778483,0.00036856782],"about_ca_topic_score_codex":0.00006452716,"about_ca_topic_score_gemma":0.000012364653,"teacher_disagreement_score":0.89602244,"about_ca_system_score_codex":0.000019040333,"about_ca_system_score_gemma":0.000037939906,"threshold_uncertainty_score":0.9999588},"labels":[],"label_agreement":null},{"id":"W2801177523","doi":"10.1109/iacs.2018.8355444","title":"A comparative study of open source deep learning frameworks","year":2018,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":57,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Implementation; Computer science; Benchmark (surveying); Artificial intelligence; Open source; Machine learning; Deep learning; Quality (philosophy); Data science; Software engineering; Programming language; Software","score_opus":0.04485666817750818,"score_gpt":0.3573274645369784,"score_spread":0.3124707963594702,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2801177523","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":[0.14243455,0.000007979699,0.83166105,0.00019752626,0.000053692733,0.00019196821,7.85321e-8,0.00009949154,0.025353646],"genre_scores_gemma":[0.9691122,5.7018633e-7,0.029423533,0.00008801925,0.000034125984,0.00000947754,0.0000021237606,0.0000034775164,0.0013264809],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99904335,0.00022506693,0.00017036078,0.0002853075,0.0001629828,0.00011291195],"domain_scores_gemma":[0.99907947,0.00012519433,0.00013188244,0.000504856,0.00011632324,0.000042300584],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038119341,0.00007193182,0.00015723662,0.000057526657,0.00017419535,0.0002359831,0.0013874418,0.00004814045,0.00009155809],"category_scores_gemma":[0.000084042214,0.000058424805,0.000013348692,0.000346576,0.000043138793,0.0003916574,0.0007873857,0.00031107475,0.000116092444],"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":[0.00010065749,0.0026646054,0.14903249,0.000017617112,0.00017402542,0.0000034611073,0.17880127,0.004690396,0.0010101056,0.13591382,0.0044685123,0.523123],"study_design_scores_gemma":[0.0006800054,0.0016325288,0.08028033,0.000016228127,0.000008430274,0.000002858124,0.007514897,0.88805664,0.00037572783,0.0006616103,0.020570684,0.00020008978],"about_ca_topic_score_codex":0.00040916985,"about_ca_topic_score_gemma":0.00016309702,"teacher_disagreement_score":0.8833662,"about_ca_system_score_codex":0.000008104614,"about_ca_system_score_gemma":0.00001590655,"threshold_uncertainty_score":0.2578235},"labels":[],"label_agreement":null},{"id":"W2801451195","doi":"10.1109/ijcnn.2018.8489269","title":"An Ensemble Generation Method Based on Instance Hardness","year":2018,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Boosting (machine learning); Resampling; Outlier; Noise (video); Subspace topology; Ensemble learning; Pattern recognition (psychology); Class (philosophy)","score_opus":0.04236216759406364,"score_gpt":0.34331580709953785,"score_spread":0.3009536395054742,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2801451195","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":[0.002612351,0.0000019502818,0.97602516,0.0013729424,0.00030472368,0.00005018753,8.4253054e-7,0.00021104854,0.019420817],"genre_scores_gemma":[0.5568426,3.2557116e-7,0.44120532,0.0013262455,0.0001466578,0.0000051031757,0.000018620056,0.000003205551,0.00045190746],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991156,0.00017728208,0.000096544776,0.00033388427,0.00016799045,0.00010870934],"domain_scores_gemma":[0.9990439,0.000030068575,0.000044495093,0.0007443851,0.00008245389,0.000054714765],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047947705,0.000067288616,0.000057045636,0.00006375899,0.00015164002,0.0001684771,0.00039655404,0.00003316261,0.00004992868],"category_scores_gemma":[0.00004707959,0.00005583884,0.000013702549,0.00021004284,0.00001467251,0.00038586452,0.000020242547,0.00006185228,0.00016900059],"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":[0.000011689355,0.00013498885,0.00056428823,0.000004376698,0.0000024804917,0.000001247027,0.0002482445,0.0020163115,0.0469677,0.34287405,0.0075506936,0.5996239],"study_design_scores_gemma":[0.00011779097,0.00015786444,0.002340091,0.0000025935217,8.866573e-7,7.648662e-7,0.0000032105927,0.9581157,0.020165727,0.00029587385,0.018719474,0.00007999695],"about_ca_topic_score_codex":0.000037878326,"about_ca_topic_score_gemma":0.000050394785,"teacher_disagreement_score":0.9560994,"about_ca_system_score_codex":0.000018148558,"about_ca_system_score_gemma":0.000041303498,"threshold_uncertainty_score":0.22770417},"labels":[],"label_agreement":null},{"id":"W2804364191","doi":"10.22215/etd/2009-09134","title":"Learning a test Oracle towards automating image segmentation evaluation","year":2009,"lang":"en","type":"dissertation","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University; Canadian Heritage; Library and Archives Canada","funders":"","keywords":"Oracle; Test (biology); Computer science; Information retrieval; Artificial intelligence; Art; Software engineering","score_opus":0.017327998231560802,"score_gpt":0.33566582616278573,"score_spread":0.31833782793122495,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2804364191","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":[0.043945163,0.00046129213,0.5299001,0.002096384,0.0014746976,0.001933155,0.00001035899,0.0039965785,0.4161823],"genre_scores_gemma":[0.574372,0.00009731388,0.38091755,0.0002496869,0.0003634846,0.00024863306,0.014049925,0.00007888367,0.029622534],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99726593,0.0002991664,0.0004894175,0.0007001049,0.0009768315,0.0002685366],"domain_scores_gemma":[0.9981577,0.00014734651,0.00061163143,0.00053903146,0.00046562462,0.00007866586],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0014569232,0.00029011903,0.0002386129,0.0002904491,0.00035860733,0.0007442517,0.0006295263,0.00020747069,0.00017050924],"category_scores_gemma":[0.0014143108,0.0002856487,0.00008468302,0.00053142384,0.000009219607,0.0010784502,0.00004479165,0.00054603704,0.0003229725],"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":[0.0000033756585,0.000058591453,0.00013429817,0.000056412293,0.000009081494,0.0000015442026,0.001218973,0.00017504052,0.0064357123,0.0008370651,0.0006447668,0.9904251],"study_design_scores_gemma":[0.00040235647,0.00021718077,0.0738238,0.00012972135,0.000058778296,0.000006381171,0.00089311844,0.917723,0.00414179,0.0008633373,0.001278413,0.0004621013],"about_ca_topic_score_codex":0.00019045576,"about_ca_topic_score_gemma":0.000116387724,"teacher_disagreement_score":0.98996305,"about_ca_system_score_codex":0.00018963685,"about_ca_system_score_gemma":0.00035459522,"threshold_uncertainty_score":0.9999596},"labels":[],"label_agreement":null},{"id":"W2806149066","doi":"10.1609/aaai.v32i1.11369","title":"Dataset Evolver: An Interactive Feature Engineering Notebook","year":2018,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Feature engineering; Feature (linguistics); Computer science; Construct (python library); Artificial intelligence; Reinforcement learning; Science and engineering; Machine learning; Human–computer interaction; Software engineering; Engineering; Deep learning; Programming language","score_opus":0.05272340630652117,"score_gpt":0.3101749047573195,"score_spread":0.25745149845079834,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2806149066","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":[0.20617233,0.00007100871,0.7130998,0.032897566,0.004669081,0.0021966537,0.0006628459,0.0012388667,0.03899186],"genre_scores_gemma":[0.98926854,0.000006596666,0.010086912,0.0002470355,0.0001733579,0.000012795057,0.00002412841,0.000010729479,0.00016993197],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99857736,0.000018526463,0.0002787441,0.00051700056,0.00035141196,0.0002569593],"domain_scores_gemma":[0.99854887,0.000068689216,0.000272571,0.00053476205,0.00047987496,0.000095245654],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040198752,0.00019075705,0.0001680247,0.00012215352,0.00018552909,0.00032878947,0.0022578286,0.000080811784,0.00006529215],"category_scores_gemma":[0.0004920113,0.00014401246,0.00004888028,0.00041832618,0.00017054654,0.0009603527,0.00039850356,0.00039351307,0.00018930504],"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":[0.00008615603,0.0001238139,0.00017805301,0.000029803128,0.000018976452,4.7849966e-7,0.0021071846,0.000032997534,0.09274387,0.78834736,0.003562625,0.11276869],"study_design_scores_gemma":[0.000031330204,0.00045409187,0.00079571514,0.00018889921,0.000012696936,0.000008989622,0.0002745637,0.5362067,0.43750408,0.015889654,0.00831449,0.00031875572],"about_ca_topic_score_codex":0.00004763179,"about_ca_topic_score_gemma":0.000014046051,"teacher_disagreement_score":0.7830962,"about_ca_system_score_codex":0.0000388774,"about_ca_system_score_gemma":0.000058571328,"threshold_uncertainty_score":0.5872658},"labels":[],"label_agreement":null},{"id":"W2808399504","doi":"10.48550/arxiv.1806.04613","title":"Improving Regression Performance with Distributional Losses","year":2018,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Overfitting; Regression; Ambiguity; Computer science; Generalization; Machine learning; Artificial intelligence; Reinforcement learning; Statistics; Mathematics; Artificial neural network","score_opus":0.046546165568875586,"score_gpt":0.18778576980743275,"score_spread":0.14123960423855716,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2808399504","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":[0.34127575,0.000017654324,0.6570906,0.00010983941,0.0001863665,0.000085965585,0.000019826806,0.0001944544,0.0010195425],"genre_scores_gemma":[0.9946798,0.00005521477,0.003985528,0.000025017487,0.00011117466,8.032763e-7,0.00020135904,0.00000903116,0.0009320441],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998561,0.000081577746,0.00011897473,0.000887539,0.00011612833,0.00023478144],"domain_scores_gemma":[0.9982518,0.000047866793,0.0002968902,0.0011096138,0.00019122563,0.00010259311],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020687492,0.00021871775,0.00016318823,0.00011662963,0.0002863598,0.0001516271,0.0012648985,0.00015466503,0.000023865361],"category_scores_gemma":[0.000039461127,0.00018882747,0.00005424602,0.00033892383,0.0001375416,0.0005006585,0.0012173043,0.00046978425,0.00009357316],"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":[0.0005295947,0.0005783864,0.39114583,0.0011532683,0.00025167016,0.00040262248,0.00047565027,0.110990964,0.0004270708,0.43779403,0.005324682,0.05092624],"study_design_scores_gemma":[0.00029539797,0.000118599724,0.03430319,0.0002172573,0.000029872466,0.000011385676,0.00001252436,0.96081185,0.0002500932,0.0015516111,0.0020231325,0.00037509436],"about_ca_topic_score_codex":0.00008263808,"about_ca_topic_score_gemma":0.000009997155,"teacher_disagreement_score":0.8498209,"about_ca_system_score_codex":0.00013833574,"about_ca_system_score_gemma":0.00023615442,"threshold_uncertainty_score":0.7700161},"labels":[],"label_agreement":null},{"id":"W2812183302","doi":"","title":"High-Precision Numerical Integratioin: Progress and Challenges","year":2008,"lang":"en","type":"article","venue":"eScholarship (California Digital Library)","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Realm; Field (mathematics); Relation (database); Computer science; Calculus (dental); Mathematics; Epistemology; History; Philosophy; Data mining; Archaeology; Pure mathematics","score_opus":0.0268234140250789,"score_gpt":0.22807565727410137,"score_spread":0.20125224324902247,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2812183302","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":[0.58320546,0.020837741,0.2625886,0.090650074,0.001102088,0.001416316,0.001187861,0.0065546986,0.03245718],"genre_scores_gemma":[0.9701922,0.0006163892,0.028247308,0.00025053837,0.00010778779,0.000020970634,0.00025610824,0.000028205544,0.00028051942],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99830294,0.00011906962,0.000304948,0.0006178185,0.00036466893,0.0002905572],"domain_scores_gemma":[0.9988049,0.00016647349,0.000115291805,0.00062474865,0.000032551325,0.0002559847],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00015273562,0.00022751518,0.00021690471,0.00013844497,0.0002290398,0.0010611931,0.000790342,0.00011170775,0.00003635647],"category_scores_gemma":[0.00023376633,0.0001837773,0.000057968628,0.00034196093,0.00012007956,0.0054728165,0.0004980167,0.00039045804,0.00077765546],"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":[0.000049972015,0.00026594324,0.075872265,0.000050345177,0.000021129363,0.00007711543,0.00016469856,0.0000044794656,0.000022068027,0.10119659,0.002568813,0.81970656],"study_design_scores_gemma":[0.0008554317,0.0003955895,0.18412629,0.00011449812,0.000007846925,0.00028766657,0.00003279419,0.009667776,0.000741061,0.022953972,0.7799704,0.00084667385],"about_ca_topic_score_codex":0.0000016655285,"about_ca_topic_score_gemma":2.0212279e-7,"teacher_disagreement_score":0.81885993,"about_ca_system_score_codex":0.000013180251,"about_ca_system_score_gemma":0.00005808489,"threshold_uncertainty_score":0.9999758},"labels":[],"label_agreement":null},{"id":"W2883256923","doi":"10.1145/3239570","title":"Evaluation-as-a-Service for the Computational Sciences","year":2018,"lang":"en","type":"article","venue":"Journal of Data and Information Quality","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":44,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Data science; Crowdsourcing; Field (mathematics); Executable; Domain (mathematical analysis); Service (business); Confidentiality; Big data; Work (physics); World Wide Web; Data mining; Computer security","score_opus":0.2061877675601156,"score_gpt":0.4578079204475153,"score_spread":0.2516201528873997,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2883256923","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":[0.0058391117,0.00007849322,0.9734832,0.019206787,0.0002177447,0.00011506471,0.00004469369,0.0000085965785,0.0010062787],"genre_scores_gemma":[0.8973797,0.000042385753,0.09706096,0.0051139263,0.00024900606,0.000003672358,0.00014365141,0.0000013123814,0.000005379151],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987254,0.00012480281,0.00041695428,0.000069864866,0.00060145976,0.00006148206],"domain_scores_gemma":[0.9973268,0.00054960593,0.0005627371,0.00029531625,0.0012331458,0.000032423948],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010551997,0.000040530882,0.00006271511,0.00006530986,0.00039962598,0.000363438,0.00097566034,0.00001806932,0.000015459624],"category_scores_gemma":[0.0013400802,0.000024683803,0.000013462014,0.0002195429,0.00007974594,0.008163187,0.0001553626,0.000064792206,0.000017077993],"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":[0.000021000766,0.000019091029,0.00046695967,0.000022281247,0.000026881635,1.6282891e-8,0.001999551,0.0005775252,0.000008514745,0.2633557,0.008554601,0.72494787],"study_design_scores_gemma":[0.00033629942,0.00010187821,0.026371997,0.0000076970255,0.000014535349,0.000017652175,0.00033011916,0.8309835,0.000006493758,0.009466233,0.13232292,0.000040643696],"about_ca_topic_score_codex":0.000029331752,"about_ca_topic_score_gemma":0.000006664369,"teacher_disagreement_score":0.8915406,"about_ca_system_score_codex":0.000012198363,"about_ca_system_score_gemma":0.00030507141,"threshold_uncertainty_score":0.59181136},"labels":[],"label_agreement":null},{"id":"W2885260234","doi":"10.1016/j.patcog.2018.08.004","title":"Online local pool generation for dynamic classifier selection","year":2018,"lang":"en","type":"article","venue":"Pattern Recognition","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure; Université du Québec à Montréal","funders":"Fundação de Amparo à Ciência e Tecnologia do Estado de Pernambuco; Conselho Nacional de Desenvolvimento Científico e Tecnológico; Coordenação de Aperfeiçoamento de Pessoal de Nível Superior","keywords":"Classifier (UML); Computer science; Artificial intelligence; Pattern recognition (psychology); Machine learning; Feature selection; Margin classifier; Data mining; Quadratic classifier","score_opus":0.05118502926776238,"score_gpt":0.30591031235097965,"score_spread":0.2547252830832173,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2885260234","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":[0.077901736,0.000007768237,0.91987514,0.0011344857,0.0004936293,0.00020979652,0.000049588172,0.00019482926,0.00013302358],"genre_scores_gemma":[0.9721862,0.00000853787,0.024249382,0.0006665789,0.0006610818,0.0000635371,0.0020004949,0.000013097687,0.0001510833],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99898875,0.00008319853,0.00020203379,0.0004010798,0.00014285572,0.00018207433],"domain_scores_gemma":[0.99932563,0.00004174869,0.00011777278,0.00021814054,0.0002470308,0.000049686998],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023342385,0.00010782784,0.00008389062,0.00011395478,0.0002064632,0.00012427747,0.0001811058,0.00008371214,0.000059418435],"category_scores_gemma":[0.0000577766,0.00010737762,0.00004187995,0.00019039049,0.000033362972,0.00043090794,0.00003247287,0.00010610025,0.00027537657],"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":[0.00000637745,0.00007713073,0.00036572482,0.000010949552,0.000006977553,1.8018109e-7,0.00006716644,0.00001054358,0.0071339565,0.00006902007,0.0010267856,0.9912252],"study_design_scores_gemma":[0.00034019342,0.00023625512,0.010681128,0.000015509122,0.000011381023,0.000012696813,0.000014243411,0.9803696,0.0038533064,0.00079727784,0.0035136568,0.00015472303],"about_ca_topic_score_codex":0.00004275077,"about_ca_topic_score_gemma":0.00043249564,"teacher_disagreement_score":0.99107045,"about_ca_system_score_codex":0.000073599316,"about_ca_system_score_gemma":0.000030593863,"threshold_uncertainty_score":0.43787324},"labels":[],"label_agreement":null},{"id":"W2887615774","doi":"10.1609/aaai.v33i01.33013470","title":"On-Line Adaptative Curriculum Learning for GANs","year":2019,"lang":"en","type":"preprint","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Machine Learning and Data Classification","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":false,"ca_institutions":"Institut National de la Recherche Scientifique; McGill University","funders":"","keywords":"Discriminator; Computer science; Generator (circuit theory); Generative grammar; Adversarial system; Artificial intelligence; Cover (algebra); Machine learning; Curriculum; Convergence (economics); Quality (philosophy)","score_opus":0.11362376742260104,"score_gpt":0.3441957825344797,"score_spread":0.23057201511187864,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2887615774","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":[0.032561705,0.000046916124,0.9373361,0.010068002,0.0021430645,0.0020648434,0.000047049394,0.00032517232,0.015407163],"genre_scores_gemma":[0.9914502,0.000059901722,0.0069031403,0.00018025126,0.00014084754,0.00014046968,0.000018696895,0.000027662976,0.0010788115],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970931,0.00005355831,0.000707877,0.0011060569,0.00063198706,0.00040742653],"domain_scores_gemma":[0.99647677,0.00038678892,0.0012065903,0.00064352946,0.001194826,0.00009152557],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00091288483,0.00042688256,0.0004920933,0.0002191906,0.00026896741,0.00047585065,0.0034215068,0.00025863783,0.00003249178],"category_scores_gemma":[0.002209996,0.00032365724,0.00026336362,0.00040069662,0.00017263567,0.00023716659,0.001129086,0.0014530995,0.00016554775],"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":[0.00006510402,0.00014690499,0.00011887417,0.00018691526,0.000029640443,1.2894252e-7,0.0012568976,0.013471132,0.0017610149,0.9304497,0.0003940258,0.05211964],"study_design_scores_gemma":[0.0000349206,0.0005014383,0.00006534676,0.0006907271,0.000022295124,9.62029e-7,0.00041874466,0.7623204,0.035320178,0.19982636,0.000460164,0.00033843747],"about_ca_topic_score_codex":0.00007466094,"about_ca_topic_score_gemma":0.000006889492,"teacher_disagreement_score":0.95888853,"about_ca_system_score_codex":0.00008514239,"about_ca_system_score_gemma":0.00024933947,"threshold_uncertainty_score":0.99992156},"labels":[],"label_agreement":null},{"id":"W2891021639","doi":"10.1609/aaai.v33i01.33013714","title":"MixUp as Locally Linear Out-of-Manifold Regularization","year":2019,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":265,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; National Research Council Canada","funders":"National Key Research and Development Program of China; Beijing Advanced Innovation Center for Big Data and Brain Computing; National Natural Science Foundation of China","keywords":"Computer science; Regularization (linguistics); Manifold (fluid mechanics); Artificial neural network; Benchmark (surveying); Artificial intelligence; Machine learning; Mixing (physics); Nonlinear dimensionality reduction; Algorithm; Dimensionality reduction","score_opus":0.05000555547855106,"score_gpt":0.29572975316366,"score_spread":0.24572419768510895,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2891021639","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":[0.3311834,0.0000512027,0.515138,0.017922012,0.0027162684,0.0016977271,0.00001464085,0.0004031312,0.13087365],"genre_scores_gemma":[0.9935583,0.00002005828,0.0045048944,0.00014820846,0.000048859485,0.0000073228434,0.000002548161,0.000010097112,0.0016997444],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9982797,0.000024108153,0.0005129222,0.00045621346,0.00051766285,0.00020941744],"domain_scores_gemma":[0.9981741,0.00007522299,0.0005461858,0.00048469508,0.000661285,0.00005852024],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00055411895,0.0001638984,0.00022068812,0.000119270466,0.000085213615,0.00012659506,0.0019993202,0.00009675505,0.00009262513],"category_scores_gemma":[0.0005136003,0.00012598226,0.00008714118,0.0005025837,0.00009998667,0.00042772535,0.00034821455,0.0002511619,0.00047918063],"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":[0.00003261459,0.00006171255,0.0005906293,0.000045761015,0.0000075519592,8.619432e-8,0.0006860977,0.00007808337,0.078852,0.89188975,0.000054713273,0.027701022],"study_design_scores_gemma":[0.00004123158,0.0003605091,0.00059478433,0.00027820547,0.000011723391,0.0000022411218,0.0002725825,0.25107524,0.6250774,0.12112559,0.00093156705,0.00022888991],"about_ca_topic_score_codex":0.000038995433,"about_ca_topic_score_gemma":0.0000044696453,"teacher_disagreement_score":0.7707641,"about_ca_system_score_codex":0.000025699917,"about_ca_system_score_gemma":0.00011223692,"threshold_uncertainty_score":0.6159057},"labels":[],"label_agreement":null},{"id":"W2892679931","doi":"10.1016/j.asoc.2018.09.021","title":"Combining heterogeneous classifiers via granular prototypes","year":2018,"lang":"en","type":"article","venue":"Applied Soft Computing","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":24,"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","funders":"","keywords":"Computer science; AdaBoost; Random subspace method; Ensemble learning; Artificial intelligence; Random forest; Machine learning; Decision tree; Support vector machine; Exploit; Pattern recognition (psychology); Cascading classifiers; Class (philosophy); Base (topology); Multiclass classification; Boosting (machine learning); Data mining; Mathematics","score_opus":0.014238642978448488,"score_gpt":0.2516835991202298,"score_spread":0.23744495614178132,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2892679931","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":[0.02544516,0.000028197986,0.9654546,0.00028592598,0.00031308396,0.00034085772,4.9765714e-7,0.0007513063,0.0073803808],"genre_scores_gemma":[0.9244345,7.6007217e-7,0.074747965,0.0005286344,0.00020614734,0.00001834363,0.000014334757,0.0000193068,0.000030033101],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99829036,0.00007371358,0.00031051235,0.0006162693,0.00028835595,0.0004207968],"domain_scores_gemma":[0.9987454,0.0001354429,0.00019075106,0.0007334458,0.00007913495,0.00011585659],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005299259,0.00019565945,0.00019602818,0.0001069059,0.00058465276,0.00023958097,0.00091602944,0.00008743174,0.000010452841],"category_scores_gemma":[0.000042559142,0.00019404387,0.00005148921,0.0003888577,0.000120799836,0.0001365452,0.00036659103,0.00026276195,0.00031929908],"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":[0.00002946726,0.00011963078,0.0033673798,0.000053178184,0.000044918004,0.000013606524,0.0029283133,0.0013862813,0.014302547,0.114506476,0.000561021,0.8626872],"study_design_scores_gemma":[0.0005720195,0.00016489229,0.002866067,0.000033175267,0.000010582696,0.00004681428,0.000040798128,0.96548563,0.005421321,0.006273597,0.018605946,0.00047915953],"about_ca_topic_score_codex":0.00002277195,"about_ca_topic_score_gemma":0.0000035464625,"teacher_disagreement_score":0.96409935,"about_ca_system_score_codex":0.000035172296,"about_ca_system_score_gemma":0.000040782706,"threshold_uncertainty_score":0.7912879},"labels":[],"label_agreement":null},{"id":"W2894980798","doi":"10.1007/s10618-018-0592-8","title":"Classification with label noise: a Markov chain sampling framework","year":2018,"lang":"en","type":"article","venue":"Data Mining and Knowledge Discovery","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Australian Research Council","keywords":"Markov chain; Computer science; Probabilistic logic; Correctness; Artificial intelligence; Noise (video); Markov chain Monte Carlo; Pattern recognition (psychology); Sampling (signal processing); Machine learning; Probability distribution; Variable-order Markov model; Hidden Markov model; Algorithm; Markov model; Bayesian probability; Mathematics; Statistics","score_opus":0.0757148656264769,"score_gpt":0.33957449440473064,"score_spread":0.26385962877825375,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2894980798","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":[0.06412975,0.00057631487,0.92931,0.0008459876,0.0003342037,0.00011569745,0.00012764444,0.00019931713,0.0043610376],"genre_scores_gemma":[0.7611699,0.000072047515,0.23636203,0.00015172525,0.0004664535,0.000015293786,0.00083192403,0.000019592346,0.0009110174],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99840343,0.00010769021,0.00021205432,0.00083801046,0.00016913486,0.00026965648],"domain_scores_gemma":[0.99755156,0.00030809658,0.00013817694,0.0018207467,0.00008496294,0.00009647956],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00069082325,0.0001772872,0.00016494507,0.000117806674,0.00035878696,0.00067268364,0.0011506642,0.00008838509,0.0000056651666],"category_scores_gemma":[0.0003800834,0.00014365952,0.0000118373655,0.00045260228,0.00016491502,0.0016657057,0.00072581315,0.00018565093,0.00005346184],"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":[0.00008546699,0.00025540942,0.025889887,0.00010063508,0.000057814894,0.0000040550112,0.0048773335,8.878618e-7,0.0009901616,0.07178422,0.007658148,0.888296],"study_design_scores_gemma":[0.001324303,0.0006088335,0.15891114,0.00094209204,0.00008025403,0.000073167605,0.0018234225,0.7161181,0.0001380723,0.0010726912,0.117757626,0.0011503331],"about_ca_topic_score_codex":0.000026683427,"about_ca_topic_score_gemma":0.0000754251,"teacher_disagreement_score":0.88714564,"about_ca_system_score_codex":0.000020222544,"about_ca_system_score_gemma":0.00012776311,"threshold_uncertainty_score":0.64867043},"labels":[],"label_agreement":null},{"id":"W2898490583","doi":"10.1109/ciss.2019.8693043","title":"Efficient learning of neighbor representations for boundary trees and forests","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Machine Learning and Data Classification","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":false,"ca_institutions":"University of Toronto","funders":"","keywords":"MNIST database; Boundary (topology); Differentiable function; Similarity (geometry); Tree (set theory); Computer science; Artificial intelligence; Pattern recognition (psychology); Mathematics; Deep learning; Combinatorics; Image (mathematics)","score_opus":0.023790470625414624,"score_gpt":0.30857976347864446,"score_spread":0.28478929285322985,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2898490583","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":[0.03307001,0.00023293374,0.9614472,0.0009906561,0.00029478365,0.00045730118,0.000019127938,0.00012303582,0.003364975],"genre_scores_gemma":[0.93874985,0.000021568494,0.05904992,0.000025560974,0.000043182703,0.000055016117,0.00015406338,0.0000108531885,0.0018900079],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987367,0.00008155866,0.00028611612,0.00056171784,0.00018810996,0.00014580632],"domain_scores_gemma":[0.9983986,0.00037825783,0.00029641873,0.00075712136,0.00012136447,0.000048242484],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038771782,0.00013761646,0.00022232637,0.00015052696,0.00011710647,0.00020372416,0.0005004703,0.00010844093,0.000008148743],"category_scores_gemma":[0.0003016081,0.00012224505,0.0000780808,0.00009860514,0.000051607345,0.00006222383,0.00080868625,0.00028060406,0.000006286273],"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":[0.00003593589,0.00016756082,0.0637543,0.00077999744,0.00009155275,9.58774e-7,0.0021541065,0.44855592,0.0006146702,0.37786296,0.002450775,0.10353127],"study_design_scores_gemma":[0.00021598981,0.00005886074,0.085048504,0.000047957245,0.000012992797,0.0000016767516,0.00004073037,0.9089725,0.0000982284,0.0020225907,0.003352518,0.00012741989],"about_ca_topic_score_codex":0.00014777413,"about_ca_topic_score_gemma":0.000029318944,"teacher_disagreement_score":0.9056798,"about_ca_system_score_codex":0.000017402623,"about_ca_system_score_gemma":0.00013777091,"threshold_uncertainty_score":0.49850085},"labels":[],"label_agreement":null},{"id":"W2912810480","doi":"10.1145/3178372","title":"Proceedings of the 27th International Conference on Compiler Construction","year":2018,"lang":"en","type":"paratext","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Télécom Paris; Université de Nantes; Peking University; Universidade Federal de Minas Gerais; Universität des Saarlandes; Vrije Universiteit Brussel; Uppsala Universitet; Centre National de la Recherche Scientifique; Purdue University; North Carolina State University; Chinese Academy of Sciences; University of Glasgow; Université de Strasbourg; University of New South Wales; University of Alberta; Colorado State University; University of Pittsburgh; Ohio State University; Carnegie Mellon University","keywords":"Compiler; Computer science; Programming language; Code (set theory); Software engineering; Artificial intelligence","score_opus":0.032855669916155156,"score_gpt":0.28872561650885237,"score_spread":0.25586994659269724,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2912810480","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":[0.00044994496,0.0000055813607,0.023145238,0.0031087815,0.004441267,0.00014669553,0.000036943205,0.000045891673,0.96861964],"genre_scores_gemma":[0.33492902,0.00021714457,0.040548626,0.0011601328,0.0015371416,0.000045421162,0.00034019744,0.0000349036,0.6211874],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99889576,0.000021053458,0.00023519083,0.00036502848,0.00038096195,0.0001020231],"domain_scores_gemma":[0.99878514,0.000024207186,0.00041125558,0.00033749553,0.00041382748,0.000028089093],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0001512745,0.0001401492,0.0001476894,0.000097589305,0.0000823061,0.0001786041,0.0016317613,0.0001263246,0.0017608111],"category_scores_gemma":[0.000037628182,0.00008984131,0.000055771885,0.00017349675,0.0001652335,0.00017997423,0.00030307515,0.00029741495,0.0014706453],"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":[0.0000052537116,0.000024087667,0.00014453345,0.000019942543,0.00001652715,2.2199169e-8,0.000071411836,0.0000030488975,0.00034248637,0.48380175,0.50959337,0.005977544],"study_design_scores_gemma":[0.000311888,0.00013738118,0.003913823,0.00032983714,0.000011172627,0.000021515372,0.00007953097,0.04168619,0.0031115697,0.0020840804,0.94799095,0.0003220836],"about_ca_topic_score_codex":0.000027848773,"about_ca_topic_score_gemma":0.000002141125,"teacher_disagreement_score":0.48171768,"about_ca_system_score_codex":0.000036027846,"about_ca_system_score_gemma":0.000096528835,"threshold_uncertainty_score":0.9993068},"labels":[],"label_agreement":null},{"id":"W2913668833","doi":"","title":"Proceedings of the 25th international conference on Machine learning","year":2008,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":5550,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Presentation (obstetrics); Library science; Computer science; Medical education; Artificial intelligence; Medicine","score_opus":0.040987082393800944,"score_gpt":0.2591540437091648,"score_spread":0.21816696131536384,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2913668833","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":[0.22633003,0.000015144561,0.051128063,0.012292791,0.00047542498,0.00016623395,0.000003468231,0.0003199859,0.70926887],"genre_scores_gemma":[0.9893543,0.00001931917,0.0044488665,0.00015270128,0.000020838675,0.0000023529606,0.0000026816203,0.0000023412906,0.0059966086],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994281,0.000012137105,0.000104115126,0.00015537711,0.00023308334,0.000067185254],"domain_scores_gemma":[0.999646,0.000013071547,0.000096027004,0.00012976733,0.00009512779,0.000020022559],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012281208,0.00005142665,0.000051337847,0.000039720577,0.00010586725,0.000032622516,0.0007436085,0.000018702072,0.000064105596],"category_scores_gemma":[0.000092803806,0.00003182023,0.000025096033,0.00014215194,0.00003773272,0.00017117625,0.00015259409,0.00016429738,0.000026958305],"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":[0.0000039127112,0.00003506115,0.04961115,0.000003005371,0.0000045968723,2.674352e-7,0.00035920562,0.000043789652,0.002855791,0.9420904,0.0009901052,0.004002699],"study_design_scores_gemma":[0.00021468206,0.00007085153,0.12529348,0.000019837438,0.000001383044,0.000025973979,0.00003614451,0.8545552,0.00349582,0.0006476269,0.015547141,0.00009187099],"about_ca_topic_score_codex":0.000039961495,"about_ca_topic_score_gemma":0.000002034837,"teacher_disagreement_score":0.9414428,"about_ca_system_score_codex":0.000010414266,"about_ca_system_score_gemma":0.000021404534,"threshold_uncertainty_score":0.13818221},"labels":[],"label_agreement":null},{"id":"W2914110112","doi":"10.1016/j.patrec.2019.02.009","title":"A new hyperparameters optimization method for convolutional neural networks","year":2019,"lang":"en","type":"article","venue":"Pattern Recognition Letters","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":105,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Key Research and Development Program of China; Canadian Institute for Advanced Research","keywords":"Hyperparameter; Hyperparameter optimization; Bayesian optimization; Computer science; Convolutional neural network; Gaussian process; Artificial intelligence; Artificial neural network; Machine learning; Gaussian; Algorithm; Support vector machine","score_opus":0.02314881426054435,"score_gpt":0.26545929147094044,"score_spread":0.24231047721039609,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2914110112","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":[0.00484016,0.000015537138,0.9843998,0.009269175,0.0007878713,0.00040785232,0.000017686396,0.00018231606,0.00007958968],"genre_scores_gemma":[0.13140504,0.0000053445924,0.85296035,0.014074838,0.0003204732,0.0000803373,0.001030579,0.000024166022,0.000098868004],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987263,0.00014320551,0.00023426594,0.0004643026,0.00017927088,0.00025265568],"domain_scores_gemma":[0.9990589,0.00030004207,0.00016314028,0.00031850164,0.00006589138,0.00009351464],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029574058,0.00014379852,0.00014266152,0.00012238137,0.00008693075,0.00018227124,0.00034147082,0.00006284745,0.0001405351],"category_scores_gemma":[0.000045882258,0.00014802323,0.000092380906,0.0001868529,0.000010889632,0.0005321102,0.000053625157,0.00015156502,0.00012480927],"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":[0.000022038592,0.00002174772,0.003613602,0.00002193021,0.000027200802,9.080538e-7,0.00010553789,0.31454575,0.0006089715,0.00012404687,0.005816845,0.6750914],"study_design_scores_gemma":[0.00071954104,0.000050931198,0.0018886366,0.00001535873,0.0000124366525,0.00001540355,0.000007625936,0.9956718,0.00004826938,0.00009463955,0.0012746592,0.00020066254],"about_ca_topic_score_codex":0.000056331035,"about_ca_topic_score_gemma":0.0000021659541,"teacher_disagreement_score":0.68112606,"about_ca_system_score_codex":0.00004217242,"about_ca_system_score_gemma":0.000021196196,"threshold_uncertainty_score":0.60362124},"labels":[],"label_agreement":null},{"id":"W2916199673","doi":"10.1177/0962280219829885","title":"Prediction intervals with random forests","year":2019,"lang":"en","type":"article","venue":"Statistical Methods in Medical Research","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":53,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"HEC Montréal","funders":"","keywords":"Random forest; Computer science; Covariate; Prediction interval; Calibration; Tree (set theory); Data mining; Regression; Interval (graph theory); Parametric statistics; Cart; Statistics; Machine learning; Mathematics","score_opus":0.11733146660538908,"score_gpt":0.5295953286551724,"score_spread":0.4122638620497834,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2916199673","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":[0.001231846,0.000046302383,0.98581463,0.0023269777,0.00024311041,0.0003206654,0.000008275831,0.00006817348,0.009940035],"genre_scores_gemma":[0.15616171,0.0000335232,0.8430324,0.00012817269,0.000089064306,0.00008072532,0.000025280142,0.000011844397,0.00043723756],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9920716,0.004554745,0.00035988208,0.00057681487,0.0019242212,0.0005127052],"domain_scores_gemma":[0.9864148,0.012258116,0.000039114322,0.00066225027,0.0002665578,0.00035915413],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.018758154,0.00010112385,0.0002478553,0.00027722036,0.00007220577,0.0001182646,0.0009863201,0.00013110305,0.001038131],"category_scores_gemma":[0.035101596,0.00006973299,0.000019987503,0.0008507797,0.00027034958,0.0001991362,0.0003670312,0.0013564732,0.00022892043],"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":[0.00012921236,0.00007905403,0.015597556,0.000055187775,0.0000069803573,0.00003724471,0.00011204915,0.000012673885,0.000056381698,0.1994792,0.0014164041,0.78301805],"study_design_scores_gemma":[0.0023340744,0.000737239,0.19260347,0.00023949429,0.0000026395144,0.000019077066,0.00006376723,0.7150648,0.000102071994,0.062127825,0.026554542,0.00015097606],"about_ca_topic_score_codex":0.00010622664,"about_ca_topic_score_gemma":0.00005631314,"teacher_disagreement_score":0.7828671,"about_ca_system_score_codex":0.00007493543,"about_ca_system_score_gemma":0.00029339903,"threshold_uncertainty_score":0.99987507},"labels":[],"label_agreement":null},{"id":"W2920848790","doi":"10.1007/978-3-030-29135-8_8","title":"AutoML @ NeurIPS 2018 Challenge: Design and Results","year":2019,"lang":"en","type":"book-chapter","venue":"˜The œSpringer series on challenges in machine learning","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Acadia University","funders":"Microsoft Research","keywords":"Lifelong learning; Competition (biology); Computer science; Duration (music); Artificial intelligence; Autonomous learning; Data science; Machine learning; Mathematics education; Psychology; Pedagogy","score_opus":0.057603605698104465,"score_gpt":0.26014440435925273,"score_spread":0.20254079866114827,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2920848790","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":[0.00007240787,0.04359129,0.02354107,0.05835682,0.0026490407,0.0021905657,0.000041515832,0.0019099789,0.8676473],"genre_scores_gemma":[0.13716497,0.17105299,0.021302804,0.00091628695,0.0013808409,0.00017183776,0.00024208525,0.00067524624,0.6670929],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9952746,0.0006262711,0.00090105255,0.0018188304,0.0007406593,0.00063860853],"domain_scores_gemma":[0.99556935,0.0011231367,0.0008220712,0.0022506423,0.000085393694,0.00014937969],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0028520261,0.00085868157,0.00076614873,0.0004995837,0.0004254907,0.00033020854,0.0018665405,0.00055857754,0.000029151435],"category_scores_gemma":[0.0002202616,0.00070880906,0.00013907612,0.00010698834,0.00020743885,0.00048600984,0.0011440965,0.0035195036,0.00037967687],"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":[0.00036199132,0.00007591734,0.0000422193,0.00030970716,0.00011203991,0.0001037804,0.0038279446,0.0066532823,0.0000119644465,0.5242,0.00041601792,0.4638851],"study_design_scores_gemma":[0.001015933,0.0011761326,0.0012391023,0.0005758003,0.000032432843,0.00007710435,0.00008344626,0.09593384,0.0000047629087,0.00878297,0.88998157,0.0010969094],"about_ca_topic_score_codex":0.00003997791,"about_ca_topic_score_gemma":0.00024924494,"teacher_disagreement_score":0.8895655,"about_ca_system_score_codex":0.00011974791,"about_ca_system_score_gemma":0.00011683621,"threshold_uncertainty_score":0.9995363},"labels":[],"label_agreement":null},{"id":"W2922315434","doi":"10.1016/j.heliyon.2019.e01708","title":"Feature identification in time series data sets","year":2019,"lang":"en","type":"article","venue":"Heliyon","topic":"Machine Learning and Data Classification","field":"Computer Science","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":"McMaster University; University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Identification (biology); Computer science; Feature (linguistics); Time series; Pattern recognition (psychology); Series (stratigraphy); Data mining; Artificial intelligence; Machine learning; Biology","score_opus":0.017880587791459474,"score_gpt":0.276202086460948,"score_spread":0.25832149866948856,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2922315434","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":[0.7147822,0.0051126056,0.14030711,0.10673434,0.0034099796,0.0019545916,0.00028513715,0.0020373636,0.0253767],"genre_scores_gemma":[0.9061092,0.00062570325,0.033333145,0.00082621287,0.00016843877,0.00002507381,0.0033710478,0.000034046145,0.055507142],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9991401,0.00007115881,0.000101529724,0.00038695894,0.00018453498,0.000115747556],"domain_scores_gemma":[0.9983196,0.000028012018,0.00006556608,0.0015393413,0.000021566433,0.000025872247],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00041080907,0.0000644004,0.00007384038,0.000077063436,0.000032072378,0.00018636411,0.0012477622,0.000051722833,0.000035051005],"category_scores_gemma":[0.00006345012,0.000060676917,0.000009204608,0.00026422963,0.000008499539,0.0011301291,0.00034767552,0.0001370129,0.0027352276],"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":[0.000094197465,0.00044784718,0.35644993,0.0010593163,0.000036662947,0.000033191896,0.0026022368,0.00046208364,0.14140303,0.07540077,0.076628,0.34538272],"study_design_scores_gemma":[0.00035435363,0.000043499025,0.62867117,0.00014618234,0.000003467192,0.000020925483,0.000023460629,0.08161787,0.0012633728,0.00039494742,0.28719324,0.00026751787],"about_ca_topic_score_codex":0.0000073949714,"about_ca_topic_score_gemma":0.000014541689,"teacher_disagreement_score":0.3451152,"about_ca_system_score_codex":0.000017734536,"about_ca_system_score_gemma":0.000024639938,"threshold_uncertainty_score":0.9980413},"labels":[],"label_agreement":null},{"id":"W2936965162","doi":"10.5430/air.v8n1p51","title":"Adaptations of Relief for continuous domains of bioinformatics","year":2019,"lang":"en","type":"article","venue":"Artificial Intelligence Research","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Categorical variable; Feature (linguistics); Feature selection; Set (abstract data type); Margin (machine learning); Metric space; Euclidean geometry; Feature vector; Computer science; Euclidean distance; Metric (unit); Pattern recognition (psychology); Artificial intelligence; Mathematics; Machine learning; Discrete mathematics; Engineering; Geometry","score_opus":0.13959635976547657,"score_gpt":0.4132818983240236,"score_spread":0.27368553855854705,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2936965162","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":[0.040366624,0.000050452923,0.9543994,0.00079015654,0.00012276243,0.00047253811,0.000016846521,0.00002870353,0.0037525357],"genre_scores_gemma":[0.92829406,0.000046488647,0.07135972,0.000009730573,0.0000200493,0.000020411779,0.0000143658835,0.0000049703776,0.00023018404],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998511,0.00010665603,0.00048852095,0.00018522904,0.00045823987,0.00025031515],"domain_scores_gemma":[0.99743295,0.0010347015,0.00015424701,0.00062441063,0.0007021611,0.000051511364],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020094889,0.000059999024,0.0001540562,0.00027325042,0.000089311274,0.000052587628,0.0007719121,0.000052093248,0.000028694301],"category_scores_gemma":[0.0009084272,0.00005447156,0.000056704463,0.0007293422,0.00013956107,0.0002702872,0.0001381415,0.00016386593,0.00015716143],"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":[0.000019638142,0.00008454008,0.00026950045,0.00005659198,0.000006961915,1.223349e-7,0.0012379269,0.00050595345,0.009357954,0.7427903,0.00014612211,0.2455244],"study_design_scores_gemma":[0.0000513885,0.0006647504,0.00060831103,0.00006018065,0.0000033063648,0.000001370754,0.0021936202,0.82978207,0.09208356,0.069080144,0.0053587556,0.00011252686],"about_ca_topic_score_codex":0.0001453095,"about_ca_topic_score_gemma":0.00002621105,"teacher_disagreement_score":0.8879275,"about_ca_system_score_codex":0.000019516365,"about_ca_system_score_gemma":0.00015107504,"threshold_uncertainty_score":0.22212857},"labels":[],"label_agreement":null},{"id":"W2938667921","doi":"10.1016/j.fss.2019.04.018","title":"Granular counting of uncertain data","year":2019,"lang":"en","type":"article","venue":"Fuzzy Sets and Systems","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Government of Canada","keywords":"Mathematics; Granular computing; Algorithm; Quadratic equation; Domain (mathematical analysis); Time complexity; Counting problem; Computer science; Data mining; Rough set","score_opus":0.04214106870362486,"score_gpt":0.2840175366040163,"score_spread":0.24187646790039144,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2938667921","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":[0.8026939,0.0062297564,0.14095443,0.001971224,0.0035053522,0.0011145015,0.00029720095,0.00037114316,0.04286248],"genre_scores_gemma":[0.998463,0.000017736958,0.0010809725,0.000022708926,0.00003053325,0.0000014417761,0.00009912833,0.0000032056498,0.0002813017],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99924165,0.000070220216,0.00016632157,0.0002592837,0.000167484,0.00009502976],"domain_scores_gemma":[0.99883586,0.000060683247,0.000114193135,0.00092524604,0.000034405217,0.000029639985],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006930502,0.000054870656,0.00012365355,0.00003674425,0.000040539195,0.00011100543,0.00056980585,0.00002906122,0.000002348137],"category_scores_gemma":[0.000035088484,0.000043324326,0.000008710406,0.00010084369,0.0000118718835,0.00029436126,0.00020446039,0.00005672418,0.000030631036],"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":[0.000013023606,0.00008569714,0.48928908,0.0014087824,0.000042696873,0.000009843217,0.0018103578,0.0008764803,0.0051005436,0.39101106,0.013355965,0.09699648],"study_design_scores_gemma":[0.0002432318,0.000041863048,0.027776081,0.000094417956,0.0000047049484,0.00001762799,0.00014145063,0.8743328,0.000010460111,0.0002065064,0.09700787,0.0001229899],"about_ca_topic_score_codex":0.0005440201,"about_ca_topic_score_gemma":0.000004437872,"teacher_disagreement_score":0.8734563,"about_ca_system_score_codex":0.0000044500734,"about_ca_system_score_gemma":0.000020002242,"threshold_uncertainty_score":0.17667148},"labels":[],"label_agreement":null},{"id":"W2943204979","doi":"10.1109/dsw.2019.8755559","title":"Introducing Graph Smoothness Loss for Training Deep Learning Architectures","year":2019,"lang":"en","type":"preprint","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"HEC Montréal; Université de Montréal","funders":"","keywords":"Computer science; Robustness (evolution); Smoothness; Artificial intelligence; Cross entropy; Graph; Entropy (arrow of time); Deep learning; Machine learning; Algorithm; Pattern recognition (psychology); Theoretical computer science; Mathematics","score_opus":0.026066491949612258,"score_gpt":0.28283615435022125,"score_spread":0.256769662400609,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2943204979","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":[0.00866518,0.00022286265,0.9835261,0.0021505163,0.0013207147,0.00052227644,0.000006463728,0.00069570326,0.002890175],"genre_scores_gemma":[0.7734045,0.000021905329,0.22434944,0.00021903082,0.0004958193,0.0001190428,0.00024392946,0.00004038115,0.001105952],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971731,0.00022486324,0.0004152175,0.0013732173,0.00032757185,0.00048607076],"domain_scores_gemma":[0.9974349,0.0005157402,0.0003804813,0.0014375321,0.00012949876,0.00010186009],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010884346,0.00036448555,0.00044951137,0.00037247426,0.00026395937,0.0005919829,0.0018216262,0.00026164122,0.000022355742],"category_scores_gemma":[0.0005868458,0.0003283218,0.00022306111,0.00022585769,0.000049023114,0.000120499586,0.0011533281,0.0013602175,0.000032559994],"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":[0.00001621223,0.000026776139,0.0020046525,0.00037671655,0.000062894906,0.0000021004992,0.004683207,0.44023553,0.00015965558,0.031353813,0.00023031057,0.52084816],"study_design_scores_gemma":[0.00038169944,0.000084136445,0.004723971,0.00013738655,0.000025653853,0.00001276439,0.00018002428,0.9582947,0.00014846562,0.018028766,0.017327823,0.00065464014],"about_ca_topic_score_codex":0.00010965964,"about_ca_topic_score_gemma":0.000031710584,"teacher_disagreement_score":0.76473933,"about_ca_system_score_codex":0.000045986024,"about_ca_system_score_gemma":0.00014395217,"threshold_uncertainty_score":0.9999169},"labels":[],"label_agreement":null},{"id":"W2945163429","doi":"10.7717/peerj-cs.194","title":"The k conditional nearest neighbor algorithm for classification and class probability estimation","year":2019,"lang":"en","type":"article","venue":"PeerJ Computer Science","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":40,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; Western University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"k-nearest neighbors algorithm; Nonparametric statistics; Pattern recognition (psychology); Posterior probability; Computer science; Naive Bayes classifier; Benchmark (surveying); Algorithm; Artificial intelligence; Classifier (UML); Mathematics; Bayesian probability; Statistics; Support vector machine","score_opus":0.01833268062500404,"score_gpt":0.2739356002516186,"score_spread":0.2556029196266146,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2945163429","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":[0.007737174,0.000027422117,0.98436475,0.00640761,0.00059136626,0.000539531,0.000010781558,0.00013495763,0.00018638613],"genre_scores_gemma":[0.5014479,0.00000448724,0.49803433,0.00020602813,0.00008697593,0.00006405531,0.000041047388,0.000004761543,0.00011042169],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982074,0.00006765746,0.00023574906,0.0007005546,0.0004981109,0.00029053877],"domain_scores_gemma":[0.9981267,0.0004903812,0.0001608269,0.0007790727,0.0003402563,0.00010275058],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0017099782,0.00011868741,0.00010478961,0.00008167111,0.0008171412,0.0010523394,0.001125265,0.000038654765,0.000002249382],"category_scores_gemma":[0.00014864508,0.000087187334,0.000032040796,0.00047968113,0.00036861893,0.0011889623,0.00028242276,0.00012532565,0.000044572902],"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":[0.0000024342298,0.00002585024,0.0014302079,0.000011118002,0.0000024236483,9.617201e-8,0.0001057623,0.0006635652,0.00036476416,0.27355278,0.00036544076,0.7234756],"study_design_scores_gemma":[0.000185441,0.000078419114,0.14420858,0.000005894579,0.0000018721169,0.000008785947,0.0000046857963,0.8333433,0.00005909189,0.015053714,0.006949361,0.00010084346],"about_ca_topic_score_codex":0.0000097574175,"about_ca_topic_score_gemma":0.0000028949555,"teacher_disagreement_score":0.83267975,"about_ca_system_score_codex":0.00007407946,"about_ca_system_score_gemma":0.00021428411,"threshold_uncertainty_score":0.9999847},"labels":[],"label_agreement":null},{"id":"W2945829261","doi":"10.3390/electronics8050579","title":"The Tabu_Genetic Algorithm: A Novel Method for Hyper-Parameter Optimization of Learning Algorithms","year":2019,"lang":"en","type":"article","venue":"Electronics","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":45,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"National Key Research and Development Program of China; Jiangsu Key Laboratory of Precision and Micro-Manufacturing Technology; Natural Science Foundation of Hebei Province; National Natural Science Foundation of China","keywords":"Tabu search; Algorithm; Computer science; Artificial intelligence; Machine learning; Genetic algorithm; Bayesian optimization; Population-based incremental learning; Artificial neural network; Hill climbing; Meta-optimization; Bayesian network","score_opus":0.01279240580306074,"score_gpt":0.2779970604962316,"score_spread":0.26520465469317084,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2945829261","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":[0.00027306567,0.0012044125,0.99727297,0.0005741919,0.00016089225,0.00028312698,0.000002431183,0.00006344996,0.00016545047],"genre_scores_gemma":[0.0035707215,0.00026479538,0.994863,0.00005296392,0.000040517316,0.000038184673,0.000034117307,0.00001537505,0.0011203323],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99889207,0.00010068737,0.00021570115,0.00030315205,0.00019340678,0.00029497885],"domain_scores_gemma":[0.9985961,0.0005821878,0.00018781518,0.0004757217,0.00012724761,0.00003093216],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008469884,0.000102511236,0.00013234503,0.00005170596,0.00016225305,0.00010065761,0.0005780861,0.00005733871,0.000004547811],"category_scores_gemma":[0.00019406603,0.00007873295,0.000063257234,0.00027495058,0.00001581168,0.00013814084,0.00008065023,0.0002149376,0.000009700923],"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":[0.000007703203,0.000031502135,0.0000652245,0.0000108040285,0.000021457137,2.8242573e-8,0.00012812947,0.13620956,0.003788031,0.0138163585,0.00006416623,0.845857],"study_design_scores_gemma":[0.00030153192,0.000249786,0.000066933644,0.0000043622663,0.000008446146,0.000006019413,0.000015715032,0.9075333,0.001682184,0.0004420748,0.089598164,0.0000915153],"about_ca_topic_score_codex":0.000005821962,"about_ca_topic_score_gemma":0.0000022056777,"teacher_disagreement_score":0.84576553,"about_ca_system_score_codex":0.000040243303,"about_ca_system_score_gemma":0.000116039635,"threshold_uncertainty_score":0.32106364},"labels":[],"label_agreement":null},{"id":"W2946149145","doi":"10.1007/978-3-030-18305-9_13","title":"Instance Ranking and Numerosity Reduction Using Matrix Decomposition and Subspace Learning","year":2019,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Numerosity adaptation effect; Computer science; Dimensionality reduction; Ranking (information retrieval); Reduction (mathematics); Subspace topology; Matrix decomposition; Similarity (geometry); Artificial intelligence; Rank (graph theory); Measure (data warehouse); Matrix (chemical analysis); Pattern recognition (psychology); Cluster analysis; Data mining; Decomposition; Similarity measure; Machine learning; Mathematics; Eigenvalues and eigenvectors","score_opus":0.014870139166824392,"score_gpt":0.27747405352300447,"score_spread":0.2626039143561801,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2946149145","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":[0.013220635,0.00092904776,0.9840684,0.0004265097,0.0006629475,0.00023846427,0.0000011902126,0.00012708985,0.00032569363],"genre_scores_gemma":[0.65648973,0.00018659615,0.3428431,0.00009038701,0.000175074,0.0000013643165,0.000008713578,0.000021531769,0.00018348215],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975444,0.000076672804,0.00030104557,0.0012567001,0.00048048695,0.00034067064],"domain_scores_gemma":[0.9986466,0.00019179565,0.00034227502,0.00060581794,0.00011648671,0.00009699703],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008887185,0.0003278247,0.0003370561,0.0004987664,0.00047735288,0.00071674364,0.000662076,0.00021839429,0.0000029000341],"category_scores_gemma":[0.000058390873,0.0003328733,0.0000368308,0.00034010987,0.00031678003,0.0009773552,0.0006619473,0.0008665863,0.000005899215],"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":[0.000020928619,0.000018370863,0.0029787107,0.00015987994,0.000012316347,0.000014931643,0.0017747036,0.09942708,0.008886719,0.026527891,0.0000030582821,0.86017543],"study_design_scores_gemma":[0.00026333856,0.00009166107,0.0020829316,0.000459473,0.000011136027,0.00024931005,8.136393e-7,0.98555523,0.00046356927,0.00993568,0.0004255881,0.00046127252],"about_ca_topic_score_codex":0.000053301617,"about_ca_topic_score_gemma":0.000015982958,"teacher_disagreement_score":0.8861281,"about_ca_system_score_codex":0.00018788087,"about_ca_system_score_gemma":0.00018232675,"threshold_uncertainty_score":0.9999123},"labels":[],"label_agreement":null},{"id":"W2946309990","doi":"10.1007/978-3-030-18305-9_62","title":"Principal Sample Analysis for Data Ranking","year":2019,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Numerosity adaptation effect; Computer science; Reduction (mathematics); Ranking (information retrieval); Data reduction; Cluster analysis; Sample (material); Artificial intelligence; Data mining; Principal component analysis; Sample space; Selection (genetic algorithm); Principal (computer security); Field (mathematics); Pattern recognition (psychology); Machine learning; Mathematics","score_opus":0.053914105437575785,"score_gpt":0.3056288085389437,"score_spread":0.2517147031013679,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2946309990","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":[0.000013493653,0.00019191683,0.99638355,0.0007398718,0.000931591,0.00043011515,0.00009594641,0.00014236917,0.0010711577],"genre_scores_gemma":[0.046849728,0.000029960951,0.9506919,0.00076493295,0.00039328152,0.000007958635,0.0006691398,0.000027907148,0.00056520326],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99593216,0.00003766958,0.00047828734,0.0022363444,0.0007971495,0.0005183741],"domain_scores_gemma":[0.993223,0.0014766793,0.0003867704,0.0046158414,0.00018990882,0.000107774256],"candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0019263974,0.0003755969,0.0005574711,0.0011179275,0.0002568171,0.00075681123,0.0076203668,0.00022255848,0.000020431944],"category_scores_gemma":[0.00049511966,0.00034148264,0.00014992755,0.0010156679,0.00021596348,0.0008001168,0.0028122424,0.0005501896,0.00003427086],"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":[0.0000078353605,0.00002167708,0.0016703716,0.000072775256,0.0000916521,0.0000047248695,0.00027216983,0.068983145,0.000029044857,0.062481232,0.000040187602,0.8663252],"study_design_scores_gemma":[0.00018652357,0.000057321104,0.00077107374,0.000071498565,0.000058688136,0.0000047702833,4.4375525e-8,0.95276225,0.00002473606,0.024661701,0.021000126,0.00040126994],"about_ca_topic_score_codex":0.000090102454,"about_ca_topic_score_gemma":0.0002542161,"teacher_disagreement_score":0.8837791,"about_ca_system_score_codex":0.00014370438,"about_ca_system_score_gemma":0.00057954236,"threshold_uncertainty_score":0.99990374},"labels":[],"label_agreement":null},{"id":"W2949221912","doi":"10.48550/arxiv.1807.05887","title":"Toward Interpretable Deep Reinforcement Learning with Linear Model U-Trees","year":2018,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Reinforcement learning; Computer science; Artificial intelligence; Artificial neural network; Tree (set theory); Function (biology); Machine learning; Feature (linguistics); Decision tree; Deep neural networks; Mathematics","score_opus":0.06759661223877765,"score_gpt":0.2031394876909434,"score_spread":0.13554287545216576,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2949221912","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":[0.019437477,0.000023113449,0.96955484,0.00012765366,0.00015225445,0.0001815989,0.0000018245519,0.00041503675,0.0101062255],"genre_scores_gemma":[0.9790334,0.00009473719,0.015112803,0.00007876013,0.000070435686,0.0000017753728,0.0000841057,0.00002138575,0.005502587],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99805534,0.00012696012,0.00020171712,0.0011146737,0.00014703574,0.0003542869],"domain_scores_gemma":[0.9979283,0.00005114279,0.00033729748,0.0013174751,0.0002086128,0.00015713877],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00029490783,0.0003200244,0.00029321926,0.00023114315,0.00022093681,0.00018582561,0.0017916475,0.00020324725,0.000039403552],"category_scores_gemma":[0.00005413482,0.00031356036,0.00010424026,0.0003581513,0.00011073643,0.00051821134,0.0020188782,0.0008494989,0.00016873714],"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":[0.00004201947,0.000026760794,0.001482298,0.00004582943,0.00005486298,0.000028175422,0.00056046195,0.964176,0.00001113769,0.032871936,0.000110398025,0.0005901039],"study_design_scores_gemma":[0.00028632334,0.00014417696,0.0001981311,0.00011421359,0.00004710855,0.000003744662,0.00006173047,0.9949574,0.000043407737,0.0027213267,0.0010387476,0.00038371218],"about_ca_topic_score_codex":0.0001771218,"about_ca_topic_score_gemma":0.000048134865,"teacher_disagreement_score":0.9595959,"about_ca_system_score_codex":0.00016784278,"about_ca_system_score_gemma":0.00020501149,"threshold_uncertainty_score":0.99993163},"labels":[],"label_agreement":null},{"id":"W2949244450","doi":"10.48550/arxiv.1506.02465","title":"ASlib: A Benchmark Library for Algorithm Selection","year":2015,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Selection (genetic algorithm); Benchmark (surveying); Set (abstract data type); Task (project management); Exploit; Variety (cybernetics); Data mining; Range (aeronautics); Algorithm; Selection algorithm; Interface (matter); Machine learning; Artificial intelligence; Engineering","score_opus":0.06976755450058429,"score_gpt":0.20087813200016802,"score_spread":0.1311105774995837,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2949244450","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":[0.0033376967,0.000054251977,0.9906346,0.00037272717,0.0005768063,0.0003328251,0.000070323695,0.0007174524,0.0039033133],"genre_scores_gemma":[0.8297695,0.00015441614,0.15404406,0.00025311977,0.00053358544,0.000009999713,0.0012494904,0.000058972582,0.013926851],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983711,0.00014313619,0.0001550567,0.0009923589,0.000078983736,0.00025934068],"domain_scores_gemma":[0.9985182,0.00009713914,0.00024056407,0.00083381066,0.00013992796,0.00017031033],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00028934365,0.00022613282,0.0002170898,0.00024384909,0.00015503052,0.00023695582,0.0013869283,0.00026403661,0.000022319073],"category_scores_gemma":[0.000054591375,0.00026130528,0.00013302133,0.00052183634,0.000036456317,0.00083061995,0.0010774571,0.0004625609,0.000059514914],"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":[0.0001090587,0.00038263932,0.0064666015,0.00030732027,0.00023727545,0.00007307393,0.0005426131,0.10809078,0.00003539366,0.6355134,0.12090475,0.12733707],"study_design_scores_gemma":[0.00031060647,0.000068119276,0.0007015497,0.00002812306,0.00003081326,0.0000033994113,0.000015244981,0.89700973,0.000031958647,0.055913642,0.045603886,0.00028290518],"about_ca_topic_score_codex":0.00005510968,"about_ca_topic_score_gemma":0.000006105357,"teacher_disagreement_score":0.8365905,"about_ca_system_score_codex":0.000111196765,"about_ca_system_score_gemma":0.00037738035,"threshold_uncertainty_score":0.9999839},"labels":[],"label_agreement":null},{"id":"W2949431720","doi":"10.48550/arxiv.1208.3719","title":"Auto-WEKA: Combined Selection and Hyperparameter Optimization of Classification Algorithms","year":2012,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":94,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Hyperparameter; Machine learning; Computer science; Hyperparameter optimization; MNIST database; Artificial intelligence; Bayesian optimization; Feature selection; Classifier (UML); Selection (genetic algorithm); Data mining; Artificial neural network; Support vector machine","score_opus":0.07618852931793457,"score_gpt":0.20567779428024544,"score_spread":0.12948926496231086,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2949431720","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":[0.045791358,0.000047256508,0.95241535,0.00013804463,0.00029007977,0.00022159929,0.000009890858,0.0001976543,0.00088875],"genre_scores_gemma":[0.96476984,0.0001480142,0.03439193,0.000019852976,0.00004444644,0.0000017606166,0.00015944413,0.0000128355505,0.0004518699],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99856555,0.00021535055,0.00023071431,0.00070049055,0.00009430156,0.000193618],"domain_scores_gemma":[0.998453,0.00009128548,0.00045509686,0.0007024121,0.00019323068,0.00010492531],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033965491,0.00020549657,0.00024484989,0.00026472204,0.00010294795,0.000086602646,0.0005728629,0.00027128612,0.000015655756],"category_scores_gemma":[0.00005950807,0.0002340328,0.000069238966,0.0004751303,0.00007090547,0.00054272084,0.00051014364,0.00038413037,0.000013233491],"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":[0.00006478423,0.0003454348,0.02471143,0.00022646885,0.0001249533,0.0000038884614,0.0004745448,0.7407151,0.00060835684,0.20902127,0.00015815995,0.023545587],"study_design_scores_gemma":[0.00030409495,0.000047710317,0.020146599,0.000030480527,0.000061316015,0.0000031905104,0.000019733767,0.9774168,0.00008316398,0.0013957233,0.00027138053,0.00021980656],"about_ca_topic_score_codex":0.0000885252,"about_ca_topic_score_gemma":0.0000058302944,"teacher_disagreement_score":0.9189785,"about_ca_system_score_codex":0.00010300234,"about_ca_system_score_gemma":0.0000841686,"threshold_uncertainty_score":0.95435804},"labels":[],"label_agreement":null},{"id":"W2949622489","doi":"10.48550/arxiv.1906.07658","title":"Consistency of semi-supervised learning algorithms on graphs: Probit and one-hot methods","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Air Force Office of Scientific Research; Natural Sciences and Engineering Research Council of Canada; California Institute of Technology; National Science Foundation","keywords":"Graph; Laplacian matrix; Mathematics; Consistency (knowledge bases); Generalization; Semi-supervised learning; Function (biology); Computer science; Algorithm; Artificial intelligence; Mathematical optimization; Combinatorics","score_opus":0.10054188920245208,"score_gpt":0.24543326471929605,"score_spread":0.14489137551684397,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2949622489","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":[0.08134356,0.00013894706,0.9116825,0.00016252515,0.00031207403,0.0003780529,0.000012928399,0.00022513008,0.005744301],"genre_scores_gemma":[0.94593567,0.00027831597,0.052278534,0.00005193125,0.00002046092,0.0000012883359,0.00005025849,0.000017696584,0.001365854],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975107,0.00068730075,0.0002602189,0.0011558315,0.00011776339,0.00026821563],"domain_scores_gemma":[0.9976782,0.00036754395,0.00042728632,0.0012432295,0.00016566653,0.00011803971],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008725219,0.00027898003,0.000444816,0.0003795163,0.00015477325,0.00009253828,0.0010601637,0.00026982356,0.00001723468],"category_scores_gemma":[0.00015615944,0.00030977503,0.00014421983,0.00047809447,0.00013393124,0.00023823617,0.0012793494,0.00094300736,0.000027403463],"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":[0.000115717274,0.000377188,0.024187291,0.0009259836,0.00033201647,0.000047020578,0.0013592896,0.13629149,0.0014605694,0.7706181,0.00013295682,0.064152405],"study_design_scores_gemma":[0.0006033124,0.00023756511,0.009859156,0.00028621766,0.00008885289,0.000003130394,0.00013075996,0.9704559,0.00042165525,0.016589992,0.0008542605,0.000469222],"about_ca_topic_score_codex":0.0001409718,"about_ca_topic_score_gemma":0.000005463047,"teacher_disagreement_score":0.8645921,"about_ca_system_score_codex":0.000056442288,"about_ca_system_score_gemma":0.000180849,"threshold_uncertainty_score":0.99993545},"labels":[],"label_agreement":null},{"id":"W2950277768","doi":"","title":"Scalable Bayesian Optimization Using Deep Neural Networks","year":2015,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":376,"is_retracted":false,"has_abstract":true,"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; Hyperparameter; Bayesian optimization; Artificial intelligence; Artificial neural network; Convolutional neural network; Deep learning; Gaussian process; Global Positioning System; Machine learning; Benchmark (surveying); Optimization problem; Scalability; Surrogate model; Gaussian; Algorithm","score_opus":0.07416914068091068,"score_gpt":0.2071218247056708,"score_spread":0.13295268402476013,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2950277768","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":[0.00499872,0.00007977828,0.9922126,0.00010194484,0.0006255783,0.00016208633,0.000003665801,0.0003161442,0.0014994643],"genre_scores_gemma":[0.96826375,0.000036091515,0.031026307,0.000068170084,0.00012916436,3.9790945e-7,0.00012960895,0.000018537317,0.00032797307],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982349,0.00025051844,0.0001811435,0.0009339853,0.00009110034,0.00030831783],"domain_scores_gemma":[0.9980234,0.000043955635,0.00029631975,0.0012310237,0.00020528358,0.00020004637],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00035069138,0.0002464372,0.00023086938,0.00020773165,0.00019801565,0.0002762661,0.0013989942,0.00027909453,0.000023684923],"category_scores_gemma":[0.000051751245,0.00029076682,0.00009093125,0.0006251398,0.00005628445,0.00059969485,0.0013741492,0.00059412257,0.000015127969],"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":[0.0000085015745,0.000027026485,0.0024311172,0.000014845637,0.000015554415,0.0000311177,0.000047442703,0.98519415,0.0000010042919,0.010814682,0.000109709224,0.0013048294],"study_design_scores_gemma":[0.00021568399,0.000018430865,0.0002102396,0.000023103283,0.00003794356,0.000005740778,0.000017528411,0.996922,0.0000011185416,0.002138042,0.000110272376,0.00029988706],"about_ca_topic_score_codex":0.00024559838,"about_ca_topic_score_gemma":0.00002274833,"teacher_disagreement_score":0.963265,"about_ca_system_score_codex":0.00022880136,"about_ca_system_score_gemma":0.00011886417,"threshold_uncertainty_score":0.99995446},"labels":[],"label_agreement":null},{"id":"W2951131435","doi":"10.48550/arxiv.1811.01742","title":"META-DES.H: a dynamic ensemble selection technique using meta-learning and a dynamic weighting approach","year":2018,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Machine Learning and Data Classification","field":"Computer Science","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":"École de Technologie Supérieure","funders":"Fundação de Amparo à Ciência e Tecnologia do Estado de Pernambuco; Conselho Nacional de Desenvolvimento Científico e Tecnológico; Natural Sciences and Engineering Research Council of Canada; École de technologie supérieure","keywords":"Classifier (UML); Weighting; Computer science; Artificial intelligence; Machine learning; Cascading classifiers; Ensemble learning; Random subspace method; Weighted voting; Voting; Pattern recognition (psychology)","score_opus":0.12767780688695862,"score_gpt":0.235398383507808,"score_spread":0.10772057662084938,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2951131435","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":[0.059493057,0.00039160257,0.93779224,0.000028043443,0.00008220094,0.00038944415,0.000005725188,0.00055107364,0.0012665852],"genre_scores_gemma":[0.84788394,0.00012311019,0.15083615,0.000011868279,0.000022885113,0.00000904592,0.00004515429,0.000031725136,0.0010361137],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99678934,0.0006973071,0.000291783,0.0016676288,0.00013700656,0.00041694104],"domain_scores_gemma":[0.9981421,0.00012326018,0.000574913,0.00079781766,0.00021704266,0.00014482201],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011771347,0.00046857927,0.00068831915,0.0005452024,0.0006588091,0.0003200111,0.0009186925,0.00037146767,0.000024174107],"category_scores_gemma":[0.00008878678,0.00046685926,0.00035317018,0.0009291092,0.00017934585,0.0006097892,0.0015559677,0.0011910581,0.000012324294],"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":[0.0002217285,0.0010060515,0.007871214,0.00308814,0.03327777,0.00034614812,0.00388726,0.76087856,0.026908396,0.1430503,0.00008502163,0.01937943],"study_design_scores_gemma":[0.0001470004,0.0000581435,0.0002039616,0.00003280015,0.0036468203,0.000076849625,0.000045709206,0.9843136,0.00011253811,0.010706985,0.00019887746,0.00045670877],"about_ca_topic_score_codex":0.00035947713,"about_ca_topic_score_gemma":0.000051065428,"teacher_disagreement_score":0.7883909,"about_ca_system_score_codex":0.00035071743,"about_ca_system_score_gemma":0.00015821662,"threshold_uncertainty_score":0.99977833},"labels":[],"label_agreement":null},{"id":"W2952144181","doi":"10.1145/3292500.3330962","title":"Tackle Balancing Constraint for Incremental Semi-Supervised Support Vector Learning","year":2019,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"National Science Foundation","keywords":"Constraint (computer-aided design); Computer science; Benchmark (surveying); Support vector machine; Convergence (economics); Incremental learning; Semi-supervised learning; Generalization; Reduction (mathematics); Artificial intelligence; Machine learning; Algorithm; Mathematical optimization; Mathematics","score_opus":0.013303598792265033,"score_gpt":0.25373439733191927,"score_spread":0.24043079853965424,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2952144181","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":[0.08338554,0.000013651577,0.88352954,0.0014158929,0.000420504,0.00044787818,0.000008005218,0.0004742528,0.030304749],"genre_scores_gemma":[0.95497996,0.0000019078368,0.041237675,0.00036900426,0.000052915657,0.000018251005,0.0001143477,0.000009323225,0.0032166454],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989681,0.000052392494,0.0001895235,0.00036593276,0.00017865744,0.00024534095],"domain_scores_gemma":[0.9993249,0.00013617372,0.000073701754,0.00034800038,0.00004390708,0.000073292875],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00048835715,0.00010617029,0.0001294218,0.0000571049,0.00011372142,0.00014795254,0.00039750454,0.0000450702,0.00049136416],"category_scores_gemma":[0.00008959138,0.00009576318,0.000053761283,0.00012001158,0.000016216489,0.0003470005,0.00012826783,0.00015201523,0.00039384444],"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":[0.00005631669,0.00021877473,0.23651953,0.00027432144,0.00009527161,0.000007976843,0.0025152452,0.0013413881,0.25356996,0.33502805,0.023770824,0.14660232],"study_design_scores_gemma":[0.0013259944,0.0004037109,0.016708216,0.000024687193,0.000007710214,0.000022861388,0.00041791663,0.8848977,0.005738292,0.00017807365,0.08989832,0.00037653462],"about_ca_topic_score_codex":0.000042490898,"about_ca_topic_score_gemma":0.0000038896055,"teacher_disagreement_score":0.8835563,"about_ca_system_score_codex":0.000041817948,"about_ca_system_score_gemma":0.000076146476,"threshold_uncertainty_score":0.5380093},"labels":[],"label_agreement":null},{"id":"W2952316226","doi":"10.48550/arxiv.1902.08673","title":"Ising-Dropout: A Regularization Method for Training and Compression of Deep Neural Networks","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"MNIST database; Overfitting; Computer science; Initialization; Artificial intelligence; Regularization (linguistics); Dropout (neural networks); Inference; Machine learning; Artificial neural network; Deep neural networks; Deep learning; Pattern recognition (psychology)","score_opus":0.07685834504908302,"score_gpt":0.23463728531275846,"score_spread":0.15777894026367545,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2952316226","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":[0.007661327,0.00007896585,0.99115145,0.00010435682,0.00031458802,0.0003042181,0.000008287212,0.00009101567,0.00028576585],"genre_scores_gemma":[0.9428616,0.00002767336,0.056692097,0.000036010435,0.000043391497,7.9946955e-7,0.0001135674,0.000011962244,0.00021290207],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986202,0.00023035206,0.00018720608,0.00072755705,0.00005757602,0.00017708406],"domain_scores_gemma":[0.99841034,0.00025895587,0.00041487833,0.00072753755,0.00012091171,0.00006738091],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042075067,0.00017322852,0.00029174067,0.00016332025,0.000114371636,0.000082470004,0.0006642883,0.0002151619,0.0000027434296],"category_scores_gemma":[0.000065059416,0.00018858351,0.00008905199,0.00023627235,0.0000462015,0.0002494097,0.0007156482,0.0003132287,7.6231044e-7],"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":[0.000027636212,0.000021988079,0.0013215755,0.0001103453,0.000024956506,0.0000024222115,0.0003823546,0.87067145,0.00008940935,0.0900633,0.000019171404,0.03726538],"study_design_scores_gemma":[0.00038474228,0.00005170912,0.0011191593,0.00006700942,0.00004558274,0.0000025790628,0.00005724959,0.98889816,0.00002566808,0.009028403,0.000137164,0.00018260443],"about_ca_topic_score_codex":0.000042942727,"about_ca_topic_score_gemma":0.000006485703,"teacher_disagreement_score":0.9352003,"about_ca_system_score_codex":0.000034298795,"about_ca_system_score_gemma":0.00003760588,"threshold_uncertainty_score":0.7690212},"labels":[],"label_agreement":null},{"id":"W2957298014","doi":"","title":"STRADS-AP: Simplifying Distributed Machine Learning Programming without Introducing a New Programming Model.","year":2019,"lang":"en","type":"article","venue":"USENIX Annual Technical Conference","topic":"Machine Learning and Data Classification","field":"Computer Science","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":"Vector Institute; University of Toronto","funders":"","keywords":"Computer science; Inductive programming; Programming language; Programming domain; Functional reactive programming; Programming paradigm; Reactive programming; Artificial intelligence","score_opus":0.02694820491428026,"score_gpt":0.28542457794627957,"score_spread":0.25847637303199933,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2957298014","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":[0.0150301475,0.00007878322,0.9796251,0.0018918199,0.000121858226,0.0006747448,0.000025102452,0.0019996923,0.0005527316],"genre_scores_gemma":[0.76104105,0.000012574104,0.23800394,0.000068698806,0.00008647523,0.00003241416,0.00018605767,0.000029671372,0.00053912366],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99635655,0.00018406667,0.0006415896,0.0013105624,0.00066151685,0.000845728],"domain_scores_gemma":[0.9975897,0.00018717922,0.00036073916,0.0012264973,0.0002650892,0.0003708016],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008654195,0.00042086127,0.0004888504,0.00018451244,0.00031255497,0.0008008171,0.0016573004,0.00023788749,0.00003341632],"category_scores_gemma":[0.0008174117,0.00038977776,0.00012720592,0.0008112498,0.0000875778,0.001149411,0.0008202567,0.0014562899,0.00011695716],"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":[0.000064357664,0.00022358465,0.02765835,0.00012899039,0.000041217976,0.000015335283,0.0012949659,0.014049153,0.008860726,0.08392428,0.00032705296,0.86341196],"study_design_scores_gemma":[0.0007300648,0.00038018072,0.0025503936,0.00016288398,0.000025831245,0.0000573933,0.0001371119,0.9389045,0.00032395116,0.0012431251,0.054747496,0.00073702075],"about_ca_topic_score_codex":0.00027403282,"about_ca_topic_score_gemma":0.000060823553,"teacher_disagreement_score":0.9248554,"about_ca_system_score_codex":0.00011022366,"about_ca_system_score_gemma":0.00033323953,"threshold_uncertainty_score":0.9998554},"labels":[],"label_agreement":null},{"id":"W2962719937","doi":"","title":"SELF-INFORMED NEURAL NETWORK STRUCTURE LEARNING","year":2015,"lang":"en","type":"article","venue":"International Conference on Learning Representations","topic":"Machine Learning and Data Classification","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":"Université de Montréal","funders":"","keywords":"Computer science; Artificial intelligence; Classifier (UML); Artificial neural network; Cognitive neuroscience of visual object recognition; Visualization; Pattern recognition (psychology); Machine learning; Task (project management); Similarity (geometry); Object (grammar); Image (mathematics)","score_opus":0.06063609321300034,"score_gpt":0.35074877230090973,"score_spread":0.2901126790879094,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2962719937","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":[0.13820878,0.00011196018,0.26099035,0.043732125,0.006768119,0.00090187165,0.000025653324,0.004832135,0.544429],"genre_scores_gemma":[0.9797304,0.000023960141,0.015271497,0.00021611962,0.00034681777,0.000022386977,0.00028482513,0.000014419992,0.0040895613],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99793136,0.00028477266,0.00031813758,0.0004883841,0.00068770506,0.00028964382],"domain_scores_gemma":[0.9983962,0.00026428173,0.0002790391,0.00040273077,0.0004688669,0.00018888329],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031349983,0.00018187331,0.00014414091,0.00018772151,0.00031944437,0.0006441672,0.0010100924,0.000082437226,0.0001580568],"category_scores_gemma":[0.0011912601,0.00017649728,0.00006092328,0.00037778966,0.00004119168,0.0008435655,0.00024046648,0.00081478147,0.00025264753],"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":[0.000041590523,0.00007920656,0.08234302,0.000008843573,0.00009685988,0.000020642297,0.006271688,0.35047066,0.00019460716,0.5274937,0.0051112254,0.02786794],"study_design_scores_gemma":[0.0005020733,0.00014318162,0.01514921,0.000022570252,0.000007684496,0.000031909294,0.0004894131,0.91018116,0.000037502236,0.0045807133,0.068624206,0.00023036652],"about_ca_topic_score_codex":0.00005857461,"about_ca_topic_score_gemma":0.000024212606,"teacher_disagreement_score":0.8415216,"about_ca_system_score_codex":0.00012112621,"about_ca_system_score_gemma":0.00025044775,"threshold_uncertainty_score":0.719735},"labels":[],"label_agreement":null},{"id":"W2962745351","doi":"","title":"Estimating the class prior and posterior from noisy positives and unlabeled data","year":2016,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Univariate; Discriminative model; Nonparametric statistics; Kernel density estimation; Pattern recognition (psychology); Noise (video); Computer science; Artificial intelligence; Kernel (algebra); False positive paradox; Class (philosophy); Density estimation; Parametric statistics; Support vector machine; Data modeling; False positives and false negatives; Data mining; Mathematics; Machine learning; Statistics; Multivariate statistics","score_opus":0.02574648480882142,"score_gpt":0.2736509987544086,"score_spread":0.2479045139455872,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2962745351","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":[0.49631548,0.00065265654,0.49152237,0.01001992,0.00045026492,0.00036325539,0.000081920836,0.00029761367,0.00029649845],"genre_scores_gemma":[0.9939192,0.000005325198,0.0056014173,0.00028017475,0.00007402639,0.000011225622,0.00006101247,0.0000040633863,0.000043589025],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990329,0.000094535804,0.00032873012,0.00021603973,0.00019674697,0.00013105352],"domain_scores_gemma":[0.9988547,0.00017670786,0.0003321527,0.00049969385,0.000087021246,0.000049729766],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00040215554,0.00010695308,0.00011000707,0.000051480194,0.00036650826,0.0013752237,0.0005557036,0.000040965915,7.494752e-7],"category_scores_gemma":[0.00021270334,0.000056971978,0.0000063776242,0.00011877442,0.00006136465,0.0061755963,0.00035481146,0.00008637475,0.0000121816975],"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":[0.000008290684,0.000004136337,0.0024542212,0.00010785726,0.0000064094143,4.0995303e-7,0.002052246,0.000034134908,0.0019433016,0.0009098265,0.0001590039,0.9923202],"study_design_scores_gemma":[0.00029320962,0.000023791228,0.022559987,0.00020653661,0.000006832202,0.00005412024,0.00014034325,0.973951,0.000051432755,0.000047604168,0.002556735,0.00010840379],"about_ca_topic_score_codex":0.00009763871,"about_ca_topic_score_gemma":0.0000029236492,"teacher_disagreement_score":0.99221176,"about_ca_system_score_codex":0.0000138277865,"about_ca_system_score_gemma":0.000035911202,"threshold_uncertainty_score":0.99966145},"labels":[],"label_agreement":null},{"id":"W2963001956","doi":"","title":"Bayesian hyperparameter optimization for ensemble learning","year":2016,"lang":"en","type":"article","venue":"Uncertainty in Artificial Intelligence","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure; Université Laval","funders":"","keywords":"Hyperparameter; Bayesian optimization; Hyperparameter optimization; Ensemble learning; Computer science; Machine learning; Artificial intelligence; Bayesian probability; Greedy algorithm; Mathematical optimization; Algorithm; Mathematics; Support vector machine","score_opus":0.04312508995708945,"score_gpt":0.30252744251481944,"score_spread":0.25940235255773,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963001956","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":[0.0015171065,0.000019908253,0.9939186,0.0033063723,0.00025004995,0.00024101949,0.0000027446395,0.00015645837,0.0005877714],"genre_scores_gemma":[0.9030059,0.000028861396,0.09637958,0.00013367347,0.000075452896,0.00006668342,0.000012977444,0.000011203956,0.00028566655],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998457,0.00013579341,0.00039972414,0.00049770996,0.0001744571,0.0003353251],"domain_scores_gemma":[0.99861825,0.00065689575,0.00012485738,0.00041336092,0.00011565208,0.00007101425],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006736309,0.00013854944,0.00014929619,0.00018433097,0.00014358909,0.00014180639,0.00056102773,0.00008348846,0.000063962965],"category_scores_gemma":[0.0011973907,0.00010494859,0.00005776909,0.0003921206,0.00005867349,0.0004162545,0.00007902731,0.00013170045,0.00009084018],"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":[0.000026438101,0.000030494666,0.00024986736,0.0000060410607,0.00000282399,0.0000014397136,0.00023370469,0.2725374,0.0020020066,0.10324438,0.000044945435,0.6216205],"study_design_scores_gemma":[0.00004869244,0.00010112239,0.00003236564,0.000040670617,0.0000022495049,0.0000023410566,0.00006266275,0.96288556,0.0055846875,0.028042223,0.0030220435,0.00017537497],"about_ca_topic_score_codex":0.0000742128,"about_ca_topic_score_gemma":0.000081878876,"teacher_disagreement_score":0.9014888,"about_ca_system_score_codex":0.00009071382,"about_ca_system_score_gemma":0.000055087487,"threshold_uncertainty_score":0.42796794},"labels":[],"label_agreement":null},{"id":"W2963153973","doi":"","title":"Sequential model-based ensemble optimization","year":2014,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke; Université Laval","funders":"","keywords":"Hyperparameter; Computer science; Machine learning; Artificial intelligence; Bayesian optimization; Model selection; Ensemble learning; Selection (genetic algorithm); Process (computing); Data mining","score_opus":0.018819451274919515,"score_gpt":0.25466099103787837,"score_spread":0.23584153976295885,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963153973","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":[0.00011861864,0.0000018694964,0.96017015,0.001133835,0.0000694805,0.000031397958,2.565745e-7,0.00025187645,0.03822251],"genre_scores_gemma":[0.54746497,4.0890106e-7,0.45155686,0.00041228678,0.000019448966,0.0000027027356,0.000018205792,0.000002529802,0.0005225769],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99946,0.0000537392,0.00008439024,0.0001922885,0.00011629456,0.00009331435],"domain_scores_gemma":[0.9994673,0.000026141663,0.000036192927,0.0003933069,0.0000371985,0.000039847437],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021456383,0.000050177292,0.000045238834,0.00004609828,0.000071142065,0.00010701293,0.00029499707,0.000027787919,0.000028522207],"category_scores_gemma":[0.00004605431,0.00004407001,0.000018261642,0.00011140785,0.00000872139,0.00021966471,0.000040285762,0.00004777657,0.00006303887],"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":[8.0432034e-7,0.00001046258,0.000036731813,0.000001974248,5.7494236e-7,5.729074e-8,0.000012010188,0.85727066,0.00033375015,0.11703318,0.00047734554,0.02482247],"study_design_scores_gemma":[0.000114092385,0.000015762153,0.000042260992,0.0000015956228,0.0000012310053,4.901448e-7,4.77654e-7,0.99536467,0.0007982031,0.00089316437,0.002706574,0.000061462146],"about_ca_topic_score_codex":0.000014549161,"about_ca_topic_score_gemma":0.000002717229,"teacher_disagreement_score":0.54734635,"about_ca_system_score_codex":0.000010489707,"about_ca_system_score_gemma":0.00003128221,"threshold_uncertainty_score":0.17971228},"labels":[],"label_agreement":null},{"id":"W2963371670","doi":"","title":"Learning to Reweight Examples for Robust Deep Learning","year":2018,"lang":"en","type":"article","venue":"International Conference on Machine Learning","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":418,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Hyperparameter; Overfitting; Computer science; Artificial intelligence; Machine learning; Regularization (linguistics); Deep learning; Gradient descent; Artificial neural network; Set (abstract data type); Deep neural networks; Supervised learning","score_opus":0.06198251208780124,"score_gpt":0.31968496760501225,"score_spread":0.257702455517211,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963371670","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":[0.011504817,0.000033376597,0.9407945,0.0077577196,0.0008638629,0.00031399634,0.0000066826647,0.00077421765,0.037950817],"genre_scores_gemma":[0.9147466,0.00004221943,0.07410017,0.0005946079,0.00070367206,0.0000881712,0.00026225307,0.000046219942,0.009416101],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969825,0.0003782009,0.0004632231,0.0010051137,0.0006498792,0.0005210653],"domain_scores_gemma":[0.9978133,0.0004762481,0.0003456253,0.00043767388,0.0007050349,0.00022211461],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011041221,0.00034171858,0.00028332399,0.0004921886,0.0008578479,0.0007642539,0.0016073172,0.00012249786,0.0005259847],"category_scores_gemma":[0.0025788895,0.0003335354,0.000118350654,0.000404149,0.00007584934,0.0005426779,0.0004260685,0.0010863249,0.0007732463],"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":[0.00024630886,0.00012253453,0.019587152,0.000027368756,0.00010359287,0.000013710091,0.0039247717,0.048340905,0.00546048,0.35647312,0.0005340254,0.565166],"study_design_scores_gemma":[0.00045973592,0.0009559785,0.0036995427,0.000073766605,0.0000072718144,0.000015705999,0.00020156387,0.7772194,0.00029247324,0.0009472693,0.21576768,0.00035962742],"about_ca_topic_score_codex":0.0001557361,"about_ca_topic_score_gemma":0.00009606967,"teacher_disagreement_score":0.90324175,"about_ca_system_score_codex":0.000122681,"about_ca_system_score_gemma":0.00007525834,"threshold_uncertainty_score":0.99991167},"labels":[],"label_agreement":null},{"id":"W2963507023","doi":"10.1609/aaai.v33i01.33013470","title":"On-Line Adaptative Curriculum Learning for GANs","year":2019,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":41,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institut National de la Recherche Scientifique; McGill University","funders":"","keywords":"Discriminator; Computer science; Generator (circuit theory); Generative grammar; Adversarial system; Cover (algebra); Artificial intelligence; Entropy (arrow of time); Machine learning; Convergence (economics)","score_opus":0.02301671552400114,"score_gpt":0.2934025239861666,"score_spread":0.2703858084621655,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963507023","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":[0.0109783085,0.000008125486,0.9675552,0.0015179489,0.00017970162,0.00016757204,9.4109475e-7,0.00020103224,0.019391164],"genre_scores_gemma":[0.9475101,0.000002484604,0.040094633,0.000315798,0.000034790177,0.000017308434,0.000029602423,0.0000059652393,0.011989325],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99931586,0.000045422432,0.00009783973,0.00028131195,0.00011991486,0.00013965745],"domain_scores_gemma":[0.9993436,0.00021771896,0.00005963731,0.00028180928,0.000058757447,0.000038528102],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021666847,0.00007191228,0.00007972765,0.000051712053,0.00007674775,0.000070104536,0.00032085346,0.00002634946,0.000071101684],"category_scores_gemma":[0.00016501542,0.000055940647,0.000034840705,0.00014133629,0.0000071465515,0.00019586066,0.000050825733,0.00013152938,0.0006261834],"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":[0.000006244238,0.000060326398,0.0019169874,0.000010802664,0.000007404337,3.334811e-7,0.00031643585,0.012846007,0.00030288048,0.9341494,0.0024510033,0.0479322],"study_design_scores_gemma":[0.00027930728,0.0003500011,0.00106969,0.000008813594,0.0000014401073,9.5088984e-7,0.00008414734,0.95917934,0.00019117341,0.001996817,0.036740478,0.00009785064],"about_ca_topic_score_codex":0.000027233635,"about_ca_topic_score_gemma":0.0000037042319,"teacher_disagreement_score":0.94633335,"about_ca_system_score_codex":0.000013791721,"about_ca_system_score_gemma":0.000021105598,"threshold_uncertainty_score":0.80485296},"labels":[],"label_agreement":null},{"id":"W2963711014","doi":"10.1145/3450975","title":"HyperNOMAD","year":2021,"lang":"en","type":"article","venue":"ACM Transactions on Mathematical Software","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal; Group for Research in Decision Analysis","funders":"","keywords":"MNIST database; Hyperparameter; Computer science; Artificial intelligence; Artificial neural network; Flexibility (engineering); Process (computing); Categorical variable; Machine learning; Deep learning; Field (mathematics); Mathematics","score_opus":0.026208269386408824,"score_gpt":0.26984025901411496,"score_spread":0.24363198962770613,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2963711014","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":[0.00082819833,0.000031972097,0.9933044,0.0046353075,0.000098723176,0.00005211566,0.0000066516895,0.00044361126,0.00059905864],"genre_scores_gemma":[0.047766976,0.000013022116,0.949637,0.00049734354,0.00002041663,0.00002567649,0.000010707231,0.000011335466,0.0020175064],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99902964,0.000065297114,0.00017551804,0.00031990543,0.00024012792,0.00016948958],"domain_scores_gemma":[0.9980925,0.00046015193,0.000031930842,0.0012521611,0.00006459231,0.00009869082],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000121022895,0.00010404684,0.00012650831,0.000045711804,0.00017820501,0.00012435102,0.00060079846,0.000061647595,0.00048418646],"category_scores_gemma":[0.0005109763,0.000092341426,0.00008150673,0.00031192144,0.000024822213,0.00021153009,0.000020971856,0.0002219195,0.001225172],"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":[0.00000238727,0.00033513943,0.00006101954,0.000049717448,0.000019642688,0.000022524539,0.00018687117,0.00016375112,0.00016978588,0.023034254,0.00007567666,0.97587925],"study_design_scores_gemma":[0.00055542134,0.00011302242,0.002771992,0.000117632764,0.00003814576,0.00023892784,0.00009083694,0.008027435,0.0051674773,0.95632666,0.026070384,0.0004820832],"about_ca_topic_score_codex":0.0000017480612,"about_ca_topic_score_gemma":0.0000017143725,"teacher_disagreement_score":0.97539717,"about_ca_system_score_codex":0.000024641167,"about_ca_system_score_gemma":0.000049371,"threshold_uncertainty_score":0.9995525},"labels":[],"label_agreement":null},{"id":"W2964096266","doi":"","title":"Toward Robustness against Label Noise in Training Deep Discriminative Neural Networks","year":2017,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":186,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Robustness (evolution); Discriminative model; Artificial intelligence; Inference; Convolutional neural network; Deep neural networks; Pattern recognition (psychology); Machine learning; Noise (video); Training set; Graphical model; Artificial neural network; Noise measurement; Image (mathematics); Noise reduction","score_opus":0.0666042164439337,"score_gpt":0.29915740305396926,"score_spread":0.23255318661003554,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2964096266","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":[0.05892183,0.0001890202,0.93276095,0.0018770155,0.0012468885,0.00037612088,0.0000041619937,0.00032432136,0.004299708],"genre_scores_gemma":[0.99810404,0.000007067553,0.0013639332,0.00021212286,0.00011827331,0.000060366376,0.00007394577,0.000008929559,0.000051314822],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983118,0.00011604368,0.0006100682,0.00025866838,0.00034440123,0.00035898268],"domain_scores_gemma":[0.9982266,0.000049479226,0.0008543229,0.0005851656,0.00018922877,0.00009523325],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0006086789,0.00020283838,0.00024498298,0.0001965169,0.0006990519,0.003048989,0.0012143634,0.000104521205,7.9074294e-7],"category_scores_gemma":[0.00028414454,0.00017699426,0.000033223187,0.00023606364,0.00007036065,0.010526673,0.00019653891,0.00037866452,0.000008833825],"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":[0.000009880215,0.00001821094,0.0012969179,0.00019242392,0.0000031059624,0.000004933349,0.008231872,0.30696285,0.000016158954,0.0019163281,0.00004880345,0.6812985],"study_design_scores_gemma":[0.0004935086,0.000025010464,0.01094786,0.00014052504,0.0000031074048,0.000021564398,0.0010829566,0.9866949,0.0000051618244,0.00001324253,0.00036176073,0.00021042449],"about_ca_topic_score_codex":0.00010377196,"about_ca_topic_score_gemma":0.00001734681,"teacher_disagreement_score":0.9391822,"about_ca_system_score_codex":0.00007466594,"about_ca_system_score_gemma":0.00005695038,"threshold_uncertainty_score":0.99798596},"labels":[],"label_agreement":null},{"id":"W2964160158","doi":"","title":"Quantifying Learning Guarantees for Convex but Inconsistent Surrogates","year":2018,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Machine Learning and Data Classification","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":"Université de Montréal","funders":"","keywords":"Consistency (knowledge bases); Ranking (information retrieval); Computer science; Quadratic equation; Regular polygon; Upper and lower bounds; Mathematical optimization; Machine learning; Tree (set theory); Hinge loss; Computation; Artificial intelligence; Calibration; Function (biology); Mathematics; Algorithm; Statistics; Support vector machine","score_opus":0.12825073163858444,"score_gpt":0.22634125295504934,"score_spread":0.0980905213164649,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2964160158","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":[0.34166697,0.000019328696,0.6560887,0.00021036903,0.00019513095,0.00010491051,0.0000027855415,0.00024549803,0.001466319],"genre_scores_gemma":[0.9947012,0.000019449313,0.0034803066,0.00007011166,0.00007213285,7.132102e-7,0.000014637179,0.000008583141,0.0016328645],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989289,0.00011609044,0.00012433507,0.00052613765,0.000053474716,0.00025105363],"domain_scores_gemma":[0.9989138,0.00025953536,0.0001314388,0.00043991016,0.00018019027,0.00007511005],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038762164,0.00012143447,0.000138936,0.00012842639,0.00043697492,0.00010872709,0.00062672445,0.00006047645,0.000019550716],"category_scores_gemma":[0.00019689735,0.00012899895,0.00007727622,0.00037366705,0.00012358837,0.00046354625,0.00017883042,0.00014096819,0.00016427724],"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":[0.000083065104,0.00009091059,0.1097622,0.000058860383,0.00006565198,0.000022247885,0.00068875117,0.0039087394,0.0031530054,0.8739926,0.00042766042,0.0077462816],"study_design_scores_gemma":[0.0006378345,0.00022052696,0.010229675,0.000029873716,0.000022243052,0.000006654451,0.00032660415,0.97149414,0.0012091182,0.0024011503,0.013167159,0.0002550191],"about_ca_topic_score_codex":0.000100432255,"about_ca_topic_score_gemma":0.00008307819,"teacher_disagreement_score":0.9675854,"about_ca_system_score_codex":0.00003961452,"about_ca_system_score_gemma":0.000048254286,"threshold_uncertainty_score":0.52604246},"labels":[],"label_agreement":null},{"id":"W2964273174","doi":"10.1109/icdm.2016.0121","title":"Learning Deep Networks from Noisy Labels with Dropout Regularization","year":2016,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":188,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Institute for Advanced Research; National Science Foundation","keywords":"Softmax function; Dropout (neural networks); Computer science; Artificial intelligence; MNIST database; Regularization (linguistics); Stochastic gradient descent; Deep neural networks; Deep learning; Artificial neural network; Noise (video); Machine learning; Pattern recognition (psychology); Gradient descent; Underdetermined system; Algorithm","score_opus":0.00550017393021877,"score_gpt":0.20106685055813017,"score_spread":0.1955666766279114,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2964273174","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":[0.0045469888,0.000025934949,0.98796004,0.0024148386,0.00007949709,0.000054212553,5.0238873e-7,0.00037957676,0.004538413],"genre_scores_gemma":[0.93696934,0.00001856675,0.056799736,0.00017347679,0.000103429826,0.000006248518,0.000036494246,0.00001017931,0.0058825505],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990595,0.00011120332,0.00012474327,0.0003558267,0.00018012346,0.00016860692],"domain_scores_gemma":[0.9991737,0.00013392557,0.00009485608,0.00047321914,0.00006111705,0.00006317623],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017689717,0.000093974035,0.00008530374,0.00004370918,0.00013337238,0.00014130695,0.00038676165,0.000054462696,0.0000910209],"category_scores_gemma":[0.0000714866,0.00005362626,0.000015541968,0.0002198941,0.000027920458,0.000511492,0.0000969547,0.000107816915,0.00013091728],"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":[0.000017667267,0.00003859728,0.08103498,0.0000026905363,0.000025691608,0.000005178054,0.00030588414,0.004294148,0.0028111017,0.13261698,0.0005612408,0.77828586],"study_design_scores_gemma":[0.00054303923,0.0001260399,0.034010515,0.000040531897,0.0000075132616,0.0000041772278,0.000019731298,0.94827956,0.0004986901,0.0015939559,0.014647156,0.00022906567],"about_ca_topic_score_codex":0.00007446702,"about_ca_topic_score_gemma":0.000038751474,"teacher_disagreement_score":0.94398546,"about_ca_system_score_codex":0.00002280285,"about_ca_system_score_gemma":0.000020059882,"threshold_uncertainty_score":0.21868154},"labels":[],"label_agreement":null},{"id":"W2969721664","doi":"","title":"ProcSy: Procedural Synthetic Dataset Generation Towards Influence Factor Studies Of Semantic Segmentation Networks","year":2019,"lang":"en","type":"article","venue":"Computer Vision and Pattern Recognition","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":32,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Artificial intelligence; Segmentation; Factor (programming language); Natural language processing; Programming language","score_opus":0.050971514007209257,"score_gpt":0.3210912784910192,"score_spread":0.2701197644838099,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2969721664","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":[0.5417066,0.0000912553,0.45728642,0.00030715455,0.00025050686,0.0002558253,0.00004962197,0.000047625566,0.0000050037956],"genre_scores_gemma":[0.99079156,0.0001684054,0.007066421,0.0005047392,0.00008780684,0.000016057837,0.0013491196,0.0000073647852,0.000008503285],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987913,0.00013633403,0.0003069274,0.0004240351,0.00020795233,0.00013348224],"domain_scores_gemma":[0.9992018,0.000071907896,0.00022418164,0.00029625426,0.0001577313,0.000048126964],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002159547,0.00014690869,0.000185463,0.00011085859,0.00008436739,0.00014317947,0.00019767057,0.000055768993,0.000014300003],"category_scores_gemma":[0.000023739409,0.000120903234,0.000026079191,0.00015177614,0.000031558513,0.0007602286,0.00016690644,0.0001095431,0.000047270925],"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":[0.0000074944196,0.000046191,0.0035536445,0.0002121432,0.000019566081,0.0000011183773,0.0004624335,0.00048129208,0.0037763938,0.000016487378,0.00060615694,0.99081707],"study_design_scores_gemma":[0.00042909515,0.00036758243,0.053297624,0.00028183535,0.000014599367,0.00002468143,0.000030811236,0.9432465,0.0017741269,0.00008964701,0.00023181,0.00021171093],"about_ca_topic_score_codex":0.00001891444,"about_ca_topic_score_gemma":0.000005448427,"teacher_disagreement_score":0.99060535,"about_ca_system_score_codex":0.000019788333,"about_ca_system_score_gemma":0.000019495523,"threshold_uncertainty_score":0.4930291},"labels":[],"label_agreement":null},{"id":"W2979333226","doi":"10.1109/ccece.2019.8861966","title":"Semiparametric Subsampling and Data Condensation for Large-Scale Data Analytics","year":2019,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","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":false,"ca_institutions":"Simon Fraser University; University of Waterloo","funders":"","keywords":"Computer science; Cluster analysis; Data mining; Benchmark (surveying); Artificial intelligence; Scalability; Pattern recognition (psychology); Random forest; Voronoi diagram; Machine learning; Mathematics","score_opus":0.1126477890387248,"score_gpt":0.35165097768998654,"score_spread":0.23900318865126174,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2979333226","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":[0.012335527,0.000081550315,0.985531,0.0008742174,0.0001238464,0.00018148731,0.00017728024,0.00009418394,0.00060095574],"genre_scores_gemma":[0.681378,0.000031520605,0.31356937,0.0002606242,0.00004994675,0.0000023694454,0.0036635767,0.000007383611,0.0010371871],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99889743,0.000027317768,0.00015249914,0.00063185,0.0001409392,0.00014998711],"domain_scores_gemma":[0.99659353,0.00033628676,0.000080690625,0.0028931682,0.000049079754,0.000047267666],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010440216,0.00006845079,0.000099750556,0.000102613005,0.00007556158,0.0002431137,0.0016399971,0.000040324514,0.000016158147],"category_scores_gemma":[0.0003318024,0.000060336464,0.0000075696166,0.00032800692,0.000007737363,0.0010068406,0.0011623085,0.00007692603,0.000043023225],"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":[0.000035371333,0.00030065034,0.34320477,0.00035311538,0.00011139311,0.0000012165601,0.00072294835,0.0009912702,0.0018856965,0.40765393,0.041730575,0.20300908],"study_design_scores_gemma":[0.0002486398,0.000018305736,0.00994353,0.000004077832,0.000009057314,0.0000022453346,0.00004052458,0.94612694,0.000022220067,0.00047005634,0.043029893,0.000084512605],"about_ca_topic_score_codex":0.000030023031,"about_ca_topic_score_gemma":0.000039601455,"teacher_disagreement_score":0.94513565,"about_ca_system_score_codex":0.000008166866,"about_ca_system_score_gemma":0.000032765412,"threshold_uncertainty_score":0.304755},"labels":[],"label_agreement":null},{"id":"W2983785293","doi":"10.48550/arxiv.1911.02590","title":"Optimizing Millions of Hyperparameters by Implicit Differentiation","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":43,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Hyperparameter; Hessian matrix; Computer science; Function (biology); Inverse; Hyperparameter optimization; Machine learning; Artificial intelligence; Algorithm; Mathematical optimization; Mathematics; Applied mathematics","score_opus":0.04998806090801263,"score_gpt":0.19333540997927917,"score_spread":0.14334734907126653,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2983785293","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":[0.26085097,0.000050347327,0.73757297,0.00009601721,0.0002613629,0.00014442553,0.00003988274,0.000098974626,0.0008850644],"genre_scores_gemma":[0.9946408,0.00014982153,0.0042608213,0.000033696528,0.000014170063,6.4932374e-7,0.00020842082,0.0000111244335,0.0006804424],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99864364,0.00013194853,0.00019499137,0.00075093063,0.00008550655,0.00019299066],"domain_scores_gemma":[0.9980671,0.00011662882,0.00038910442,0.0012596602,0.00009135315,0.00007614668],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014487875,0.00019420926,0.00026570974,0.00022170352,0.00007665616,0.00007572491,0.0012839771,0.00019126221,0.0000130807675],"category_scores_gemma":[0.00003588948,0.00021951071,0.00014178651,0.0003331947,0.00004241919,0.0002637426,0.0009332492,0.00038924773,0.000044074783],"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":[0.000039029062,0.000307072,0.021214109,0.00031381196,0.00023932153,0.00001122059,0.0007087921,0.79215294,0.0068287174,0.17060706,0.0027435014,0.0048344014],"study_design_scores_gemma":[0.00028601586,0.00003998922,0.0050783767,0.000063411295,0.000054350872,9.469245e-7,0.000034801717,0.99049675,0.0005033895,0.0025648277,0.00059112493,0.00028601752],"about_ca_topic_score_codex":0.00020630518,"about_ca_topic_score_gemma":0.000005184018,"teacher_disagreement_score":0.73378986,"about_ca_system_score_codex":0.000087232,"about_ca_system_score_gemma":0.00006886472,"threshold_uncertainty_score":0.8951387},"labels":[],"label_agreement":null},{"id":"W2990476648","doi":"10.1287/ijoc.2020.1023","title":"JANOS: An Integrated Predictive and Prescriptive Modeling Framework","year":2021,"lang":"en","type":"preprint","venue":"INFORMS journal on computing","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Computer science; Novelty; Flexibility (engineering); Set (abstract data type); Predictive analytics; Machine learning; Artificial intelligence; Artificial neural network; Plan (archaeology); Data mining","score_opus":0.03252656625127179,"score_gpt":0.29681140848117743,"score_spread":0.26428484222990567,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2990476648","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":[0.13078602,0.00027512212,0.86630285,0.00034583273,0.0013384215,0.00014411654,0.0000063706925,0.00019963537,0.0006016336],"genre_scores_gemma":[0.80337715,0.000121466495,0.19553295,0.00041548483,0.000451122,0.0000028551665,0.000064538704,0.000019054523,0.000015376678],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974297,0.00023479089,0.0007427155,0.0006427632,0.00057174463,0.00037826694],"domain_scores_gemma":[0.99744654,0.00021202628,0.00072089036,0.00077358953,0.0005508829,0.00029605502],"candidate_categories":["metaepi_narrow","scholarly_communication","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0011857767,0.0003761933,0.00042174567,0.00033083433,0.00051627576,0.0031235914,0.0012476571,0.00038292585,0.0000059962963],"category_scores_gemma":[0.0007443996,0.0003063711,0.00011498904,0.0002704846,0.000041678846,0.0012740195,0.0014890142,0.0045585334,0.0000051976976],"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":[0.0000354722,0.000075292555,0.0006815176,0.000051505554,0.00010880885,0.000051811556,0.00937991,0.6724401,0.000010070716,0.006191931,0.000049508562,0.31092405],"study_design_scores_gemma":[0.00018379198,0.00022770796,0.0014062761,0.0015214855,0.000015970605,0.00018721851,0.00087769766,0.9901366,0.00001490437,0.004696924,0.00040360473,0.00032776655],"about_ca_topic_score_codex":0.00006413158,"about_ca_topic_score_gemma":0.0000029994965,"teacher_disagreement_score":0.67259115,"about_ca_system_score_codex":0.00017699414,"about_ca_system_score_gemma":0.0004333396,"threshold_uncertainty_score":0.99993885},"labels":[],"label_agreement":null},{"id":"W2997060212","doi":"10.1609/aaai.v34i04.6029","title":"Quadruply Stochastic Gradient Method for Large Scale Nonlinear Semi-Supervised Ordinal Regression AUC Optimization","year":2020,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Government of Jiangsu Province; National Natural Science Foundation of China","keywords":"Ordinal regression; Generalization; Computer science; Benchmark (surveying); Scalability; Ranking (information retrieval); Ordinal Scale; Ordinal data; Regression; Binary classification; Scale (ratio); Mathematics; Mathematical optimization; Artificial intelligence; Algorithm; Machine learning; Statistics; Support vector machine","score_opus":0.07678475938076705,"score_gpt":0.33235058833096354,"score_spread":0.25556582895019647,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2997060212","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":[0.0036601955,0.00001327931,0.9821104,0.012807078,0.00021854209,0.00054113124,0.000025413825,0.00013155512,0.00049240724],"genre_scores_gemma":[0.72876924,0.000009771146,0.27024642,0.0006690028,0.00014509562,0.000056650195,0.000012167246,0.00001844483,0.000073220705],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99798673,0.000042801472,0.0005314521,0.0006654637,0.00044025027,0.00033328912],"domain_scores_gemma":[0.99828994,0.00015252816,0.000444361,0.00029988503,0.00065929163,0.00015400072],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00072984106,0.00023017365,0.00027982853,0.0000924912,0.0003173409,0.00024202732,0.0015820377,0.00009582492,0.000039861727],"category_scores_gemma":[0.0010667756,0.00016850191,0.00012797758,0.0006706772,0.00006568674,0.0004076669,0.0003197799,0.00029771237,0.000030286277],"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":[0.0005553021,0.0004480322,0.00020717141,0.00027412004,0.000035070207,3.9705452e-7,0.009144139,0.032797907,0.056177333,0.7698917,0.0010478245,0.129421],"study_design_scores_gemma":[0.0000717121,0.00029833041,0.000021376347,0.00014279915,0.000017936662,0.0000018441505,0.0005666272,0.9461736,0.046940956,0.0052792924,0.00030143358,0.00018409763],"about_ca_topic_score_codex":0.000017528819,"about_ca_topic_score_gemma":0.000003530983,"teacher_disagreement_score":0.9133757,"about_ca_system_score_codex":0.000034848093,"about_ca_system_score_gemma":0.00009503067,"threshold_uncertainty_score":0.68713087},"labels":[],"label_agreement":null},{"id":"W2997788840","doi":"10.1609/aaai.v34i06.6589","title":"BOWL: Bayesian Optimization for Weight Learning in Probabilistic Soft Logic","year":2020,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":3,"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 Montréal","funders":"Air Force Research Laboratory; National Science Foundation; Advanced Research Projects Agency; Defense Advanced Research Projects Agency; Institut de Valorisation des Données; Canada First Research Excellence Fund","keywords":"Artificial intelligence; Computer science; Machine learning; Statistical relational learning; Probabilistic logic; Robustness (evolution); Metric (unit); Gaussian process; Data mining; Gaussian; Relational database","score_opus":0.07613362771478273,"score_gpt":0.29558453698937487,"score_spread":0.21945090927459215,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2997788840","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":[0.003314025,0.000013926431,0.9685884,0.024609173,0.00013458137,0.0006019513,0.0000027323508,0.00015280697,0.0025823896],"genre_scores_gemma":[0.97425467,0.000016058662,0.025158208,0.000365343,0.00006301748,0.000054932196,0.0000037137024,0.000011024464,0.000073058654],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99845284,0.000031015286,0.00046947954,0.0005217739,0.00027072013,0.00025417042],"domain_scores_gemma":[0.9989103,0.00013922006,0.00035016905,0.00017162833,0.00034850108,0.00008019325],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047385928,0.00016559318,0.00020587773,0.0000897283,0.00015667052,0.00020940341,0.0013000582,0.00007842221,0.000036106416],"category_scores_gemma":[0.0022808837,0.0001300199,0.00006855256,0.0006804576,0.00010075002,0.0003619701,0.00019252083,0.00032937297,0.000021105598],"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":[0.000073839365,0.00006760152,0.0006425793,0.00010387608,0.000004542464,1.7252144e-7,0.0013695424,0.029016228,0.0052129314,0.8961311,0.000077649805,0.067299925],"study_design_scores_gemma":[0.000036312867,0.0002195185,0.00013750188,0.000084189145,0.0000055162186,7.7349273e-7,0.00015702755,0.93569833,0.011887033,0.051420096,0.00020915376,0.00014454707],"about_ca_topic_score_codex":0.0000138568175,"about_ca_topic_score_gemma":0.0000038950643,"teacher_disagreement_score":0.9709406,"about_ca_system_score_codex":0.000035295394,"about_ca_system_score_gemma":0.0000875227,"threshold_uncertainty_score":0.5302058},"labels":[],"label_agreement":null},{"id":"W2998113314","doi":"10.1109/access.2020.3041480","title":"Conditional Activation GAN: Improved Auxiliary Classifier GAN","year":2020,"lang":"en","type":"preprint","venue":"IEEE Access","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"National Research Foundation of Korea; National Research Foundation","keywords":"Discriminator; Classifier (UML); Hyperparameter; Computation; Generative adversarial network; Normalization (sociology); Computer science; Algorithm; Pattern recognition (psychology); Artificial intelligence; Deep learning; Detector","score_opus":0.07755484816134543,"score_gpt":0.3434814203426344,"score_spread":0.26592657218128896,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2998113314","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":[0.0038205113,0.000028240207,0.972535,0.014589166,0.0018017207,0.00039729563,0.0000887656,0.0005841219,0.006155137],"genre_scores_gemma":[0.991259,0.000019516803,0.0040257736,0.0019252215,0.000854465,0.00012737543,0.0014182824,0.000027741324,0.00034261768],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997564,0.00018188432,0.00041668463,0.0011003164,0.00046334384,0.00027378],"domain_scores_gemma":[0.99777216,0.00015762338,0.00050437695,0.0012148423,0.00018353193,0.000167469],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00027009094,0.00031764124,0.00030257698,0.00017443515,0.00018814785,0.0011419782,0.0028613412,0.00032461731,0.000077507495],"category_scores_gemma":[0.00018269036,0.00031942106,0.00012334403,0.00032308252,0.000058642785,0.0012182735,0.0007545237,0.0011558615,0.00014640609],"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":[0.00025669945,0.0012276823,0.015419134,0.0024495963,0.0008457899,0.000118619086,0.0029027562,0.025398353,0.13989723,0.14756045,0.41221386,0.25170982],"study_design_scores_gemma":[0.0007077032,0.00007220638,0.114692286,0.00016138046,0.00004413143,0.000010937658,0.000016344347,0.7595342,0.02234584,0.0613527,0.039960742,0.0011015704],"about_ca_topic_score_codex":0.00016970339,"about_ca_topic_score_gemma":0.000010429918,"teacher_disagreement_score":0.9874385,"about_ca_system_score_codex":0.00011432249,"about_ca_system_score_gemma":0.00040409772,"threshold_uncertainty_score":0.9999258},"labels":[],"label_agreement":null},{"id":"W2998503844","doi":"10.1609/aaai.v34i04.5717","title":"Efficient Inference of Optimal Decision Trees","year":2020,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":53,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Computer Research Institute of Montréal","funders":"","keywords":"Heuristics; Inference; Computer science; Decision tree; Incremental decision tree; Tree (set theory); Path (computing); K-ary tree; Class (philosophy); Machine learning; Alternating decision tree; Artificial intelligence; Search tree; Node (physics); Algorithm; Mathematics; Decision tree learning; Mathematical optimization; Tree structure; Search algorithm; Combinatorics; Binary tree","score_opus":0.08163294719885679,"score_gpt":0.31706551243419345,"score_spread":0.23543256523533668,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2998503844","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":[0.48253635,0.000030238623,0.5024101,0.008624053,0.00024340421,0.00034867003,0.000010442095,0.00012929644,0.0056674685],"genre_scores_gemma":[0.9856229,0.000016934591,0.014125351,0.00015875573,0.000037051057,0.000008026858,6.8126775e-7,0.000007330511,0.000023014418],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980707,0.000021770284,0.00059956824,0.00048660886,0.0005968879,0.00022443236],"domain_scores_gemma":[0.9982841,0.0002065254,0.00051128195,0.00033848043,0.0005454806,0.0001141246],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003998864,0.00018120554,0.0002623382,0.00009416018,0.00011720486,0.00013275382,0.0023435785,0.00007146547,0.00005082191],"category_scores_gemma":[0.001669609,0.00013100571,0.00010610134,0.000828559,0.00021320328,0.0001721267,0.00052210846,0.00028343097,0.00007713691],"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":[0.0000901627,0.00009854845,0.00050693314,0.000035599016,0.000007580137,1.9718523e-7,0.0019055047,0.0040258863,0.06377737,0.7786028,0.00008358368,0.15086585],"study_design_scores_gemma":[0.000030789724,0.00028153125,0.0011471994,0.0001498418,0.000007970924,0.0000010394997,0.00028805397,0.7192427,0.2680939,0.0104806665,0.00012694435,0.00014936448],"about_ca_topic_score_codex":0.000024398327,"about_ca_topic_score_gemma":0.000002458497,"teacher_disagreement_score":0.76812214,"about_ca_system_score_codex":0.000017573619,"about_ca_system_score_gemma":0.00009463113,"threshold_uncertainty_score":0.53422576},"labels":[],"label_agreement":null},{"id":"W3003316882","doi":"10.1007/s11704-019-8390-z","title":"A revisit to MacKay algorithm and its application to deep network compression","year":2020,"lang":"en","type":"article","venue":"Frontiers of Computer Science","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":5,"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":"Computer science; Hyperparameter; Pruning; Algorithm; Heuristic; Artificial neural network; Residual; Artificial intelligence; Machine learning; Relevance (law); Simple (philosophy); Convolutional neural network; Deep neural networks; Deep learning","score_opus":0.009270603287504127,"score_gpt":0.24131028518357978,"score_spread":0.23203968189607566,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3003316882","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":[0.001261848,0.00032789065,0.98987865,0.0076721846,0.00033995725,0.0003321269,0.0000023970608,0.000106346,0.00007859553],"genre_scores_gemma":[0.17509593,0.000011039407,0.82237685,0.0023123238,0.00017518985,0.000011396204,0.0000031898528,0.0000048721986,0.000009221348],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998267,0.000053599502,0.00023913015,0.00071581616,0.0004446349,0.00027979977],"domain_scores_gemma":[0.99875474,0.00002727617,0.00011932801,0.00049942144,0.00016437899,0.000434838],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004916247,0.00012159292,0.000196494,0.00012347172,0.00020366188,0.0001790799,0.0016406828,0.000029390894,9.453084e-7],"category_scores_gemma":[0.00005563686,0.000114258655,0.000023477443,0.0015508628,0.00005803295,0.0005413736,0.00097036577,0.00010088025,0.000035674697],"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":[0.000007690495,0.00001557882,0.0007336389,0.000015338679,0.000003375905,9.615387e-7,0.0010154431,0.014071554,0.0016098849,0.0045110844,0.013815849,0.9641996],"study_design_scores_gemma":[0.00009413479,0.00014415415,0.009770975,0.000022418677,0.0000024023846,0.0000023428336,0.0000051922734,0.9635046,0.0006115043,0.00016305242,0.025544303,0.00013489835],"about_ca_topic_score_codex":0.000006158426,"about_ca_topic_score_gemma":3.4977325e-7,"teacher_disagreement_score":0.9640647,"about_ca_system_score_codex":0.000023027953,"about_ca_system_score_gemma":0.00004921517,"threshold_uncertainty_score":0.46593326},"labels":[],"label_agreement":null},{"id":"W3006265316","doi":"10.1109/mis.2020.2973255","title":"Asymptotic Meta Learning for Cross Validation of Models for Financial Data","year":2020,"lang":"en","type":"article","venue":"IEEE Intelligent Systems","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"Air Force Office of Scientific Research; National Natural Science Foundation of China; National Science Foundation","keywords":"Computer science; Machine learning; Artificial intelligence; Meta learning (computer science); Cross-validation; Field (mathematics); Online machine learning; Big data; Deep learning; Unsupervised learning; Algorithm; Data mining; Mathematics","score_opus":0.23586777478734555,"score_gpt":0.3570641386205989,"score_spread":0.12119636383325333,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3006265316","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":[0.001715732,0.00029012715,0.99580616,0.0004454465,0.00072897243,0.00072317786,0.000105436324,0.00011178333,0.0000731905],"genre_scores_gemma":[0.9881848,0.0000149656835,0.010693962,0.000060064813,0.00030115832,0.00013317303,0.00034943735,0.000015745149,0.00024671308],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984028,0.00011254088,0.00052078936,0.0005373453,0.00023661648,0.00018994509],"domain_scores_gemma":[0.9982563,0.00036558992,0.00036389692,0.00070920854,0.00022942845,0.0000755387],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009790357,0.00013212599,0.0003133171,0.000054937904,0.0001237545,0.00020334341,0.0013075991,0.00007188235,0.0000020396992],"category_scores_gemma":[0.0007280242,0.00011784363,0.00011163567,0.00017859324,0.00002118004,0.00063311873,0.00012601588,0.00010455041,0.000014467752],"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":[0.000060666873,0.000057492194,0.00030232416,0.0007776966,0.0001967087,4.174144e-7,0.0011583971,0.92686415,0.001745614,0.05586819,0.0037267657,0.009241561],"study_design_scores_gemma":[0.00015632052,0.00014392393,0.000014335501,0.000022056494,0.00007709594,0.0000014316378,0.000022408927,0.9651816,0.006438878,0.0004719196,0.027349997,0.00012005635],"about_ca_topic_score_codex":0.000066930515,"about_ca_topic_score_gemma":0.0000014909944,"teacher_disagreement_score":0.98646903,"about_ca_system_score_codex":0.000019964398,"about_ca_system_score_gemma":0.00008000112,"threshold_uncertainty_score":0.48055238},"labels":[],"label_agreement":null},{"id":"W3006406045","doi":"10.1609/aaai.v35i5.16512","title":"Parameterizing Branch-and-Bound Search Trees to Learn Branching Policies","year":2021,"lang":"en","type":"preprint","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":23,"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 Montréal; Polytechnique Montréal","funders":"Institut de Valorisation des Données; Compute Canada; Canadian Institute for Advanced Research","keywords":"Branching (polymer chemistry); Branch and bound; Generalization; Computer science; Tree (set theory); Benchmark (surveying); Search tree; Integer programming; Mathematical optimization; Theoretical computer science; Artificial intelligence; Search algorithm; Mathematics; Algorithm; Combinatorics","score_opus":0.11579523998778825,"score_gpt":0.3423432507773105,"score_spread":0.22654801078952225,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3006406045","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":[0.8833695,0.000116787756,0.09436721,0.016943075,0.0006657866,0.0005915137,0.0000132463865,0.00018367266,0.003749183],"genre_scores_gemma":[0.99096596,0.00013797205,0.008030923,0.00040949965,0.00012432785,0.000040944742,0.000004666215,0.000022892584,0.00026282846],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9969807,0.00008043748,0.0006768173,0.0010884866,0.0007092045,0.00046435677],"domain_scores_gemma":[0.99784654,0.00019749568,0.0004286264,0.00073728495,0.0006187272,0.00017130778],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0009793458,0.00038540206,0.0004983865,0.0002906524,0.00036424334,0.0021097134,0.002869545,0.00020855623,0.000024015211],"category_scores_gemma":[0.0010435834,0.00031883587,0.00015957953,0.0006479735,0.00025145715,0.0003994556,0.0032592232,0.0012007222,0.000036649097],"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":[0.000047292953,0.00010330943,0.0013136921,0.0003101681,0.000046909565,8.36729e-7,0.012780907,0.0009581202,0.12815093,0.4856405,0.00006086058,0.37058648],"study_design_scores_gemma":[0.00006533174,0.0004218067,0.014182754,0.0034575735,0.000063859974,0.000025780257,0.003424157,0.24245746,0.6094867,0.12444105,0.0005636814,0.0014098338],"about_ca_topic_score_codex":0.0006800983,"about_ca_topic_score_gemma":0.00009902393,"teacher_disagreement_score":0.4813358,"about_ca_system_score_codex":0.00006378072,"about_ca_system_score_gemma":0.00022612803,"threshold_uncertainty_score":0.9999264},"labels":[],"label_agreement":null},{"id":"W301125580","doi":"10.1007/978-3-642-40261-6_44","title":"On Achieving Near-Optimal “Anti-Bayesian” Order Statistics-Based Classification for Asymmetric Exponential Distributions","year":2013,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Machine Learning and Data Classification","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":"Carleton University","funders":"","keywords":"Exponential family; Order statistic; Bayesian probability; Natural exponential family; Computer science; Exponential function; Exponential distribution; Beta distribution; Bayes' theorem; Gamma distribution; Probability distribution; Bayesian statistics; Statistics; Mathematics; Applied mathematics; Bayesian inference; Mathematical analysis","score_opus":0.019986934837925505,"score_gpt":0.27215613209919676,"score_spread":0.25216919726127124,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W301125580","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":[0.00006063108,0.00006279632,0.9950809,0.0018178247,0.0011869064,0.0007907397,0.00017616105,0.0002138987,0.0006101438],"genre_scores_gemma":[0.17810418,0.0000087760145,0.82021433,0.0005083928,0.00026781432,0.000071976974,0.0005716749,0.00004004165,0.00021284334],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99593467,0.000079298574,0.0006452522,0.0017208069,0.0009399915,0.00068000075],"domain_scores_gemma":[0.9954297,0.0016222877,0.0005491291,0.0016192596,0.0005749831,0.00020463046],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0008946581,0.0005327014,0.00046380304,0.0008959722,0.0007927322,0.0014572394,0.002362821,0.00033428925,0.00004784334],"category_scores_gemma":[0.0009034405,0.0005012106,0.00012257803,0.0010544831,0.0005138483,0.0005312381,0.0003615258,0.0008502058,0.00013568382],"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":[0.000012774321,0.00009485764,0.000059292128,0.000057451125,0.000011540191,0.0000053402523,0.000075709635,0.0647737,0.00013952676,0.22550741,0.00047805085,0.70878434],"study_design_scores_gemma":[0.00038943588,0.0002704615,0.0015820534,0.00014392736,0.000016169728,0.00000635926,1.0050203e-7,0.9746237,0.00016046528,0.018533483,0.0037273723,0.00054651697],"about_ca_topic_score_codex":0.000032710275,"about_ca_topic_score_gemma":0.000014036918,"teacher_disagreement_score":0.90984994,"about_ca_system_score_codex":0.0003648689,"about_ca_system_score_gemma":0.0008364143,"threshold_uncertainty_score":0.99974394},"labels":[],"label_agreement":null},{"id":"W3015276915","doi":"10.1145/3318464.3389696","title":"Complaint-driven Training Data Debugging for Query 2.0","year":2020,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Innovative Research Group Project of the National Natural Science Foundation of China","keywords":"Debugging; Retraining; Heuristic; Set (abstract data type); Training set; Inference; Training (meteorology)","score_opus":0.32643656262678244,"score_gpt":0.34280366940857515,"score_spread":0.016367106781792706,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3015276915","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":[0.00015121535,0.000017995866,0.9696946,0.025804523,0.00007595222,0.0001022228,0.000019756131,0.00043202305,0.0037016773],"genre_scores_gemma":[0.54600984,0.000002002586,0.45070356,0.0027786223,0.00013000774,0.0000067485876,0.0002846212,0.0000064123155,0.000078192585],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99915785,0.00003457201,0.00013539524,0.00041311904,0.00010356047,0.00015549362],"domain_scores_gemma":[0.99900717,0.00016646704,0.000051853076,0.00065871095,0.000023139228,0.00009268517],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021573625,0.00006800532,0.00009485736,0.000024134999,0.0001251468,0.00014939667,0.0014333244,0.000021532951,0.00001674968],"category_scores_gemma":[0.000257357,0.000060853472,0.000019784791,0.00013084561,0.000012740758,0.00052324345,0.00040558967,0.00008553544,0.00004843379],"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":[0.000010987707,0.000024673285,0.0010787838,0.000051571384,0.00002783731,0.000004187794,0.002908063,0.0007345667,0.001801647,0.32021144,0.061076898,0.61206937],"study_design_scores_gemma":[0.0001374561,0.000024552557,0.00049801875,0.000004413781,0.0000028954776,0.0000027221222,0.00006197289,0.85041684,0.000028365168,0.00022444632,0.14852145,0.00007686062],"about_ca_topic_score_codex":0.000018545903,"about_ca_topic_score_gemma":0.000011138601,"teacher_disagreement_score":0.8496823,"about_ca_system_score_codex":0.000006440299,"about_ca_system_score_gemma":0.00004714385,"threshold_uncertainty_score":0.2663497},"labels":[],"label_agreement":null},{"id":"W3015333924","doi":"10.1145/3377930.3390226","title":"GeneCAI","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Army Research Office; Canadian Institute for Advanced Research; National Science Foundation","keywords":"Computer science; Hyperparameter; Scalability; Pareto principle; Artificial intelligence; Multi-objective optimization; Machine learning; Mathematical optimization","score_opus":0.050573533228502145,"score_gpt":0.2905393398512218,"score_spread":0.23996580662271969,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3015333924","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":[0.00010752467,0.00006584167,0.9215241,0.023423223,0.00038658603,0.00006389477,0.0000028862175,0.0005799741,0.05384598],"genre_scores_gemma":[0.48729742,0.000060479877,0.5064832,0.0029362764,0.00033886073,0.000026449834,0.00018483095,0.000013391455,0.0026591225],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99912447,0.000046670233,0.000119439974,0.00047180342,0.0001483033,0.00008933834],"domain_scores_gemma":[0.9989134,0.0000209849,0.00007300793,0.0008966666,0.000025946656,0.00007000733],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000099151395,0.00009800446,0.00010401093,0.00003593293,0.000032351752,0.00024599457,0.0013075547,0.00008529923,0.000045610373],"category_scores_gemma":[0.000054415472,0.0000862903,0.00004587836,0.0000822869,0.000007461206,0.00007207036,0.0019155585,0.0003764047,0.00060637813],"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":[0.00000116582,0.000025662144,0.00051474746,0.00007846603,0.000021378497,0.000009822164,0.0003159064,0.00043198356,0.0003757293,0.7056376,0.06029754,0.23229003],"study_design_scores_gemma":[0.00007467955,0.000019021943,0.011202757,0.000015396714,0.0000055628448,0.0000032282544,0.0000038446487,0.67516965,0.00023611613,0.03790993,0.27505592,0.00030388692],"about_ca_topic_score_codex":0.000055575263,"about_ca_topic_score_gemma":0.0000032451578,"teacher_disagreement_score":0.6747377,"about_ca_system_score_codex":0.000013331481,"about_ca_system_score_gemma":0.00008097908,"threshold_uncertainty_score":0.77939665},"labels":[],"label_agreement":null},{"id":"W3022874458","doi":"10.21105/joss.01958","title":"LFSpy: A Python Implementation of Local Feature Selection for Data Classification with scikit-learn Compatibility","year":2020,"lang":"en","type":"article","venue":"The Journal of Open Source Software","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Vector Institute","funders":"Canarie","keywords":"Python (programming language); Compatibility (geochemistry); Computer science; Feature selection; Open source; Software; Artificial intelligence; Programming language; Engineering","score_opus":0.08536450931383907,"score_gpt":0.36319397274698895,"score_spread":0.27782946343314985,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3022874458","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":[0.023128781,0.000049233877,0.9657933,0.010471661,0.000039611285,0.00043796684,0.000029242645,0.00003577029,0.000014404604],"genre_scores_gemma":[0.8919471,0.000007978349,0.10748453,0.00030060377,0.00008695933,0.0000042230395,0.00012493008,0.000013852203,0.000029849403],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998496,0.00034356717,0.00039511282,0.00025123756,0.00037952128,0.00013455372],"domain_scores_gemma":[0.9975451,0.00029578613,0.0009965041,0.0006423161,0.00043475593,0.00008549276],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018630256,0.00011155206,0.00022731215,0.000050115497,0.00022662783,0.00020604234,0.0026041802,0.00004288152,0.000012716867],"category_scores_gemma":[0.00023926044,0.00007137733,0.000036701447,0.0004634598,0.000070519796,0.0011874348,0.00042483272,0.00030623836,0.0000023765874],"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":[0.0013489177,0.00018136922,0.083451234,0.00022182644,0.00017213797,8.3590567e-7,0.0086607775,0.006786285,0.0021629904,0.0013525332,0.028177556,0.86748356],"study_design_scores_gemma":[0.0040893257,0.003021841,0.23474261,0.00018063544,0.00030832252,0.00016681667,0.010023231,0.66947395,0.0028118095,0.00063351967,0.074104235,0.00044373045],"about_ca_topic_score_codex":0.0001901469,"about_ca_topic_score_gemma":0.0001047224,"teacher_disagreement_score":0.8688183,"about_ca_system_score_codex":0.000046698733,"about_ca_system_score_gemma":0.00026607016,"threshold_uncertainty_score":0.4839258},"labels":[],"label_agreement":null},{"id":"W3032150799","doi":"10.1109/jproc.2020.2989782","title":"Towards Robust Pattern Recognition: A Review","year":2020,"lang":"en","type":"review","venue":"Proceedings of the IEEE","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":153,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Chinese Academy of Sciences; National Natural Science Foundation of China; China Association for Science and Technology","keywords":"Computer science; Robustness (evolution); Artificial intelligence; Perspective (graphical); Machine learning; Pattern recognition (psychology)","score_opus":0.09618442242372488,"score_gpt":0.3118657382337085,"score_spread":0.21568131580998362,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3032150799","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":[7.378881e-8,0.9893895,0.0024684512,0.0031922706,0.00036937423,0.00057070266,0.000025555219,0.000118200354,0.003865883],"genre_scores_gemma":[0.0000012805484,0.9956076,0.0033912337,0.0005205276,0.00022505346,0.00009060289,0.0000150634505,0.000022043396,0.00012655147],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99830896,0.000035866626,0.00058038806,0.00051036605,0.00039346336,0.00017095736],"domain_scores_gemma":[0.99829435,0.00004320944,0.0010184463,0.00036825478,0.00020243644,0.00007330052],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004984498,0.00027871548,0.0009684623,0.0000617146,0.00007936275,0.000118208714,0.002726281,0.00011608322,0.000018892802],"category_scores_gemma":[0.00036121768,0.00017450486,0.00042556852,0.0008230212,0.000036255296,0.00026567865,0.00043103637,0.0005334901,0.00015800275],"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":[1.7478685e-7,0.0000102714275,8.1261106e-7,0.047518343,0.000022176102,2.99565e-7,0.000020243904,1.9140007e-8,2.6743047e-7,0.000119909666,0.017760523,0.93454695],"study_design_scores_gemma":[0.000031465665,0.00002064963,0.0000020685384,0.055545382,0.00024325988,0.00005109117,0.0000012137929,0.00014636791,0.000004226818,0.00012560628,0.94364035,0.00018832606],"about_ca_topic_score_codex":0.000009671883,"about_ca_topic_score_gemma":2.5005124e-7,"teacher_disagreement_score":0.93435866,"about_ca_system_score_codex":0.000047326143,"about_ca_system_score_gemma":0.00015483683,"threshold_uncertainty_score":0.7116102},"labels":[],"label_agreement":null},{"id":"W3033862284","doi":"10.1109/icmla51294.2020.00180","title":"Learning across label confidence distributions using Filtered Transfer Learning","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; Princess Margaret Cancer Centre; University of Toronto; University Health Network","funders":"Mitacs","keywords":"Transfer of learning; Computer science; Machine learning; Artificial intelligence; Task (project management); Artificial neural network; Deep learning; Retraining; Range (aeronautics); Low Confidence; Meta learning (computer science)","score_opus":0.08604629868095026,"score_gpt":0.3459375196527729,"score_spread":0.25989122097182266,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3033862284","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":[0.02604179,0.00010751879,0.9672968,0.003626567,0.0004079222,0.00023812217,0.00006426658,0.0011645906,0.0010524272],"genre_scores_gemma":[0.95394725,0.000071275615,0.043901138,0.0001949707,0.00016471648,0.000029077304,0.0007727316,0.000031921656,0.00088691403],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9966092,0.0005022586,0.000548465,0.0013006548,0.00047642415,0.0005630075],"domain_scores_gemma":[0.9982485,0.00021879301,0.00020636774,0.0008898737,0.00019934848,0.00023712571],"candidate_categories":["metaepi_narrow","scholarly_communication","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.00065833825,0.00041037044,0.00044850702,0.00007543872,0.00080242474,0.0011913828,0.0017165712,0.0003182156,0.00008207765],"category_scores_gemma":[0.00062566047,0.00041834524,0.00016237937,0.00044131977,0.00009906638,0.0004422611,0.001753222,0.0029966314,0.0001493827],"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":[0.000087952794,0.000477319,0.01439377,0.0013316338,0.00049053936,0.00017848314,0.02247365,0.2947109,0.053546127,0.4139281,0.0019515989,0.19642995],"study_design_scores_gemma":[0.00032816973,0.000080192505,0.002227233,0.0001514837,0.000027210768,0.000019457513,0.00021109202,0.9802923,0.00074105465,0.0014315048,0.013906955,0.00058331137],"about_ca_topic_score_codex":0.00066107285,"about_ca_topic_score_gemma":0.000029028855,"teacher_disagreement_score":0.92790544,"about_ca_system_score_codex":0.00011787506,"about_ca_system_score_gemma":0.00026141683,"threshold_uncertainty_score":0.9998455},"labels":[],"label_agreement":null},{"id":"W3034361442","doi":"10.1145/3397271.3401395","title":"A Lightweight Environment for Learning Experimental IR Research Practices","year":2020,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Session (web analytics); Cloud computing; Context (archaeology); Data science; Open source; World Wide Web; Software; Programming language","score_opus":0.18844678400354692,"score_gpt":0.4048209110683452,"score_spread":0.2163741270647983,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3034361442","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":[0.0072078034,0.00030576563,0.9292529,0.04918952,0.00006462609,0.00036354695,0.0000010253785,0.000289883,0.013324925],"genre_scores_gemma":[0.87986606,0.000024162624,0.117407404,0.00042875402,0.00016397427,0.00008957462,0.000017406943,0.000009059227,0.001993592],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987274,0.00020058286,0.0001231369,0.00042235578,0.00031817507,0.00020834606],"domain_scores_gemma":[0.9991765,0.000313568,0.0001116389,0.00025748555,0.000024758887,0.000116051],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006358697,0.00006886322,0.0000709304,0.00004243099,0.00028249228,0.00021856786,0.0005468785,0.00003243778,0.00011198641],"category_scores_gemma":[0.00043780592,0.0000576464,0.000028602059,0.00014374482,0.000026728301,0.0004615296,0.00027632288,0.0002482687,0.0004027469],"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":[0.00017161209,0.0006816334,0.005408492,0.00010683943,0.000064735184,0.000015307163,0.017646963,0.0008204939,0.26289582,0.5173988,0.060444158,0.13434519],"study_design_scores_gemma":[0.00021383914,0.0003918086,0.00041757245,0.0000025484771,0.0000013278711,0.0000016837197,0.00043855744,0.22249469,0.016491985,0.00009584745,0.75935763,0.00009253318],"about_ca_topic_score_codex":0.000020328598,"about_ca_topic_score_gemma":4.641893e-7,"teacher_disagreement_score":0.87265825,"about_ca_system_score_codex":0.000028697019,"about_ca_system_score_gemma":0.000028048558,"threshold_uncertainty_score":0.51766306},"labels":[],"label_agreement":null},{"id":"W3035888673","doi":"10.23919/date48585.2020.9116535","title":"Probabilistic Sequential Multi-Objective Optimization of Convolutional Neural Networks","year":2020,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; MNIST database; Hyperparameter; Probabilistic logic; Convolutional neural network; Pareto principle; Multi-objective optimization; Speedup; Inference; Parameterized complexity; Artificial intelligence; Machine learning; Bayesian optimization; Mathematical optimization; Artificial neural network; Algorithm; Mathematics","score_opus":0.03493261542718523,"score_gpt":0.2640941623591727,"score_spread":0.22916154693198748,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3035888673","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":[0.0004219268,0.000019342637,0.9972226,0.0014743932,0.00010175576,0.00011435365,0.0000031467612,0.00018151972,0.00046097604],"genre_scores_gemma":[0.8846849,0.0000017091261,0.114913546,0.0002482057,0.00005585622,0.000005388993,0.000050693267,0.0000033572385,0.00003634255],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992874,0.000086149346,0.00016537905,0.00023677247,0.0001291368,0.000095119205],"domain_scores_gemma":[0.9995323,0.000049872488,0.00009336309,0.0001598287,0.00010538342,0.000059267953],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009378235,0.0000643998,0.000083369705,0.00002356818,0.000050358223,0.000037389247,0.0002766481,0.000033801087,0.000044417764],"category_scores_gemma":[0.00016170337,0.000057646215,0.000029578598,0.00024023552,0.00004002868,0.00024669094,0.00010361835,0.000096382464,0.000006102792],"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":[0.0000072984526,0.000026430283,0.0006765501,0.000007314533,0.0000052533096,4.333927e-7,0.0001278764,0.9710653,0.0000545464,0.025982095,0.00018400096,0.0018629467],"study_design_scores_gemma":[0.00022708677,0.00005301798,0.0036790103,0.000002029835,0.000003728187,0.0000018652869,0.0000070623005,0.9958297,0.00002493279,0.00005365081,0.000055846678,0.00006209339],"about_ca_topic_score_codex":0.000031549112,"about_ca_topic_score_gemma":0.000002895186,"teacher_disagreement_score":0.884263,"about_ca_system_score_codex":0.00001538303,"about_ca_system_score_gemma":0.000037105918,"threshold_uncertainty_score":0.23507445},"labels":[],"label_agreement":null},{"id":"W3037881973","doi":"","title":"RelatIF: Identifying Explanatory Training Samples via Relative Influence","year":2020,"lang":"en","type":"article","venue":"International Conference on Artificial Intelligence and Statistics","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; University of Waterloo","funders":"","keywords":"Outlier; Computer science; Machine learning; Constraint (computer-aided design); Class (philosophy); Training (meteorology); Artificial intelligence; Econometrics; Mathematics; Geography","score_opus":0.26809332033682753,"score_gpt":0.37037197020667495,"score_spread":0.10227864986984742,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3037881973","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":[0.0015130219,0.000020951868,0.9887015,0.005533937,0.00026366196,0.00009048685,0.000086158056,0.00010817424,0.0036821077],"genre_scores_gemma":[0.91463965,0.00009388525,0.08412224,0.00091293064,0.000081625796,0.000009782701,0.00006909127,0.000008229452,0.00006256165],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99834144,0.000121400335,0.00043246002,0.00049733766,0.00041423657,0.00019309539],"domain_scores_gemma":[0.9986769,0.0005056251,0.0002027601,0.00020423764,0.00024831027,0.00016214182],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029287863,0.00016671559,0.00015834084,0.000108559034,0.0001913696,0.0004154711,0.0006455621,0.00006494222,0.00012305376],"category_scores_gemma":[0.0012158168,0.00016786937,0.000026570044,0.00018037316,0.00013132041,0.0007023285,0.00013805793,0.00034874797,0.00023935531],"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":[0.000021132802,0.000014494864,0.00015173957,0.000005881813,0.000014455785,0.000012858936,0.0033998194,0.00030506286,0.001048617,0.7731393,0.000055105058,0.22183156],"study_design_scores_gemma":[0.00003577042,0.00014026412,0.0017606427,0.000052103784,0.0000071664394,0.000009859763,0.00097388966,0.659647,0.0007052916,0.3350254,0.0014009251,0.00024169695],"about_ca_topic_score_codex":0.000053613927,"about_ca_topic_score_gemma":0.00002924796,"teacher_disagreement_score":0.91312665,"about_ca_system_score_codex":0.0000308419,"about_ca_system_score_gemma":0.0000846248,"threshold_uncertainty_score":0.6845514},"labels":[],"label_agreement":null},{"id":"W3037950864","doi":"","title":"Maxout Networks","year":2013,"lang":"en","type":"preprint","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":451,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"MNIST database; Dropout (neural networks); Leverage (statistics); Computer science; Benchmark (surveying); Artificial intelligence; Machine learning; Set (abstract data type); Simple (philosophy); Deep learning","score_opus":0.020431643763492435,"score_gpt":0.25699749816475026,"score_spread":0.23656585440125782,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3037950864","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":[0.00024592725,0.0001418518,0.953654,0.0025675718,0.00082411355,0.00012709988,8.5788326e-7,0.00051810703,0.04192049],"genre_scores_gemma":[0.691803,0.00017875295,0.28292778,0.0014740309,0.00057762046,0.00012150821,0.0002624416,0.00002305137,0.022631872],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989518,0.00006878027,0.00016882466,0.0004926275,0.00014899678,0.00016897684],"domain_scores_gemma":[0.99828863,0.000041022464,0.000116197276,0.0014307093,0.000051724226,0.00007171222],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019443319,0.00013903518,0.00013185097,0.000059747203,0.000049997216,0.00050849275,0.0014724776,0.0001816316,0.00016213977],"category_scores_gemma":[0.000029098319,0.00011444015,0.000053645937,0.000077955636,0.00001415734,0.00014765296,0.0018677617,0.0005736002,0.0007250243],"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":[6.3304014e-7,0.000035526187,0.0013796389,0.00003577211,0.000021337355,0.0000025891993,0.00009499935,0.015425619,0.0000067300784,0.46736902,0.074811526,0.4408166],"study_design_scores_gemma":[0.000032719836,0.000005806632,0.00805417,0.000014511503,0.0000023693433,0.0000018859045,0.0000014763407,0.94217014,0.0000036125957,0.0061703837,0.043386076,0.00015686032],"about_ca_topic_score_codex":0.00025657966,"about_ca_topic_score_gemma":0.000004806216,"teacher_disagreement_score":0.9267445,"about_ca_system_score_codex":0.000020115185,"about_ca_system_score_gemma":0.00004381678,"threshold_uncertainty_score":0.93189627},"labels":[],"label_agreement":null},{"id":"W3040388267","doi":"10.1145/3377930.3390210","title":"Advanced statistical analysis of empirical performance scaling","year":2020,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","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":"University of British Columbia","funders":"","keywords":"Scaling; Computer science; Heuristic; Range (aeronautics); Polynomial; Time complexity; Algorithm; Solver; Degree (music); Bounded function; Theoretical computer science; Artificial intelligence; Mathematics","score_opus":0.03903037565258369,"score_gpt":0.3306267773805176,"score_spread":0.2915964017279339,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3040388267","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":[0.09407853,0.000008136489,0.90130424,0.0025207386,0.000015109467,0.000021274307,0.0000040932578,0.00007682079,0.0019710795],"genre_scores_gemma":[0.8641996,0.000004704939,0.13526793,0.00047139468,0.000008272156,0.0000011268263,0.000023201801,0.0000015344747,0.000022288881],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99931604,0.000037929705,0.00017316078,0.000216049,0.00016855486,0.00008824697],"domain_scores_gemma":[0.9994979,0.00010390511,0.000052849107,0.000230977,0.00003590126,0.0000785055],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011195577,0.00004763927,0.0001367187,0.00006717147,0.000032299697,0.000024714323,0.0003155728,0.000017854652,0.000071974035],"category_scores_gemma":[0.00014305476,0.000038930342,0.00003291153,0.0009531888,0.000020012296,0.00016646448,0.00008521941,0.00007343631,0.000028998073],"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":[0.000033607477,0.00008539119,0.29419538,0.00005610982,0.00021417157,0.0000028565105,0.0014636277,0.02807541,0.0018200844,0.096380495,0.0012682658,0.5764046],"study_design_scores_gemma":[0.00005654749,0.000035067984,0.20287973,0.0000010512957,0.000027357093,1.4907651e-7,0.000012574783,0.79521203,0.00023010423,0.000015568241,0.0014886868,0.000041107694],"about_ca_topic_score_codex":0.000005764491,"about_ca_topic_score_gemma":9.742932e-7,"teacher_disagreement_score":0.77012104,"about_ca_system_score_codex":0.000005468001,"about_ca_system_score_gemma":0.000019291456,"threshold_uncertainty_score":0.15875334},"labels":[],"label_agreement":null},{"id":"W3045004532","doi":"10.1016/j.neucom.2020.07.061","title":"On hyperparameter optimization of machine learning algorithms: Theory and practice","year":2020,"lang":"en","type":"article","venue":"Neurocomputing","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":3145,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Hyperparameter; Computer science; Machine learning; Algorithm; Artificial intelligence; Optimization algorithm; Mathematical optimization; Mathematics","score_opus":0.024198532046667116,"score_gpt":0.2728189988463539,"score_spread":0.2486204667996868,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3045004532","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":[0.005179388,0.00006481799,0.9899376,0.0028784862,0.00005346368,0.00008036472,6.9986544e-7,0.00016532079,0.0016398577],"genre_scores_gemma":[0.77294767,0.000017896979,0.22480716,0.0021448308,0.00005017155,0.0000013167278,0.0000068831678,0.000010896336,0.000013194336],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985576,0.000627737,0.00018740943,0.00034261166,0.0001713379,0.00011327907],"domain_scores_gemma":[0.9975276,0.0019762258,0.00020492944,0.00017392116,0.00005341085,0.00006390102],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00064684823,0.00009394666,0.000115323906,0.00005149522,0.00011381016,0.000085244086,0.00024974422,0.00002957093,0.000004107045],"category_scores_gemma":[0.003425969,0.000087740395,0.000021484264,0.00024017628,0.000022680984,0.0002721931,0.00019155808,0.00027824845,0.000007518759],"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":[0.00009135167,0.00006156471,0.0004458441,0.000046445268,0.000014876134,0.000010385819,0.0018677652,0.5596306,0.0013253344,0.059434064,0.00005476355,0.377017],"study_design_scores_gemma":[0.00019619681,0.00022181193,0.0003597135,0.000012719192,0.000006404682,0.00002053635,0.000028666718,0.99680376,0.000175954,0.00014084912,0.0019543774,0.000079014644],"about_ca_topic_score_codex":0.0000056174463,"about_ca_topic_score_gemma":3.489929e-8,"teacher_disagreement_score":0.76776826,"about_ca_system_score_codex":0.0000047037593,"about_ca_system_score_gemma":0.000012187355,"threshold_uncertainty_score":0.41014522},"labels":[],"label_agreement":null},{"id":"W3046421115","doi":"10.1145/3377929.3389999","title":"Combining sequential model-based algorithm configuration with default-guided probabilistic sampling","year":2020,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","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":"University of British Columbia","funders":"","keywords":"Computer science; Configurator; Probabilistic logic; Range (aeronautics); Algorithm; Machine learning; State (computer science); Bayesian probability; Artificial intelligence; Data mining; Engineering","score_opus":0.07335969130006187,"score_gpt":0.2974487569523458,"score_spread":0.22408906565228393,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3046421115","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":[0.000780954,0.0000068099384,0.9917256,0.0044728247,0.00004210839,0.00018751578,0.0000039721426,0.00047487213,0.0023052937],"genre_scores_gemma":[0.51795727,3.6887468e-7,0.48090202,0.00094934186,0.000031836098,0.000014794693,0.00009889783,0.000007828888,0.00003764205],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988414,0.00006743433,0.00021748553,0.00043317964,0.0002647249,0.00017578447],"domain_scores_gemma":[0.9992436,0.000068407884,0.00010699385,0.00033363304,0.00012335926,0.00012396084],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018191,0.00012642477,0.00012526065,0.000040229515,0.00015174758,0.00026081383,0.00040253098,0.00004186408,0.000015214885],"category_scores_gemma":[0.0000932626,0.00010292915,0.00002624285,0.0002693092,0.000032999054,0.0003437141,0.000053565895,0.00015618988,0.00004456385],"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":[0.000029634519,0.00009003206,0.00023823947,0.00007609744,0.000023166947,0.0000081131375,0.0010787428,0.65934455,0.005693383,0.15359215,0.00071843056,0.17910747],"study_design_scores_gemma":[0.0004789947,0.00010355078,0.000109739725,0.0000128256015,0.00000821032,0.0000037453958,0.000015061709,0.9970753,0.00091964373,0.0005357157,0.000581546,0.00015562434],"about_ca_topic_score_codex":0.00003729149,"about_ca_topic_score_gemma":0.000004488909,"teacher_disagreement_score":0.51717633,"about_ca_system_score_codex":0.000027904229,"about_ca_system_score_gemma":0.00016889512,"threshold_uncertainty_score":0.4197329},"labels":[],"label_agreement":null},{"id":"W3083082685","doi":"10.1109/tvcg.2020.3030380","title":"HyperTendril: Visual Analytics for User-Driven Hyperparameter Optimization of Deep Neural Networks","year":2020,"lang":"en","type":"article","venue":"IEEE Transactions on Visualization and Computer Graphics","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"Korea Electric Power Corporation; National Research Foundation of Korea","keywords":"Hyperparameter; Computer science; Hyperparameter optimization; Visual analytics; Machine learning; Task (project management); Artificial intelligence; Analytics; Set (abstract data type); Artificial neural network; Visualization; Data mining; Support vector machine","score_opus":0.028787277363841214,"score_gpt":0.2790546234670804,"score_spread":0.25026734610323914,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3083082685","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":[0.001370049,0.000024475718,0.99752736,0.00033023386,0.000298004,0.0002533262,0.000009776406,0.00018050104,0.000006249364],"genre_scores_gemma":[0.9689178,0.00009769604,0.02876754,0.0020381834,0.0000780956,0.000018840154,0.00005517573,0.000021508658,0.0000051565635],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99873215,0.00011222434,0.00036269415,0.00041926088,0.00020420269,0.00016944921],"domain_scores_gemma":[0.99910986,0.00016263872,0.00016792343,0.00022912801,0.00019545876,0.00013498045],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008832205,0.0001781715,0.00022945441,0.0002014208,0.00019572489,0.00014427707,0.00027145218,0.000114229595,0.000005147997],"category_scores_gemma":[0.000009091352,0.00017748194,0.00010663565,0.0007461389,0.000058200618,0.00034961948,0.000006939024,0.00015133459,8.5437324e-7],"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":[0.00003838209,0.00013539814,0.00015871125,0.000041448526,0.00004427748,5.1072357e-7,0.00031673344,0.92615527,0.000015204423,0.05235499,0.000060164577,0.020678915],"study_design_scores_gemma":[0.0005479674,0.00051660347,0.00020292512,0.00000996486,0.000044047756,0.0000033206172,0.000013556306,0.99806786,0.00013786813,0.00003509023,0.00023920297,0.00018160683],"about_ca_topic_score_codex":0.0000047137446,"about_ca_topic_score_gemma":0.0000039296065,"teacher_disagreement_score":0.96875983,"about_ca_system_score_codex":0.000009045113,"about_ca_system_score_gemma":0.000014689693,"threshold_uncertainty_score":0.72375035},"labels":[],"label_agreement":null},{"id":"W3083995206","doi":"10.5194/egusphere-egu2020-1963","title":"Entropy Ensemble Filter: Does information content assessment of bootstrapped training datasets before model training lead to better trade-off between ensemble size and predictive performance?","year":2020,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Ensemble learning; Computer science; Ensemble forecasting; Machine learning; Artificial intelligence; Predictive modelling; Training set; Limiting; Artificial neural network; Entropy (arrow of time); Field (mathematics); Data mining; Mathematics; Engineering","score_opus":0.059900413399336674,"score_gpt":0.28116042128592333,"score_spread":0.22126000788658667,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3083995206","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":[0.27383387,0.0000043902983,0.717457,0.007190934,0.000042196094,0.00032627716,0.0003836033,0.00012222066,0.0006395409],"genre_scores_gemma":[0.90869254,0.000009210196,0.08896325,0.001545111,0.000065461565,0.000028679457,0.00066991744,0.000008954402,0.00001688195],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99814373,0.00007822992,0.0005884377,0.0004116046,0.00043770263,0.00034030908],"domain_scores_gemma":[0.9989186,0.0001510058,0.0002472016,0.00039242665,0.00005114679,0.00023964471],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041994985,0.00022507003,0.0003578649,0.00010170496,0.00015612358,0.00018289877,0.00049953966,0.00007971209,0.000010619414],"category_scores_gemma":[0.00011242749,0.00017299117,0.000051452236,0.00021844331,0.000046590292,0.0019638578,0.00020487471,0.00027279064,0.0000051699794],"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":[0.00007451319,0.00005071454,0.018589849,0.0002250231,0.00012587772,0.0000020609882,0.06475595,0.007974408,0.012188513,0.0041123778,0.0014260279,0.8904747],"study_design_scores_gemma":[0.00069875416,0.00052175,0.070089445,0.000047139103,0.000027196536,0.0000030779054,0.0011875493,0.92397845,0.0015084605,0.00012731082,0.0016092719,0.0002016263],"about_ca_topic_score_codex":0.000015725334,"about_ca_topic_score_gemma":0.0000058620376,"teacher_disagreement_score":0.916004,"about_ca_system_score_codex":0.000035470686,"about_ca_system_score_gemma":0.0001160343,"threshold_uncertainty_score":0.70543754},"labels":[],"label_agreement":null},{"id":"W3084274250","doi":"10.3233/aic-200630","title":"Empirical scaling analyzer: An automated system for empirical analysis of performance scaling","year":2020,"lang":"en","type":"article","venue":"AI Communications","topic":"Machine Learning and Data Classification","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":"University of British Columbia","funders":"","keywords":"Computer science; Scaling; Function (biology); Empirical research; Algorithm; Key (lock); Spectrum analyzer; Data mining; Statistics; Mathematics","score_opus":0.1187793596545258,"score_gpt":0.41343810745346654,"score_spread":0.29465874779894075,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3084274250","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":[0.08590584,0.00014159927,0.89712745,0.014973707,0.00003802368,0.00021424206,0.0000451648,0.001110752,0.00044322756],"genre_scores_gemma":[0.9088363,0.000021182126,0.09000828,0.0006433725,0.000021428164,0.000036433863,0.00041895584,0.000009430235,0.0000045987645],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99833256,0.00034675395,0.0005451019,0.00036430053,0.00022174254,0.00018952721],"domain_scores_gemma":[0.9965079,0.00040945702,0.000251466,0.0024010595,0.00026645433,0.0001636654],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000612394,0.00012407682,0.00033754163,0.0002623897,0.00041611437,0.00012775123,0.0024579042,0.00007804103,0.0000033762417],"category_scores_gemma":[0.0002047392,0.000119580494,0.00015509847,0.0025104443,0.00008207529,0.00047292726,0.0004402257,0.00022287024,0.000012370004],"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":[0.000112635506,0.0013176627,0.60180795,0.0006992234,0.0025535112,0.000001798713,0.023682654,0.15995449,0.0049569015,0.08164036,0.004357252,0.118915536],"study_design_scores_gemma":[0.00015264214,0.00005625178,0.055414952,0.00001835554,0.00023934337,0.0000010730167,0.00015398285,0.9388547,0.00010916003,0.000010097971,0.0048677456,0.00012172976],"about_ca_topic_score_codex":0.00003743908,"about_ca_topic_score_gemma":0.000015594664,"teacher_disagreement_score":0.82293046,"about_ca_system_score_codex":0.000047185127,"about_ca_system_score_gemma":0.000093494236,"threshold_uncertainty_score":0.4876351},"labels":[],"label_agreement":null},{"id":"W3088973847","doi":"10.1109/compsac48688.2020.0-221","title":"Evaluation of Parameter Update Effects in Deep Semi-Supervised Learning Algorithms","year":2020,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","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":false,"ca_institutions":"Concordia University","funders":"","keywords":"Machine learning; Artificial intelligence; Computer science; Computation; Classifier (UML); Algorithm; Artificial neural network; Graph; Key (lock); Theoretical computer science","score_opus":0.036394299071345025,"score_gpt":0.2915690500420888,"score_spread":0.25517475097074377,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3088973847","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":[0.070839845,0.000101471116,0.92514884,0.0019701459,0.000060746315,0.0001980841,2.7814363e-7,0.00011406868,0.0015664913],"genre_scores_gemma":[0.94570106,0.0000073318965,0.053863116,0.00035369882,0.000021055346,0.000016541393,0.000018708868,0.0000050649815,0.000013407821],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982818,0.0005749744,0.00020448351,0.0003035401,0.0005069297,0.00012830445],"domain_scores_gemma":[0.99931055,0.00018615268,0.00008085033,0.000248367,0.000114951305,0.00005912075],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013062836,0.00008128501,0.00012898649,0.00007021899,0.000029886445,0.00004933911,0.00035232728,0.000042068743,0.000048374186],"category_scores_gemma":[0.0010880352,0.00007220549,0.000029465496,0.00042904838,0.000012597418,0.00031239426,0.00010883939,0.00018027639,0.000073812385],"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":[0.000004883709,0.00003697215,0.007280017,0.000036969814,0.000010883333,0.00000164794,0.0012246091,0.015787046,0.0022174655,0.0034124556,0.00007430943,0.96991277],"study_design_scores_gemma":[0.0005264494,0.00007209884,0.018059017,0.000010495544,0.000011437372,6.522308e-7,0.000025246223,0.9786672,0.0015934912,0.000552831,0.00039899352,0.00008210503],"about_ca_topic_score_codex":0.000040160496,"about_ca_topic_score_gemma":0.000007364445,"teacher_disagreement_score":0.96983063,"about_ca_system_score_codex":0.000024137133,"about_ca_system_score_gemma":0.000044485332,"threshold_uncertainty_score":0.29444543},"labels":[],"label_agreement":null},{"id":"W3092136498","doi":"10.1109/tpami.2021.3075372","title":"Winning Solutions and Post-Challenge Analyses of the ChaLearn AutoDL Challenge 2019","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Institució Catalana de Recerca i Estudis Avançats; Centre National de la Recherche Scientifique; Chinese Academy of Sciences; CHIST-ERA; Microsoft; Agence Nationale de la Recherche; University of Edinburgh; Institut national de recherche en informatique et en automatique (INRIA); Acadia University; Google Research; Nvidia; Birla Institute of Technology and Science, Pilani; Amazon Catalyst","keywords":"Computer science; Modular design; Benchmark (surveying); Machine learning; Artificial intelligence; Variety (cybernetics); Code (set theory); Modularity (biology); Sorting; Matching (statistics); Component (thermodynamics); Deep learning; Programming language","score_opus":0.0516221799101339,"score_gpt":0.30762450371598676,"score_spread":0.25600232380585286,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3092136498","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":[0.004601324,0.0016756813,0.9872939,0.005949814,0.00012205583,0.00006887716,0.000056860765,0.000050973078,0.00018054406],"genre_scores_gemma":[0.9960251,0.0025908463,0.00081742567,0.00019962525,0.000014269369,0.000008459581,0.000012105366,0.000008430035,0.00032377482],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99832815,0.0002502055,0.00037420008,0.00055010134,0.00028515043,0.0002122184],"domain_scores_gemma":[0.9985687,0.00019140844,0.00017395205,0.0008122793,0.00016073888,0.00009288873],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003136294,0.0001885233,0.00030618493,0.0003091856,0.00038599566,0.000103495484,0.0004044719,0.00007146478,0.000087083514],"category_scores_gemma":[0.000023734992,0.00014297418,0.00023211935,0.0010310784,0.000111415706,0.00022071655,0.000028971346,0.00035705426,0.000008412247],"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":[0.0000065130316,0.000277259,0.0009444014,0.000049418133,0.0007374004,0.000006890977,0.0012954999,0.011654356,0.004028745,0.0016882811,0.000009786698,0.97930145],"study_design_scores_gemma":[0.0003212401,0.0003709068,0.046962194,0.00015651727,0.0018716156,0.000066613706,0.0006662585,0.849168,0.09800527,0.0009075881,0.0007263687,0.0007774362],"about_ca_topic_score_codex":0.00143654,"about_ca_topic_score_gemma":0.0016045285,"teacher_disagreement_score":0.9914237,"about_ca_system_score_codex":0.000016877648,"about_ca_system_score_gemma":0.000043381548,"threshold_uncertainty_score":0.5830318},"labels":[],"label_agreement":null},{"id":"W3092705373","doi":"10.48550/arxiv.2010.09443","title":"Efficient Estimation and Evaluation of Prediction Rules in Semi-Supervised Settings under Stratified Sampling","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Estimator; Leverage (statistics); Computer science; Missing data; Random forest; Data mining; Consistency (knowledge bases); Stratified sampling; Machine learning; Sampling (signal processing); Imputation (statistics); Artificial intelligence; Brier score; Regression; Statistics; Mathematics","score_opus":0.12365368866271075,"score_gpt":0.24692241835275455,"score_spread":0.12326872969004381,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3092705373","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":[0.510419,0.000023389675,0.48886997,0.00018438378,0.00006595253,0.00020601392,0.000018257138,0.000059690537,0.00015333507],"genre_scores_gemma":[0.9929434,0.000019809442,0.006769564,0.000018437848,0.000017123799,0.0000017346424,0.00021484867,0.0000068237096,0.000008244459],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984343,0.00028654686,0.00025227925,0.00071340235,0.00019148808,0.00012196295],"domain_scores_gemma":[0.99889964,0.000111867215,0.00028717672,0.0004702703,0.00016950683,0.00006156793],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009156913,0.00015385685,0.00018791144,0.00022897033,0.00007180317,0.000076798126,0.00037813664,0.00015503106,0.0000056765252],"category_scores_gemma":[0.00014868658,0.00018282603,0.00004150948,0.00035724198,0.000043305397,0.00016341191,0.00039703608,0.00033777833,0.0000049364553],"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":[0.000012100926,0.000037658356,0.002031759,0.000104294,0.000013349428,0.0000011608623,0.00049171626,0.96102476,0.00042180822,0.030268963,0.000006930904,0.005585503],"study_design_scores_gemma":[0.00045282723,0.000022964294,0.052786082,0.00013218106,0.000054944037,7.0734603e-7,0.00012519842,0.92838967,0.00005703766,0.017848866,0.0000035953726,0.00012594121],"about_ca_topic_score_codex":0.000114100636,"about_ca_topic_score_gemma":0.000015795475,"teacher_disagreement_score":0.4825244,"about_ca_system_score_codex":0.00015193001,"about_ca_system_score_gemma":0.0001833363,"threshold_uncertainty_score":0.7455429},"labels":[],"label_agreement":null},{"id":"W3094515489","doi":"10.48550/arxiv.2010.12721","title":"PEP: Parameter Ensembling by Perturbation","year":2020,"lang":"en","type":"preprint","venue":"PubMed","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"National Institute of Biomedical Imaging and Bioengineering","keywords":"Overfitting; MNIST database; Calibration; Computer science; Artificial intelligence; Gaussian; Variance (accounting); Perturbation (astronomy); Mathematics; Set (abstract data type); Statistics; Pattern recognition (psychology); Algorithm; Machine learning; Artificial neural network; Physics","score_opus":0.05086988193139504,"score_gpt":0.24644345442400623,"score_spread":0.19557357249261118,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3094515489","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":[0.003480771,0.000504914,0.96097594,0.02669886,0.0011514591,0.00074895757,0.000032202533,0.0007281754,0.0056787264],"genre_scores_gemma":[0.97965115,0.00007174529,0.015106617,0.001290926,0.0002830653,0.0013592175,0.00054124533,0.000021684507,0.0016743429],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982524,0.00014847849,0.00025423794,0.00076442305,0.00030843267,0.00027203333],"domain_scores_gemma":[0.9985678,0.0001538028,0.00023157912,0.0008425425,0.00005293388,0.00015133219],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037901456,0.00018888296,0.00019493279,0.00008197314,0.00007617888,0.00055917684,0.0010771666,0.00017242973,0.000004682542],"category_scores_gemma":[0.0006916957,0.00018273095,0.00008274756,0.0001632507,0.000019087895,0.00021278881,0.0008498353,0.0006316062,0.000055894983],"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":[0.000006490662,0.000040861294,0.0005217916,0.0000919605,0.00003444073,0.0000035256955,0.0004753495,0.00017115388,0.00005671884,0.0071263225,0.033293277,0.9581781],"study_design_scores_gemma":[0.00043450767,0.000026812639,0.097417034,0.000036899935,0.000050851697,0.0000086949285,0.000017275455,0.58505106,0.0006979097,0.032589305,0.28261492,0.0010547639],"about_ca_topic_score_codex":0.000038199454,"about_ca_topic_score_gemma":9.281708e-7,"teacher_disagreement_score":0.97617036,"about_ca_system_score_codex":0.0000619659,"about_ca_system_score_gemma":0.000038276252,"threshold_uncertainty_score":0.74515516},"labels":[],"label_agreement":null},{"id":"W3098804530","doi":"","title":"Decision trees as partitioning machines to characterize their generalization properties","year":2020,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Moncton; Université Laval","funders":"","keywords":"Generalization; Dimension (graph theory); Pruning; Decision tree; Bounded function; Mathematics; Binary decision diagram; Function (biology); VC dimension; Combinatorics; Binary tree; Integer (computer science); Upper and lower bounds; Discrete mathematics; Tree (set theory); Binary number; Weight-balanced tree; Simple (philosophy); Algorithm; Computer science; Binary search tree; Artificial intelligence; Arithmetic","score_opus":0.045104908451804655,"score_gpt":0.25600826252564246,"score_spread":0.2109033540738378,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3098804530","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":[0.15419555,0.00014405073,0.83654416,0.0070121465,0.00044354392,0.00037022986,0.000008678548,0.00068442035,0.0005972573],"genre_scores_gemma":[0.99454033,0.000006149566,0.0021939913,0.0028298525,0.00017020205,0.00006544662,0.00013129867,0.0000080828495,0.000054667133],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99868506,0.00007846302,0.0005126633,0.00021435102,0.00033230882,0.00017713502],"domain_scores_gemma":[0.99909216,0.000020302274,0.0002964211,0.00022826208,0.00022304563,0.00013980418],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00021689424,0.00015497727,0.00015620618,0.00012211573,0.0003418516,0.0017191351,0.00045730712,0.000051567902,0.0000053038634],"category_scores_gemma":[0.00027290842,0.00011577494,0.000029639106,0.0005381326,0.000012890977,0.005172016,0.00010763393,0.00010989155,0.00021566087],"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":[0.00006743578,0.000022474162,0.0017284733,0.00040055884,0.00000880928,0.0000010798439,0.017937794,0.058976807,0.015798727,0.0056924727,0.0019866268,0.89737874],"study_design_scores_gemma":[0.00014805947,0.00007451476,0.0037490597,0.000118684926,0.0000023034245,0.000016637796,0.00015244308,0.95871115,0.0007084713,0.000023948265,0.03613315,0.00016157143],"about_ca_topic_score_codex":0.000067543086,"about_ca_topic_score_gemma":0.0000025885322,"teacher_disagreement_score":0.8997344,"about_ca_system_score_codex":0.000028521961,"about_ca_system_score_gemma":0.000053211894,"threshold_uncertainty_score":0.99931717},"labels":[],"label_agreement":null},{"id":"W3103390726","doi":"","title":"Learning Discrete Energy-based Models via Auxiliary-variable Local Exploration","year":2020,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Machine Learning and Data Classification","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":"University of Alberta","funders":"","keywords":"Flexibility (engineering); Computer science; Software; Fuzz testing; Autoregressive model; Function (biology); Energy (signal processing); Partition function (quantum field theory); Machine learning; Artificial intelligence; Algorithm; Mathematics; Programming language","score_opus":0.0675045391712458,"score_gpt":0.1742403597032125,"score_spread":0.1067358205319667,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3103390726","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":[0.0017133226,0.000009962202,0.9940276,0.0010512291,0.000056884266,0.000048405414,0.0000019368592,0.00038235378,0.0027082653],"genre_scores_gemma":[0.9930169,0.000011975697,0.0059072883,0.00048103408,0.000040433355,7.163352e-7,0.0000664458,0.000010513281,0.00046472347],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99878883,0.00018410315,0.00012236595,0.0006014322,0.000091425936,0.00021182351],"domain_scores_gemma":[0.9991838,0.000063675776,0.000108730004,0.00039617188,0.00006991089,0.00017772522],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014169184,0.00013789193,0.00012565868,0.00007820834,0.00022722213,0.000091324015,0.0006216684,0.00007229951,0.000025101408],"category_scores_gemma":[0.000034335055,0.00015377313,0.000053816333,0.00079691573,0.000048400227,0.0015455656,0.00016972763,0.00022191713,0.000079350655],"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":[0.000018519775,0.0000137090165,0.00020837033,0.000006838008,0.0000055059395,0.000013793862,0.00010966693,0.6933223,0.0001925979,0.3034391,0.000096857766,0.0025727362],"study_design_scores_gemma":[0.0003470464,0.00010772447,0.000041611776,0.0000081720955,0.0000115579505,6.425132e-7,0.000073776544,0.9833086,0.00021401297,0.011114416,0.0045906743,0.00018175934],"about_ca_topic_score_codex":0.00016062452,"about_ca_topic_score_gemma":0.000009484008,"teacher_disagreement_score":0.99130356,"about_ca_system_score_codex":0.000054122847,"about_ca_system_score_gemma":0.00008452165,"threshold_uncertainty_score":0.62706864},"labels":[],"label_agreement":null},{"id":"W3107092601","doi":"10.1109/access.2020.3041873","title":"DCBT-Net: Training Deep Convolutional Neural Networks With Extremely Noisy Labels","year":2020,"lang":"en","type":"article","venue":"IEEE Access","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Ministry of Science and ICT, South Korea; National Research Foundation of Korea; National IT Industry Promotion Agency; Kyungpook National University; National Research Foundation","keywords":"Computer science; Convolutional neural network; Artificial intelligence; Training (meteorology); Net (polyhedron); Machine learning; Pattern recognition (psychology); Speech recognition; Mathematics","score_opus":0.07748383957779421,"score_gpt":0.287544198648785,"score_spread":0.2100603590709908,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3107092601","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":[0.023509923,0.00014993145,0.9695768,0.005060541,0.00027479394,0.00010320165,0.000003871618,0.00027956828,0.0010413681],"genre_scores_gemma":[0.99086535,0.0000049665136,0.006034803,0.0025978743,0.00039525313,0.0000146843895,0.000029003795,0.000012656574,0.000045404908],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987074,0.000084161264,0.00018516641,0.00045634396,0.0002882654,0.0002786419],"domain_scores_gemma":[0.9992027,0.00010013615,0.00013003885,0.00033231237,0.00007195342,0.00016285264],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014508393,0.00014246975,0.00014719837,0.00004006355,0.00016808727,0.00042618168,0.0012635438,0.000051694606,0.000035816538],"category_scores_gemma":[0.000042491738,0.000120439305,0.000030972195,0.00045957993,0.00005084168,0.0010309402,0.00013309879,0.00027872287,0.000027831717],"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":[0.00013334012,0.00012379783,0.08530978,0.00006390764,0.000101651916,0.0001197175,0.004284986,0.49495202,0.0010787151,0.02377226,0.007883188,0.3821766],"study_design_scores_gemma":[0.00034994064,0.00006148368,0.035748016,0.000009098369,0.0000067035962,0.0000146391885,0.000016728136,0.96061736,0.000042192467,0.00008355623,0.0028753653,0.00017488623],"about_ca_topic_score_codex":0.00004430736,"about_ca_topic_score_gemma":0.000031188934,"teacher_disagreement_score":0.96735543,"about_ca_system_score_codex":0.000017233642,"about_ca_system_score_gemma":0.000052590764,"threshold_uncertainty_score":0.49113724},"labels":[],"label_agreement":null},{"id":"W3110902746","doi":"10.1609/aaai.v35i10.17109","title":"Warm Starting CMA-ES for Hyperparameter Optimization","year":2021,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"National Institute of Advanced Industrial Science and Technology","keywords":"Bayesian optimization; Hyperparameter; Computer science; Adaptation (eye); Initialization; Machine learning; CMA-ES; Artificial intelligence; Task (project management); Random search; Bayesian probability; Algorithm; Evolution strategy; Evolutionary algorithm","score_opus":0.09431824299911165,"score_gpt":0.31262217584602,"score_spread":0.21830393284690833,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3110902746","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":[0.036886945,0.000030731124,0.9456621,0.011662337,0.0004428109,0.00035294707,0.000009181567,0.0001289058,0.0048240833],"genre_scores_gemma":[0.9098672,0.000024226403,0.08937024,0.00033033543,0.000061806444,0.00003504182,0.0000046646924,0.000010045715,0.00029640962],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99855316,0.000021634942,0.00042236355,0.0004633231,0.00029790797,0.0002416314],"domain_scores_gemma":[0.99823654,0.00016366385,0.00033479073,0.00031912353,0.0008902765,0.00005559104],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000473397,0.000144886,0.00017586211,0.00006987953,0.00022815543,0.00034706696,0.0010089695,0.00006610847,0.000041285923],"category_scores_gemma":[0.0014798183,0.000114221315,0.00009622862,0.00048234998,0.000086474145,0.0004134176,0.00023781248,0.0001802924,0.00002356141],"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":[0.0000266924,0.00007897191,0.00020528417,0.000045351106,0.000010492491,1.7074431e-7,0.0005851674,0.002379783,0.038215816,0.8589799,0.00018801223,0.09928438],"study_design_scores_gemma":[0.000021539125,0.00007037447,0.000046712554,0.000076073426,0.00000869656,0.0000019733468,0.00023257673,0.57742774,0.37876928,0.042821232,0.00040115567,0.00012265374],"about_ca_topic_score_codex":0.000010063037,"about_ca_topic_score_gemma":0.0000037655886,"teacher_disagreement_score":0.8729803,"about_ca_system_score_codex":0.000026607093,"about_ca_system_score_gemma":0.00010291038,"threshold_uncertainty_score":0.465781},"labels":[],"label_agreement":null},{"id":"W3111113979","doi":"10.48550/arxiv.2012.05390","title":"Ensemble Squared: A Meta AutoML System","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science","score_opus":0.13886642874274416,"score_gpt":0.20245143876052626,"score_spread":0.0635850100177821,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3111113979","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":[0.004382939,0.00010959116,0.98120534,0.00086202973,0.00050625164,0.00026359688,0.000028969884,0.0013080053,0.011333269],"genre_scores_gemma":[0.99372804,0.000029617937,0.004601974,0.00011131734,0.00008539265,0.0000025267618,0.00007266596,0.000018205881,0.001350248],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99764115,0.0003191895,0.00021856384,0.0014081417,0.00012925266,0.0002837279],"domain_scores_gemma":[0.99738234,0.000099242694,0.00033413738,0.0018509484,0.00011238984,0.00022091725],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00030244893,0.00032100015,0.00047538272,0.00019220894,0.00017141993,0.00024431304,0.0024072768,0.0002407482,0.0000221241],"category_scores_gemma":[0.00005656829,0.0003383245,0.00032137442,0.00059737364,0.000042225456,0.00032061385,0.002138666,0.0007197961,0.0005056154],"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":[0.000015159855,0.00005049672,0.00035172253,0.0003613419,0.00051939534,0.00035588458,0.0002617567,0.050905026,0.00006661698,0.9439881,0.0018917907,0.0012327001],"study_design_scores_gemma":[0.00021917993,0.00003903923,0.0005703111,0.00004758262,0.00045631666,0.000008422481,0.00007039116,0.984052,0.000048268106,0.0063201655,0.007774079,0.0003942398],"about_ca_topic_score_codex":0.00031394072,"about_ca_topic_score_gemma":0.000018410208,"teacher_disagreement_score":0.98934513,"about_ca_system_score_codex":0.0001886128,"about_ca_system_score_gemma":0.00021082883,"threshold_uncertainty_score":0.9999069},"labels":[],"label_agreement":null},{"id":"W3112420807","doi":"","title":"Improving Zero-Shot Neural Architecture Search with Parameters Scoring","year":2021,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","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":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Computer science; Metric (unit); Task (project management); Artificial neural network; Artificial intelligence; Machine learning; Noise (video); Performance metric; Monotonic function; Process (computing); Data mining; Mathematics; Engineering","score_opus":0.030343302492578814,"score_gpt":0.26196997902605723,"score_spread":0.2316266765334784,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3112420807","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":[0.10886427,0.000031263062,0.8858075,0.0022552074,0.000081329425,0.00005151016,6.927522e-7,0.00019541889,0.0027127964],"genre_scores_gemma":[0.7979155,0.0000015182235,0.20101489,0.00032199733,0.000021388782,0.0000041701273,0.0000111147965,0.0000066662246,0.0007027471],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988806,0.00009620198,0.00010296248,0.00042784872,0.00024842995,0.00024395259],"domain_scores_gemma":[0.99909335,0.00009187872,0.00003331355,0.0006352687,0.000059100938,0.00008709221],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017586444,0.000096588345,0.000088443114,0.0000612277,0.00012730603,0.00033652852,0.0004149605,0.000026891687,0.000014711102],"category_scores_gemma":[0.00006103863,0.000071721544,0.000027153072,0.00036779352,0.00002080885,0.00025985073,0.00021797608,0.00028454425,0.00002062442],"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":[0.000018401526,0.000061633815,0.013698421,0.00006530405,0.000024668823,0.00012539112,0.0008606595,0.01738125,0.027419914,0.034121286,0.000163799,0.90605927],"study_design_scores_gemma":[0.00054465694,0.00019621175,0.020568404,0.00003926314,0.000009792567,0.00030847552,0.00014506232,0.9482251,0.027418993,0.00041922522,0.0016954704,0.0004293659],"about_ca_topic_score_codex":0.00018447952,"about_ca_topic_score_gemma":0.000040156887,"teacher_disagreement_score":0.93084383,"about_ca_system_score_codex":0.000017034383,"about_ca_system_score_gemma":0.0000856531,"threshold_uncertainty_score":0.32451522},"labels":[],"label_agreement":null},{"id":"W3113263614","doi":"10.17504/protocols.io.sg4ebyw","title":"IsletCore Equipment Setup for Human Islet Isolation v1","year":2018,"lang":"en","type":"preprint","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Islet; Isolation (microbiology); Computer science; Biology; Biotechnology; Insulin; Bioinformatics","score_opus":0.05321653840450439,"score_gpt":0.3374871675863246,"score_spread":0.28427062918182017,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3113263614","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":[0.0024796021,0.000026717662,0.9787227,0.003499543,0.0009021093,0.0005826248,0.000039588354,0.00044504993,0.013302069],"genre_scores_gemma":[0.5842622,0.000015377136,0.39937896,0.0011507208,0.0013078774,0.0003611491,0.0031157346,0.0000434033,0.010364631],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980974,0.00008242476,0.00037786408,0.00088736095,0.00028287628,0.00027206718],"domain_scores_gemma":[0.99783045,0.00007236487,0.000319377,0.0015213976,0.00018027464,0.000076126526],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006362446,0.0002464526,0.00022557461,0.00014989488,0.00026894262,0.00046488005,0.0013750573,0.00023905499,0.00012872518],"category_scores_gemma":[0.00007241642,0.00022360263,0.000120079676,0.00010174691,0.0000372163,0.00022089851,0.0013263656,0.00032025934,0.00017910011],"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":[0.000020762933,0.00024676402,0.0012884056,0.0005182218,0.000115108494,0.0000018617922,0.0015851309,0.00063097826,0.0036125754,0.6360342,0.2800391,0.07590691],"study_design_scores_gemma":[0.0004980537,0.00028093165,0.0037370299,0.00011530749,0.000032758657,0.0000036791932,0.000019993216,0.6928145,0.0009349752,0.09804991,0.20278491,0.0007279529],"about_ca_topic_score_codex":0.0001391243,"about_ca_topic_score_gemma":0.000025063313,"teacher_disagreement_score":0.6921835,"about_ca_system_score_codex":0.00009279334,"about_ca_system_score_gemma":0.00009260353,"threshold_uncertainty_score":0.91182506},"labels":[],"label_agreement":null},{"id":"W3121928352","doi":"","title":"Get Another Label? Improving Data Quality and Data Mining Using Multiple, Noisy Labelers","year":2008,"lang":"en","type":"article","venue":"The Faculty Digital Archive (New York University)","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":98,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; National Science Foundation","keywords":"Computer science; Quality (philosophy); Sequence labeling; Set (abstract data type); Imperfect; Crowdsourcing; Artificial intelligence; Focus (optics); Outsourcing; Machine learning; Data quality; Data mining; Task (project management); Engineering; Operations management","score_opus":0.24402127701889942,"score_gpt":0.31307837567426927,"score_spread":0.06905709865536985,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3121928352","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":[0.24271375,0.000065984845,0.7464391,0.0017443502,0.00009822247,0.00026505708,0.0033494222,0.00031798438,0.005006137],"genre_scores_gemma":[0.82275337,0.000029468198,0.16757135,0.00032477605,0.00013463525,2.1073805e-7,0.0044576433,0.000029401386,0.0046991194],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99834514,0.00014251513,0.00017077704,0.000796638,0.00025657273,0.0002883871],"domain_scores_gemma":[0.99713844,0.0003386252,0.00019187522,0.0021722945,0.000028451852,0.00013033647],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026364633,0.00018085171,0.00017232234,0.00012086549,0.00058477564,0.0002859009,0.0037329255,0.00003799778,0.0000022184995],"category_scores_gemma":[0.00029321312,0.00014993154,0.000023427394,0.00042020515,0.00024572774,0.0024211637,0.004218226,0.00020977543,0.00001623761],"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":[0.00029107093,0.0003715764,0.14890797,0.00009284961,0.00033910104,0.00016553073,0.013485005,0.00055673334,0.0037355423,0.013524918,0.024673555,0.79385614],"study_design_scores_gemma":[0.0020595128,0.00007296279,0.04969462,0.000057140813,0.000050831288,0.00009488981,0.0014816623,0.72091675,0.000024928058,0.00024650033,0.22457974,0.00072045624],"about_ca_topic_score_codex":0.0014461206,"about_ca_topic_score_gemma":0.00020142521,"teacher_disagreement_score":0.7931357,"about_ca_system_score_codex":0.00003584612,"about_ca_system_score_gemma":0.00016691172,"threshold_uncertainty_score":0.69367665},"labels":[],"label_agreement":null},{"id":"W3124328990","doi":"10.48550/arxiv.2101.08732","title":"Self-Adaptive Training: Bridging Supervised and Self-Supervised Learning","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; National Natural Science Foundation of China","keywords":"Computer science; Artificial intelligence; Machine learning; Bridging (networking); Deep learning; Artificial neural network; Generalization; Noise (video); Supervised learning; Deep neural networks; Code (set theory); Stochastic gradient descent; Mathematics","score_opus":0.06963188995158896,"score_gpt":0.19440663444832382,"score_spread":0.12477474449673485,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3124328990","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":[0.39809382,0.00018210289,0.59650105,0.00026192758,0.00028069672,0.00024217636,0.000005514965,0.0011968015,0.0032358782],"genre_scores_gemma":[0.9600725,0.0005052648,0.038690377,0.00009043086,0.000099245735,0.0000017963316,0.00009109701,0.000030704516,0.00041857042],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99680877,0.0005817186,0.00025582392,0.0017310064,0.0001593064,0.00046339328],"domain_scores_gemma":[0.9979513,0.00020317992,0.0002605043,0.0011141349,0.00020222673,0.0002686192],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005435963,0.00042208648,0.00046237366,0.00029976442,0.00042509774,0.00053203414,0.001274971,0.00031972112,0.000022875078],"category_scores_gemma":[0.0000955643,0.0005200626,0.00016980212,0.0006527504,0.00006304766,0.0007132424,0.002097673,0.0013500953,0.00002694257],"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":[0.00017640898,0.0016885496,0.06288531,0.001969698,0.002243917,0.0037138835,0.09390895,0.26089385,0.0007987466,0.43005902,0.00041344,0.14124824],"study_design_scores_gemma":[0.00060574163,0.000068363406,0.004587398,0.000102911385,0.000098372606,0.000019943442,0.0012026031,0.9909303,0.000026879941,0.00069149846,0.0011032779,0.0005627139],"about_ca_topic_score_codex":0.00016538218,"about_ca_topic_score_gemma":0.000023554476,"teacher_disagreement_score":0.73003644,"about_ca_system_score_codex":0.00018153715,"about_ca_system_score_gemma":0.0004069951,"threshold_uncertainty_score":0.9997251},"labels":[],"label_agreement":null},{"id":"W3126985315","doi":"10.48550/arxiv.2107.04497","title":"Batch Inverse-Variance Weighting: Deep Heteroscedastic Regression","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Heteroscedasticity; Variance (accounting); Weighting; Computer science; Noise (video); Mean squared error; Regression; Artificial intelligence; Statistics; Algorithm; Mathematics; Machine learning; Pattern recognition (psychology)","score_opus":0.0654492402742479,"score_gpt":0.20390368172700973,"score_spread":0.13845444145276184,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3126985315","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":[0.10725109,0.00009467851,0.88812655,0.0003460183,0.0010176697,0.00014834285,0.00000562344,0.0003716564,0.0026383512],"genre_scores_gemma":[0.9857709,0.00020970091,0.011771199,0.00016950932,0.00010582451,0.0000012988954,0.00013413372,0.000020500098,0.001816949],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972834,0.00036627147,0.0002410623,0.0015943215,0.00015018822,0.00036477734],"domain_scores_gemma":[0.996961,0.00014403184,0.00040550565,0.002103337,0.00017948519,0.00020666723],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00029583232,0.0003494829,0.00034261844,0.00020058677,0.00026226984,0.000361724,0.002003984,0.0003409452,0.00006151289],"category_scores_gemma":[0.0001803185,0.0003770596,0.00018041216,0.0006495173,0.0000787223,0.00057228206,0.002558642,0.0009727923,0.00013425708],"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":[0.00011672939,0.0007702654,0.041709978,0.0010188529,0.0003550997,0.0028860061,0.0029384748,0.5422899,0.0026337479,0.37649542,0.0037119424,0.02507355],"study_design_scores_gemma":[0.000331695,0.000028255286,0.004387175,0.00026688064,0.000040914045,0.000010220527,0.00008622564,0.9884301,0.00013946873,0.003794544,0.0020199216,0.00046463488],"about_ca_topic_score_codex":0.00014548653,"about_ca_topic_score_gemma":0.00007992934,"teacher_disagreement_score":0.8785198,"about_ca_system_score_codex":0.00018734061,"about_ca_system_score_gemma":0.00021979443,"threshold_uncertainty_score":0.99986815},"labels":[],"label_agreement":null},{"id":"W3129917300","doi":"10.48550/arxiv.2102.07834","title":"One Line To Rule Them All: Generating LO-Shot Soft-Label Prototypes","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Machine Learning and Data Classification","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":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Modular design; Machine learning; Artificial intelligence; Code (set theory); Set (abstract data type); Class (philosophy); Training set; Line (geometry); k-nearest neighbors algorithm; Soft computing; Data mining; Artificial neural network","score_opus":0.18071841787871445,"score_gpt":0.23697906773696367,"score_spread":0.05626064985824922,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3129917300","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":[0.18266395,0.000036603466,0.8136227,0.00092013495,0.00028039364,0.0004679307,0.000013027592,0.00033938096,0.0016558837],"genre_scores_gemma":[0.9385589,0.000051164374,0.058287248,0.00058733975,0.00017880133,0.00000797502,0.00019106452,0.000024361108,0.0021131404],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997719,0.00022096476,0.00023259902,0.0013377583,0.0001469292,0.00034273634],"domain_scores_gemma":[0.9976321,0.00008186023,0.00022995686,0.0016181816,0.00022711963,0.00021079098],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00037630153,0.00028111134,0.00031155828,0.00015699532,0.0002000496,0.0004593924,0.0017166366,0.00022014312,0.00006393384],"category_scores_gemma":[0.00014221991,0.00033806387,0.00010244452,0.00055458484,0.000036710902,0.0003314226,0.0023420246,0.0006889136,0.00023008669],"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":[0.00012377801,0.0015032982,0.0077932416,0.0006772507,0.00056566775,0.0005344066,0.0030840354,0.64766955,0.011952124,0.24385428,0.0015268219,0.08071552],"study_design_scores_gemma":[0.00037732284,0.0000714934,0.001025728,0.00015920617,0.000054643195,0.000004617791,0.000059215276,0.99111605,0.0010255515,0.0026589942,0.00287667,0.00057053304],"about_ca_topic_score_codex":0.00027705095,"about_ca_topic_score_gemma":0.000068547335,"teacher_disagreement_score":0.75589496,"about_ca_system_score_codex":0.00013005799,"about_ca_system_score_gemma":0.00024029169,"threshold_uncertainty_score":0.99990714},"labels":[],"label_agreement":null},{"id":"W3130556965","doi":"10.1007/s40614-021-00280-4","title":"Correction to: Machine Learning to Analyze Single-Case Data: A Proof of Concept","year":2021,"lang":"en","type":"article","venue":"Perspectives on Behavior Science","topic":"Machine Learning and Data Classification","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":"Polytechnique Montréal; Université de Montréal","funders":"","keywords":"Computer science; Proof of concept; Data science; Artificial intelligence; Machine learning; Operating system","score_opus":0.06344809036465525,"score_gpt":0.3340216859986938,"score_spread":0.27057359563403854,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3130556965","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":[0.40404207,0.00022784936,0.5885376,0.002491059,0.0014333519,0.0005115138,0.00006200352,0.00026909634,0.002425481],"genre_scores_gemma":[0.9734716,0.0000025247493,0.02571526,0.00008176422,0.000040576742,0.00002027135,0.000018461908,0.000008211441,0.0006413447],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99736917,0.00014983848,0.00024684888,0.0012929207,0.00063545804,0.00030574744],"domain_scores_gemma":[0.99741566,0.00014241235,0.00014198903,0.0015471003,0.0005120825,0.00024072708],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000819102,0.00015068946,0.00018759664,0.00037184363,0.0004004137,0.00031177755,0.0014338708,0.000027190134,0.00003183263],"category_scores_gemma":[0.002545789,0.000146197,0.000038485545,0.0030369752,0.00019405536,0.00088986795,0.0008763438,0.0002969025,0.000021802574],"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":[0.000051516094,0.002506402,0.0133268945,0.000015221354,0.000016474018,0.0006442455,0.047882505,0.009786537,0.24370542,0.014095996,0.0010082287,0.66696054],"study_design_scores_gemma":[0.0010086871,0.0035358712,0.088510364,0.00027247207,0.00010434868,0.0025278192,0.029759824,0.5771529,0.2870509,0.00005679769,0.008503848,0.0015161214],"about_ca_topic_score_codex":0.00026594003,"about_ca_topic_score_gemma":0.00013974482,"teacher_disagreement_score":0.66544443,"about_ca_system_score_codex":0.00018329981,"about_ca_system_score_gemma":0.00025218553,"threshold_uncertainty_score":0.596174},"labels":[],"label_agreement":null},{"id":"W3130803020","doi":"10.48550/arxiv.1809.00082","title":"NEU: A Meta-Algorithm for Universal UAP-Invariant Feature Representation","year":2018,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Feature (linguistics); Feature vector; Algorithm; Computer science; Invariant (physics); Artificial intelligence; Representation (politics); Pattern recognition (psychology); Euclidean space; Function (biology); Mathematics; Pure mathematics","score_opus":0.1291869983052002,"score_gpt":0.23750837335484354,"score_spread":0.10832137504964334,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3130803020","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":[0.0014806989,0.000057281894,0.994146,0.0010155995,0.00070542214,0.0005195915,0.00013004405,0.00037350232,0.001571844],"genre_scores_gemma":[0.7242873,0.00021456963,0.25254846,0.00038424434,0.0007376006,0.000011186638,0.0012379097,0.00006913178,0.020509623],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997471,0.00029598753,0.00018887446,0.0015760469,0.0001331396,0.0003349817],"domain_scores_gemma":[0.9969686,0.00021135574,0.00043991016,0.001865913,0.00035085602,0.00016331412],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004573698,0.0003469057,0.00044855982,0.0003037117,0.00028651033,0.00025756197,0.0018933695,0.00037374988,0.00003997621],"category_scores_gemma":[0.000107772554,0.00035926225,0.0004322111,0.000602499,0.00010297173,0.0005929187,0.0012586925,0.0005590902,0.00006985473],"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":[0.00017746336,0.0004233332,0.00078863604,0.00025788194,0.0038143666,0.0003879903,0.0011287954,0.060619153,0.000157051,0.84348255,0.048749395,0.040013354],"study_design_scores_gemma":[0.00053265324,0.000087450724,0.00062362547,0.000019103612,0.00083638006,0.0000065208646,0.00004775924,0.96242326,0.000093328505,0.019206598,0.015714072,0.0004092182],"about_ca_topic_score_codex":0.00028053997,"about_ca_topic_score_gemma":0.000039519848,"teacher_disagreement_score":0.90180415,"about_ca_system_score_codex":0.00016554992,"about_ca_system_score_gemma":0.00023344463,"threshold_uncertainty_score":0.9998859},"labels":[],"label_agreement":null},{"id":"W3132725505","doi":"10.48550/arxiv.2102.06966","title":"Graph Convolution for Semi-Supervised Classification: Improved Linear Separability and Out-of-Distribution Generalization","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Graph; Classifier (UML); Linear classifier; Separable space; Mathematics; Convolution (computer science); Computer science; Pattern recognition (psychology); Artificial intelligence; Graphical model; Algorithm; Discrete mathematics; Artificial neural network","score_opus":0.08802823376145545,"score_gpt":0.2319680894281704,"score_spread":0.14393985566671497,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3132725505","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":[0.16039228,0.00007590214,0.8380566,0.00022076089,0.00049662293,0.00042732604,0.00013484126,0.00013384719,0.000061785984],"genre_scores_gemma":[0.9888292,0.0002473093,0.0074308678,0.00002720797,0.000079114,0.0000068504064,0.0031990365,0.000010590961,0.00016980979],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99808663,0.0002524315,0.00032043963,0.0010662057,0.00008061289,0.0001936624],"domain_scores_gemma":[0.9976769,0.00011468706,0.00043413945,0.0010810732,0.00059112854,0.000102062506],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004858671,0.00022343348,0.00029487224,0.0001084286,0.00018431574,0.00010170627,0.0005581535,0.00031548287,0.0000053526746],"category_scores_gemma":[0.00018624883,0.0002678112,0.00014973225,0.00040408614,0.0001184101,0.0004037105,0.00045668185,0.0002682356,0.0000018998539],"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":[0.00035501397,0.0009802515,0.057148125,0.0027878946,0.00043907983,0.000013004866,0.0019995181,0.14491591,0.01942246,0.75718904,0.0016174305,0.013132276],"study_design_scores_gemma":[0.00050178345,0.000049194874,0.014941322,0.000044534874,0.00007168224,8.4695034e-7,0.000078134435,0.97872084,0.000314455,0.004174032,0.00085100625,0.00025217643],"about_ca_topic_score_codex":0.00010648638,"about_ca_topic_score_gemma":0.00004751235,"teacher_disagreement_score":0.8338049,"about_ca_system_score_codex":0.00014351192,"about_ca_system_score_gemma":0.00021879257,"threshold_uncertainty_score":0.9999774},"labels":[],"label_agreement":null},{"id":"W3136718240","doi":"10.1109/tcyb.2021.3059631","title":"Hierarchical Semantic Risk Minimization for Large-Scale Classification","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Cybernetics","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Tianjin Science and Technology Program; National Natural Science Foundation of China","keywords":"Computer science; Hierarchy; Construct (python library); Artificial intelligence; Machine learning; Node (physics); Decision tree; Class hierarchy; Data mining; Class (philosophy); Task (project management); Scale (ratio); Tree (set theory); Mathematics","score_opus":0.020845932057904068,"score_gpt":0.27016750685005725,"score_spread":0.24932157479215317,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3136718240","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":[0.0037730231,0.00003083167,0.9920723,0.0023923123,0.0005904344,0.00020094583,0.00009166762,0.00020975595,0.0006387597],"genre_scores_gemma":[0.87453777,0.00019923208,0.1236851,0.00021891216,0.00006706084,0.00006874782,0.00008834392,0.000019789806,0.0011150191],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99848706,0.00018830551,0.00029261466,0.0005204341,0.00025912267,0.00025249436],"domain_scores_gemma":[0.99857587,0.00030861597,0.0001223765,0.0007445203,0.00014507162,0.00010352218],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021377129,0.00014342404,0.00014213962,0.00011205095,0.00034855696,0.0001639661,0.00032218994,0.00012552495,0.000028159455],"category_scores_gemma":[0.00005347391,0.00015097157,0.000109240595,0.0004390944,0.000027726273,0.00018866466,0.0000034572079,0.00030628647,0.00006316358],"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":[0.0001348293,0.0033590589,0.0012286014,0.00018835287,0.00018083068,0.000011516078,0.004646822,0.07143977,0.01863248,0.09230787,0.0038213425,0.80404854],"study_design_scores_gemma":[0.0006383469,0.0001013713,0.0043827994,0.00001903201,0.000050160284,0.0000114208015,0.00007641176,0.9637234,0.01301018,0.0012746317,0.01650587,0.0002063405],"about_ca_topic_score_codex":0.000008363695,"about_ca_topic_score_gemma":0.000075791046,"teacher_disagreement_score":0.8922837,"about_ca_system_score_codex":0.000036490525,"about_ca_system_score_gemma":0.000100847385,"threshold_uncertainty_score":0.6156442},"labels":[],"label_agreement":null},{"id":"W3142903789","doi":"10.1287/opre.2021.0034","title":"Strong Optimal Classification Trees","year":2024,"lang":"en","type":"article","venue":"Operations Research","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Flexibility (engineering); Heuristic; Computer science; Mathematical optimization; Integer (computer science); Decision tree; Machine learning; Revenue; Integer programming; Ranging; Artificial intelligence; Tree (set theory); Sample (material); Relaxation (psychology); Operations research; Mathematics; Statistics; Economics","score_opus":0.15154269227938005,"score_gpt":0.4452963514217984,"score_spread":0.29375365914241836,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3142903789","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":[0.009265702,0.00047267656,0.9495042,0.017097076,0.00022168763,0.00021537539,0.000008856019,0.00039588212,0.022818547],"genre_scores_gemma":[0.9637838,0.00006392779,0.026969615,0.000017620909,0.00014690375,0.00009805034,0.00008708851,0.000008963043,0.008824056],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984177,0.00028299703,0.00015315665,0.0004214408,0.00048016728,0.0002445342],"domain_scores_gemma":[0.99893975,0.00015600391,0.0000047546373,0.00063581887,0.00018726426,0.000076396034],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001277219,0.0000667708,0.000054917175,0.00035595158,0.00048506103,0.0017946531,0.0006504489,0.00004804028,0.00010886588],"category_scores_gemma":[0.00019241821,0.000057494213,0.000027353755,0.0010269205,0.00006596675,0.00095067907,0.00015314581,0.00042295526,0.001354656],"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":[0.0000010927179,0.000032138643,0.00006770531,0.000008817813,0.0000066902935,0.000004202689,0.00042308794,0.003303655,0.006611299,0.86000973,0.0058500287,0.12368155],"study_design_scores_gemma":[0.000037324768,0.00003945555,0.0037251038,0.000014901914,0.0000010779985,0.000005737223,0.000105130486,0.9088482,0.00025535005,0.00014973343,0.08675541,0.00006253313],"about_ca_topic_score_codex":0.000117636715,"about_ca_topic_score_gemma":0.00010046128,"teacher_disagreement_score":0.9545181,"about_ca_system_score_codex":0.00008091354,"about_ca_system_score_gemma":0.00025562794,"threshold_uncertainty_score":0.9994229},"labels":[],"label_agreement":null},{"id":"W3146200671","doi":"10.1109/iccit.2007.4420473","title":"Investigating the Performance of Naive- Bayes Classifiers and K- Nearest Neighbor Classifiers","year":2007,"lang":"en","type":"article","venue":"2007 International Conference on Convergence Information Technology (ICCIT 2007)","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":126,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Naive Bayes classifier; Artificial intelligence; k-nearest neighbors algorithm; Computer science; Bayes error rate; Machine learning; Classifier (UML); Bayes classifier; Pattern recognition (psychology); Random subspace method; Bayesian probability; Bayes' theorem; Data mining; Support vector machine","score_opus":0.023613763142237787,"score_gpt":0.2723399187404118,"score_spread":0.24872615559817401,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3146200671","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":[0.49164343,0.000090503134,0.42875478,0.01853477,0.0030238554,0.000626063,0.000036749723,0.0006295576,0.056660283],"genre_scores_gemma":[0.9915473,0.00023409809,0.006940806,0.00091499335,0.000055443106,0.000021119224,0.000044606844,0.00000671527,0.00023491142],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980096,0.000042013395,0.0007381757,0.00030269456,0.0005658516,0.00034162652],"domain_scores_gemma":[0.99797595,0.0001739631,0.00066357973,0.0005108074,0.0005732304,0.000102483056],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009936177,0.00022075976,0.0001869347,0.00064011646,0.00028347023,0.00016906789,0.0014174192,0.00023863616,0.00020478993],"category_scores_gemma":[0.0005602869,0.00018004882,0.000043573607,0.00064383494,0.00054623676,0.001742013,0.00026161852,0.00057879335,0.00018103064],"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":[0.00003297048,0.00003410734,0.082606465,0.000034505018,0.00004208378,0.0000014578872,0.0005756646,0.00011030337,0.0010828003,0.75784826,0.0016324831,0.15599892],"study_design_scores_gemma":[0.0007850529,0.00042630234,0.15851855,0.00020447365,0.00001446153,0.000057988487,0.0023675845,0.7850226,0.008293711,0.004376672,0.039390128,0.0005424284],"about_ca_topic_score_codex":0.000045499928,"about_ca_topic_score_gemma":0.000011427137,"teacher_disagreement_score":0.78491235,"about_ca_system_score_codex":0.00008580969,"about_ca_system_score_gemma":0.00017193049,"threshold_uncertainty_score":0.73421776},"labels":[],"label_agreement":null},{"id":"W3155042034","doi":"10.7717/peerj-cs.464","title":"Optimal 1-NN prototypes for pathological geometries","year":2021,"lang":"en","type":"article","venue":"PeerJ Computer Science","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Classifier (UML); Parametric statistics; Heuristic; Artificial intelligence; Machine learning; Algorithm; Mathematical optimization; Mathematics","score_opus":0.026700955112118188,"score_gpt":0.2941873908895498,"score_spread":0.26748643577743164,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3155042034","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":[0.019988956,0.000085076455,0.97446805,0.0040661274,0.00056753424,0.00024030384,0.0000051919465,0.0002519668,0.00032677717],"genre_scores_gemma":[0.30009332,0.000005121659,0.69895697,0.00047376464,0.00014829136,0.00006212396,0.000012443757,0.000004307168,0.00024367741],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980014,0.000048537375,0.0002017077,0.000855939,0.00049148424,0.0004009434],"domain_scores_gemma":[0.9983269,0.0001860657,0.00008163516,0.00080423406,0.0004674319,0.0001337236],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011403835,0.00012506233,0.00015523545,0.00016718825,0.00046127176,0.00084887433,0.0015858673,0.0000428489,0.000009998751],"category_scores_gemma":[0.0004898719,0.000105006584,0.000061685554,0.0014780911,0.00024734804,0.0008386753,0.00076909433,0.0001331359,0.000044612563],"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":[0.000014746639,0.0002818736,0.003077858,0.00005837123,0.000009907266,0.00005885163,0.00088594266,0.0044123637,0.013930194,0.24966793,0.0030644615,0.7245375],"study_design_scores_gemma":[0.00035289564,0.00029272452,0.035388175,0.000016937855,0.000004195702,0.00013828264,0.000011966758,0.89042956,0.015176138,0.002475706,0.0553934,0.00032001385],"about_ca_topic_score_codex":0.0000031783816,"about_ca_topic_score_gemma":9.414264e-7,"teacher_disagreement_score":0.8860172,"about_ca_system_score_codex":0.000033328073,"about_ca_system_score_gemma":0.00030972259,"threshold_uncertainty_score":0.81857145},"labels":[],"label_agreement":null},{"id":"W3159955930","doi":"10.24908/pceea.vi0.13741","title":"USING MACHINE LEARNING AS A TOOL TO HELP GUIDE UNDECLARED/UNDECIDED FIRST-YEAR ENGINEERING STUDENTS TOWARDS A DISCIPLINE","year":2019,"lang":"en","type":"article","venue":"Proceedings of the Canadian Engineering Education Association (CEEA)","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Categorization; Machine learning; Class (philosophy); Artificial intelligence; Decision tree; Classifier (UML); Computer science; Logistic regression; Random forest; Engineering education; Mathematics education; Psychology; Engineering; Engineering management","score_opus":0.010057068636650282,"score_gpt":0.2578494121216062,"score_spread":0.24779234348495593,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3159955930","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":[0.97307855,0.00007123063,0.009412613,0.011731705,0.0023399456,0.0010711746,0.000025011364,0.00036724648,0.0019025299],"genre_scores_gemma":[0.96955115,0.000006037505,0.025645947,0.00026427113,0.00015457609,0.00004221976,0.000019652194,0.000044716744,0.00427141],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979723,0.000013463057,0.0004253382,0.00042081784,0.0007382742,0.00042980624],"domain_scores_gemma":[0.9984969,0.00006537904,0.00037132535,0.00030015368,0.00048937515,0.00027688214],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00095055613,0.00022693312,0.0002407879,0.0004992217,0.00023617646,0.00047713416,0.0011930706,0.00014071522,0.000028704022],"category_scores_gemma":[0.0024792242,0.00022901413,0.00009877273,0.0010927031,0.0000056039335,0.0006476485,0.00024798204,0.00039120388,0.00006641178],"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":[0.000009832534,0.00015390594,0.82006,0.00045650333,0.00021169166,4.1797944e-7,0.00377338,0.09873919,0.0132287685,0.05643178,0.0045217234,0.0024127993],"study_design_scores_gemma":[0.00074760587,0.00010085289,0.38963172,0.0006080837,0.00006764944,0.000013076746,0.00034777136,0.50151545,0.002041163,0.00036967537,0.10361122,0.00094574585],"about_ca_topic_score_codex":0.011108469,"about_ca_topic_score_gemma":0.0019861546,"teacher_disagreement_score":0.4304283,"about_ca_system_score_codex":0.0026458823,"about_ca_system_score_gemma":0.00065182714,"threshold_uncertainty_score":0.99547666},"labels":[],"label_agreement":null},{"id":"W3165716853","doi":"","title":"AutoLRS: Automatic Learning-Rate Schedule by Bayesian Optimization on the Fly","year":2021,"lang":"en","type":"preprint","venue":"King Abdullah University of Science and Technology Repository (King Abdullah University of Science and Technology)","topic":"Machine Learning and Data Classification","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":"Kootenay Association for Science & Technology","funders":"","keywords":"Computer science; Hyperparameter; Schedule; Machine learning; Speedup; Artificial intelligence; Bayesian optimization; Process (computing); Generality; On the fly","score_opus":0.005965306014060832,"score_gpt":0.188064786336779,"score_spread":0.18209948032271817,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3165716853","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":[0.9296967,0.0004957564,0.05086748,0.015049643,0.00036236175,0.000458421,0.00000841137,0.0010244913,0.0020367315],"genre_scores_gemma":[0.97412086,0.00038877336,0.025203556,0.000035361692,0.000008519432,5.099379e-7,0.0000056225444,0.000010627617,0.00022618729],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9960509,0.00014788778,0.00033588355,0.0017787425,0.0010503432,0.00063626544],"domain_scores_gemma":[0.9953625,0.00015675422,0.0010424837,0.0015585405,0.001717907,0.00016177275],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":["sts"],"category_scores_codex":[0.0025681283,0.0003798227,0.00057510217,0.0028395508,0.004593023,0.00032053533,0.0048249736,0.00069306284,0.0000072962252],"category_scores_gemma":[0.0008884826,0.00040106475,0.00007092639,0.006421165,0.021234246,0.0010329874,0.004367801,0.0014582425,0.0000024461158],"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":[0.000102194186,0.0011819684,0.064833544,0.0012012755,0.0005499002,0.0006509185,0.013942429,0.011431082,0.4845621,0.2014682,0.0011322506,0.21894415],"study_design_scores_gemma":[0.0010447951,0.00082518184,0.0035238673,0.0019742453,0.0002327421,0.00023811436,0.038542815,0.9085713,0.038159024,0.0021070375,0.0034523476,0.0013285091],"about_ca_topic_score_codex":0.00041475354,"about_ca_topic_score_gemma":0.00002642683,"teacher_disagreement_score":0.89714026,"about_ca_system_score_codex":0.00033267887,"about_ca_system_score_gemma":0.0016528824,"threshold_uncertainty_score":0.99984413},"labels":[],"label_agreement":null},{"id":"W3168725586","doi":"10.1142/s0218001421510113","title":"Case-Base Maintenance: An Approach Based on Active Semi-Supervised Learning","year":2021,"lang":"en","type":"article","venue":"International Journal of Pattern Recognition and Artificial Intelligence","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"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":"Bottleneck; Computer science; Machine learning; Representativeness heuristic; Artificial intelligence; Benchmark (surveying); Set (abstract data type); Quality (philosophy); Knowledge base; Base (topology); Case-based reasoning; Semi-supervised learning; Data mining; Selection (genetic algorithm); Mathematics","score_opus":0.10131980997354358,"score_gpt":0.31735890629918845,"score_spread":0.21603909632564489,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3168725586","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":[0.13041994,0.00001575798,0.86651284,0.0019415333,0.0004988803,0.00004427115,0.00002403217,0.00003148452,0.0005112411],"genre_scores_gemma":[0.98513484,0.000044872042,0.0131297875,0.0012619606,0.00028974336,0.0000041859867,0.0001009912,0.000009490148,0.000024104349],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99829954,0.00030262477,0.00047880708,0.00032302373,0.0004481254,0.00014789392],"domain_scores_gemma":[0.99796444,0.00019988796,0.00034392823,0.00017166218,0.0011805458,0.00013953846],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005458325,0.00013543818,0.00015089585,0.00022908206,0.00012752124,0.00038573955,0.00038078564,0.000061812505,0.00013340713],"category_scores_gemma":[0.00049082725,0.00012432928,0.00008369869,0.00017689492,0.000048895432,0.0006170709,0.00006158501,0.00045589232,0.00003818686],"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":[0.000069449,0.00025370714,0.0002781691,0.000008239659,0.000026794045,0.0012862026,0.00059517135,0.002381771,0.0015213402,0.00069721934,0.000019715022,0.9928622],"study_design_scores_gemma":[0.00022887859,0.00031901104,0.00044191434,0.00016692463,0.000017022447,0.004213965,0.002146279,0.9602967,0.02697151,0.0045307064,0.0004118175,0.000255264],"about_ca_topic_score_codex":0.000025262501,"about_ca_topic_score_gemma":0.000011296809,"teacher_disagreement_score":0.99260694,"about_ca_system_score_codex":0.000053232325,"about_ca_system_score_gemma":0.000105111416,"threshold_uncertainty_score":0.5070001},"labels":[],"label_agreement":null},{"id":"W3171883680","doi":"10.21428/594757db.521714b7","title":"Incremental Learning with Self-labeling of Incoming High-dimensional Data","year":2021,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","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":false,"ca_institutions":"University of Regina","funders":"","keywords":"Incremental learning; Computer science; Curse of dimensionality; Dimensionality reduction; Artificial intelligence; Classifier (UML); Labeled data; Machine learning; Pattern recognition (psychology)","score_opus":0.02090479990951331,"score_gpt":0.2549431291356656,"score_spread":0.23403832922615228,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3171883680","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":[0.33206043,0.0001419903,0.6615971,0.001926078,0.00015190357,0.000080565136,0.000008385209,0.00040742024,0.003626172],"genre_scores_gemma":[0.6042831,0.0000037204775,0.39534822,0.00007488982,0.000017309467,6.8578186e-7,0.00013666588,0.000003911504,0.00013150559],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989167,0.00011008158,0.00017372744,0.00038476507,0.00029256646,0.00012219574],"domain_scores_gemma":[0.9988671,0.000109247565,0.00010440112,0.0007843078,0.000092808405,0.00004216939],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004196267,0.00007532066,0.00010838678,0.00004695936,0.00012124896,0.00006945925,0.0005957603,0.0000243981,0.00004835918],"category_scores_gemma":[0.00009559461,0.00006173059,0.000009726127,0.00028241065,0.000015348667,0.0005006494,0.0009209059,0.00017136619,0.000017767417],"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":[0.000069807626,0.0010875133,0.17836046,0.00024817837,0.00041076372,0.0001729066,0.0016910188,0.015463046,0.24608608,0.28842834,0.0032802618,0.2647016],"study_design_scores_gemma":[0.00086478225,0.00011356691,0.013443413,0.0000765404,0.000022956316,0.00007902656,0.0001522133,0.9629084,0.017085424,0.00014229468,0.0048561343,0.00025528838],"about_ca_topic_score_codex":0.00016826444,"about_ca_topic_score_gemma":0.000033383825,"teacher_disagreement_score":0.94744533,"about_ca_system_score_codex":0.000016008578,"about_ca_system_score_gemma":0.00012756183,"threshold_uncertainty_score":0.25173005},"labels":[],"label_agreement":null},{"id":"W3173288964","doi":"","title":"Nonparametric Regression with Shallow Overparametrized Neural Networks Trained by GD with Early Stopping","year":2021,"lang":"en","type":"article","venue":"Conference on Learning Theory","topic":"Machine Learning and Data Classification","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":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Early stopping; Lipschitz continuity; Artificial neural network; Nonparametric statistics; Noise (video); Kernel (algebra); Nonparametric regression; Kernel regression; Computer science; Regression; Mathematics; Stochastic gradient descent; Gradient descent; Artificial intelligence; Algorithm; Pattern recognition (psychology); Statistics; Discrete mathematics; Mathematical analysis","score_opus":0.017533912706447753,"score_gpt":0.24806449918660997,"score_spread":0.23053058648016223,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3173288964","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":[0.13718185,0.00023863188,0.8562986,0.00093197724,0.00011193474,0.00015424307,0.000001944588,0.00042343387,0.0046573533],"genre_scores_gemma":[0.9886162,0.00004860498,0.007759444,0.00029588817,0.000047370042,0.000023599494,0.00007957862,0.00003217488,0.0030971183],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99694747,0.00088262773,0.00025698385,0.0009101014,0.00052224664,0.00048057604],"domain_scores_gemma":[0.9974723,0.00090677454,0.00031837588,0.0008838845,0.00022739256,0.00019131311],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00087082817,0.0003284532,0.00035987244,0.00023703798,0.00038388334,0.00061571965,0.0007636517,0.00013880561,0.00008391469],"category_scores_gemma":[0.0007311957,0.0002351858,0.00006063877,0.0015025885,0.00012912652,0.00047502993,0.00014925796,0.0011757354,0.00002785183],"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":[0.0015969224,0.00045505416,0.023918295,0.000061416074,0.00017133406,0.0002871182,0.0020258871,0.05412488,0.0031653806,0.24704354,0.00045426836,0.6666959],"study_design_scores_gemma":[0.0016439651,0.0011058701,0.013555924,0.0003169813,0.00002868756,0.00006177541,0.00022986555,0.9796097,0.00022942162,0.0008236279,0.0018203511,0.00057380064],"about_ca_topic_score_codex":0.000016887303,"about_ca_topic_score_gemma":0.000004592549,"teacher_disagreement_score":0.92548484,"about_ca_system_score_codex":0.00005226528,"about_ca_system_score_gemma":0.00016193494,"threshold_uncertainty_score":0.95905983},"labels":[],"label_agreement":null},{"id":"W3173576323","doi":"10.48550/arxiv.2106.10865","title":"Benign Overfitting in Multiclass Classification: All Roads Lead to Interpolation","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Simons Institute for the Theory of Computing, University of California Berkeley; King Abdullah University of Science and Technology; National Science Foundation","keywords":"Overfitting; Support vector machine; Artificial intelligence; Computer science; Interpretability; Machine learning; Pattern recognition (psychology); Multiclass classification; Structural risk minimization; Binary classification; Multinomial logistic regression; Artificial neural network; Mathematics; Algorithm","score_opus":0.11989088008773824,"score_gpt":0.23569305859118153,"score_spread":0.11580217850344329,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3173576323","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":[0.28034243,0.00002893815,0.71548605,0.0010133862,0.00047555505,0.00025199674,0.000005854873,0.00020072072,0.002195033],"genre_scores_gemma":[0.9857992,0.000051995117,0.012885602,0.0002493832,0.00007425247,0.0000033470187,0.00016554445,0.000017586599,0.0007530838],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973259,0.00036546143,0.00035329233,0.0014808169,0.0001394439,0.00033511716],"domain_scores_gemma":[0.9975922,0.000159314,0.00030841626,0.0016025768,0.00017960303,0.00015786933],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00054575823,0.00028252252,0.00030024984,0.0004578264,0.00010098708,0.0003429749,0.0015255039,0.00028753572,0.000020018666],"category_scores_gemma":[0.00024623537,0.00035872014,0.00012019275,0.0009203469,0.000035449466,0.0006140755,0.0015906304,0.0008108943,0.00010821509],"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":[0.00010630336,0.0006390256,0.14304875,0.00024323002,0.00016225719,0.00041881792,0.007293143,0.49911126,0.0059106555,0.30182952,0.0011018176,0.0401352],"study_design_scores_gemma":[0.00030019143,0.000026298265,0.060333576,0.00013611553,0.000017124335,0.0000023879231,0.00035842246,0.9360669,0.00007136891,0.0009098983,0.0014193509,0.0003583632],"about_ca_topic_score_codex":0.0005064109,"about_ca_topic_score_gemma":0.00043760025,"teacher_disagreement_score":0.70545673,"about_ca_system_score_codex":0.00037331233,"about_ca_system_score_gemma":0.00019275528,"threshold_uncertainty_score":0.99988645},"labels":[],"label_agreement":null},{"id":"W3173940976","doi":"","title":"HyperNOMAD: Hyperparameter optimization of deep neural networks using mesh adaptive direct search","year":2019,"lang":"en","type":"article","venue":"PolyPublie (École Polytechnique de Montréal)","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal; Group for Research in Decision Analysis","funders":"","keywords":"MNIST database; Hyperparameter; Computer science; Artificial intelligence; Artificial neural network; Machine learning; Flexibility (engineering); Process (computing); Deep learning; Categorical variable; Mathematics","score_opus":0.01656619601874932,"score_gpt":0.24225709994542838,"score_spread":0.22569090392667907,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3173940976","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":[0.06686341,0.0003922599,0.9305897,0.0004253315,0.00015120447,0.00047631242,0.000007579426,0.00037059706,0.0007236486],"genre_scores_gemma":[0.68930566,0.000025637975,0.3101979,0.00025629942,0.00004310821,0.000029090135,0.000023616582,0.000026443595,0.00009225757],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977479,0.00033340318,0.00042515676,0.0005772337,0.00039979594,0.0005164958],"domain_scores_gemma":[0.9979922,0.00020561679,0.00026551992,0.0011964769,0.00017471758,0.00016544829],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00070828013,0.0002529053,0.0003553934,0.00036224717,0.00014235309,0.00019222185,0.00095185544,0.00020122212,0.000030954085],"category_scores_gemma":[0.00009910979,0.00024749342,0.00012908257,0.00080128474,0.000060182436,0.00077880145,0.0003826454,0.00040966386,0.000009465761],"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":[0.000040413288,0.00007662693,0.024779731,0.000013223839,0.000023321134,0.0000046938844,0.00013409695,0.9372191,0.0015024706,0.0067407656,0.00002306958,0.029442508],"study_design_scores_gemma":[0.0002615273,0.00015430196,0.010579707,0.000020252299,0.000015179436,0.00003969684,0.00003253671,0.9875573,0.00096937845,0.000063114436,0.000054502372,0.00025252337],"about_ca_topic_score_codex":0.0029738836,"about_ca_topic_score_gemma":0.00011094298,"teacher_disagreement_score":0.62244225,"about_ca_system_score_codex":0.00019334926,"about_ca_system_score_gemma":0.0000822651,"threshold_uncertainty_score":0.99999774},"labels":[],"label_agreement":null},{"id":"W3174302393","doi":"10.1609/aaai.v35i10.17105","title":"Precision-based Boosting","year":2021,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"AdaBoost; Boosting (machine learning); Classifier (UML); Computer science; Artificial intelligence; Mistake; Pattern recognition (psychology); Word error rate; Machine learning; Class (philosophy)","score_opus":0.07738616526443978,"score_gpt":0.3108552515835713,"score_spread":0.23346908631913152,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3174302393","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":[0.1370701,0.00013506506,0.69167817,0.051468935,0.0016838891,0.0007093548,0.000017183402,0.0005820683,0.11665525],"genre_scores_gemma":[0.9847802,0.000010503684,0.014430208,0.0003598349,0.00004702553,0.00001152932,0.0000017231371,0.0000076082724,0.00035138873],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9983699,0.000031132564,0.00040969136,0.00048566048,0.00047249126,0.00023112392],"domain_scores_gemma":[0.9981799,0.00021461087,0.00031147682,0.00044458229,0.0007798727,0.0000695593],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005284098,0.00014641426,0.00016642957,0.000077915254,0.00021793242,0.00032554558,0.0015497211,0.00006480842,0.00008448169],"category_scores_gemma":[0.0019245293,0.00011156456,0.000090893416,0.0007406824,0.00010549753,0.00028606938,0.00032223028,0.00029053172,0.0001112156],"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":[0.000013351021,0.0000737556,0.00044505205,0.0000231271,0.000004344892,6.0564304e-7,0.00023904575,0.000109642744,0.05433329,0.75616455,0.00017899879,0.18841425],"study_design_scores_gemma":[0.000023007253,0.000071380346,0.0011856746,0.00022354232,0.000006698728,0.000003627467,0.0001729556,0.3145382,0.60958916,0.07310906,0.0009024307,0.0001742091],"about_ca_topic_score_codex":0.00001694697,"about_ca_topic_score_gemma":0.000005431306,"teacher_disagreement_score":0.8477101,"about_ca_system_score_codex":0.000028002036,"about_ca_system_score_gemma":0.00019975976,"threshold_uncertainty_score":0.45494705},"labels":[],"label_agreement":null},{"id":"W3177819996","doi":"10.1007/978-3-030-88210-5_25","title":"Label Noise in Segmentation Networks: Mitigation Must Deal with Bias","year":2021,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Computer science; Segmentation; Noise (video); Artificial intelligence; Pattern recognition (psychology); Machine learning","score_opus":0.023540115029536256,"score_gpt":0.2589179553971054,"score_spread":0.23537784036756912,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3177819996","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":[0.0008119659,0.0002883611,0.9960779,0.00090071175,0.00042766627,0.000296326,0.000002780387,0.000109029694,0.0010852688],"genre_scores_gemma":[0.2419704,0.00010262521,0.75554276,0.001407387,0.00039880062,0.000025255506,0.00018378615,0.000038492006,0.0003305079],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99692637,0.00009424327,0.00044703562,0.0013259957,0.0007687653,0.0004375786],"domain_scores_gemma":[0.99806553,0.00036476954,0.00033040126,0.0009260783,0.000199992,0.00011322813],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008690321,0.00036710952,0.0003380489,0.0006320948,0.00017560128,0.00065217586,0.0013382101,0.0002247892,0.000010731234],"category_scores_gemma":[0.00005760707,0.0003279296,0.00004095166,0.0010199407,0.00026326085,0.00077030016,0.00044900135,0.0008007973,0.00001542465],"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":[0.000007717038,0.000039250124,0.0022711656,0.000030517376,0.0000058993523,0.00007746368,0.00045330427,0.17591761,0.00012706182,0.01049993,0.000013294589,0.81055677],"study_design_scores_gemma":[0.0005023171,0.0001680197,0.0041342704,0.00052047864,0.000006662114,0.000052555843,7.4229314e-7,0.988858,0.0002628635,0.004484085,0.0005213577,0.00048865506],"about_ca_topic_score_codex":0.000068142486,"about_ca_topic_score_gemma":0.00096913404,"teacher_disagreement_score":0.81294036,"about_ca_system_score_codex":0.00030437743,"about_ca_system_score_gemma":0.00047264612,"threshold_uncertainty_score":0.99991727},"labels":[],"label_agreement":null},{"id":"W3179186621","doi":"10.1109/memea52024.2021.9478696","title":"Biological Data Classification via Faster MAXimum Feasible Subsystem Algorithm","year":2021,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Hyperparameter; Computer science; Naive Bayes classifier; Support vector machine; Machine learning; Artificial intelligence; Statistical classification; Algorithm; Precision and recall; Logistic regression; Data mining","score_opus":0.11923392680673482,"score_gpt":0.3128357248205287,"score_spread":0.19360179801379385,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3179186621","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":[0.0006163889,0.00012675233,0.9865062,0.0043754657,0.00038064708,0.000087528126,0.000021810089,0.00031079073,0.0075744176],"genre_scores_gemma":[0.5352664,0.00006179669,0.4561973,0.0008876799,0.00034746446,0.000021441881,0.0032875345,0.00001484449,0.003915541],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99814826,0.0002568882,0.0002684127,0.00085625553,0.000243136,0.00022703377],"domain_scores_gemma":[0.9971237,0.00007881076,0.00009891849,0.0024807293,0.00012039824,0.000097397766],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005413553,0.00012496606,0.00014539197,0.000055702738,0.00013037371,0.0003054338,0.0014881896,0.0000971053,0.00013394958],"category_scores_gemma":[0.000105712636,0.00009847736,0.000031572326,0.000442252,0.00002867801,0.00067152426,0.00080029864,0.0001653382,0.0006699338],"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":[0.0000016730618,0.00014168206,0.004014367,0.000012822191,0.000017438504,0.00002272232,0.000060504037,0.0000031275094,0.009037613,0.03347929,0.010224835,0.9429839],"study_design_scores_gemma":[0.00020101544,0.000028255723,0.022061119,0.000007758546,0.000004666895,0.000096776486,0.00006217673,0.8837095,0.0007139259,0.00072999904,0.092188284,0.00019651136],"about_ca_topic_score_codex":0.000031876225,"about_ca_topic_score_gemma":0.000016074353,"teacher_disagreement_score":0.9427874,"about_ca_system_score_codex":0.000031678926,"about_ca_system_score_gemma":0.00008783149,"threshold_uncertainty_score":0.86108667},"labels":[],"label_agreement":null},{"id":"W3182947351","doi":"10.1007/s10994-021-05980-1","title":"Triply stochastic gradient method for large-scale nonlinear similar unlabeled classification","year":2021,"lang":"en","type":"article","venue":"Machine Learning","topic":"Machine Learning and Data Classification","field":"Computer Science","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":"Western University","funders":"Priority Academic Program Development of Jiangsu Higher Education Institutions; Government of Jiangsu Province; Six Talent Peaks Project in Jiangsu Province; National Natural Science Foundation of China","keywords":"Scalability; Classifier (UML); Computer science; Artificial intelligence; Generalization; Machine learning; Kernel (algebra); Stochastic gradient descent; Benchmark (surveying); Data point; Nonlinear system; Scale (ratio); Linear classifier; Algorithm; Mathematics; Artificial neural network","score_opus":0.024356367146481445,"score_gpt":0.3079578563482156,"score_spread":0.28360148920173417,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3182947351","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":[0.0017207799,0.00037016824,0.9895494,0.006588617,0.00034681335,0.0002890391,0.00003532015,0.00046372743,0.0006361252],"genre_scores_gemma":[0.15939605,0.000030439702,0.8339679,0.0008141656,0.00029558584,0.00013354412,0.0013375324,0.000060264025,0.003964481],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971566,0.0005810369,0.0004578716,0.0009221923,0.00036730754,0.0005149725],"domain_scores_gemma":[0.99785346,0.0005692575,0.0002940671,0.0008349519,0.0002822647,0.00016597692],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0015761071,0.00026105918,0.00033707827,0.00017345084,0.0006090223,0.00028828645,0.00063228287,0.00012295166,0.000051946863],"category_scores_gemma":[0.0013424793,0.00025837208,0.00016208529,0.0007241412,0.00001766507,0.0003290605,0.0002458759,0.00055682374,0.00006181988],"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":[0.00021427177,0.0016494818,0.011998376,0.0004187297,0.0002788752,0.00004935765,0.007543456,0.09687438,0.046444427,0.19708796,0.0037811573,0.63365954],"study_design_scores_gemma":[0.0009780715,0.00010597069,0.0025636242,0.00002122874,0.000030103349,0.000023214985,0.00013748612,0.8654332,0.0003861267,0.00060693384,0.12945557,0.0002584526],"about_ca_topic_score_codex":0.000027002046,"about_ca_topic_score_gemma":0.00006664413,"teacher_disagreement_score":0.76855886,"about_ca_system_score_codex":0.000080593185,"about_ca_system_score_gemma":0.00013553242,"threshold_uncertainty_score":0.9999868},"labels":[],"label_agreement":null},{"id":"W3191277661","doi":"10.1109/bhi50953.2021.9508596","title":"Cold-Start Hospital Length of Stay Prediction Using Positive-Unlabeled Learning","year":2021,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","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":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Artificial intelligence; Machine learning; Computer science; Health care","score_opus":0.013503754380405604,"score_gpt":0.2423270858186671,"score_spread":0.2288233314382615,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3191277661","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":[0.37258703,0.00006464258,0.6240148,0.0004282446,0.00019191738,0.00006540369,0.000007021457,0.00015184989,0.002489117],"genre_scores_gemma":[0.94985175,0.000015642938,0.04907618,0.00003878205,0.00003879782,0.0000018633269,0.000048766815,0.0000066004545,0.0009215944],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989338,0.00016110536,0.00020762274,0.00030970288,0.0002379448,0.00014981307],"domain_scores_gemma":[0.99921876,0.000076426346,0.000121727644,0.00032895818,0.00020310927,0.00005099503],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025401425,0.00008386959,0.00011971689,0.00006116691,0.00013404667,0.00008625533,0.00020330043,0.000046640605,0.00004499086],"category_scores_gemma":[0.00015689341,0.00008262667,0.000039698432,0.00035347766,0.00002391963,0.00045642062,0.00014402502,0.00017559953,0.000012916493],"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":[0.000025463587,0.0008848952,0.2516577,0.00010614655,0.0002080518,0.000047222984,0.003503894,0.009427453,0.3755251,0.2763879,0.0013624687,0.08086369],"study_design_scores_gemma":[0.00054296805,0.00030881402,0.0878097,0.000050019735,0.000021594744,0.00001484771,0.0002848972,0.85813826,0.045740917,0.00014100876,0.006728567,0.00021842554],"about_ca_topic_score_codex":0.000074218806,"about_ca_topic_score_gemma":0.000004540621,"teacher_disagreement_score":0.8487108,"about_ca_system_score_codex":0.00003736992,"about_ca_system_score_gemma":0.0001023052,"threshold_uncertainty_score":0.33694178},"labels":[],"label_agreement":null},{"id":"W3193959263","doi":"10.1051/itmconf/20171400002","title":"Explaining the Results of an Optimization-Based Decision Support System – A Machine Learning Approach","year":2017,"lang":"en","type":"article","venue":"DOAJ (DOAJ: Directory of Open Access Journals)","topic":"Machine Learning and Data Classification","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":false,"ca_institutions":"Tetra Tech (Canada); Université Laval","funders":"","keywords":"Computer science; Machine learning; Classifier (UML); Artificial intelligence; Decision support system; Decision tree; Software; Data mining","score_opus":0.21294258851328268,"score_gpt":0.5079612200032303,"score_spread":0.2950186314899476,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3193959263","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":[0.030655611,0.00077274843,0.953605,0.0003500181,0.00047093644,0.00048153428,0.000048204252,0.00012297205,0.013492954],"genre_scores_gemma":[0.95392346,0.000217892,0.045470234,0.00005051963,0.00008265479,0.000024858353,0.000097035794,0.00002727945,0.000106060754],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9964569,0.0007058625,0.0010082088,0.00061492133,0.00092773966,0.0002863404],"domain_scores_gemma":[0.9939013,0.0006768435,0.0027144754,0.0021239517,0.00039560226,0.00018779418],"candidate_categories":["sts","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0055638445,0.00025125925,0.00053314236,0.000483672,0.0013605903,0.003544901,0.00912536,0.000095469964,0.00016169588],"category_scores_gemma":[0.0019328846,0.00018218585,0.00012401896,0.000511788,0.00013144762,0.003853236,0.0013591284,0.00051865476,0.000004960986],"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":[0.00050551567,0.00034102745,0.09949364,0.00015235253,0.0000863877,0.000024481575,0.00079765165,0.7742369,0.0020773774,0.0015411108,0.0023344718,0.11840908],"study_design_scores_gemma":[0.00086792815,0.000028239621,0.08899961,0.0002840819,0.000025999869,0.000016676478,0.00009204654,0.9067988,0.0009189501,0.000100832345,0.001644106,0.00022272248],"about_ca_topic_score_codex":0.0010688294,"about_ca_topic_score_gemma":0.000020595642,"teacher_disagreement_score":0.92326784,"about_ca_system_score_codex":0.000058025413,"about_ca_system_score_gemma":0.00020214886,"threshold_uncertainty_score":0.9999395},"labels":[],"label_agreement":null},{"id":"W3196967454","doi":"10.1109/qrs54544.2021.00116","title":"The Challenge of Reproducible ML: An Empirical Study on The Impact of Bugs","year":2021,"lang":"en","type":"article","venue":"2021 IEEE 21st International Conference on Software Quality, Reliability and Security (QRS)","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Computer science; Determinism; Inference; Software bug; Reproducibility; Software; Machine learning; Artificial intelligence; Face (sociological concept); Causal inference; Software engineering; Programming language; Statistics","score_opus":0.11430068119320197,"score_gpt":0.4201996151009927,"score_spread":0.3058989339077907,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3196967454","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":[0.9764558,0.000059228256,0.0039467206,0.01578588,0.00042145964,0.0003392248,0.00013824206,0.000058144928,0.002795313],"genre_scores_gemma":[0.99914926,0.00018975008,0.0002789745,0.000104916006,0.000085133586,0.000025706746,0.000039788654,0.000007313386,0.00011916431],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9956048,0.0016934852,0.0006928632,0.00093746214,0.0008682088,0.00020318285],"domain_scores_gemma":[0.99469453,0.0016019575,0.00039119265,0.002193066,0.0010185991,0.00010063599],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0042963573,0.00020692778,0.00032957303,0.00006241138,0.0002549404,0.00023834196,0.0012607386,0.000098723045,0.00014041018],"category_scores_gemma":[0.0041578556,0.00012762083,0.00016132378,0.00029092852,0.00025482714,0.0002703684,0.0003252844,0.0005532941,0.000011311241],"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":[0.00043992128,0.007763709,0.2064069,0.00011805059,0.00030659093,0.000010402311,0.025873406,0.00036685434,0.0004438902,0.7220569,0.0008686363,0.035344686],"study_design_scores_gemma":[0.0014603047,0.003968172,0.7161769,0.00022337379,0.000039210932,0.000014152122,0.008127679,0.041501656,0.0019217816,0.22352718,0.0023011477,0.0007384323],"about_ca_topic_score_codex":0.0007344012,"about_ca_topic_score_gemma":0.00020653602,"teacher_disagreement_score":0.50977,"about_ca_system_score_codex":0.00006738812,"about_ca_system_score_gemma":0.00032618412,"threshold_uncertainty_score":0.5204227},"labels":[],"label_agreement":null},{"id":"W3198645887","doi":"10.14778/3476249.3476304","title":"Explaining inference queries with bayesian optimization","year":2021,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Inference; Python (programming language); Bayesian inference; Query optimization; Predicate (mathematical logic); Bayesian probability; Data mining; Information retrieval; Theoretical computer science; Artificial intelligence; Programming language","score_opus":0.010849102484855025,"score_gpt":0.230534737405498,"score_spread":0.219685634920643,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3198645887","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":[0.018158924,0.00010999857,0.9489129,0.008225379,0.00017292488,0.00022891702,0.0000025909967,0.00018301408,0.02400531],"genre_scores_gemma":[0.86676115,0.000025763002,0.1328185,0.00010743906,0.000018055447,0.000020438607,0.0000030121548,0.000005056619,0.00024057478],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99921966,0.000010206338,0.00014933074,0.00023543503,0.0002607639,0.00012459555],"domain_scores_gemma":[0.99934465,0.000033063938,0.00017946758,0.0001932817,0.00021562216,0.000033923057],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016262077,0.00008466735,0.00009384204,0.000035456647,0.00012845875,0.00014424132,0.00048126688,0.000022227552,0.00001270003],"category_scores_gemma":[0.00017639263,0.00005594676,0.000024587966,0.00037709414,0.000036193553,0.00043552092,0.00025621633,0.00009546215,0.0000016413103],"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":[0.000032864595,0.0002041107,0.061489403,0.00019923106,0.00006567672,0.0000023600667,0.0062238458,0.019589946,0.020793522,0.8592628,0.00085768267,0.03127851],"study_design_scores_gemma":[0.0014919383,0.00037834127,0.026113223,0.00073975633,0.00006319653,0.00011481956,0.0030301565,0.61113423,0.3404017,0.0054568923,0.010341077,0.0007346419],"about_ca_topic_score_codex":0.000016841266,"about_ca_topic_score_gemma":0.0000031902534,"teacher_disagreement_score":0.85380596,"about_ca_system_score_codex":0.00002555895,"about_ca_system_score_gemma":0.00006039668,"threshold_uncertainty_score":0.22814426},"labels":[],"label_agreement":null},{"id":"W3198964105","doi":"10.1007/978-3-030-86593-1_14","title":"Minimum Consistent Subset Problem for Trees","year":2021,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Combinatorics; Vertex (graph theory); Colored; Planar graph; Chromatic scale; Graph; Undirected graph; Mathematics; Time complexity; Computer science; Discrete mathematics","score_opus":0.026286471008057522,"score_gpt":0.26399217281602244,"score_spread":0.2377057018079649,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3198964105","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":[0.000020290398,0.00059884635,0.990762,0.0033308133,0.0010531942,0.0004974884,0.00002392165,0.00015982616,0.0035536245],"genre_scores_gemma":[0.035130054,0.000069024725,0.959442,0.0017288084,0.00052766816,0.00005250183,0.00015104249,0.00004344486,0.0028554494],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99652296,0.000044516473,0.00051331084,0.0016900774,0.00068459514,0.0005445605],"domain_scores_gemma":[0.99690247,0.00069119036,0.00032598467,0.0015817686,0.00034459852,0.00015398007],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00091014,0.00042527376,0.00048091685,0.00047067355,0.00027990976,0.00076004636,0.0024802254,0.00026026543,0.000018173369],"category_scores_gemma":[0.00018580271,0.00038765042,0.00016614347,0.0004151224,0.0003900554,0.00038387984,0.0008362169,0.00054110284,0.000024929188],"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":[0.000007329882,0.00004649639,0.000091935595,0.00009950783,0.000017394128,0.00003549297,0.000428193,0.0060286014,0.0003266123,0.12962125,0.0003099563,0.8629872],"study_design_scores_gemma":[0.0006326855,0.00033472505,0.00039686344,0.0006001669,0.000023130418,0.00011624556,4.900229e-7,0.8147749,0.0009234069,0.11331188,0.06779221,0.0010933138],"about_ca_topic_score_codex":0.000015140948,"about_ca_topic_score_gemma":0.00015135607,"teacher_disagreement_score":0.8618939,"about_ca_system_score_codex":0.0001740425,"about_ca_system_score_gemma":0.0007041381,"threshold_uncertainty_score":0.99985754},"labels":[],"label_agreement":null},{"id":"W3199268650","doi":"10.23977/jaip.2020.040104","title":"Progressive Sampling-Based Joint Automatic Model Selection of Machine Learning and Feature Selection","year":2021,"lang":"en","type":"article","venue":"Journal of Artificial Intelligence Practice","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Machine learning; Artificial intelligence; Computer science; Feature selection; Hyperparameter; Model selection; Selection (genetic algorithm); Data pre-processing; Bayesian optimization; Preprocessor; Feature (linguistics); Bayesian inference; Bayesian probability","score_opus":0.055212396438347966,"score_gpt":0.35274937334783774,"score_spread":0.29753697690948977,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3199268650","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":[0.013534159,0.0005102066,0.9803519,0.0052273707,0.00015128618,0.00007526399,0.000001026924,0.000043263528,0.00010552275],"genre_scores_gemma":[0.6382697,0.00006930023,0.36144948,0.00008797356,0.000074298056,0.0000018876482,0.000003122575,0.000007871241,0.000036312234],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981367,0.0004272038,0.0006038235,0.00023818579,0.0004352918,0.00015881789],"domain_scores_gemma":[0.9965323,0.0005382881,0.001417959,0.00013576902,0.0012877978,0.00008789055],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014364324,0.00012665233,0.00023688689,0.00020940027,0.00020011474,0.00024318852,0.00018949856,0.000089600966,0.000023300812],"category_scores_gemma":[0.0047142464,0.00011437219,0.00007466988,0.00068074424,0.000042976048,0.0011256686,0.000059576072,0.0007956004,0.000004066223],"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":[0.00022809544,0.0007664388,0.0011578461,0.00017872942,0.00012610825,0.00005066239,0.0017637635,0.2631367,0.09523108,0.018891525,0.000104781655,0.6183643],"study_design_scores_gemma":[0.00004583364,0.00030546368,0.0001699155,0.00009082301,0.000055165616,0.00060957833,0.00023646367,0.9334576,0.06236923,0.0017977672,0.0007611269,0.00010103561],"about_ca_topic_score_codex":0.000017209943,"about_ca_topic_score_gemma":0.000012462635,"teacher_disagreement_score":0.67032087,"about_ca_system_score_codex":0.00006370462,"about_ca_system_score_gemma":0.00040605108,"threshold_uncertainty_score":0.5643734},"labels":[],"label_agreement":null},{"id":"W3199600733","doi":"10.1287/ijoc.2020.1023","title":"JANOS: An Integrated Predictive and Prescriptive Modeling Framework","year":2022,"lang":"en","type":"article","venue":"Archivio istituzionale della ricerca (Alma Mater Studiorum Università di Bologna)","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":43,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Computer science; Predictive analytics; Machine learning; Solver; Artificial intelligence; Flexibility (engineering); Artificial neural network; Data mining","score_opus":0.01949630646604297,"score_gpt":0.23627289788862255,"score_spread":0.21677659142257957,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3199600733","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":[0.15331663,0.0002506993,0.824099,0.0018212271,0.0004600514,0.0003988002,0.00028379058,0.00042736455,0.01894244],"genre_scores_gemma":[0.974167,0.00010452072,0.020904358,0.0003197449,0.00005921116,0.000040913485,0.0002939922,0.000023577444,0.0040866714],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9971761,0.0005640803,0.00025898908,0.0010094111,0.0005121705,0.00047924358],"domain_scores_gemma":[0.99863625,0.00017675558,0.00015310483,0.00070977584,0.00012632599,0.00019781374],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0003918413,0.00030726974,0.0002989786,0.0003422317,0.0014751421,0.00015049492,0.0012608253,0.0000734459,0.000057864065],"category_scores_gemma":[0.000056532102,0.00031525688,0.000070147194,0.00051580864,0.00018316283,0.00084510876,0.002032164,0.0007427932,0.000023728167],"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":[0.00039792934,0.00059715664,0.013651172,0.000042500815,0.00027854627,0.00022915947,0.011880389,0.06689469,0.0005238915,0.89460814,0.0013132736,0.00958313],"study_design_scores_gemma":[0.00077374553,0.00074666156,0.022157187,0.000044112538,0.0000867337,0.0001254538,0.004763317,0.92469275,0.000030082352,0.006976397,0.03895027,0.00065330765],"about_ca_topic_score_codex":0.00011091687,"about_ca_topic_score_gemma":0.000021509348,"teacher_disagreement_score":0.8876318,"about_ca_system_score_codex":0.00019975161,"about_ca_system_score_gemma":0.00014550598,"threshold_uncertainty_score":0.99992996},"labels":[],"label_agreement":null},{"id":"W3205360344","doi":"10.1109/ichi52183.2021.00019","title":"An Empirical Investigation of PU Learning for Predicting Length of Stay","year":2021,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Artificial intelligence; Coronavirus disease 2019 (COVID-19); Machine learning; Computer science; Affect (linguistics); Patient care; Medicine; Psychology; Nursing","score_opus":0.04142016933193261,"score_gpt":0.3263854123188732,"score_spread":0.2849652429869406,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3205360344","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":[0.3262148,0.000014387832,0.67254966,0.00052341743,0.000036503796,0.00004122311,0.0000014153344,0.000057851066,0.00056075567],"genre_scores_gemma":[0.8638163,0.0000023069572,0.13591452,0.000048040358,0.00002264174,0.000003620284,0.000053003085,0.0000032425278,0.00013629874],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99922675,0.00013624817,0.00021277722,0.00020110451,0.00014235702,0.00008075991],"domain_scores_gemma":[0.9991618,0.00019499636,0.00014376614,0.00028159277,0.00017521762,0.000042649015],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004532535,0.000045015655,0.000093313116,0.00004459346,0.000053572967,0.000028663355,0.00020062408,0.00003424166,0.000008947081],"category_scores_gemma":[0.0004601066,0.000041349722,0.000026533677,0.00021746995,0.000022738664,0.0003038938,0.000051801188,0.00008486823,8.5816635e-7],"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":[0.000008015782,0.00007430306,0.81874895,0.00010556679,0.000018419036,5.2534693e-7,0.002560427,0.002963541,0.072300196,0.034067657,0.00028651036,0.06886587],"study_design_scores_gemma":[0.00018506858,0.00016297547,0.1261311,0.000015624235,0.0000055259666,0.0000019778888,0.0002256464,0.8191565,0.051947497,0.00094766053,0.0011606338,0.00005974474],"about_ca_topic_score_codex":0.000023253353,"about_ca_topic_score_gemma":0.000008275361,"teacher_disagreement_score":0.816193,"about_ca_system_score_codex":0.0000072474186,"about_ca_system_score_gemma":0.00008830252,"threshold_uncertainty_score":0.16861928},"labels":[],"label_agreement":null},{"id":"W3205700046","doi":"10.1109/smartiot52359.2021.00060","title":"Machine Learning-as-a-Service Performance Evaluation on Multi-class Datasets","year":2021,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Winnipeg","funders":"","keywords":"Computer science; Machine learning; Cloud computing; Artificial intelligence; Class (philosophy); Table (database); Service (business); IBM; Process (computing); Service provider; Data science; Data mining; Operating system","score_opus":0.0474917778370254,"score_gpt":0.3144535249562416,"score_spread":0.2669617471192162,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3205700046","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":[0.28580835,0.0012065065,0.46156946,0.07745925,0.0026228807,0.001466416,0.00021552571,0.0031803476,0.16647124],"genre_scores_gemma":[0.97250736,0.00010202985,0.016369868,0.004473423,0.00006097098,0.000030723888,0.0031982209,0.000014758337,0.003242622],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99811864,0.00031498476,0.00020548516,0.0005726562,0.0005754105,0.0002128203],"domain_scores_gemma":[0.99847686,0.000108808934,0.00010419687,0.000982839,0.00023603217,0.00009124644],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0008421577,0.0001446288,0.00011497297,0.000080544436,0.00025385714,0.00020827597,0.0006064378,0.000060750095,0.00040642312],"category_scores_gemma":[0.0004408095,0.00012890247,0.00002792812,0.0005472076,0.000011891781,0.00054513436,0.00026311327,0.00034746123,0.0019785168],"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":[0.000041326493,0.00075114955,0.009775503,0.00008562198,0.000047780024,0.000026548876,0.00077491504,0.027606312,0.004904199,0.06607876,0.007434345,0.8824735],"study_design_scores_gemma":[0.0005344224,0.00007101592,0.01716201,0.000016812859,0.0000075407315,0.000013468923,0.000019090152,0.89635974,0.0015172207,0.000061698636,0.08408269,0.00015426378],"about_ca_topic_score_codex":0.00015273836,"about_ca_topic_score_gemma":0.00011927881,"teacher_disagreement_score":0.8823193,"about_ca_system_score_codex":0.000055924374,"about_ca_system_score_gemma":0.00016560174,"threshold_uncertainty_score":0.99879855},"labels":[],"label_agreement":null},{"id":"W3206265976","doi":"10.48550/arxiv.2107.00848","title":"Systematic Evaluation of Causal Discovery in Visual Model Based\\n Reinforcement Learning","year":2021,"lang":"","type":"preprint","venue":"arXiv (Cornell University)","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Polytechnique Montréal","funders":"","keywords":"Causality (physics); Causal model; Causal structure; Reinforcement learning; Premise; Computer science; Modularity (biology); Artificial intelligence; Machine learning; Causal reasoning; Representation (politics); Psychology; Mathematics; Cognition","score_opus":0.09601638270821015,"score_gpt":0.24662773212372352,"score_spread":0.15061134941551335,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3206265976","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":[0.338039,0.00010118475,0.6601487,0.000031454612,0.00022466884,0.00072924106,0.0000031242032,0.000038216902,0.0006844012],"genre_scores_gemma":[0.9976476,0.00014241277,0.0006664156,0.00002456072,0.000027013524,0.000009033974,0.0002561804,0.000024466048,0.0012023222],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99313724,0.0027880094,0.0011039594,0.0017274907,0.0007680158,0.00047530347],"domain_scores_gemma":[0.9953163,0.00040293095,0.0016183167,0.0016449081,0.00086299557,0.00015451343],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0050458345,0.0005074842,0.0009267081,0.00076339964,0.0002125426,0.0003660384,0.0013342942,0.00036814908,0.00005801074],"category_scores_gemma":[0.00095436175,0.0006096404,0.00031974423,0.0014095926,0.00012312317,0.0015024877,0.0014015025,0.0011591855,0.000023700144],"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":[0.000051455554,0.00024629149,0.003414219,0.006498181,0.00009465669,0.00003338402,0.0008429593,0.97098154,0.00016829053,0.017349225,0.000002248419,0.0003175219],"study_design_scores_gemma":[0.0012584405,0.00012344283,0.0017885522,0.0070449384,0.0004936726,0.0000021227668,0.00082554726,0.9872989,0.0001279929,0.00051515375,0.0000011350836,0.00052012486],"about_ca_topic_score_codex":0.00062448054,"about_ca_topic_score_gemma":0.00016992941,"teacher_disagreement_score":0.6596086,"about_ca_system_score_codex":0.0010543307,"about_ca_system_score_gemma":0.002116486,"threshold_uncertainty_score":0.9996355},"labels":[],"label_agreement":null},{"id":"W3209720970","doi":"10.1145/3473910","title":"Semi-Supervised Ensemble Learning for Dealing with Inaccurate and Incomplete Supervision","year":2021,"lang":"en","type":"article","venue":"ACM Transactions on Knowledge Discovery from Data","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"IBM (Canada); University of Alberta","funders":"","keywords":"Computer science; Machine learning; Artificial intelligence; Classifier (UML); Ensemble learning; Supervised learning; Noise (video); Semi-supervised learning; Labeled data; Data mining; Artificial neural network","score_opus":0.059776607221555915,"score_gpt":0.3027910564366063,"score_spread":0.2430144492150504,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3209720970","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":[0.039680418,0.0006353926,0.9573585,0.0011622432,0.0001706511,0.00016293427,0.00046720746,0.00014129691,0.00022139557],"genre_scores_gemma":[0.91025007,0.00041198917,0.08588918,0.00009828782,0.00006424505,0.000030046223,0.0028408028,0.0000277228,0.0003876642],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99822265,0.0001513577,0.0002477473,0.00096790574,0.00016898336,0.00024137204],"domain_scores_gemma":[0.99657106,0.0008309593,0.00007348633,0.0022910624,0.00013550125,0.00009794674],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027541383,0.00020894116,0.00022742298,0.00007963314,0.0005407056,0.0005617004,0.0012116978,0.00007216357,0.000024323075],"category_scores_gemma":[0.00019108846,0.00018670829,0.000041444335,0.00027109066,0.000040446135,0.0020904588,0.00018756269,0.00032287385,0.00002749107],"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":[0.0002385264,0.0004968649,0.0021240085,0.00016635965,0.00022034548,0.000022512397,0.0020543423,0.0029826562,0.022526728,0.005456049,0.0003800954,0.9633315],"study_design_scores_gemma":[0.0029418538,0.000413971,0.007561781,0.00043186973,0.00017337438,0.000045883135,0.0008076325,0.91626984,0.0096697975,0.0027544764,0.05805703,0.0008724777],"about_ca_topic_score_codex":0.00021632719,"about_ca_topic_score_gemma":0.0005946452,"teacher_disagreement_score":0.962459,"about_ca_system_score_codex":0.000028545657,"about_ca_system_score_gemma":0.00013747974,"threshold_uncertainty_score":0.7613743},"labels":[],"label_agreement":null},{"id":"W3211229017","doi":"10.14778/3551793.3551804","title":"A scalable AutoML approach based on graph neural networks","year":2022,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Scalability; Scripting language; Metadata; Pipeline (software); Artificial intelligence; Machine learning; Graph; Pipeline transport; Theoretical computer science; Database; Programming language; World Wide Web","score_opus":0.012770768817358303,"score_gpt":0.21496839349981606,"score_spread":0.20219762468245775,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3211229017","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":[0.16984214,0.00091908086,0.48526505,0.081706524,0.005062535,0.006236517,0.00007373475,0.0030000778,0.24789436],"genre_scores_gemma":[0.99109983,0.0000020377447,0.0074948114,0.0009179666,0.000034033987,0.00015997852,0.00000587282,0.000009044433,0.00027640068],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986434,0.000028766097,0.00019797633,0.0003581157,0.00054267794,0.00022908194],"domain_scores_gemma":[0.9993181,0.000034188542,0.00022163267,0.000310207,0.00006639535,0.000049430768],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00061705365,0.00011886866,0.00012172312,0.00010369971,0.00038572343,0.00009674426,0.0014575786,0.00002077916,0.000016349464],"category_scores_gemma":[0.000053680164,0.000086346336,0.00009150135,0.00070227904,0.000033950477,0.00014523316,0.0006012432,0.0003255756,0.0000015755095],"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":[0.00012838113,0.0014606979,0.016204458,0.00015123459,0.000051885614,9.5124807e-7,0.0009407894,0.6324161,0.0032570483,0.24861503,0.03973371,0.057039715],"study_design_scores_gemma":[0.00029984192,0.0001360351,0.0030244654,0.000007322508,0.000007282446,0.0000053255044,0.000054025037,0.99106103,0.000464435,0.000547872,0.0042958753,0.000096466145],"about_ca_topic_score_codex":0.00003393227,"about_ca_topic_score_gemma":1.4447184e-7,"teacher_disagreement_score":0.8212577,"about_ca_system_score_codex":0.000068635316,"about_ca_system_score_gemma":0.000021174548,"threshold_uncertainty_score":0.35211012},"labels":[],"label_agreement":null},{"id":"W3211462868","doi":"","title":"Iterative Teaching by Label Synthesis","year":2021,"lang":"en","type":"article","venue":"Neural Information Processing Systems","topic":"Machine Learning and Data Classification","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":false,"ca_institutions":"McGill University; Université de Montréal","funders":"","keywords":"Computer science; Selection (genetic algorithm); Contrast (vision); Iterative method; Algorithm; Artificial intelligence; Theoretical computer science; Machine learning","score_opus":0.017800298451563695,"score_gpt":0.268583519151509,"score_spread":0.2507832206999453,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3211462868","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":[0.0067488686,0.00064646255,0.9697065,0.0034568254,0.0005901988,0.00015007133,0.000022714,0.00060220156,0.018076174],"genre_scores_gemma":[0.99334514,0.0000050226176,0.005146592,0.00056602404,0.000054482687,0.000043252785,0.00012174932,0.0000052483965,0.00071249745],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987806,0.00019100141,0.0003842042,0.00017585103,0.00029993278,0.00016840792],"domain_scores_gemma":[0.9990478,0.00009415099,0.00028674773,0.0002984763,0.00021270118,0.00006013746],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0003878561,0.000115231116,0.00013226972,0.000077090386,0.00038854862,0.0018677032,0.00034025914,0.00005557928,0.000004069192],"category_scores_gemma":[0.00039473275,0.00010180785,0.000021497939,0.00026360538,0.000013950421,0.005620966,0.000078739635,0.00022309051,0.00008391972],"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":[0.0000041000985,0.000053904576,0.0004616246,0.00039507233,0.000012505524,0.0000033210752,0.00456347,0.0007585364,0.0030296757,0.02648675,0.01686989,0.9473612],"study_design_scores_gemma":[0.000138808,0.000013668044,0.00017261205,0.000108292545,0.000004057503,0.00006400227,0.0003690473,0.8959173,0.0012052582,0.000026102425,0.10182091,0.00015993863],"about_ca_topic_score_codex":0.000030286037,"about_ca_topic_score_gemma":5.278684e-7,"teacher_disagreement_score":0.9865963,"about_ca_system_score_codex":0.000042719857,"about_ca_system_score_gemma":0.00007643625,"threshold_uncertainty_score":0.99916846},"labels":[],"label_agreement":null},{"id":"W3212638064","doi":"10.48550/arxiv.2012.12896","title":"How Does a Neural Network's Architecture Impact Its Robustness to Noisy Labels?","year":2020,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Robustness (evolution); Computer science; Network architecture; Architecture; Artificial intelligence; Predictive power; Artificial neural network; Machine learning; Pattern recognition (psychology)","score_opus":0.05291688621403645,"score_gpt":0.19300890424610756,"score_spread":0.1400920180320711,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3212638064","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":[0.29350585,0.000018030742,0.695531,0.010170955,0.00012535798,0.00013258077,0.000008739442,0.00026901654,0.0002384851],"genre_scores_gemma":[0.99618465,0.0000066848984,0.002080047,0.00075490127,0.00019040228,4.5030652e-7,0.000012597381,0.000010714618,0.00075953355],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986788,0.00014167209,0.00008108471,0.00066343835,0.00008365125,0.00035137028],"domain_scores_gemma":[0.99889135,0.00007075919,0.00008386994,0.0005269715,0.0000716368,0.00035539398],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010510846,0.00018080413,0.00016623746,0.00007819163,0.00017222698,0.0002544648,0.0011416887,0.000063593274,0.000019526853],"category_scores_gemma":[0.00009628879,0.00014597923,0.00009042193,0.0012219597,0.000024966235,0.0005796275,0.00039500248,0.00028076145,0.000053315052],"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":[0.000042033917,0.000019779089,0.0048112655,0.000014630477,0.000020593749,0.00008690041,0.00025321383,0.9696892,0.00031528348,0.018697742,0.0011545491,0.004894846],"study_design_scores_gemma":[0.00029552882,0.0001390263,0.007777532,0.000009772003,0.000013700557,0.0000051312795,0.000033032346,0.9858606,0.000056394474,0.00031880575,0.0052435757,0.00024691538],"about_ca_topic_score_codex":0.000027520407,"about_ca_topic_score_gemma":0.000032921394,"teacher_disagreement_score":0.70267886,"about_ca_system_score_codex":0.00004204281,"about_ca_system_score_gemma":0.000043191558,"threshold_uncertainty_score":0.595286},"labels":[],"label_agreement":null},{"id":"W3213378669","doi":"10.1109/tit.2023.3320098","title":"Benign Overfitting in Multiclass Classification: All Roads Lead to Interpolation","year":2023,"lang":"en","type":"article","venue":"IEEE Transactions on Information Theory","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; King Abdullah University of Science and Technology; Google; National Science Foundation","keywords":"Overfitting; Interpolation (computer graphics); Artificial intelligence; Pattern recognition (psychology); Computer science; Lead (geology); Machine learning; Mathematics; Algorithm; Data mining; Artificial neural network; Geology; Image (mathematics)","score_opus":0.02861077349041017,"score_gpt":0.28863320351680366,"score_spread":0.26002243002639347,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3213378669","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":[0.008948492,0.0000020216182,0.98369235,0.0023873344,0.0006401631,0.00029423335,0.000014578954,0.0006126398,0.0034081903],"genre_scores_gemma":[0.9922401,0.000013640717,0.0061773704,0.00095538114,0.000024964267,0.000120954835,0.000056977853,0.000009392307,0.00040122005],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984317,0.00020437292,0.00053008023,0.00024983485,0.0003219235,0.0002620797],"domain_scores_gemma":[0.9987614,0.00032196823,0.00015255548,0.0005837301,0.00009027549,0.00009004129],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0012617242,0.00015069902,0.00012472393,0.0009660172,0.00018601766,0.0002285494,0.00048545186,0.000097944176,0.00003122343],"category_scores_gemma":[0.000086158536,0.00015583089,0.000058242065,0.0013479103,0.00002366012,0.0024232017,0.0000069466782,0.0003096096,0.0024610776],"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":[0.000100330966,0.00009374992,0.00014652005,0.00003358631,0.00002239262,0.000001238622,0.01255325,0.08166648,0.002353508,0.09114589,0.0011211232,0.8107619],"study_design_scores_gemma":[0.00048713738,0.000081147315,0.00889129,0.0000465736,0.0000055442233,0.0000038302405,0.0010179636,0.9757869,0.0016432354,0.0015926255,0.010204827,0.00023892745],"about_ca_topic_score_codex":0.000028233166,"about_ca_topic_score_gemma":0.000020423955,"teacher_disagreement_score":0.9832916,"about_ca_system_score_codex":0.00012994652,"about_ca_system_score_gemma":0.000048876253,"threshold_uncertainty_score":0.99831563},"labels":[],"label_agreement":null},{"id":"W3214424617","doi":"10.1016/j.inffus.2021.10.015","title":"An investigation into the effects of label noise on Dynamic Selection algorithms","year":2021,"lang":"en","type":"article","venue":"Information Fusion","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure; Université du Québec à Montréal","funders":"Fundação de Amparo à Ciência e Tecnologia do Estado de Pernambuco; Conselho Nacional de Desenvolvimento Científico e Tecnológico; Coordenação de Aperfeiçoamento de Pessoal de Nível Superior","keywords":"Computer science; Noise (video); Selection (genetic algorithm); Algorithm; Code (set theory); Set (abstract data type); Selection algorithm; Class (philosophy); Machine learning; Data mining; Artificial intelligence","score_opus":0.005788984834492993,"score_gpt":0.24897287652156982,"score_spread":0.24318389168707683,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3214424617","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":[0.5865296,0.000027545473,0.41054535,0.0016549581,0.00042779354,0.00019571035,0.0000019652814,0.00016720168,0.00044986524],"genre_scores_gemma":[0.98416746,0.000039909963,0.0146944495,0.00070227426,0.000024245286,0.000017177837,0.00029068656,0.0000034091872,0.0000603687],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991148,0.00015470898,0.00023761737,0.00012049681,0.00029037206,0.00008200526],"domain_scores_gemma":[0.999045,0.000115414514,0.00020246733,0.00038884443,0.00020671861,0.000041546653],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003037858,0.00007574026,0.00006653724,0.00011133402,0.00020437893,0.00013168878,0.00026198238,0.000055538763,0.000004525535],"category_scores_gemma":[0.00022726988,0.000057266025,0.000019589637,0.00053575257,0.00002158482,0.0016304083,0.00005841968,0.00013386468,0.000059648883],"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":[0.000009083956,0.00006446153,0.0008956528,0.00010203426,0.0000056591944,4.2140155e-7,0.008984452,0.0012689966,0.06033574,0.017499123,0.00032872648,0.91050565],"study_design_scores_gemma":[0.00032539383,0.00019973428,0.043753743,0.000050871513,0.000004977711,0.000005152438,0.00010985558,0.9282159,0.02441044,0.00089806836,0.0019373145,0.00008852099],"about_ca_topic_score_codex":0.00010926192,"about_ca_topic_score_gemma":0.000025863452,"teacher_disagreement_score":0.92694694,"about_ca_system_score_codex":0.000046156572,"about_ca_system_score_gemma":0.000074744305,"threshold_uncertainty_score":0.23352407},"labels":[],"label_agreement":null},{"id":"W3217600415","doi":"10.48550/arxiv.2012.12896","title":"How Does a Neural Network's Architecture Impact Its Robustness to Noisy\\n Labels?","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Robustness (evolution); Computer science; Network architecture; Architecture; Predictive power; Artificial intelligence; Artificial neural network; Machine learning; Deep neural networks","score_opus":0.06389736011308098,"score_gpt":0.20980635045547222,"score_spread":0.14590899034239124,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3217600415","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":[0.1445883,0.000052484615,0.8443354,0.009026747,0.0006803358,0.00039314877,0.000055407047,0.0005333148,0.00033489137],"genre_scores_gemma":[0.99304336,0.00002994262,0.0044991192,0.00035857136,0.00041092816,0.0000021171804,0.00010186736,0.000027656717,0.0015264206],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99724907,0.00031908118,0.00016423492,0.0015784227,0.00015342033,0.0005357735],"domain_scores_gemma":[0.9974733,0.00011786234,0.00027076018,0.0015296356,0.00014933704,0.00045910844],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002100413,0.0004521409,0.00042045765,0.00021617138,0.00021824196,0.0006702196,0.0028504182,0.0002633313,0.000018973202],"category_scores_gemma":[0.00013964967,0.00038516638,0.00024999992,0.001091564,0.00004362929,0.00042843402,0.0029060922,0.0012023761,0.00005305653],"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":[0.00004299718,0.00002932227,0.0017472253,0.00006904486,0.00006187525,0.00016461509,0.00019222863,0.9779204,0.0000712632,0.014697561,0.001197461,0.0038060045],"study_design_scores_gemma":[0.00026922996,0.000097213946,0.00670694,0.00006799907,0.000048055637,0.0000075894604,0.000022473901,0.98540926,0.000024529894,0.0035070584,0.0032767511,0.00056288077],"about_ca_topic_score_codex":0.00011040556,"about_ca_topic_score_gemma":0.00009925294,"teacher_disagreement_score":0.8484551,"about_ca_system_score_codex":0.00014821018,"about_ca_system_score_gemma":0.00017194783,"threshold_uncertainty_score":0.99986005},"labels":[],"label_agreement":null},{"id":"W37862573","doi":"10.1121/10.0021887","title":"Identify, Organize, and Retrieve Items Using Zotero.","year":2009,"lang":"en","type":"article","venue":"Teacher librarian","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Information retrieval; Psychology; World Wide Web","score_opus":0.02735356471066435,"score_gpt":0.27870559635136277,"score_spread":0.2513520316406984,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W37862573","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":[0.4071046,0.00046681287,0.5626989,0.013420874,0.0003743764,0.00019999873,0.0000026383777,0.000964655,0.0147671],"genre_scores_gemma":[0.96911335,0.0000068179165,0.028717889,0.0005789831,0.0001478586,5.2354466e-7,0.000012855134,0.000009302475,0.0014124196],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99906075,0.00010305665,0.00016124609,0.00034811356,0.00014898277,0.00017787302],"domain_scores_gemma":[0.99925,0.000024047871,0.000080998376,0.0005284029,0.000015590882,0.00010096685],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026132335,0.00010762081,0.00010882138,0.000087028726,0.00012824773,0.00056682585,0.0004727541,0.00007412143,0.00004531655],"category_scores_gemma":[0.00007699455,0.000101207464,0.000019030038,0.00036449914,0.00002251384,0.001404944,0.00012715676,0.00020810365,0.000041746633],"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":[0.00003037869,0.00034938924,0.081860006,0.000035000652,0.00005251659,0.00005936133,0.007913263,0.000023863437,0.07447953,0.29162443,0.018392948,0.5251793],"study_design_scores_gemma":[0.00087968557,0.00018066289,0.7741951,0.000053284664,0.000022451019,0.000111629466,0.000104953826,0.14300859,0.002833143,0.019653192,0.058293074,0.0006642349],"about_ca_topic_score_codex":0.000038820268,"about_ca_topic_score_gemma":8.4679317e-7,"teacher_disagreement_score":0.69233507,"about_ca_system_score_codex":0.00001531351,"about_ca_system_score_gemma":0.000037119156,"threshold_uncertainty_score":0.5465915},"labels":[],"label_agreement":null},{"id":"W4200001896","doi":"10.3233/faia210316","title":"Data-Centric Machine Learning: Improving Model Performance and Understanding Through Dataset Analysis","year":2021,"lang":"en","type":"book-chapter","venue":"Frontiers in artificial intelligence and applications","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Research Unit on Children's Psychosocial Maladjustment","funders":"","keywords":"Computer science; Machine learning; Artificial intelligence; Classifier (UML); Training set; Metric (unit); Performance metric; Test set; Test data; Process (computing); Set (abstract data type); Data set; Data mining; Domain (mathematical analysis); Labeled data; Engineering; Mathematics","score_opus":0.12201287236945606,"score_gpt":0.3056667902057088,"score_spread":0.18365391783625273,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200001896","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":[0.0000072611774,0.0021303366,0.9918193,0.00036532,0.00006400014,0.00025246912,0.00085495994,0.000059685015,0.0044466583],"genre_scores_gemma":[0.20088565,0.06823183,0.58993113,0.00069531257,0.00063276326,0.00030451434,0.09885614,0.0001884874,0.0402742],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997891,0.00003526374,0.0004996599,0.0011006868,0.00023180942,0.00024157458],"domain_scores_gemma":[0.99825907,0.000079269295,0.0002839549,0.0012493825,0.00004111745,0.00008719785],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004147752,0.00026015934,0.00037739903,0.000396419,0.00040369903,0.00035183327,0.00087046396,0.00016940421,0.000013215913],"category_scores_gemma":[0.000032178737,0.0002764025,0.000040251645,0.00049212115,0.00015989534,0.00061733,0.0007203974,0.0006156583,0.000009056917],"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":[0.000006262393,0.000036708763,0.00064061367,0.000072035946,0.00011652579,0.0000029591063,0.00019135588,0.009220057,0.000005922395,0.69457275,0.00085055607,0.29428428],"study_design_scores_gemma":[0.000018584433,0.000011397088,0.0000124538965,0.00002392691,0.00016260934,0.00000390616,0.00012422117,0.91338897,0.000009521743,0.03958716,0.046387136,0.000270106],"about_ca_topic_score_codex":0.000053033953,"about_ca_topic_score_gemma":0.00012843596,"teacher_disagreement_score":0.9041689,"about_ca_system_score_codex":0.000091596885,"about_ca_system_score_gemma":0.00008724797,"threshold_uncertainty_score":0.9999688},"labels":[],"label_agreement":null},{"id":"W4200318242","doi":"10.1109/tbme.2021.3133594","title":"Online Adaptation Boosts SSVEP-Based BCI Performance","year":2021,"lang":"en","type":"article","venue":"IEEE Transactions on Biomedical Engineering","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":44,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada; Universidade de Macau","keywords":"Brain–computer interface; Adaptation (eye); Work (physics); Signal processing; Field (mathematics)","score_opus":0.016700728805069016,"score_gpt":0.23108330428385906,"score_spread":0.21438257547879006,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200318242","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":[0.012351316,0.00003027771,0.98482275,0.0016239524,0.00070169335,0.000044484896,0.000016846454,0.00036657482,0.000042125608],"genre_scores_gemma":[0.9345778,0.000041688967,0.06486679,0.00022017064,0.000057841036,0.000013856245,0.00006173657,0.000011888053,0.00014823445],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998932,0.000027848659,0.00019913417,0.00030414344,0.000334716,0.00020217271],"domain_scores_gemma":[0.9992865,0.000100573474,0.000032271153,0.00038613958,0.000052579275,0.00014194688],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012289046,0.0001225445,0.00010801924,0.0001736224,0.0001000015,0.000057438934,0.0002537246,0.00008230817,0.00003917799],"category_scores_gemma":[0.000023866154,0.00012336994,0.000055299064,0.0006276582,0.00002358944,0.00022878763,0.0000022178958,0.0003203483,0.000056267425],"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":[0.000008478886,0.0005327465,0.000007178046,0.00007252157,0.000022793969,0.000022626451,0.00015147938,0.5240683,0.009629427,0.00040033378,0.00008350927,0.46500063],"study_design_scores_gemma":[0.0003073112,0.000083295185,0.0007336237,0.000055790686,0.00000632605,0.0000137223715,0.0000068220456,0.9769,0.00850008,0.0000031721902,0.013254711,0.0001351666],"about_ca_topic_score_codex":0.000008568547,"about_ca_topic_score_gemma":0.0000037297668,"teacher_disagreement_score":0.9222265,"about_ca_system_score_codex":0.00005773214,"about_ca_system_score_gemma":0.00011533914,"threshold_uncertainty_score":0.503088},"labels":[],"label_agreement":null},{"id":"W4205892261","doi":"10.1007/s13253-021-00483-x","title":"Hidden Markov and Semi-Markov Models When and Why are These Models Useful for Classifying States in Time Series Data?","year":2022,"lang":"en","type":"article","venue":"Journal of Agricultural Biological and Environmental Statistics","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":23,"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":"Agencia Nacional de Promoción Científica y Tecnológica","keywords":"Hidden Markov model; Autoregressive model; Computer science; Artificial intelligence; Context (archaeology); Hidden semi-Markov model; Machine learning; Markov model; Markov chain; Time series; Pattern recognition (psychology); Data mining; Variable-order Markov model; Econometrics; Mathematics; Geography","score_opus":0.03681079504648487,"score_gpt":0.22414407053766186,"score_spread":0.18733327549117698,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4205892261","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":[0.906045,0.0013016927,0.08782993,0.0024609307,0.000050852843,0.00019939298,0.002085481,0.000011644723,0.000015033376],"genre_scores_gemma":[0.9184056,0.0024609598,0.07816087,0.00019315642,0.000036380934,0.000007901767,0.0006250609,0.00000429067,0.00010577426],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9989794,0.00013876926,0.0002858536,0.0002607391,0.00018190534,0.00015331415],"domain_scores_gemma":[0.9992962,0.0002518031,0.00024388189,0.00010766277,0.000008870858,0.000091604416],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003664645,0.00012782213,0.00021016355,0.000030191071,0.00017738168,0.00012400688,0.00033437726,0.00004089732,0.000017381186],"category_scores_gemma":[0.00003256751,0.0000732556,0.000016014455,0.000040039977,0.000092691196,0.00064674765,0.00072643027,0.00021632279,2.9800827e-7],"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":[0.002016427,0.0018398307,0.3357584,0.0003556925,0.00048204453,0.00031193037,0.01187142,0.021412695,0.031411555,0.014458406,0.05574211,0.5243395],"study_design_scores_gemma":[0.001224981,0.0013678652,0.49328986,0.000041743588,0.00004067839,0.0006172204,0.0028696188,0.45025718,0.0000245945,0.04427612,0.0055046254,0.00048549916],"about_ca_topic_score_codex":0.000009992181,"about_ca_topic_score_gemma":0.000004176052,"teacher_disagreement_score":0.523854,"about_ca_system_score_codex":0.000042483047,"about_ca_system_score_gemma":0.0000044313815,"threshold_uncertainty_score":0.29872766},"labels":[],"label_agreement":null},{"id":"W4206630568","doi":"10.1109/bigdata52589.2021.9671816","title":"MixNN: Combating Noisy Labels in Deep Learning by Mixing with Nearest Neighbors","year":2021,"lang":"en","type":"article","venue":"2021 IEEE International Conference on Big Data (Big Data)","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Overfitting; Computer science; Artificial intelligence; Pattern recognition (psychology); Machine learning; Noise (video); Deep learning; Transfer of learning; Ground truth; Representation (politics); Artificial neural network; Image (mathematics)","score_opus":0.19693395144726453,"score_gpt":0.33696667031590244,"score_spread":0.1400327188686379,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4206630568","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":[0.02869965,0.00033183847,0.9289626,0.01569127,0.0043798676,0.00034213922,0.003848758,0.00027607963,0.017467823],"genre_scores_gemma":[0.9444745,0.00035308642,0.0125692645,0.0005836203,0.00054536824,0.000017496879,0.040454805,0.000030629526,0.0009712294],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99618155,0.000368579,0.0005005599,0.0016084185,0.0009354804,0.0004054143],"domain_scores_gemma":[0.99584216,0.00037152594,0.00033594636,0.0029845035,0.00032118615,0.00014465084],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00088338886,0.00029557804,0.00028849184,0.0002074319,0.00021573728,0.0011802072,0.0052831084,0.00010464356,0.00015313366],"category_scores_gemma":[0.0010332199,0.0002867221,0.000023017861,0.00065131136,0.000079925645,0.0017223331,0.0021388095,0.00087018125,0.00018320202],"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":[0.00006393323,0.00040609424,0.019926643,0.00004048997,0.000117236326,0.00029088007,0.00037342947,0.00080188754,0.008576834,0.018284364,0.008602978,0.94251525],"study_design_scores_gemma":[0.0012436607,0.00011235058,0.006865844,0.00045424278,0.000017056633,0.000061878854,0.00035761244,0.8698495,0.0010689336,0.00022051587,0.11911658,0.00063184893],"about_ca_topic_score_codex":0.00057541014,"about_ca_topic_score_gemma":0.0019952927,"teacher_disagreement_score":0.9418834,"about_ca_system_score_codex":0.00008976681,"about_ca_system_score_gemma":0.00038259063,"threshold_uncertainty_score":0.9999585},"labels":[],"label_agreement":null},{"id":"W4206751735","doi":"10.30534/ijatcse/2021/281022021","title":"A Study of incremental Learning model using deep neural network","year":2021,"lang":"en","type":"article","venue":"International Journal of Advanced Trends in Computer Science and Engineering","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"National Institute of Standards and Technology; Canadian Institute for Advanced Research","keywords":"Forgetting; Artificial intelligence; Computer science; Deep learning; Process (computing); Field (mathematics); Machine learning; Incremental learning; Artificial neural network; Deep neural networks; Mathematics","score_opus":0.023368921954817937,"score_gpt":0.3023242578367013,"score_spread":0.27895533588188337,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4206751735","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":[0.49923664,0.00006329022,0.50024277,0.00006301886,0.0003683045,0.0000087068365,1.198735e-7,0.0000069320654,0.000010190557],"genre_scores_gemma":[0.77446085,0.000009214027,0.22543733,0.000017020591,0.00007062562,3.3717117e-7,4.917631e-7,0.0000026820333,0.0000014194916],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987671,0.00002568475,0.0003317114,0.00018900628,0.000544879,0.00014166304],"domain_scores_gemma":[0.99926,0.000046667723,0.0001859866,0.00011838325,0.00033691176,0.00005204988],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005269671,0.00007677177,0.00013558326,0.00042899817,0.000049708517,0.00012373934,0.00060319604,0.000013913917,8.0323343e-7],"category_scores_gemma":[0.000067651235,0.000075002405,0.000025088017,0.0007153508,0.000025328764,0.0010475654,0.00033764212,0.0002086321,5.911026e-8],"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":[0.00000412266,0.000046986705,0.003033862,0.0000014456286,0.000008507657,0.000040686762,0.0005637842,0.81489235,0.0028022937,0.00026578933,5.6867935e-7,0.17833962],"study_design_scores_gemma":[0.00047305497,0.00009904626,0.014912366,0.000039158193,0.0000025983009,0.00017219225,0.00006359919,0.9838843,0.00020625858,0.00006897243,0.000012607542,0.0000658683],"about_ca_topic_score_codex":0.00000471097,"about_ca_topic_score_gemma":0.0000048775,"teacher_disagreement_score":0.2752242,"about_ca_system_score_codex":0.00007658616,"about_ca_system_score_gemma":0.000053708864,"threshold_uncertainty_score":0.30585095},"labels":[],"label_agreement":null},{"id":"W4211173503","doi":"10.1515/9783110629453-084","title":"84 Automated machine learning","year":2020,"lang":"en","type":"book-chapter","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":96,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Centre National de la Recherche Scientifique; BrainLinks-BrainTools; Eidgenössische Technische Hochschule Zürich; Deutsche Forschungsgemeinschaft; Institut national de recherche en informatique et en automatique (INRIA); Generalitat de Catalunya; Natural Sciences and Engineering Research Council of Canada; European Commission; Centres de Recerca de Catalunya","keywords":"Computer science; Artificial intelligence","score_opus":0.02329552522663692,"score_gpt":0.2429454570042957,"score_spread":0.2196499317776588,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4211173503","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":[2.3575005e-7,0.00021253378,0.16272776,0.0035139783,0.00016606615,0.00009191182,0.0000075384555,0.0045670792,0.8287129],"genre_scores_gemma":[0.0037000356,0.00011719319,0.025006741,0.0008868841,0.00016446541,0.000004218799,0.00057824265,0.000053302207,0.9694889],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985313,0.00003956001,0.0002837373,0.00065088883,0.00032753806,0.0001669669],"domain_scores_gemma":[0.99885964,0.00007423946,0.00022889845,0.0006440767,0.000054995293,0.00013816424],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00016476234,0.000280599,0.00027510745,0.0001259328,0.00013576406,0.00021750564,0.00095835555,0.00019991952,0.00050857005],"category_scores_gemma":[0.00007806365,0.00025031285,0.0000958683,0.00006345321,0.000026954494,0.00018532872,0.00043187788,0.00082771824,0.0033566577],"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":[0.0000021301082,0.000004630354,0.000025072044,0.000023851155,0.00002620741,0.000022896293,0.00004918149,0.00006318146,0.000033015378,0.9460733,0.012866802,0.040809765],"study_design_scores_gemma":[0.00006974353,0.000042098167,0.00004416303,0.000019003146,0.000007200383,0.000008980674,4.809291e-7,0.41977078,0.0000051960474,0.002032965,0.5778008,0.0001985859],"about_ca_topic_score_codex":0.00003509866,"about_ca_topic_score_gemma":0.000007595395,"teacher_disagreement_score":0.9440403,"about_ca_system_score_codex":0.000034595636,"about_ca_system_score_gemma":0.000067520064,"threshold_uncertainty_score":0.99999493},"labels":[],"label_agreement":null},{"id":"W4212816054","doi":"10.1145/3488560.3498376","title":"An Ensemble Model for Combating Label Noise","year":2022,"lang":"en","type":"article","venue":"Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Computer science; Artificial intelligence; Noise (video); Machine learning; Artificial neural network; Consistency (knowledge bases); Pattern recognition (psychology); Image (mathematics); Set (abstract data type); Matching (statistics); Measure (data warehouse); Function (biology); Data mining; Mathematics; Statistics","score_opus":0.16405802616967322,"score_gpt":0.37567839057985014,"score_spread":0.21162036441017693,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4212816054","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":[0.8992205,0.00003764257,0.07265512,0.01833172,0.00040976374,0.00071890745,0.0013814861,0.00014876203,0.00709605],"genre_scores_gemma":[0.9331508,0.000015108698,0.06607331,0.00021460571,0.0000377583,0.00004433429,0.00020274645,0.000007696831,0.00025361055],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985311,0.000022421325,0.00021107712,0.0004912479,0.00055427896,0.0001898934],"domain_scores_gemma":[0.9988223,0.00011437674,0.00015958703,0.0005627071,0.00026896136,0.000072108494],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011180412,0.00010215367,0.00010721057,0.00011710799,0.00041340993,0.00029829162,0.00484807,0.000021334976,0.000016702617],"category_scores_gemma":[0.00065027946,0.000084894724,0.000020093918,0.00014557656,0.000047930705,0.0008387347,0.0031596057,0.00023308137,9.146743e-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":[0.0002435007,0.0003721188,0.0134535665,0.000093373295,0.000057265162,4.1156588e-7,0.0031919838,0.0009620961,0.07399175,0.7485186,0.005198983,0.15391633],"study_design_scores_gemma":[0.00039753458,0.00015526098,0.00067972025,0.00002618944,0.0000044679377,0.0000042804313,0.00059527665,0.99466383,0.00048414015,0.0022420406,0.0006526155,0.00009462829],"about_ca_topic_score_codex":0.000021194644,"about_ca_topic_score_gemma":0.0000041126095,"teacher_disagreement_score":0.99370176,"about_ca_system_score_codex":0.000028612832,"about_ca_system_score_gemma":0.00013112476,"threshold_uncertainty_score":0.90090007},"labels":[],"label_agreement":null},{"id":"W4213251046","doi":"10.1145/3495256","title":"Automating data science","year":2022,"lang":"en","type":"article","venue":"Communications of the ACM","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":44,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Automation; Computer science; Data science; Process (computing); Engineering","score_opus":0.1379017813942821,"score_gpt":0.36646717004845997,"score_spread":0.22856538865417786,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4213251046","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.061792914,0.0023663738,0.033678174,0.84960324,0.0011547584,0.0007653855,0.0001818664,0.0008220273,0.049635254],"genre_scores_gemma":[0.71895003,0.000012266061,0.28083426,0.000122045196,0.000003261902,0.000010281383,0.00002071749,0.000001854493,0.00004529119],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990855,0.00021881217,0.00014234429,0.00018222872,0.00028803461,0.00008308883],"domain_scores_gemma":[0.90294063,0.00021830174,0.00016955019,0.09660567,0.000048815535,0.000017029215],"candidate_categories":["metaresearch","sts","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0016518947,0.00003335527,0.00004487362,0.00006298884,0.0014768931,0.000058530135,0.19040483,0.0000051005604,0.000007342245],"category_scores_gemma":[0.009991313,0.000026955733,0.000015038915,0.0010274637,0.00024636587,0.000512274,0.27093932,0.00020182246,0.000006374524],"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":[0.0000016859193,0.0003166092,0.012899079,0.000015374848,0.000015164559,1.883382e-7,0.0017408684,0.00090884924,0.016826298,0.80341804,0.023879964,0.13997787],"study_design_scores_gemma":[0.00012960941,0.000020060883,0.098326355,0.000013172241,0.000008334517,0.000024796514,0.0002040271,0.77219844,0.0004258066,0.03747001,0.09105801,0.000121409175],"about_ca_topic_score_codex":0.00005386673,"about_ca_topic_score_gemma":0.000004773993,"teacher_disagreement_score":0.8494812,"about_ca_system_score_codex":0.00003318257,"about_ca_system_score_gemma":0.00017586026,"threshold_uncertainty_score":0.99982303},"labels":[],"label_agreement":null},{"id":"W4213308398","doi":"10.1007/978-3-030-05318-5","title":"Automated Machine Learning","year":2019,"lang":"en","type":"book","venue":"˜The œSpringer series on challenges in machine learning","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":1396,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"BrainLinks-BrainTools; Deutsche Forschungsgemeinschaft; Institut national de recherche en informatique et en automatique (INRIA); Generalitat de Catalunya; Natural Sciences and Engineering Research Council of Canada; European Commission; Centres de Recerca de Catalunya","keywords":"Computer science; Artificial intelligence; Machine learning","score_opus":0.033428940533425835,"score_gpt":0.2644895588843254,"score_spread":0.23106061835089958,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4213308398","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":[0.000333611,0.040555377,0.006284851,0.018220726,0.0039047548,0.0021031266,0.000050628394,0.010450142,0.9180968],"genre_scores_gemma":[0.094544,0.02331496,0.003232031,0.00059687486,0.00091488025,0.00019625157,0.00090798194,0.0005389113,0.8757541],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9930906,0.0014634507,0.0010652805,0.00207798,0.0012188716,0.0010837617],"domain_scores_gemma":[0.99482846,0.0011333765,0.0011164014,0.0025869142,0.00014677037,0.00018810034],"candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0026984354,0.0012079981,0.0011767383,0.0008609636,0.000727798,0.0005388971,0.0035979063,0.0007807134,0.00011545458],"category_scores_gemma":[0.00039293413,0.0010052061,0.00031939364,0.000458869,0.00019213167,0.00067285076,0.001688169,0.007542444,0.001370023],"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":[0.00050353975,0.0005291744,0.0055952137,0.0022505648,0.000691207,0.00047748047,0.012891459,0.115422815,0.00014006812,0.30788544,0.0042754347,0.5493376],"study_design_scores_gemma":[0.00057742407,0.0005107746,0.001750807,0.0004881146,0.00002819413,0.000061530394,0.000085734704,0.34383234,0.000005224452,0.0009481778,0.6507673,0.00094434764],"about_ca_topic_score_codex":0.00013072687,"about_ca_topic_score_gemma":0.00073339994,"teacher_disagreement_score":0.6464919,"about_ca_system_score_codex":0.0004404461,"about_ca_system_score_gemma":0.0003053231,"threshold_uncertainty_score":0.99940753},"labels":[],"label_agreement":null},{"id":"W4224511660","doi":"10.1111/rssb.12502","title":"Efficient Evaluation of Prediction Rules in Semi-Supervised Settings under Stratified Sampling","year":2022,"lang":"en","type":"article","venue":"Journal of the Royal Statistical Society Series B (Statistical Methodology)","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"National Institute of Neurological Disorders and Stroke; National Institute of General Medical Sciences; National Heart, Lung, and Blood Institute","keywords":"Estimator; Leverage (statistics); Stratified sampling; Computer science; Missing data; Random forest; Consistency (knowledge bases); Data mining; Machine learning; Sampling (signal processing); Imputation (statistics); Regression; Artificial intelligence; Statistics; Mathematics","score_opus":0.09762707363528889,"score_gpt":0.35690913996393064,"score_spread":0.25928206632864176,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4224511660","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":[0.047545567,0.00008872868,0.9487002,0.0023354632,0.0006175849,0.000225309,0.00037906034,0.00001937641,0.000088701476],"genre_scores_gemma":[0.4086274,0.000004169128,0.5910873,0.0001581119,0.000051636896,0.000014852879,0.000030079133,0.000009198731,0.000017296039],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9925376,0.0044187545,0.0010438983,0.00032546345,0.0013711754,0.00030311008],"domain_scores_gemma":[0.9941959,0.004337928,0.00065374596,0.00035190096,0.0003507423,0.000109778935],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011195336,0.00016887301,0.0004319909,0.00006614783,0.00036029844,0.00006156411,0.00077056803,0.00009399228,0.00025010025],"category_scores_gemma":[0.0050539654,0.00012846383,0.0001464357,0.00040082436,0.00027910896,0.00009425525,0.000390623,0.0009646818,0.000001473431],"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":[0.0002719114,0.0003951927,0.0019535583,0.00011188583,0.00013402883,0.000005753274,0.0022333185,0.51216835,0.0018871941,0.43045247,0.0025076705,0.047878645],"study_design_scores_gemma":[0.0007608485,0.00032454677,0.11266596,0.000026671307,0.000115580624,0.00003890166,0.000978094,0.8030494,0.00006930336,0.081565484,0.0002853519,0.00011989528],"about_ca_topic_score_codex":0.00005465195,"about_ca_topic_score_gemma":0.0000047285357,"teacher_disagreement_score":0.3610818,"about_ca_system_score_codex":0.00032938368,"about_ca_system_score_gemma":0.00036124082,"threshold_uncertainty_score":0.60504335},"labels":[],"label_agreement":null},{"id":"W4226000139","doi":"10.1093/imaiai/iaae002","title":"PACMAN: PAC-style bounds accounting for the Mismatch between Accuracy and Negative log-loss","year":2024,"lang":"en","type":"preprint","venue":"Information and Inference A Journal of the IMA","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure; McGill University","funders":"Universidad de Buenos Aires; Consejo Nacional de Investigaciones Científicas y Técnicas","keywords":"Generalization; Computer science; Algorithm; Function (biology); Metric (unit); Generalization error; Cross entropy; Mathematics; Artificial intelligence; Artificial neural network; Pattern recognition (psychology)","score_opus":0.026705443778082257,"score_gpt":0.3117600080436237,"score_spread":0.28505456426554143,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4226000139","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":[0.19257168,0.0018786482,0.7051216,0.09500757,0.0024551759,0.0010878409,0.00016357398,0.00009786532,0.0016160387],"genre_scores_gemma":[0.99520266,0.0004816519,0.0035232652,0.00052718,0.00019714105,0.0000122800275,0.000009889551,0.000004668977,0.000041276915],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99875975,0.00007255931,0.00061493996,0.000114808514,0.00029532192,0.0001426276],"domain_scores_gemma":[0.9969359,0.0010725709,0.0011998432,0.00038334468,0.00035487063,0.000053447897],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0012863532,0.0001596465,0.00021152655,0.00012486301,0.00033783563,0.0020837022,0.0009936307,0.00010718326,0.0000032509417],"category_scores_gemma":[0.0014771756,0.00008496188,0.00009527427,0.00014856615,0.00010146217,0.0016509163,0.0011872188,0.0008733403,0.000006018836],"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":[0.000028068336,0.000011984262,0.008036128,0.00055120984,0.00018975807,7.0001175e-7,0.017363044,0.0003704412,0.000019882995,0.020334823,0.004864736,0.94822925],"study_design_scores_gemma":[0.0014402467,0.00024306982,0.21717726,0.0023121997,0.00034314237,0.00024485055,0.002304819,0.43693444,0.00038523113,0.20108849,0.13677357,0.0007526881],"about_ca_topic_score_codex":0.00004521676,"about_ca_topic_score_gemma":0.0000042846823,"teacher_disagreement_score":0.9474765,"about_ca_system_score_codex":0.000036296715,"about_ca_system_score_gemma":0.00026211777,"threshold_uncertainty_score":0.9989522},"labels":[],"label_agreement":null},{"id":"W4230018868","doi":"10.1007/978-1-4939-7131-2_100620","title":"Machine Learning","year":2018,"lang":"en","type":"book-chapter","venue":"","topic":"Machine Learning and Data Classification","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 Calgary","funders":"","keywords":"Computer science; Artificial intelligence","score_opus":0.023914811781202586,"score_gpt":0.2448290499737136,"score_spread":0.22091423819251102,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4230018868","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":[2.4595772e-7,0.00019813434,0.22594005,0.0005393832,0.00018192695,0.000048192378,0.000002626343,0.00045700933,0.7726324],"genre_scores_gemma":[0.0003763553,0.00013147712,0.017507596,0.00024741873,0.00023532158,0.0000018447564,0.0001396256,0.000024879633,0.98133546],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988693,0.0000227114,0.00019731508,0.00050152774,0.0002564083,0.00015273844],"domain_scores_gemma":[0.9988342,0.000055098924,0.00017359333,0.0007883536,0.00007249098,0.00007625421],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00024119917,0.00020794258,0.0001765028,0.00013330125,0.00013225825,0.00016293618,0.00084957253,0.00017331539,0.003078223],"category_scores_gemma":[0.00004300307,0.00017802381,0.000072146795,0.000028991717,0.000043292424,0.00016525049,0.0003457048,0.000506853,0.006125417],"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":[0.0000010085004,0.0000031247364,0.00002033562,0.000007856617,0.000012004849,0.0000039902247,0.00004717684,0.000002791184,0.000004847092,0.9206153,0.010035831,0.06924571],"study_design_scores_gemma":[0.000058262078,0.0000626897,0.00002427047,0.000022524398,0.0000057422876,0.0000111158715,5.460058e-7,0.030870995,0.000005563696,0.020397054,0.94832754,0.00021368847],"about_ca_topic_score_codex":0.000021306449,"about_ca_topic_score_gemma":0.000012555738,"teacher_disagreement_score":0.9382917,"about_ca_system_score_codex":0.000026536223,"about_ca_system_score_gemma":0.000041192514,"threshold_uncertainty_score":0.9978331},"labels":[],"label_agreement":null},{"id":"W4230875287","doi":"10.1007/978-1-4614-6170-8_100067","title":"Machine Learning","year":2014,"lang":"en","type":"book-chapter","venue":"","topic":"Machine Learning and Data Classification","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 Calgary","funders":"","keywords":"Computer science; Artificial intelligence","score_opus":0.018826025830332445,"score_gpt":0.2314418248966873,"score_spread":0.21261579906635486,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4230875287","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":[4.577445e-8,0.0001357314,0.4270444,0.000626142,0.00010644352,0.000033065,0.0000010673966,0.00034041266,0.57171273],"genre_scores_gemma":[0.0012931213,0.00012036724,0.013304617,0.00035028308,0.00014852431,0.0000020674145,0.00014745642,0.000025625066,0.98460793],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988845,0.00003126866,0.00020453223,0.00047768798,0.00025489836,0.00014712066],"domain_scores_gemma":[0.998816,0.00008749878,0.00018454697,0.0007864773,0.00004656213,0.00007890235],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00028871483,0.00021083704,0.00020562366,0.00013031755,0.00011483531,0.00015147439,0.00081688457,0.00016965799,0.0006053789],"category_scores_gemma":[0.00005029307,0.00018118217,0.00007929238,0.000022994116,0.000023459035,0.00008808161,0.0002803579,0.0006204732,0.002761589],"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":[4.813097e-7,0.0000013366159,0.000018529325,0.000008035748,0.0000067216665,0.0000017958432,0.000010969754,0.000017038901,0.0000029522214,0.831349,0.0023543816,0.16622877],"study_design_scores_gemma":[0.000062543695,0.000039470055,0.000028466879,0.000020389878,0.0000054717893,0.000009070963,1.7463628e-7,0.07284961,0.0000025382167,0.011311594,0.91546124,0.00020940106],"about_ca_topic_score_codex":0.000026216412,"about_ca_topic_score_gemma":0.00000927637,"teacher_disagreement_score":0.91310686,"about_ca_system_score_codex":0.00002253697,"about_ca_system_score_gemma":0.000028975737,"threshold_uncertainty_score":0.99801487},"labels":[],"label_agreement":null},{"id":"W4231283574","doi":"10.1017/cbo9781107298019.017","title":"Kernel Methods","year":2014,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Margin (machine learning); AdaBoost; Sample complexity; Computational complexity theory; Kernel (algebra); Computer science; Feature (linguistics); Feature vector; Kernel method; Support vector machine; Artificial intelligence; Space (punctuation); Time complexity; Base (topology); Mathematics; Algorithm; Theoretical computer science; Machine learning; Discrete mathematics","score_opus":0.031483106830976666,"score_gpt":0.25602233258539464,"score_spread":0.22453922575441798,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4231283574","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":[3.9054692e-7,0.000039002345,0.45781836,0.000041301377,0.00017063826,0.000081505415,0.000015873688,0.00021434178,0.5416186],"genre_scores_gemma":[0.00009510539,0.000037640064,0.0360531,0.000118360134,0.000112432266,3.9077685e-7,0.000055322096,0.000024562647,0.96350306],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985213,0.00016195224,0.00016575081,0.0006954451,0.00023235228,0.0002231503],"domain_scores_gemma":[0.9978719,0.00015676543,0.00027879444,0.001413665,0.00011558296,0.00016333224],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00036564644,0.00029149346,0.00031730844,0.00018212711,0.00018626922,0.00012054934,0.0016672475,0.0002944265,0.0000030100894],"category_scores_gemma":[0.000029374321,0.0003321403,0.00015925165,0.000010121262,0.00010751227,0.000112590824,0.00081559806,0.0005372347,0.00007184251],"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":[0.000005640918,0.000002426657,6.618463e-7,0.00002777929,0.000031673695,0.000023403738,0.000018279117,0.0000018120478,0.00002837058,0.9095335,0.026063913,0.06426254],"study_design_scores_gemma":[0.00019847462,0.0000297726,0.00002741006,0.000047791687,0.0000487157,0.0000125662655,0.0000018289057,0.0058552083,0.00007430046,0.000057625184,0.9932959,0.0003503777],"about_ca_topic_score_codex":0.000076787925,"about_ca_topic_score_gemma":5.321281e-7,"teacher_disagreement_score":0.967232,"about_ca_system_score_codex":0.00009827303,"about_ca_system_score_gemma":0.000079521145,"threshold_uncertainty_score":0.99991304},"labels":[],"label_agreement":null},{"id":"W4232665336","doi":"10.1017/cbo9781107298019.022","title":"Online Learning","year":2014,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Machine Learning and Data Classification","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":"University of Waterloo","funders":"","keywords":"Artificial intelligence; Computer science; Taste; Set (abstract data type); Contrast (vision); Machine learning; Mathematics; Psychology","score_opus":0.02258322938578103,"score_gpt":0.2119069479352656,"score_spread":0.18932371854948457,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4232665336","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":[0.000011265526,0.000043274984,0.17054309,0.00006679129,0.00015951772,0.00010011032,0.000031321997,0.00041261473,0.828632],"genre_scores_gemma":[0.0011081947,0.000059251495,0.0020968325,0.000084396765,0.00015496783,1.9009755e-7,0.00022834161,0.000026706508,0.9962411],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986374,0.000083619314,0.00015865709,0.00062997005,0.00026867897,0.00022170956],"domain_scores_gemma":[0.9984441,0.00009305612,0.00028591216,0.0009136034,0.00011727262,0.00014609129],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00015366015,0.00027816754,0.00028295128,0.00018453022,0.00023727643,0.000107050146,0.0013098947,0.00026061095,0.0000026589344],"category_scores_gemma":[0.000029243689,0.00032510716,0.00013292719,0.000009995828,0.00008822547,0.000107994485,0.00070714246,0.0008391852,0.00006569209],"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":[0.000005911497,0.000005593581,0.000003217006,0.000028908107,0.00002694036,0.000039582203,0.000020947531,0.000015848007,0.000012993875,0.95812637,0.012034022,0.029679643],"study_design_scores_gemma":[0.00022584434,0.000050897743,0.00006705956,0.000072082985,0.000037408376,0.0000120942605,0.000004222786,0.009552119,0.000011959221,0.000010881883,0.9896182,0.00033727702],"about_ca_topic_score_codex":0.00006788893,"about_ca_topic_score_gemma":0.0000013914132,"teacher_disagreement_score":0.9775841,"about_ca_system_score_codex":0.000091653696,"about_ca_system_score_gemma":0.000061067134,"threshold_uncertainty_score":0.99992007},"labels":[],"label_agreement":null},{"id":"W4233637184","doi":"10.1007/978-1-4939-7131-2_100921","title":"Profile Similarity","year":2018,"lang":"en","type":"book-chapter","venue":"","topic":"Machine Learning and Data Classification","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 Calgary","funders":"","keywords":"Similarity (geometry); Computer science; Artificial intelligence","score_opus":0.028488590235063303,"score_gpt":0.25667890848631264,"score_spread":0.22819031825124933,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4233637184","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":[3.658478e-7,0.000030147432,0.18508388,0.0008076999,0.00019820324,0.00007948724,0.00000878439,0.00030579278,0.8134856],"genre_scores_gemma":[0.00012771763,0.000016319538,0.04096856,0.00039407046,0.00022334972,0.000003327581,0.00010447745,0.000012910014,0.95814925],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990571,0.000012021467,0.00015275244,0.0004424366,0.00021648298,0.00011920383],"domain_scores_gemma":[0.9986787,0.000032463002,0.00011540317,0.0010300849,0.00008229578,0.00006106239],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00018092983,0.00015289098,0.00013388488,0.00007159962,0.000078400524,0.00012598898,0.00081235747,0.00017908677,0.0039207297],"category_scores_gemma":[0.000025131703,0.00012899029,0.000053378986,0.000020412353,0.000044372304,0.00015661161,0.00029468653,0.00025745304,0.0056090304],"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":[5.7505923e-7,0.0000039628762,0.000004299785,0.000008525031,0.00000606432,0.000001770175,0.000024351863,9.639898e-8,0.0000031465597,0.8431787,0.1280876,0.028680945],"study_design_scores_gemma":[0.000038041297,0.00003591012,0.000071123395,0.000016323967,0.000004125352,0.0000042430875,4.0908049e-7,0.006128244,0.000018610677,0.04084392,0.9526668,0.00017225655],"about_ca_topic_score_codex":0.000008819349,"about_ca_topic_score_gemma":0.000009527027,"teacher_disagreement_score":0.8245792,"about_ca_system_score_codex":0.000022302509,"about_ca_system_score_gemma":0.00006256555,"threshold_uncertainty_score":0.99698985},"labels":[],"label_agreement":null},{"id":"W4233947928","doi":"10.4018/9781605669021.ch003","title":"Reducing Cognitive Overload by Meta-Learning Assisted Algorithm Selection","year":2011,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"","keywords":"Computer science; Reduct; Rough set; Machine learning; Meta learning (computer science); Data mining; Process (computing); Ranking (information retrieval); Feature selection; Information overload; Artificial intelligence; Reduction (mathematics); Cognitive load; Set (abstract data type); Algorithm; Cognition; Engineering","score_opus":0.03554735757587932,"score_gpt":0.26519153214182645,"score_spread":0.22964417456594713,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4233947928","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":[0.000004646177,0.00042569573,0.2789073,0.000043516975,0.0002929046,0.00020981095,0.00010279225,0.00052331324,0.71949005],"genre_scores_gemma":[0.11904405,0.00006667866,0.055489697,0.0009832958,0.00082703587,0.00016178284,0.0005276815,0.0002113741,0.8226884],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9973132,0.00015371991,0.00047599795,0.0011090831,0.0005501868,0.0003978341],"domain_scores_gemma":[0.9982653,0.000094850104,0.0006622493,0.00051736156,0.0002698813,0.00019032604],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00038618888,0.00054337,0.0006029191,0.00012211477,0.00033375993,0.00031477463,0.00067332527,0.00047151596,0.00011198158],"category_scores_gemma":[0.00009461182,0.00052703614,0.0003185373,0.000068565445,0.00007596661,0.00023717764,0.00028192296,0.0009586734,0.0003025985],"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":[0.000011745229,0.000018498735,0.000009089211,0.00001669785,0.00073600025,0.000014307169,0.000109067405,0.0000025848128,0.000049504884,0.5784342,0.0035340083,0.41706425],"study_design_scores_gemma":[0.0020632844,0.0014257585,0.00085607823,0.00087344984,0.005436653,0.00084054744,0.00004755659,0.026730511,0.00086183334,0.20383428,0.75241363,0.004616412],"about_ca_topic_score_codex":0.00054501236,"about_ca_topic_score_gemma":0.000017716698,"teacher_disagreement_score":0.7488796,"about_ca_system_score_codex":0.00023691457,"about_ca_system_score_gemma":0.0001914516,"threshold_uncertainty_score":0.9997181},"labels":[],"label_agreement":null},{"id":"W4235986671","doi":"10.1007/978-1-4614-6170-8_100589","title":"Profile Similarity","year":2014,"lang":"en","type":"book-chapter","venue":"","topic":"Machine Learning and Data Classification","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 Calgary","funders":"","keywords":"Similarity (geometry); Geography; Computer science; Artificial intelligence","score_opus":0.021678274948754156,"score_gpt":0.24087675509403728,"score_spread":0.21919848014528312,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4235986671","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":[6.707343e-8,0.000020481943,0.40187898,0.00093364547,0.00011443124,0.00005399499,0.0000035128778,0.00022587237,0.59676903],"genre_scores_gemma":[0.00045453483,0.000015062309,0.03127592,0.00056430907,0.00014152817,0.0000037731465,0.00011173036,0.000013434841,0.9674197],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99907374,0.000016658982,0.00015844901,0.0004211663,0.0002152158,0.000114766066],"domain_scores_gemma":[0.9986816,0.000052021816,0.00012281878,0.0010276721,0.00005260885,0.00006325428],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00021771913,0.00015506566,0.00015631354,0.000070064205,0.00006783547,0.0001170968,0.0007811379,0.00017527475,0.0007630167],"category_scores_gemma":[0.000029513783,0.00013131881,0.000058774116,0.000016118669,0.000023785284,0.00008308053,0.00023834647,0.0003165887,0.0025216893],"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":[3.2064403e-7,0.0000019763495,0.000004661177,0.000010250982,0.000003962593,9.3094235e-7,0.000006566236,7.121489e-7,0.0000022509523,0.8744333,0.037515648,0.08801946],"study_design_scores_gemma":[0.000041913583,0.0000229613,0.00008630681,0.000015101826,0.0000040270975,0.0000035332507,1.3272656e-7,0.015680999,0.000008670231,0.023389095,0.96057415,0.00017310507],"about_ca_topic_score_codex":0.000010825675,"about_ca_topic_score_gemma":0.000007011727,"teacher_disagreement_score":0.9230585,"about_ca_system_score_codex":0.000018832325,"about_ca_system_score_gemma":0.000043751308,"threshold_uncertainty_score":0.99825495},"labels":[],"label_agreement":null},{"id":"W4242293750","doi":"10.4018/9781591405573.ch028","title":"Classification Methods","year":2011,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Machine Learning and Data Classification","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":false,"ca_institutions":"York University","funders":"","keywords":"Object (grammar); Class (philosophy); Computer science; Cluster analysis; Artificial intelligence; Set (abstract data type); One-class classification; Supervised learning; Machine learning; A priori and a posteriori; Function (biology); Unsupervised learning; Task (project management); Data mining; Pattern recognition (psychology); Classifier (UML); Artificial neural network","score_opus":0.06355575369281369,"score_gpt":0.3288222292816202,"score_spread":0.2652664755888065,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4242293750","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":[3.6077853e-7,0.0001440751,0.3803673,0.0001338225,0.00039057177,0.00011909947,0.000015723583,0.00031878095,0.61851025],"genre_scores_gemma":[0.020964619,0.00003094633,0.44575286,0.0010451748,0.00052678847,0.00005134953,0.000059977374,0.00008175573,0.5314865],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99812853,0.000101436526,0.00040108446,0.00080090296,0.00030794958,0.0002601084],"domain_scores_gemma":[0.99753827,0.00005683961,0.00042110364,0.0016964077,0.00012899394,0.0001584057],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00045968915,0.000351146,0.0003196648,0.00009340828,0.00012700922,0.00018077176,0.0014176549,0.00041197936,0.00004884595],"category_scores_gemma":[0.000051109953,0.00033983766,0.0001573135,0.00003106172,0.00007413847,0.00013427518,0.00032834327,0.00040601558,0.00096075627],"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":[0.000003000035,0.0000045330667,0.00000764538,0.000009768056,0.000019274623,0.000003620298,0.000033611253,1.3273667e-7,0.000028897959,0.74769753,0.0018501303,0.25034186],"study_design_scores_gemma":[0.0000826582,0.000039217713,0.0004400798,0.00003793747,0.000024854402,0.000023013698,0.0000011188123,0.0008694264,0.000018942297,0.59644276,0.40171534,0.00030466894],"about_ca_topic_score_codex":0.000054388416,"about_ca_topic_score_gemma":0.00001219156,"teacher_disagreement_score":0.3998652,"about_ca_system_score_codex":0.00015585819,"about_ca_system_score_gemma":0.00017928415,"threshold_uncertainty_score":0.99990535},"labels":[],"label_agreement":null},{"id":"W4243478513","doi":"10.1007/978-1-4939-7131-2_100019","title":"Algorithm Evaluation","year":2018,"lang":"en","type":"book-chapter","venue":"","topic":"Machine Learning and Data Classification","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 Calgary","funders":"","keywords":"Computer science","score_opus":0.04064680106131379,"score_gpt":0.29235005421452637,"score_spread":0.25170325315321257,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4243478513","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":[7.361322e-8,0.000057149955,0.4631139,0.00032592355,0.00022618225,0.00008020678,0.0000026275823,0.00012977463,0.53606415],"genre_scores_gemma":[0.000025668034,0.000026498361,0.15788509,0.00021436355,0.00033995867,0.000006753929,0.00019154829,0.000013166327,0.841297],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987808,0.00002561207,0.00016698705,0.00043040112,0.0004977122,0.00009852417],"domain_scores_gemma":[0.99866706,0.00003066323,0.00014104108,0.00088562735,0.00022697783,0.000048633257],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.000588206,0.00014261686,0.00011235814,0.00010792568,0.000069018504,0.0001297713,0.00060090155,0.00015086544,0.003275176],"category_scores_gemma":[0.000030201525,0.00012459846,0.00004755493,0.000024222592,0.000029799987,0.00018641046,0.00015843842,0.00016600384,0.0045575886],"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":[1.5485188e-7,0.0000020488358,2.9158963e-7,0.0000017594513,0.0000059973177,4.0585277e-7,0.000021392794,5.1013615e-7,0.0000010570017,0.29836214,0.018833052,0.6827712],"study_design_scores_gemma":[0.00006455889,0.00003167865,0.000028277029,0.000014882644,0.000012092213,0.0000046965697,5.879633e-7,0.200586,0.0000055856394,0.097334616,0.7017739,0.00014316682],"about_ca_topic_score_codex":0.0000078058965,"about_ca_topic_score_gemma":0.0000047688973,"teacher_disagreement_score":0.6829408,"about_ca_system_score_codex":0.000052060812,"about_ca_system_score_gemma":0.00010363747,"threshold_uncertainty_score":0.99763596},"labels":[],"label_agreement":null},{"id":"W4245055982","doi":"10.1017/cbo9780511921803","title":"Evaluating Learning Algorithms","year":2011,"lang":"en","type":"book","venue":"Cambridge University Press eBooks","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":753,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Machine learning; Artificial intelligence; Resampling; Interdependence; Field (mathematics); Process (computing); Classifier (UML); Algorithm; Management science; Engineering; Mathematics","score_opus":0.06511601777908724,"score_gpt":0.2686649979806887,"score_spread":0.20354898020160148,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4245055982","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":[0.000008766409,0.00008517462,0.13667856,0.000014147787,0.00026555627,0.00019108439,0.000017296165,0.0005094431,0.86223],"genre_scores_gemma":[0.000107842774,0.000035499623,0.011785453,0.00003476462,0.00015156958,0.0000011777728,0.0001453989,0.0000297879,0.9877085],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9979339,0.0003007676,0.00020276262,0.0008211437,0.0004100117,0.00033141862],"domain_scores_gemma":[0.9980848,0.0001271933,0.00040970815,0.0010199732,0.0001947658,0.00016354852],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00046848413,0.0003190873,0.00031077064,0.00022412465,0.00038572124,0.00014739949,0.0017917854,0.00030443832,0.000003062188],"category_scores_gemma":[0.00006990163,0.00037836246,0.00014740696,0.000029858289,0.000098237215,0.00027011128,0.0010169218,0.0010518949,0.00007684912],"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":[0.000011532714,0.000011082291,0.0000037924353,0.00006178255,0.00005428725,0.00007609002,0.0001730849,0.000018241117,0.0000329942,0.8700614,0.03199247,0.09750323],"study_design_scores_gemma":[0.00030804973,0.000104881794,0.00005123437,0.00009775149,0.00006459766,0.000015985137,0.000011358658,0.03308615,0.000057462647,0.000014316767,0.9657724,0.0004158498],"about_ca_topic_score_codex":0.00014733957,"about_ca_topic_score_gemma":5.0579376e-7,"teacher_disagreement_score":0.9337799,"about_ca_system_score_codex":0.00023729818,"about_ca_system_score_gemma":0.00039696522,"threshold_uncertainty_score":0.99986684},"labels":[],"label_agreement":null},{"id":"W4248531488","doi":"10.22215/etd/2017-11732","title":"An Adaptive and Diversity-Based Ensemble Method for Binary Classification","year":2017,"lang":"en","type":"dissertation","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Ensemble learning; Computer science; Machine learning; Artificial intelligence; Binary number; Construct (python library); Ensemble forecasting; Stacking; Data mining; Mathematics","score_opus":0.05905510040640796,"score_gpt":0.35965771435437005,"score_spread":0.30060261394796206,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4248531488","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":[0.00091025326,0.000056198274,0.9855438,0.0005458631,0.0003147254,0.0003861079,0.000025140236,0.00019228441,0.012025618],"genre_scores_gemma":[0.2892007,0.000025466672,0.69570607,0.00019120044,0.000103552586,0.000105717954,0.0044227694,0.000026654106,0.01021787],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985794,0.00014491007,0.00016672297,0.0007286046,0.00021324173,0.00016713711],"domain_scores_gemma":[0.99808407,0.0001928955,0.00038611892,0.0010271288,0.00020804234,0.000101717014],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00059218955,0.0001994425,0.00021203527,0.00019346095,0.0009895877,0.00033719704,0.0009868414,0.00023230737,0.000008194162],"category_scores_gemma":[0.00009683592,0.00019070064,0.00006005972,0.00007239914,0.00001990792,0.00061152066,0.000066899025,0.0001800038,0.000010343934],"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":[0.00026250424,0.00015421952,0.00038640553,0.00019151723,0.000040503543,0.000002284843,0.0010713992,0.000054649852,0.010244625,0.21295895,0.0039726137,0.77066034],"study_design_scores_gemma":[0.00041801776,0.00041862216,0.03578327,0.000041968266,0.000052858646,9.744905e-7,0.00024272094,0.9485483,0.0010271168,0.0031119566,0.010005181,0.0003489866],"about_ca_topic_score_codex":0.00020082657,"about_ca_topic_score_gemma":0.00025107924,"teacher_disagreement_score":0.94849366,"about_ca_system_score_codex":0.00003402965,"about_ca_system_score_gemma":0.00014361629,"threshold_uncertainty_score":0.7776546},"labels":[],"label_agreement":null},{"id":"W4249842117","doi":"10.4018/978-1-60566-902-1.ch003","title":"Reducing Cognitive Overload by Meta-Learning Assisted Algorithm Selection","year":2010,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Machine Learning and Data Classification","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":false,"ca_institutions":"University of Regina","funders":"","keywords":"Computer science; Reduct; Rough set; Meta learning (computer science); Data mining; Machine learning; Feature selection; Process (computing); Ranking (information retrieval); Information overload; Artificial intelligence; Reduction (mathematics); Cognitive load; Algorithm; Set (abstract data type); Cognition; Engineering; Mathematics","score_opus":0.023620971721435305,"score_gpt":0.2673888547186878,"score_spread":0.2437678829972525,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4249842117","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":[0.000013445559,0.00028497164,0.2624797,0.00011806865,0.00049801945,0.00025102953,0.00013974786,0.0006128666,0.73560214],"genre_scores_gemma":[0.10685172,0.00004385774,0.13086078,0.0013270302,0.0014709863,0.00018297213,0.0007823712,0.00024758079,0.7582327],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9972497,0.00012716977,0.00046639045,0.0011217664,0.00063663925,0.00039828662],"domain_scores_gemma":[0.9981745,0.00013310782,0.0006464511,0.0005535951,0.0002910767,0.0002012888],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004285481,0.0005428841,0.0005964585,0.00012054732,0.00042577216,0.0004701399,0.0006911502,0.0006576016,0.00008854442],"category_scores_gemma":[0.0001430773,0.000526704,0.00031635794,0.00006999067,0.00009093927,0.00022538105,0.00027716358,0.0016896941,0.00023385564],"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":[0.00001197369,0.000022673581,0.000010546389,0.000021118181,0.0007700896,0.000017887734,0.00008896184,0.0000044812764,0.0006537624,0.5149676,0.002348248,0.48108262],"study_design_scores_gemma":[0.001555327,0.00074797164,0.0004859081,0.00046569246,0.003272771,0.0007167422,0.00003060515,0.029761817,0.0016675027,0.085918754,0.8721327,0.0032441658],"about_ca_topic_score_codex":0.000340206,"about_ca_topic_score_gemma":0.00003427478,"teacher_disagreement_score":0.8697845,"about_ca_system_score_codex":0.00019276574,"about_ca_system_score_gemma":0.00021971406,"threshold_uncertainty_score":0.9997184},"labels":[],"label_agreement":null},{"id":"W4249996157","doi":"10.1109/iat.2004.1342931","title":"Improving modeling of other agents using tentative stereotypes and compactification of observations","year":2004,"lang":"en","type":"article","venue":"Proceedings. IEEE/WIC/ACM International Conference on Intelligent Agent Technology, 2004. (IAT 2004).","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Stereotype (UML); Compactification (mathematics); Computer science; k-nearest neighbors algorithm; Artificial intelligence; Social psychology; Econometrics; Psychology; Mathematics","score_opus":0.15305793404916293,"score_gpt":0.3481258450136275,"score_spread":0.19506791096446455,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4249996157","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":[0.38385615,0.00017895686,0.61138684,0.0024704707,0.00043263834,0.00047536922,0.00004819654,0.00023483555,0.00091653026],"genre_scores_gemma":[0.9402368,0.00010997518,0.0593326,0.000096800584,0.000042797885,0.000031613185,0.000026885655,0.000022076978,0.00010043084],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976243,0.000022314673,0.000807271,0.0006907201,0.00054837007,0.00030705048],"domain_scores_gemma":[0.99746007,0.000038827988,0.000851894,0.00047241928,0.001091791,0.000085006504],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00039326446,0.00030530064,0.00033381273,0.0008440976,0.00015704393,0.00014125562,0.0015152277,0.00020614907,0.0000338273],"category_scores_gemma":[0.00043808785,0.00029764022,0.00008248694,0.00065093103,0.00023530789,0.0007015059,0.0002852086,0.00039652683,0.00001774662],"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":[0.00013297432,0.0009054823,0.022437641,0.00020096322,0.0003255424,0.0000031115785,0.0028982433,0.024060648,0.15478517,0.7598177,0.00017307635,0.03425946],"study_design_scores_gemma":[0.00068771676,0.0002822692,0.0016408978,0.0005302763,0.000052072464,0.000021240197,0.0015530689,0.8917636,0.07966791,0.023113932,0.00024523798,0.00044174286],"about_ca_topic_score_codex":0.00036435015,"about_ca_topic_score_gemma":0.000015067243,"teacher_disagreement_score":0.86770296,"about_ca_system_score_codex":0.00028127382,"about_ca_system_score_gemma":0.00015112426,"threshold_uncertainty_score":0.99994755},"labels":[],"label_agreement":null},{"id":"W4250238009","doi":"10.7287/peerj-cs.11v0.2/reviews/2","title":"Peer Review #2 of \"MLitB: machine learning in the browser (v0.2)\"","year":2015,"lang":"en","type":"peer-review","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Institute for Advanced Research","funders":"","keywords":"Computer science; Human–computer interaction; World Wide Web; Data science","score_opus":0.0773425382009864,"score_gpt":0.3550351386452974,"score_spread":0.277692600444311,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4250238009","genre_codex":"commentary","genre_gemma":"other","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":[1.5711095e-7,0.33719334,0.008329714,0.5174889,0.0004752373,0.0005179542,0.00003904199,0.00010568918,0.13584997],"genre_scores_gemma":[0.000029991597,0.14622237,0.005269412,0.024095112,0.00018953251,0.00008476164,0.0033891615,0.000028698316,0.820691],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99471486,0.0012209225,0.0008783075,0.00063919515,0.0022558337,0.00029089305],"domain_scores_gemma":[0.99571097,0.0003079599,0.00067549595,0.0019183945,0.0013090613,0.000078143516],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011777213,0.00033469388,0.0008222015,0.00014967775,0.00006126698,0.00009480551,0.003105843,0.00015931341,0.00042778047],"category_scores_gemma":[0.0060478672,0.00020239734,0.00018871645,0.0009417781,0.00004548276,0.00023430132,0.00045773957,0.0014866309,0.00027208473],"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":[6.4096696e-7,0.00003441014,0.000051410607,0.010422245,0.0000083545965,0.0000033973117,0.000069326285,0.000004034893,3.2462015e-7,0.0024174321,0.9308792,0.056109257],"study_design_scores_gemma":[0.00010738381,0.000050092745,0.00014773097,0.014921206,0.000042802814,0.000023355293,0.0000047246917,0.0027354285,4.4939398e-7,0.00014552474,0.9815922,0.00022913281],"about_ca_topic_score_codex":0.0012878624,"about_ca_topic_score_gemma":0.00019971577,"teacher_disagreement_score":0.684841,"about_ca_system_score_codex":0.0000536105,"about_ca_system_score_gemma":0.00032645903,"threshold_uncertainty_score":0.8253524},"labels":[],"label_agreement":null},{"id":"W4254462272","doi":"10.4018/978-1-59140-557-3.ch028","title":"Classification Methods","year":2005,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Object (grammar); Artificial intelligence; Class (philosophy); Cluster analysis; Computer science; Set (abstract data type); One-class classification; Supervised learning; Machine learning; A priori and a posteriori; Unsupervised learning; Function (biology); Pattern recognition (psychology); Data mining; Classifier (UML); Artificial neural network","score_opus":0.04420710185763262,"score_gpt":0.3352970649306779,"score_spread":0.2910899630730453,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4254462272","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":[4.8216225e-7,0.00022343967,0.33013976,0.00058463623,0.00032579605,0.0001314175,0.00001952577,0.00036743033,0.6682075],"genre_scores_gemma":[0.01021965,0.000026495007,0.4986828,0.0012870786,0.0008975657,0.00003377226,0.000055521366,0.000058365033,0.48873878],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9980055,0.0000949108,0.00042748,0.0008151471,0.0003844986,0.00027243496],"domain_scores_gemma":[0.9976544,0.00007435982,0.00039857763,0.0015950245,0.00011893524,0.00015870621],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0004627557,0.00035870544,0.0003236563,0.000096103344,0.00013675596,0.00026122172,0.0013255652,0.000408342,0.00003975452],"category_scores_gemma":[0.000053333777,0.00035437968,0.00016150897,0.000034238194,0.00006407175,0.00015117021,0.00029024653,0.00043620463,0.0009366594],"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":[0.0000019576623,0.000003872517,0.000004154459,0.000006630941,0.0000145769,0.0000023140287,0.000015603877,0.0000013487727,0.0000311064,0.65477836,0.002277574,0.34286252],"study_design_scores_gemma":[0.00011250288,0.000031558528,0.00033943378,0.000040669423,0.000024504814,0.000028846378,0.0000014229628,0.0052138926,0.00001369347,0.27854693,0.71530014,0.00034642278],"about_ca_topic_score_codex":0.000020876883,"about_ca_topic_score_gemma":0.000016427379,"teacher_disagreement_score":0.7130226,"about_ca_system_score_codex":0.0002584162,"about_ca_system_score_gemma":0.00019340661,"threshold_uncertainty_score":0.9998908},"labels":[],"label_agreement":null},{"id":"W4280641606","doi":"10.24963/ijcai.2022/455","title":"SELC: Self-Ensemble Label Correction Improves Learning with Noisy Labels","year":2022,"lang":"en","type":"article","venue":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":41,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Overfitting; Computer science; Artificial intelligence; Generalization; Code (set theory); Noise (video); Machine learning; Simplicity; Class (philosophy); Artificial neural network; Ensemble learning; Pattern recognition (psychology); Simple (philosophy); Deep neural networks; Mathematics; Image (mathematics)","score_opus":0.04012080355832404,"score_gpt":0.26595712396022453,"score_spread":0.2258363204019005,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4280641606","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":[0.5056158,0.00007010553,0.28702167,0.076163314,0.010386523,0.0022931236,0.000049401937,0.0021599156,0.116240196],"genre_scores_gemma":[0.9928484,0.00003224025,0.005175895,0.00025809158,0.00009917315,0.00009347697,0.000008150926,0.000019558649,0.0014650008],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973847,0.00005855187,0.00054309994,0.00063981157,0.0010751933,0.00029862495],"domain_scores_gemma":[0.99796283,0.00013235255,0.0007550709,0.00029524165,0.00077677413,0.00007772651],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00089313084,0.00024805882,0.00022846769,0.00025248853,0.00081558013,0.00039071988,0.0020207984,0.000056440815,0.00010739356],"category_scores_gemma":[0.00040431647,0.00019354613,0.00008602596,0.0007091445,0.00011075469,0.0006023481,0.00080359384,0.00091277243,0.00006082332],"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":[0.00020823776,0.0005076937,0.002134554,0.000041130115,0.00008687747,0.0000019561453,0.0032650472,0.0028251398,0.04519212,0.8782406,0.0007114002,0.06678526],"study_design_scores_gemma":[0.00016270082,0.0010851442,0.0020457865,0.00019961629,0.000030480816,0.000083615625,0.0022302684,0.8442457,0.1171853,0.024925528,0.007288417,0.00051749713],"about_ca_topic_score_codex":0.00014094675,"about_ca_topic_score_gemma":0.000027542437,"teacher_disagreement_score":0.85331506,"about_ca_system_score_codex":0.0002121462,"about_ca_system_score_gemma":0.00013758846,"threshold_uncertainty_score":0.78925824},"labels":[],"label_agreement":null},{"id":"W4281714090","doi":"10.5194/isprs-archives-xliii-b2-2022-593-2022","title":"ACTIVE REINFORCEMENT LEARNING FOR THE SEMANTIC SEGMENTATION OF IMAGES CAPTURED BY MOBILE SENSORS","year":2022,"lang":"en","type":"article","venue":"˜The œinternational archives of the photogrammetry, remote sensing and spatial information sciences/International archives of the photogrammetry, remote sensing and spatial information sciences","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Computer science; Artificial intelligence; Convolutional neural network; Segmentation; Intersection (aeronautics); Machine learning; Reinforcement learning; Task (project management); Set (abstract data type); Metric (unit); Labeled data; Annotation; Artificial neural network; Pattern recognition (psychology)","score_opus":0.013848760740669767,"score_gpt":0.26254826424896305,"score_spread":0.24869950350829328,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4281714090","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":[0.004248074,0.00004712189,0.9867565,0.004547273,0.0012476424,0.0010124873,0.000116636314,0.000040055682,0.0019842098],"genre_scores_gemma":[0.9960177,0.00014691004,0.002852978,0.00063197303,0.0000690982,0.0000026608163,0.00010389468,0.000009177153,0.00016559771],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9956427,0.00045084354,0.0012415152,0.00038978175,0.0018699908,0.0004051508],"domain_scores_gemma":[0.995118,0.0017774451,0.002200506,0.0005182616,0.00029502713,0.00009075624],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0018639341,0.00032445672,0.00033895628,0.0006208896,0.0022881199,0.0005901792,0.0022164383,0.000051029227,0.000007669632],"category_scores_gemma":[0.00065855915,0.00019929507,0.00031835432,0.0009152751,0.0016965221,0.0005553994,0.0013004772,0.0004903928,0.0000010227094],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013566484,0.000019209074,0.00010067599,0.000034765093,0.00008793226,9.3678274e-8,0.00540073,0.06286212,0.0049617034,0.000018694902,0.00010638767,0.92627203],"study_design_scores_gemma":[0.00069377024,0.00024626995,0.0012562653,0.00009701363,0.000043327524,0.00006639136,0.0047694733,0.9673492,0.016938403,0.0015815322,0.006736958,0.00022140908],"about_ca_topic_score_codex":0.5823028,"about_ca_topic_score_gemma":0.022859093,"teacher_disagreement_score":0.9917696,"about_ca_system_score_codex":0.000060379825,"about_ca_system_score_gemma":0.0002084574,"threshold_uncertainty_score":0.99901074},"labels":[],"label_agreement":null},{"id":"W4281788841","doi":"10.1145/3514221.3517904","title":"FILA: Online Auditing of Machine Learning Model Accuracy under Finite Labelling Budget","year":2022,"lang":"en","type":"article","venue":"Proceedings of the 2022 International Conference on Management of Data","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Audit; Pipeline (software); Computer science; Process (computing); Training set; Artificial intelligence; Machine learning; Data modeling; Labelling; Software engineering; Accounting; Programming language","score_opus":0.10600199055667883,"score_gpt":0.32951755703808333,"score_spread":0.2235155664814045,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4281788841","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":[0.18848358,0.00040515166,0.6243018,0.062584445,0.001852498,0.0019081505,0.0074581127,0.00045704492,0.11254924],"genre_scores_gemma":[0.97340477,0.00018176044,0.02429051,0.000114744704,0.000018207633,0.000011277699,0.00056434795,0.0000092881255,0.0014050844],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981307,0.000028302478,0.0004255594,0.0004101492,0.00088053494,0.00012476086],"domain_scores_gemma":[0.9982321,0.00011112721,0.00092281855,0.0004820549,0.00023004205,0.00002184209],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008681192,0.00011791876,0.0001576705,0.00017296795,0.00015695923,0.000058122496,0.0049663987,0.00001695986,0.00013322014],"category_scores_gemma":[0.00022749406,0.000104081286,0.00004749417,0.00034704932,0.00004433669,0.00059223466,0.0054974426,0.00037283002,0.0000015787123],"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":[0.00005609847,0.00034248238,0.001718706,0.00020025292,0.00017721608,5.0093325e-7,0.00023733161,0.06650443,0.0047902907,0.90249616,0.0011494854,0.022327073],"study_design_scores_gemma":[0.00026115403,0.00005920517,0.0007473597,0.00010923607,0.000022682303,0.0000010599582,0.000502049,0.989136,0.00037588325,0.006795807,0.0018956711,0.00009391975],"about_ca_topic_score_codex":0.000031593365,"about_ca_topic_score_gemma":0.000001619123,"teacher_disagreement_score":0.92263156,"about_ca_system_score_codex":0.000037589427,"about_ca_system_score_gemma":0.000034603505,"threshold_uncertainty_score":0.92288876},"labels":[],"label_agreement":null},{"id":"W4283794051","doi":"10.1609/aaai.v36i7.20762","title":"Bag Graph: Multiple Instance Learning Using Bayesian Graph Neural Networks","year":2022,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada; Ministère de la Défense Nationale","keywords":"Computer science; Artificial intelligence; Machine learning; Graph; Pooling; Artificial neural network; Bayesian network; Theoretical computer science","score_opus":0.06644305000915629,"score_gpt":0.2860817504712997,"score_spread":0.2196387004621434,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283794051","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":[0.26127607,0.00012342689,0.73007596,0.0032368056,0.0012321125,0.00061943254,0.00000950351,0.0003728543,0.0030538826],"genre_scores_gemma":[0.9953247,0.000020933032,0.004195411,0.00024664248,0.00006334746,0.000036699923,0.0000033698018,0.000018332228,0.00009061437],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99757093,0.00010594065,0.0005567527,0.00067390676,0.0006546053,0.00043788337],"domain_scores_gemma":[0.99842966,0.00014321954,0.00062574627,0.00041044914,0.00029215455,0.00009877089],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008826892,0.00024749068,0.0002530638,0.00023226273,0.0011108096,0.00030700813,0.0024999473,0.00006166336,0.000064432905],"category_scores_gemma":[0.000434282,0.000216128,0.00014731142,0.0015703116,0.00019955992,0.0005113893,0.00085583125,0.0010226497,0.0000063053467],"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":[0.00012549841,0.00017822697,0.008747631,0.00003500585,0.000023159364,0.0000016901924,0.0017132303,0.16580531,0.022129344,0.6702521,0.000103638675,0.1308852],"study_design_scores_gemma":[0.000037344118,0.00016942875,0.0004234972,0.0000413937,0.000009390098,0.000011061549,0.0006419382,0.9710264,0.007751325,0.019360723,0.00028398496,0.00024350417],"about_ca_topic_score_codex":0.00013078662,"about_ca_topic_score_gemma":0.000014757621,"teacher_disagreement_score":0.8052211,"about_ca_system_score_codex":0.00006873382,"about_ca_system_score_gemma":0.000065220556,"threshold_uncertainty_score":0.8813444},"labels":[],"label_agreement":null},{"id":"W4283802782","doi":"10.1609/aaai.v36i9.21194","title":"Fast Sparse Decision Tree Optimization via Reference Ensembles","year":2022,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"National Institute on Drug Abuse; Natural Sciences and Engineering Research Council of Canada; U.S. Department of Energy; National Science Foundation","keywords":"Computer science; Decision tree; Tree (set theory); Machine learning; Black box; Incremental decision tree; Artificial intelligence; Optimization problem; Decision tree learning; Mathematical optimization; Algorithm; Mathematics","score_opus":0.07408020904507641,"score_gpt":0.2941409187407192,"score_spread":0.2200607096956428,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283802782","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":[0.034279518,0.00002999507,0.93941784,0.0045792325,0.0006281236,0.00045926098,0.00001596421,0.00021974366,0.0203703],"genre_scores_gemma":[0.9761463,0.000034129334,0.023226593,0.00018352822,0.000036128695,0.000052902382,0.0000064630717,0.000012527899,0.0003014588],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976947,0.000055775647,0.00054510206,0.00061671005,0.00079941645,0.0002883061],"domain_scores_gemma":[0.9983262,0.00013929528,0.0005226446,0.0005141753,0.00041664677,0.00008103239],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007638126,0.00020647161,0.00021425834,0.00019710447,0.00060869794,0.00025085255,0.0026984503,0.000058285405,0.00021208997],"category_scores_gemma":[0.00040443262,0.0001676811,0.00008171582,0.0009647928,0.0001236279,0.00046497403,0.0009397044,0.00047545088,0.00006686533],"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":[0.0000893703,0.00013974807,0.00026513948,0.000013159712,0.0000069058774,4.634913e-7,0.00067124586,0.018667987,0.013481253,0.6042979,0.00028551774,0.36208135],"study_design_scores_gemma":[0.00004097471,0.00028909105,0.00039066884,0.00006214186,0.000010404679,0.000012923152,0.00047526023,0.8982022,0.039372202,0.060087156,0.00079925766,0.00025771902],"about_ca_topic_score_codex":0.000063909465,"about_ca_topic_score_gemma":0.000013386211,"teacher_disagreement_score":0.94186676,"about_ca_system_score_codex":0.00007904443,"about_ca_system_score_gemma":0.00009600294,"threshold_uncertainty_score":0.68378365},"labels":[],"label_agreement":null},{"id":"W4285288617","doi":"10.37590/able.v42.abs33","title":"A Picture is Worth 1000 Words: Using Pictorial Expression Data in Bioinformatics Assignments","year":2022,"lang":"en","type":"article","venue":"Advances in Biology Laboratory Education","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Expression (computer science); Computer science; Bioinformatics; Computational biology; Data mining; Artificial intelligence; Biology; Programming language","score_opus":0.018959073792241862,"score_gpt":0.3496564043107534,"score_spread":0.3306973305185115,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285288617","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":[0.6782141,0.011471476,0.2800335,0.0026087794,0.022613678,0.0014088292,0.0006937213,0.0003414699,0.00261444],"genre_scores_gemma":[0.9350232,0.000269017,0.062311374,0.0009750855,0.0002628256,0.00009840497,0.0010133873,0.000011108327,0.000035609737],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.99848044,0.00036096346,0.00035100355,0.00043843177,0.00016642117,0.00020276448],"domain_scores_gemma":[0.9985591,0.00008405168,0.00026730195,0.0010104972,0.000040204326,0.000038856706],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006164994,0.00012056273,0.0001363751,0.00026115213,0.00016958096,0.000042196792,0.001175613,0.00006870114,0.000044286575],"category_scores_gemma":[0.00011770592,0.00011807,0.000009436802,0.00095361524,0.00003800233,0.0015435902,0.0005674982,0.00034839244,0.000005679447],"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":[0.00008257667,0.0009911573,0.74182564,0.00009071969,0.0000112587795,0.0000030991741,0.009459397,0.0034151294,0.0055125463,0.013796928,0.0027137743,0.22209774],"study_design_scores_gemma":[0.001205322,0.00017739214,0.034650795,0.00012986902,0.000009382281,0.000007577188,0.0031123138,0.07526529,0.0007415741,0.0056098374,0.87838775,0.00070289953],"about_ca_topic_score_codex":0.000023285069,"about_ca_topic_score_gemma":0.00002778888,"teacher_disagreement_score":0.87567395,"about_ca_system_score_codex":0.00023555926,"about_ca_system_score_gemma":0.0005328419,"threshold_uncertainty_score":0.48147547},"labels":[],"label_agreement":null},{"id":"W4286898972","doi":"10.1609/aaai.v37i8.26169","title":"ProxyBO: Accelerating Neural Architecture Search via Bayesian Optimization with Zero-Cost Proxies","year":2023,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute; HEC Montréal","funders":"National Natural Science Foundation of China","keywords":"Computer science; Bayesian optimization; Bayesian probability; Architecture; Task (project management); Generalization; Search cost; Zero (linguistics); Machine learning; Artificial intelligence; Engineering; Mathematics","score_opus":0.07634166923046799,"score_gpt":0.3028746530710318,"score_spread":0.2265329838405638,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4286898972","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":[0.039237965,0.000005588323,0.9441179,0.01139146,0.0001816119,0.0009780194,0.0000054301345,0.00044719537,0.0036348477],"genre_scores_gemma":[0.9779484,0.00000971778,0.021551808,0.00009660074,0.000056982204,0.00007270887,0.000007518787,0.000018139537,0.00023811606],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99796146,0.000043642012,0.00039580083,0.00058160047,0.00062129495,0.00039619757],"domain_scores_gemma":[0.9986328,0.00009355116,0.0002907271,0.00037302033,0.000522025,0.00008786559],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006144039,0.00022517802,0.00019993597,0.00022550048,0.0004038022,0.00054808334,0.0016576868,0.00007582892,0.000023669261],"category_scores_gemma":[0.00031117923,0.00015117871,0.0000556497,0.0015905155,0.00016478123,0.00052973,0.00035729236,0.00048053553,0.00004437563],"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":[0.00013955642,0.000109010936,0.0020782745,0.00015301595,0.000023329167,0.0000016222357,0.0045001293,0.09426767,0.030221593,0.43412903,0.0001343764,0.4342424],"study_design_scores_gemma":[0.000027736372,0.00018342977,0.00047048234,0.00012526153,0.0000059120794,0.000007969348,0.00024755808,0.9123782,0.07692108,0.009412603,0.000036285117,0.00018347395],"about_ca_topic_score_codex":0.000044328404,"about_ca_topic_score_gemma":0.000010522906,"teacher_disagreement_score":0.93871045,"about_ca_system_score_codex":0.000029794739,"about_ca_system_score_gemma":0.000094209136,"threshold_uncertainty_score":0.6164889},"labels":[],"label_agreement":null},{"id":"W4287279063","doi":"10.48550/arxiv.2103.05844","title":"BIKED: A Dataset for Computational Bicycle Design with Machine Learning\\n Benchmarks","year":2021,"lang":"","type":"preprint","venue":"arXiv (Cornell University)","topic":"Machine Learning and Data Classification","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":"Ontario College of Art and Design","funders":"","keywords":"Interpretability; Variety (cybernetics); Computer science; Machine learning; Class (philosophy); Dimensionality reduction; Artificial intelligence; Representation (politics); Key (lock); Space (punctuation); Data mining","score_opus":0.0957819264067106,"score_gpt":0.21011356248006735,"score_spread":0.11433163607335675,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4287279063","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":[0.013541663,0.00014210083,0.9825091,0.000509253,0.00034116794,0.0009468322,0.0015747396,0.00014314157,0.000292043],"genre_scores_gemma":[0.88479745,0.0001863815,0.06806718,0.00017128358,0.000103550614,0.000009040782,0.045584805,0.000049806116,0.001030524],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99435246,0.0010779565,0.00052355963,0.003007348,0.00030159642,0.000737088],"domain_scores_gemma":[0.9949573,0.0011695395,0.00093028345,0.0019167971,0.00060236146,0.00042369883],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0012282734,0.00075505837,0.00071001664,0.00048571476,0.0010126065,0.0008435246,0.002424874,0.00040723642,0.00037976314],"category_scores_gemma":[0.0002715373,0.0008321898,0.00024991226,0.0013905311,0.00032048987,0.0010765196,0.0017626182,0.0015052912,0.00006971509],"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":[0.00040130466,0.00036818805,0.0056006,0.00020516657,0.00028450426,0.0002045034,0.00031340134,0.97478294,0.000018231036,0.01354637,0.0014242594,0.002850555],"study_design_scores_gemma":[0.0018197675,0.00055173907,0.003926941,0.00021370868,0.00027824417,0.000042767522,0.00020443638,0.97670573,0.000023832608,0.002414858,0.012851911,0.0009660713],"about_ca_topic_score_codex":0.00059034047,"about_ca_topic_score_gemma":0.00013085862,"teacher_disagreement_score":0.9144419,"about_ca_system_score_codex":0.00026176334,"about_ca_system_score_gemma":0.0010717446,"threshold_uncertainty_score":0.9994129},"labels":[],"label_agreement":null},{"id":"W4287883233","doi":"10.1109/dsn53405.2022.00027","title":"The Fault in Our Data Stars: Studying Mitigation Techniques against Faulty Training Data in Machine Learning Applications","year":2022,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; University of British Columbia Hospital","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Smoothing; Machine learning; Training (meteorology); Training set; Artificial intelligence; Resilience (materials science); Quality (philosophy); Fault tolerance; Data modeling; Data mining; Distributed computing; Database","score_opus":0.08916431159158557,"score_gpt":0.34101789163312163,"score_spread":0.2518535800415361,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4287883233","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":[0.013248777,0.0005307669,0.9608479,0.018117648,0.00014144696,0.0015479263,0.00030402845,0.0009705073,0.004290968],"genre_scores_gemma":[0.95850396,0.00012635926,0.036286827,0.00024976197,0.00004284433,0.0002924131,0.0042361454,0.000014586566,0.00024710523],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973632,0.00058722333,0.0004454954,0.0008442729,0.00043758276,0.00032221596],"domain_scores_gemma":[0.9966898,0.000265991,0.00019625782,0.0027788244,0.000027956998,0.00004114688],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004602918,0.00013434676,0.00014075018,0.00020627737,0.00078308774,0.0002913242,0.0049743247,0.000031538664,0.0000036391348],"category_scores_gemma":[0.00040736722,0.00011447235,0.000013142745,0.0010421042,0.000021069784,0.0010720182,0.004119829,0.00094334263,0.000006177479],"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":[0.0000067531764,0.00012445419,0.0184397,0.000010017069,0.000009115655,0.000004584055,0.0017987884,0.0032082687,0.00073630584,0.010192175,0.000569706,0.96490014],"study_design_scores_gemma":[0.00019958925,0.000024993004,0.004779937,0.000010526865,0.0000023239613,0.0000042318884,0.0055181994,0.8500055,0.000017497325,0.00029768335,0.13898304,0.00015645754],"about_ca_topic_score_codex":0.0007289162,"about_ca_topic_score_gemma":0.0018970914,"teacher_disagreement_score":0.9647437,"about_ca_system_score_codex":0.00011549404,"about_ca_system_score_gemma":0.00013652531,"threshold_uncertainty_score":0.9243616},"labels":[],"label_agreement":null},{"id":"W4288598872","doi":"10.48550/arxiv.1902.08673","title":"Ising-Dropout: A Regularization Method for Training and Compression of\\n Deep Neural Networks","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"MNIST database; Overfitting; Computer science; Initialization; Artificial intelligence; Regularization (linguistics); Dropout (neural networks); Inference; Artificial neural network; Machine learning; Deep neural networks; Deep learning","score_opus":0.0765926445852397,"score_gpt":0.23453360157309927,"score_spread":0.15794095698785957,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4288598872","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":[0.0069398517,0.00008639367,0.9917872,0.00011086152,0.00035121568,0.00031636152,0.000008335231,0.000100658486,0.00029914238],"genre_scores_gemma":[0.94034123,0.000029686214,0.05918189,0.00003883555,0.00004812098,8.754245e-7,0.0001204466,0.000012789409,0.00022610676],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985603,0.00023847919,0.00019139583,0.0007637503,0.000059076192,0.00018701686],"domain_scores_gemma":[0.99836653,0.00027393605,0.00041625544,0.00075014896,0.000121394994,0.000071707334],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043130378,0.00018241051,0.0002975994,0.00016954403,0.00012537985,0.00009265956,0.00069342187,0.0002258571,0.0000028439392],"category_scores_gemma":[0.0000679569,0.00019873279,0.000092657145,0.00024749458,0.00004716575,0.00026259208,0.0007436778,0.00033295745,9.066668e-7],"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":[0.000027799577,0.000021937234,0.001336406,0.00010797912,0.000025510075,0.0000027568983,0.00038598935,0.85882014,0.00008041437,0.098147936,0.000020423115,0.04102269],"study_design_scores_gemma":[0.00038619208,0.000051422463,0.0010804294,0.00006761813,0.000046888734,0.0000028861457,0.000056167082,0.98839074,0.000023310362,0.009534048,0.00016451669,0.00019576217],"about_ca_topic_score_codex":0.000042394873,"about_ca_topic_score_gemma":0.0000065084214,"teacher_disagreement_score":0.9334014,"about_ca_system_score_codex":0.000036039946,"about_ca_system_score_gemma":0.00003984021,"threshold_uncertainty_score":0.81040883},"labels":[],"label_agreement":null},{"id":"W4289146976","doi":"10.52591/lxai201812035","title":"ChaLearn AutoML Challenges","year":2018,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Conference Board of Canada","funders":"","keywords":"Relevance (law); Computer science; Data science; Artificial intelligence; Machine learning; Engineering ethics; Engineering; Political science","score_opus":0.03474226566271634,"score_gpt":0.2753298332905767,"score_spread":0.24058756762786035,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4289146976","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":[0.00076190126,0.00019361505,0.4839399,0.017555498,0.00024295373,0.000035364257,1.7522211e-7,0.0006588615,0.49661174],"genre_scores_gemma":[0.9606411,0.000083670784,0.033974614,0.00037771388,0.0002090325,0.0000035818694,0.0000018476836,0.00000383838,0.004704633],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9994484,0.000037143338,0.00006617796,0.00022416511,0.00010727827,0.00011684584],"domain_scores_gemma":[0.99935997,0.000025050625,0.000026104048,0.00050549506,0.000040311592,0.000043055417],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00019795775,0.000048612845,0.00004465472,0.000042632942,0.0000779651,0.000058376296,0.0004624836,0.000026021773,0.00009069232],"category_scores_gemma":[0.0000408094,0.000038770828,0.000013910588,0.00009883261,0.00003071749,0.00022049937,0.000114198825,0.000057509384,0.0017667412],"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":[3.9635768e-7,0.00001102469,0.00008445052,0.0000019487313,0.0000015592304,4.3607028e-7,0.00025311633,2.611699e-7,0.00009384226,0.51785725,0.0015749097,0.4801208],"study_design_scores_gemma":[0.00013445075,0.00015646765,0.061083406,0.0000059276376,0.0000013014538,0.000012704176,0.000042839903,0.1276418,0.00070087495,0.004460929,0.80560434,0.00015497062],"about_ca_topic_score_codex":0.000013702718,"about_ca_topic_score_gemma":0.00002102565,"teacher_disagreement_score":0.95987916,"about_ca_system_score_codex":0.000006026677,"about_ca_system_score_gemma":0.000014370258,"threshold_uncertainty_score":0.9990105},"labels":[],"label_agreement":null},{"id":"W4289364759","doi":"10.48550/arxiv.1810.11165","title":"Efficient learning of neighbor representations for boundary trees and\\n forests","year":2018,"lang":"","type":"preprint","venue":"arXiv (Cornell University)","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"MNIST database; Boundary (topology); Differentiable function; Similarity (geometry); Tree (set theory); Computer science; Artificial intelligence; Pattern recognition (psychology); Mathematics; Deep learning; Combinatorics; Image (mathematics)","score_opus":0.06586452546581235,"score_gpt":0.234209934493364,"score_spread":0.16834540902755163,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4289364759","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":[0.34364772,0.00009967293,0.6539919,0.00016921027,0.0003835806,0.00049714267,0.000048650363,0.00009011977,0.0010720482],"genre_scores_gemma":[0.99258506,0.00019530424,0.004420466,0.000018418501,0.00014642536,0.000004477181,0.00013836288,0.000027981783,0.002463523],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9966348,0.0004030054,0.0005135764,0.0018202415,0.00016462142,0.00046377614],"domain_scores_gemma":[0.99600255,0.0007185703,0.0009944843,0.0014684168,0.0005762028,0.00023979146],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008489916,0.00040551252,0.0005094661,0.0004637317,0.0008449865,0.00024792826,0.0013052404,0.0003054277,0.000047497386],"category_scores_gemma":[0.0005847865,0.00047775015,0.000278136,0.00077010866,0.00069617527,0.00026373714,0.0015913524,0.0006058942,0.00003137843],"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":[0.00025357498,0.0002844608,0.06550141,0.00036613963,0.00017414283,0.00001579716,0.0017274243,0.658949,0.00017101482,0.2638136,0.00025808968,0.00848534],"study_design_scores_gemma":[0.00089429965,0.00033900238,0.08443203,0.0001756864,0.00016712838,0.0000050815916,0.00026987263,0.904151,0.0000801899,0.0065270495,0.0025587147,0.0003999149],"about_ca_topic_score_codex":0.00031571276,"about_ca_topic_score_gemma":0.000108571745,"teacher_disagreement_score":0.6495714,"about_ca_system_score_codex":0.00011803936,"about_ca_system_score_gemma":0.00037712802,"threshold_uncertainty_score":0.9997674},"labels":[],"label_agreement":null},{"id":"W4292582487","doi":"10.3390/math10163019","title":"A Hybrid Sparrow Search Algorithm of the Hyperparameter Optimization in Deep Learning","year":2022,"lang":"en","type":"article","venue":"Mathematics","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":48,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"Natural Science Foundation of Hebei Province; National Natural Science Foundation of China","keywords":"Hyperparameter; Hyperparameter optimization; Computer science; Particle swarm optimization; Artificial intelligence; Algorithm; Deep learning; Search algorithm; Machine learning; Local search (optimization); Mathematical optimization; Multi-swarm optimization; Artificial neural network; Mathematics; Support vector machine","score_opus":0.018102962976953307,"score_gpt":0.2452464133224297,"score_spread":0.2271434503454764,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4292582487","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":[0.02343329,0.000028280157,0.9751153,0.00042257435,0.00007236086,0.0001227912,0.0000022589227,0.000038100952,0.00076506485],"genre_scores_gemma":[0.5561071,0.0000044523376,0.44343042,0.000046008245,0.000008965866,0.000023925844,0.000008717652,0.000008458443,0.00036192354],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989858,0.00021244638,0.0002028592,0.0001476662,0.0003326638,0.000118521624],"domain_scores_gemma":[0.99928606,0.00013407436,0.00011505118,0.00041987473,0.000027863509,0.000017100307],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006879689,0.000058424645,0.00009857819,0.00008205067,0.00014559779,0.000040414827,0.0006415725,0.000011672158,0.000048332247],"category_scores_gemma":[0.00014183842,0.00004661057,0.000032520515,0.00034547248,0.000021441068,0.00009282773,0.00043749585,0.00028071183,0.000005728497],"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":[0.0000013023944,0.00017284267,0.0014369279,0.000043600863,0.0000058120418,0.0000025302386,0.003513349,0.9203951,0.00015917058,0.009462231,0.000045631317,0.06476153],"study_design_scores_gemma":[0.00010482199,0.00002661906,0.00043733921,0.000007907507,0.0000022336947,0.000017814396,0.00017117531,0.9975862,0.0002425082,0.00094664516,0.00040427598,0.000052468306],"about_ca_topic_score_codex":0.00001852736,"about_ca_topic_score_gemma":0.0000010084701,"teacher_disagreement_score":0.53267384,"about_ca_system_score_codex":0.0000394904,"about_ca_system_score_gemma":0.00002757108,"threshold_uncertainty_score":0.19007239},"labels":[],"label_agreement":null},{"id":"W4293223736","doi":"10.11159/mvml22.106","title":"Investigating the Interaction between Data and Algorithms","year":2022,"lang":"en","type":"article","venue":"Proceedings of the World Congress on Electrical Engineering and Computer Systems and Science","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Algorithm","score_opus":0.022769860203890383,"score_gpt":0.2522111478606319,"score_spread":0.22944128765674154,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4293223736","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":[0.9292449,0.0015636062,0.054010827,0.009729453,0.0037577471,0.0008418424,0.000021090516,0.00033576603,0.0004947655],"genre_scores_gemma":[0.99813443,0.00000956908,0.0015958274,0.00006223152,0.00009973662,0.000011747528,6.399783e-7,0.000003865995,0.0000819269],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988673,0.000019728795,0.00017923115,0.0004033386,0.00036075685,0.00016964677],"domain_scores_gemma":[0.99928415,0.00020333652,0.00014404547,0.00024780142,0.00005138579,0.00006926569],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011792601,0.00009425202,0.00012984438,0.00014360259,0.0005961436,0.00046305393,0.0012840072,0.000011145112,1.1935946e-7],"category_scores_gemma":[0.00009708462,0.000059198093,0.000010230063,0.00089845405,0.0001191638,0.00038379774,0.0014482234,0.00032749987,8.625588e-8],"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":[0.000008591215,0.000066379274,0.056233987,0.00028849675,0.000063402644,0.0000010413214,0.0014136279,0.008750689,0.004123257,0.4920953,0.003133078,0.43382215],"study_design_scores_gemma":[0.00007163849,0.000060925846,0.011291137,0.00004820547,0.000004726506,0.00003321457,0.000020234593,0.98277354,0.000086374755,0.00005812447,0.0054749246,0.0000769432],"about_ca_topic_score_codex":0.000032585656,"about_ca_topic_score_gemma":2.799352e-7,"teacher_disagreement_score":0.97402287,"about_ca_system_score_codex":0.00002167482,"about_ca_system_score_gemma":0.000021842261,"threshold_uncertainty_score":0.45851147},"labels":[],"label_agreement":null},{"id":"W4294237904","doi":"10.1145/3558774","title":"AutoML Loss Landscapes","year":2022,"lang":"en","type":"article","venue":"ACM Transactions on Evolutionary Learning and Optimization","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Oracle (Canada); University of British Columbia","funders":"","keywords":"Computer science; Machine learning; Artificial intelligence; Set (abstract data type); Convexity; Bayesian probability; Biology","score_opus":0.008214584684334612,"score_gpt":0.23148625471691617,"score_spread":0.22327167003258155,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4294237904","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":[0.0010148191,0.00018451312,0.99393195,0.0035950795,0.00018934591,0.000085868574,0.000008674211,0.00045898918,0.0005307753],"genre_scores_gemma":[0.85606575,0.00021184991,0.14160857,0.00013865728,0.00002813091,0.00007276235,0.0001372413,0.000013741171,0.0017233017],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987604,0.00027320674,0.0001579118,0.0003693434,0.0002779271,0.000161233],"domain_scores_gemma":[0.99933547,0.0001487235,0.00008320537,0.0003280418,0.00004351637,0.00006105239],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.00025590204,0.000110711044,0.00008981292,0.00022079624,0.001575696,0.00007295084,0.00034092792,0.000037980717,0.00024212108],"category_scores_gemma":[0.000059443068,0.00012085168,0.000038576894,0.00047851616,0.000025363048,0.0003669528,0.000040927363,0.00045787438,0.000017588445],"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":[0.000015155654,0.00007490767,0.0007088503,0.000004128099,0.0000094340485,0.0000020151963,0.00020505715,0.9571798,0.00000987456,0.0018470674,0.00010688115,0.03983682],"study_design_scores_gemma":[0.0002952391,0.00018774456,0.0023086849,0.0000046624245,0.000009063186,0.00006695333,0.0001156131,0.961547,0.000004702531,0.00034270488,0.034970056,0.00014753405],"about_ca_topic_score_codex":0.000023026912,"about_ca_topic_score_gemma":0.0000014026572,"teacher_disagreement_score":0.8550509,"about_ca_system_score_codex":0.00007609163,"about_ca_system_score_gemma":0.000052253727,"threshold_uncertainty_score":0.9997241},"labels":[],"label_agreement":null},{"id":"W4297839797","doi":"10.1016/j.inffus.2022.09.010","title":"OLP++: An online local classifier for high dimensional data","year":2022,"lang":"en","type":"article","venue":"Information Fusion","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure; Université du Québec à Montréal","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada; Fonds de recherche du Québec; Fundação de Amparo à Ciência e Tecnologia do Estado de Pernambuco; Conselho Nacional de Desenvolvimento Científico e Tecnológico; Coordenação de Aperfeiçoamento de Pessoal de Nível Superior","keywords":"Computer science; Curse of dimensionality; Locality; Classifier (UML); Artificial intelligence; Leverage (statistics); Decision tree; Ensemble learning; Data mining; Machine learning; Feature vector; Euclidean distance; Majority rule; Space partitioning; Pattern recognition (psychology); Algorithm","score_opus":0.060004664030360526,"score_gpt":0.2911801952731292,"score_spread":0.23117553124276868,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4297839797","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":[0.0164876,0.000009702747,0.9772348,0.0041297027,0.0006214932,0.00023499476,0.00071956596,0.00021271645,0.00034947094],"genre_scores_gemma":[0.9049816,0.000003370102,0.051637236,0.002856034,0.00010073494,0.000048706905,0.04016879,0.000006557657,0.00019695541],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988439,0.000075559146,0.0003005895,0.00021620991,0.0004207081,0.00014303529],"domain_scores_gemma":[0.99857944,0.00006442148,0.00017854181,0.0010221337,0.0000888614,0.00006661606],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005979206,0.00008407515,0.00007915257,0.00013471802,0.0005230706,0.00012152485,0.0011439386,0.000033471282,0.00012295133],"category_scores_gemma":[0.000073370764,0.0000786993,0.000018145165,0.00023363199,0.000018428047,0.0031337452,0.0010843754,0.0001728331,0.000049863374],"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":[0.00004957032,0.00013936723,0.0000850551,0.0000150528385,0.0000045970387,4.8947095e-7,0.00042562335,0.011048447,0.00017360492,0.06732271,0.034071576,0.8866639],"study_design_scores_gemma":[0.0003047108,0.00010135172,0.003436999,0.000002009059,0.000002246021,0.0000072279463,0.00007789137,0.6749211,0.000015301628,0.0004462364,0.32060564,0.00007928976],"about_ca_topic_score_codex":0.00009596714,"about_ca_topic_score_gemma":0.000014401863,"teacher_disagreement_score":0.92559755,"about_ca_system_score_codex":0.000053634267,"about_ca_system_score_gemma":0.00009447568,"threshold_uncertainty_score":0.4023089},"labels":[],"label_agreement":null},{"id":"W4300500905","doi":"10.48550/arxiv.1511.05643","title":"A New Smooth Approximation to the Zero One Loss with a Probabilistic\\n Interpretation","year":2015,"lang":"","type":"preprint","venue":"arXiv (Cornell University)","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Hinge loss; Algorithm; Computer science; Probabilistic logic; Maxima and minima; Artificial intelligence; Mathematics; Benchmark (surveying); Machine learning; Mathematical optimization; Pattern recognition (psychology); Support vector machine","score_opus":0.07255764657942833,"score_gpt":0.20401485387456897,"score_spread":0.13145720729514065,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4300500905","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":[0.021255579,0.000028712762,0.97033143,0.0022766169,0.0005322863,0.0015665614,0.000024411514,0.00022896021,0.0037554419],"genre_scores_gemma":[0.9777083,0.00003291055,0.017621791,0.0002191765,0.00021323432,0.000008244313,0.00014358191,0.000034554905,0.004018202],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9959705,0.000666111,0.0004436105,0.0020335044,0.0003723716,0.00051389076],"domain_scores_gemma":[0.99469763,0.00021025808,0.0007468639,0.0027196165,0.0010712673,0.0005543369],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0012224223,0.00055098295,0.0004693441,0.0003492023,0.00039116526,0.00068625325,0.0028968733,0.00027583618,0.000045642693],"category_scores_gemma":[0.0006294995,0.00047312296,0.00013312801,0.001842634,0.00017915897,0.00089932926,0.0016157521,0.0010009676,0.0005785124],"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":[0.00063892367,0.00021744147,0.0012465337,0.00016019488,0.00012135373,0.000025581938,0.006664922,0.7651662,0.000010249719,0.18973498,0.001551201,0.034462377],"study_design_scores_gemma":[0.0008280204,0.0004542411,0.003642151,0.0004184703,0.00022942887,0.0000074936775,0.0001993033,0.9589522,0.000012747238,0.026814876,0.0077942666,0.0006467963],"about_ca_topic_score_codex":0.0010771853,"about_ca_topic_score_gemma":0.00048939174,"teacher_disagreement_score":0.9564527,"about_ca_system_score_codex":0.0006181638,"about_ca_system_score_gemma":0.0012226565,"threshold_uncertainty_score":0.9997721},"labels":[],"label_agreement":null},{"id":"W4308238721","doi":"10.1109/ccece49351.2022.9918388","title":"Program","year":2022,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria; Carleton University; University of British Columbia","funders":"","keywords":"NIST; Computer science; Process (computing); Relation (database); Quality (philosophy); Engineering management; Compatibility (geochemistry); Engineering; Database","score_opus":0.013140669340907487,"score_gpt":0.270739311971883,"score_spread":0.25759864263097554,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4308238721","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":[0.002721926,0.000030733245,0.7785841,0.010927573,0.0002701233,0.0001478251,9.743616e-7,0.0014885409,0.20582817],"genre_scores_gemma":[0.8915847,5.306472e-7,0.102649346,0.00049978535,0.000012805966,0.0000859701,0.000011367321,0.0000016289471,0.0051538427],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9996845,0.00003352793,0.000033210697,0.000098832585,0.000097647164,0.000052257503],"domain_scores_gemma":[0.9997279,0.0000088329225,0.000012361165,0.00023117775,0.000004699412,0.000015025663],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011855583,0.00001713484,0.000016325945,0.000020573494,0.00012898132,0.00004068998,0.00036298495,0.0000025546794,0.00019015651],"category_scores_gemma":[0.000006717784,0.000015247803,0.000008418305,0.0001547454,0.0000029349546,0.00007332048,0.00022921411,0.000060274033,0.000052016],"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":[2.5215493e-7,0.00004016975,0.0006043974,4.3677542e-7,6.1551145e-7,7.979791e-7,0.000046341513,0.00004873689,0.000034962894,0.36772007,0.0074241203,0.6240791],"study_design_scores_gemma":[0.00003581976,0.000054515327,0.004957242,6.937893e-8,2.0380321e-7,0.000005979101,0.000012858295,0.14250992,0.000015044753,0.0008321016,0.8515463,0.000029940053],"about_ca_topic_score_codex":0.0000140385655,"about_ca_topic_score_gemma":5.963932e-7,"teacher_disagreement_score":0.8888628,"about_ca_system_score_codex":0.000008133323,"about_ca_system_score_gemma":0.000011072092,"threshold_uncertainty_score":0.20820804},"labels":[],"label_agreement":null},{"id":"W4309030579","doi":"10.1109/jsen.2022.3197443","title":"Data-Driven Monitoring for Distributed Sensor Networks: An End-to-End Strategy Based on Collaborative Learning","year":2022,"lang":"en","type":"article","venue":"IEEE Sensors Journal","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Smoothing; Overfitting; End-to-end principle; Soft sensor; Artificial intelligence; Convolution (computer science); Machine learning; Real-time computing; Computer vision; Process (computing); Artificial neural network","score_opus":0.051067049805364674,"score_gpt":0.32305466017211365,"score_spread":0.27198761036674896,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4309030579","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":[0.08024343,0.000029133678,0.91526467,0.0016094642,0.0015368058,0.0003381417,0.00066068384,0.00019612115,0.00012156343],"genre_scores_gemma":[0.9657529,0.000009124353,0.032418255,0.00012695145,0.00092020445,0.000026012813,0.00056418986,0.000029142668,0.00015320975],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969188,0.0009954032,0.00038282434,0.00062560354,0.00061583176,0.0004615612],"domain_scores_gemma":[0.997776,0.00046704215,0.00037196284,0.0008303103,0.00024477477,0.00030996112],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0014124361,0.0002144757,0.00023311524,0.00022633727,0.0015781572,0.0006862313,0.0013765404,0.000050835435,0.000047369183],"category_scores_gemma":[0.0002725181,0.00021205429,0.00005654726,0.0007720206,0.000026240588,0.0006039625,0.00016726892,0.0010741025,0.000009567816],"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":[0.00010299808,0.000081246406,0.0009862159,0.0000033332617,0.000021832779,0.000042753418,0.00022352466,0.9803954,0.0008165605,0.00014339997,0.0021207281,0.015062004],"study_design_scores_gemma":[0.0006167221,0.00088145584,0.002758457,0.000018027278,0.000015897194,0.00006488683,0.00067444536,0.96005154,0.00016244939,0.00002349134,0.034487523,0.00024507978],"about_ca_topic_score_codex":0.0000145575195,"about_ca_topic_score_gemma":0.000004998458,"teacher_disagreement_score":0.8855095,"about_ca_system_score_codex":0.0001943168,"about_ca_system_score_gemma":0.0002432494,"threshold_uncertainty_score":0.99972165},"labels":[],"label_agreement":null},{"id":"W4310421030","doi":"10.48550/arxiv.2211.15088","title":"Class Adaptive Network Calibration","year":2022,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Compute Canada","keywords":"Smoothing; Computer science; Class (philosophy); Artificial intelligence; Machine learning; Code (set theory); Calibration; Artificial neural network; Scalability; Segmentation; Data mining; Mathematical optimization; Mathematics","score_opus":0.07988316392125443,"score_gpt":0.1942131229630021,"score_spread":0.11432995904174768,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4310421030","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":[0.008009299,0.00005906978,0.9793695,0.00040785375,0.0008623927,0.00021430058,0.000022000275,0.00043693103,0.010618653],"genre_scores_gemma":[0.9917902,0.00007573666,0.0042840797,0.00019044563,0.00016704241,0.000002639998,0.00022227042,0.000014949302,0.0032526394],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979949,0.00041672346,0.00016385873,0.0010355246,0.00011568803,0.00027330304],"domain_scores_gemma":[0.99806476,0.000112411326,0.000302007,0.001350819,0.000060866198,0.00010916541],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00034693565,0.00021796221,0.00020577048,0.00013752624,0.00033528457,0.00014745837,0.0017424504,0.00016862873,0.00013837496],"category_scores_gemma":[0.000029303612,0.0002669014,0.00012263346,0.00064022123,0.00004724013,0.00041536824,0.00263422,0.00089446414,0.000053796663],"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":[0.000013025044,0.000024039546,0.001797996,0.000008900592,0.000022329476,0.000038148533,0.00006938969,0.5364226,0.0000019728243,0.45859182,0.0022817033,0.0007280642],"study_design_scores_gemma":[0.00015317104,0.00004908158,0.00209521,0.00001585192,0.000024150033,0.0000021474018,0.000043224834,0.94758964,0.0000022447857,0.032862835,0.016882136,0.00028032117],"about_ca_topic_score_codex":0.00019171364,"about_ca_topic_score_gemma":0.000040024996,"teacher_disagreement_score":0.9837809,"about_ca_system_score_codex":0.00021962367,"about_ca_system_score_gemma":0.00020913644,"threshold_uncertainty_score":0.9999783},"labels":[],"label_agreement":null},{"id":"W4312322643","doi":"10.1007/978-3-031-16990-8_12","title":"K-Means","year":2022,"lang":"en","type":"book-chapter","venue":"International series in management science/operations research/International series in operations research & management science","topic":"Machine Learning and Data Classification","field":"Computer Science","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":"Public Health Ontario; York University","funders":"","keywords":"Class (philosophy); Computer science; Artificial intelligence; Machine learning; Word error rate","score_opus":0.06925613007879076,"score_gpt":0.411802892195162,"score_spread":0.3425467621163712,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312322643","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":[0.00040050276,0.000112952985,0.007224778,0.03829368,0.003665027,0.002971246,0.00015240039,0.00023858971,0.94694084],"genre_scores_gemma":[0.09033369,0.010257155,0.05554112,0.00042071586,0.0004470972,0.0029252684,0.00089882006,0.00011973651,0.8390564],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.97627956,0.0005975968,0.0017824942,0.0038959016,0.015302263,0.0021422077],"domain_scores_gemma":[0.9930161,0.00026844547,0.00014801799,0.0032536688,0.0028585,0.00045522893],"candidate_categories":["metaepi_narrow","bibliometrics","sts","scholarly_communication","open_science","research_integrity","insufficient_payload"],"consensus_categories":["sts","scholarly_communication","open_science","insufficient_payload"],"category_scores_codex":[0.02487082,0.000717484,0.0005108323,0.017724024,0.0056043873,0.00814716,0.020922536,0.00018998329,0.004605994],"category_scores_gemma":[0.0014789733,0.000775877,0.00016669597,0.007917866,0.0071199876,0.014935974,0.016177602,0.0030782197,0.000861463],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000073289426,0.00030469437,0.00014614298,0.000045350193,0.00007108897,0.00030681107,0.00077380234,0.08093215,0.00019738781,0.9053534,0.0020578285,0.009738041],"study_design_scores_gemma":[0.0008818965,0.0002456046,0.00356694,0.00036374354,0.000009326862,0.000060810773,0.0023200018,0.17472868,0.00008782606,0.031853113,0.78490335,0.0009786923],"about_ca_topic_score_codex":0.0011690807,"about_ca_topic_score_gemma":0.004890374,"teacher_disagreement_score":0.8735003,"about_ca_system_score_codex":0.0072822724,"about_ca_system_score_gemma":0.0013076555,"threshold_uncertainty_score":0.9999165},"labels":[],"label_agreement":null},{"id":"W4312847312","doi":"10.1109/icsme55016.2022.00014","title":"An Empirical Study on the Usage of Automated Machine Learning Tools","year":2022,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Computer science; Empirical research; Artificial intelligence; Machine learning; Data science; Human–computer interaction; Statistics","score_opus":0.06111834535786222,"score_gpt":0.3460897599133117,"score_spread":0.2849714145554495,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312847312","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":[0.9423221,0.000009096453,0.044624157,0.004110173,0.00010792293,0.00031472935,0.000007317052,0.0010966811,0.0074078566],"genre_scores_gemma":[0.9981764,3.3202483e-7,0.0009406132,0.00038096617,0.000009597801,0.000026691603,0.000022162361,0.0000051611573,0.00043806626],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980557,0.0010066079,0.0001722881,0.0002678822,0.0003840878,0.00011345832],"domain_scores_gemma":[0.99884546,0.00031840906,0.00009562277,0.00068472966,0.000021808142,0.000033959266],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012325845,0.000073641066,0.00009336162,0.00006953019,0.00039404904,0.00010366309,0.0009789792,0.000011299038,0.00022877743],"category_scores_gemma":[0.00015574846,0.00004713589,0.000024961217,0.0004375966,0.000015567333,0.00016740634,0.00031715469,0.000343355,0.000020787564],"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":[0.00008539409,0.005139879,0.710793,0.000011623108,0.00008621104,0.0000350696,0.017844077,0.05296146,0.0075313295,0.08120926,0.00849135,0.11581133],"study_design_scores_gemma":[0.00014248845,0.00086493965,0.2133044,7.1849365e-7,0.000002437371,0.0000029061741,0.0005580629,0.77911484,0.0000683654,0.00003996613,0.005839828,0.0000610398],"about_ca_topic_score_codex":0.00010118602,"about_ca_topic_score_gemma":0.000006725052,"teacher_disagreement_score":0.7261534,"about_ca_system_score_codex":0.000020525531,"about_ca_system_score_gemma":0.000027650989,"threshold_uncertainty_score":0.30307466},"labels":[],"label_agreement":null},{"id":"W4313396527","doi":"10.1080/21681163.2022.2154275","title":"Semi-supervised learning from coarse histopathology labels","year":2022,"lang":"en","type":"article","venue":"Computer Methods in Biomechanics and Biomedical Engineering Imaging & Visualization","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vancouver General Hospital; Queen's University; University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Artificial intelligence; Leverage (statistics); Pattern recognition (psychology); Entropy (arrow of time); Pixel; Supervised learning; Machine learning; Artificial neural network","score_opus":0.016869665151734242,"score_gpt":0.3091208660537798,"score_spread":0.2922512009020456,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313396527","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":[0.0038537781,0.00050456583,0.99329764,0.00061254227,0.0012357683,0.00010891202,0.0000064323103,0.00037293968,0.000007421493],"genre_scores_gemma":[0.121799245,0.00008337192,0.87697786,0.00051112514,0.00015320926,0.00004560163,0.00037179847,0.000034562243,0.000023218781],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99768883,0.00064252026,0.00040987582,0.0006443873,0.00030640035,0.00030800977],"domain_scores_gemma":[0.9990682,0.0003110093,0.00012553744,0.0003323247,0.00003797389,0.00012494848],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017887373,0.00019704067,0.0002589405,0.0005801565,0.00021116975,0.00013392074,0.0005506227,0.000067709174,0.000024688223],"category_scores_gemma":[0.00017560335,0.0002140115,0.000038436556,0.0010286977,0.000033735825,0.00021027937,0.0009393855,0.00044335637,0.0000021454941],"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":[0.0000068115387,0.00015808082,0.00065526133,0.000050138664,0.000011948047,0.000051073108,0.001285007,0.0042545055,0.1377469,0.026417816,0.00015997129,0.8292025],"study_design_scores_gemma":[0.00041472682,0.0000827474,0.00059455284,0.000024565683,0.00000616432,0.00003484611,0.000026887432,0.9584679,0.00029329775,0.00081342214,0.039006405,0.00023451036],"about_ca_topic_score_codex":0.000065534856,"about_ca_topic_score_gemma":2.7384567e-7,"teacher_disagreement_score":0.9542134,"about_ca_system_score_codex":0.00012136047,"about_ca_system_score_gemma":0.000040348765,"threshold_uncertainty_score":0.87271357},"labels":[],"label_agreement":null},{"id":"W4318148079","doi":"10.1109/bigdata55660.2022.10020681","title":"Don’t Blindly Use Data: Towards a Data Statement for Computational Financial Research","year":2022,"lang":"en","type":"article","venue":"2022 IEEE International Conference on Big Data (Big Data)","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Statement (logic); Data science; Data quality; Context (archaeology); Problem statement; Focus (optics); Quality (philosophy); Work (physics); Management science","score_opus":0.7268565196499841,"score_gpt":0.47980048120678986,"score_spread":0.24705603844319424,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4318148079","genre_codex":"methods","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00073853147,0.000046002388,0.6619424,0.016746527,0.005959207,0.0007169757,0.31317398,0.00013565039,0.0005407151],"genre_scores_gemma":[0.18555784,0.0002053567,0.032643326,0.001170495,0.0017209176,0.0001784737,0.777316,0.000039226907,0.0011683733],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9912679,0.0007454842,0.00084484,0.003263452,0.0032707206,0.0006075887],"domain_scores_gemma":[0.9841397,0.0009281028,0.00045244038,0.0136492085,0.00063056935,0.00019999765],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.007859824,0.00032043495,0.00030860584,0.0005789054,0.0010009978,0.0017405323,0.038418546,0.0000776883,0.0003180532],"category_scores_gemma":[0.0030133883,0.0003376369,0.000029936995,0.0007330783,0.00016596733,0.00485014,0.037829477,0.001138848,0.000122343],"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":[0.00021978295,0.000507305,0.00017613899,0.000023406306,0.00009250003,0.000028190583,0.00008689985,0.0007853724,0.00010570439,0.046860624,0.61179894,0.33931512],"study_design_scores_gemma":[0.0006289837,0.00012298074,0.001008608,0.000019019417,0.000011042762,0.00001190551,0.000058296064,0.50856847,0.0000055089877,0.0013711671,0.48797777,0.00021624756],"about_ca_topic_score_codex":0.0014059752,"about_ca_topic_score_gemma":0.0010920743,"teacher_disagreement_score":0.6292991,"about_ca_system_score_codex":0.00026452864,"about_ca_system_score_gemma":0.002472907,"threshold_uncertainty_score":0.99990755},"labels":[],"label_agreement":null},{"id":"W4319309522","doi":"10.1109/ickg55886.2022.00022","title":"Deep Associative Classifier","year":2022,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Alberta Machine Intelligence Institute","keywords":"Artificial intelligence; Computer science; Associative property; Deep learning; Artificial neural network; Classifier (UML); Deep neural networks; Machine learning; Content-addressable memory; Recurrent neural network; Pattern recognition (psychology); Mathematics","score_opus":0.015027176878753561,"score_gpt":0.24744162599370914,"score_spread":0.23241444911495557,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4319309522","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":[0.0005934643,0.00002490357,0.86244947,0.0062081157,0.00023023663,0.000046927373,0.0000015517697,0.00024304345,0.13020226],"genre_scores_gemma":[0.95578164,0.0000021153332,0.028657919,0.0017254074,0.00003498576,0.000044924724,0.000025540321,0.000004814256,0.013722661],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992257,0.0001493958,0.00007979807,0.0001991244,0.00023205295,0.000113936745],"domain_scores_gemma":[0.9995189,0.00006959351,0.000055121123,0.0003055563,0.000019245563,0.000031635755],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031061756,0.000043486005,0.00004915744,0.000045508998,0.00029799866,0.000061391525,0.00054903456,0.000010980138,0.0004808166],"category_scores_gemma":[0.000049877646,0.00004042744,0.000024282022,0.00027362266,0.000007241034,0.00017250534,0.00037572352,0.0001720338,0.0001217794],"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":[0.0000018315869,0.00006642793,0.005661996,0.0000011026941,0.000010474163,0.000003632063,0.00089208863,0.00036264496,0.00014504949,0.8410312,0.019797638,0.13202593],"study_design_scores_gemma":[0.00016324119,0.000060982406,0.04011282,3.196592e-7,0.0000018400436,0.0000059132767,0.0002481401,0.6268627,0.000037475627,0.0049018706,0.3274802,0.00012447227],"about_ca_topic_score_codex":0.00002668059,"about_ca_topic_score_gemma":0.0000062984677,"teacher_disagreement_score":0.95518816,"about_ca_system_score_codex":0.00006759707,"about_ca_system_score_gemma":0.000027731912,"threshold_uncertainty_score":0.52646047},"labels":[],"label_agreement":null},{"id":"W4319991217","doi":"10.4018/ijdwm.316150","title":"Top-K Pseudo Labeling for Semi-Supervised Image Classification","year":2022,"lang":"en","type":"article","venue":"International Journal of Data Warehousing and Mining","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Institute for Advanced Research","keywords":"Computer science; Artificial intelligence; Artificial neural network; Machine learning; Key (lock); Semi-supervised learning; Supervised learning; Set (abstract data type); Pattern recognition (psychology); Labeled data; Training set; Convergence (economics); Data mining","score_opus":0.07460392936922271,"score_gpt":0.34534800968852597,"score_spread":0.27074408031930325,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4319991217","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":[0.082143135,0.0004366539,0.9084452,0.007275275,0.0012269749,0.00007846697,0.0001681248,0.000049996455,0.00017618375],"genre_scores_gemma":[0.6478644,0.00007686983,0.35104597,0.00034927786,0.00032283607,0.00000489933,0.00027188365,0.000011622301,0.000052256215],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987031,0.00008991107,0.00038621988,0.00026560738,0.0004336693,0.00012147605],"domain_scores_gemma":[0.9986292,0.00024378927,0.0004259292,0.0003701909,0.0002755553,0.00005531214],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013189707,0.000083669154,0.00012185061,0.00022170784,0.00028210087,0.00032464362,0.0016863896,0.000020988897,0.000012512809],"category_scores_gemma":[0.00035184014,0.00008301834,0.00003532903,0.00012503884,0.00002152141,0.0012880481,0.0007167245,0.00020100176,8.9546575e-7],"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":[0.000093800765,0.00011664612,0.0023418276,0.000019242521,0.000109063294,0.00003031364,0.0019837562,0.0006510102,0.020373752,0.0037293686,0.006655739,0.9638955],"study_design_scores_gemma":[0.00123173,0.00015891415,0.0013067442,0.00007083478,0.00003087813,0.00056729326,0.0013427894,0.8734962,0.00018024475,0.00048982084,0.12093358,0.00019101682],"about_ca_topic_score_codex":0.000013089778,"about_ca_topic_score_gemma":0.0000013598731,"teacher_disagreement_score":0.96370447,"about_ca_system_score_codex":0.000064350854,"about_ca_system_score_gemma":0.00012448666,"threshold_uncertainty_score":0.33853897},"labels":[],"label_agreement":null},{"id":"W4321016149","doi":"10.1007/s10994-023-06305-0","title":"Diverse and consistent multi-view networks for semi-supervised regression","year":2023,"lang":"en","type":"article","venue":"Machine Learning","topic":"Machine Learning and Data Classification","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":"Canada Research Chairs; University of Toronto; University of New Brunswick","funders":"Institute for Infocomm Research; Agency for Science, Technology and Research","keywords":"DICOM; Computer science; Consistency (knowledge bases); Probabilistic logic; Artificial intelligence; Machine learning; Graphical model; Data mining; Regression; Mathematics","score_opus":0.04672530729582696,"score_gpt":0.29844873456331644,"score_spread":0.2517234272674895,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4321016149","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":[0.02200254,0.0012194195,0.9716623,0.0028931277,0.00039598046,0.00038050418,0.000008172188,0.0011561625,0.00028181376],"genre_scores_gemma":[0.95884115,0.0006973069,0.035926864,0.00039259368,0.00013585643,0.000069756825,0.0003844895,0.000034660643,0.0035173448],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986619,0.00019928087,0.00020597501,0.00047576573,0.00015676527,0.00030034865],"domain_scores_gemma":[0.9990568,0.00030712248,0.0001196333,0.0003556397,0.00005101773,0.00010976546],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00075689144,0.00016286156,0.00019295746,0.00012762076,0.00051143364,0.00017787129,0.00033684098,0.00007357347,0.000012237316],"category_scores_gemma":[0.00038609153,0.00013449443,0.00006190749,0.00038899097,0.00003442406,0.00022211277,0.00039244743,0.00029545827,0.00003826501],"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":[0.00002615571,0.000057698868,0.07696668,0.00015288599,0.000033630335,0.000018724137,0.0009518779,0.023479534,0.00071179436,0.004810042,0.002599133,0.89019185],"study_design_scores_gemma":[0.0006557015,0.000060453953,0.019230654,0.00006174268,0.00000995136,0.000007509839,0.00007655073,0.9267289,0.000010384869,0.000048243335,0.05295243,0.00015744807],"about_ca_topic_score_codex":0.000063382395,"about_ca_topic_score_gemma":0.000021913,"teacher_disagreement_score":0.93683857,"about_ca_system_score_codex":0.000017793564,"about_ca_system_score_gemma":0.000016008373,"threshold_uncertainty_score":0.5484524},"labels":[],"label_agreement":null},{"id":"W4321098151","doi":"10.1007/s00357-023-09430-6","title":"Classification Trees with Mismeasured Responses","year":2023,"lang":"en","type":"article","venue":"Journal of Classification","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University; University of Waterloo","funders":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Covariate; Set (abstract data type); Computer science; Inference; Identification (biology); Decision tree; Tree (set theory); Variety (cybernetics); Feature (linguistics); Machine learning; Artificial intelligence; Statistics; Data mining; Mathematics","score_opus":0.0656833040863915,"score_gpt":0.3119337141698363,"score_spread":0.24625041008344478,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4321098151","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":[0.23855099,0.0002229313,0.7001578,0.05462408,0.00079674163,0.00032441405,0.000008082096,0.00064110005,0.004673816],"genre_scores_gemma":[0.98679084,0.00014190322,0.01178819,0.000084868254,0.00016865869,0.000011504084,0.000024426761,0.000016016382,0.00097361096],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9978126,0.00033502656,0.0005995523,0.00028508948,0.0007516314,0.00021606272],"domain_scores_gemma":[0.99730515,0.00032213485,0.0009761798,0.00070050656,0.000565819,0.00013022716],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017592937,0.00014710543,0.00021537053,0.0006313982,0.0001729696,0.00023440215,0.00086773233,0.00009034878,0.000007881916],"category_scores_gemma":[0.0005825993,0.000110688845,0.00008174038,0.0014088148,0.00006597642,0.0010225414,0.00003733488,0.0002945246,0.0001394416],"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":[0.00075613445,0.00041370184,0.058968574,0.00006892058,0.0001607817,0.00006450116,0.002177806,0.0006423156,0.27112612,0.16944562,0.030910049,0.46526548],"study_design_scores_gemma":[0.0005677702,0.00026502032,0.90312,0.00005415108,0.00002319681,0.000104483515,0.000304457,0.05471612,0.000784831,0.0009991772,0.038897373,0.00016344059],"about_ca_topic_score_codex":0.0000035549876,"about_ca_topic_score_gemma":0.0000068906675,"teacher_disagreement_score":0.8441514,"about_ca_system_score_codex":0.00009029844,"about_ca_system_score_gemma":0.00031109067,"threshold_uncertainty_score":0.45137602},"labels":[],"label_agreement":null},{"id":"W4323642972","doi":"10.2139/ssrn.4359177","title":"A Novel Systematic Pipeline for Increased Predictability and Explainability of Growth Patterns in Children Using Trajectory Features","year":2023,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre for Global Health Research; Institute for Clinical Evaluative Sciences; SickKids Foundation; Hospital for Sick Children; University of Toronto","funders":"","keywords":"Predictability; Trajectory; Pipeline (software); Computer science; Econometrics; Economics; Mathematics; Statistics; Physics","score_opus":0.011983918060186529,"score_gpt":0.2565711371388183,"score_spread":0.24458721907863176,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4323642972","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":[0.62519586,0.00022169811,0.37406287,0.00013029823,0.000026552172,0.00031452777,0.000012538351,0.00003345793,0.0000022041577],"genre_scores_gemma":[0.99861836,0.00010311046,0.001170392,0.000010791977,0.000047251797,0.00001897847,0.000014164496,0.000008048592,0.000008923227],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99816275,0.00023332212,0.0004119976,0.00027647713,0.00020588805,0.00070956716],"domain_scores_gemma":[0.9990797,0.00024403995,0.00024237134,0.00028642334,0.00009371237,0.000053724852],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0045768707,0.000114910545,0.0002596508,0.0002138287,0.0001054833,0.00004922777,0.0003835639,0.000055849432,4.1667653e-7],"category_scores_gemma":[0.0008088348,0.00009600495,0.0000624889,0.00034468455,0.000030071027,0.0002610407,0.00006898665,0.0005787269,2.3549455e-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":[0.000085902626,0.000303441,0.941618,0.0039430126,0.00009610688,9.746985e-7,0.0010554711,0.00035839668,0.0031885563,0.04650187,0.0000128024085,0.00283546],"study_design_scores_gemma":[0.0013256585,0.00015447874,0.82785094,0.00039519373,0.000039447572,0.00039594484,0.00046141844,0.14850295,0.00012207015,0.020587457,3.6887698e-7,0.00016408812],"about_ca_topic_score_codex":0.0006884863,"about_ca_topic_score_gemma":0.000470479,"teacher_disagreement_score":0.3734225,"about_ca_system_score_codex":0.00028548308,"about_ca_system_score_gemma":0.0005950387,"threshold_uncertainty_score":0.39149684},"labels":[],"label_agreement":null},{"id":"W4362681872","doi":"10.1109/csde56538.2022.10089291","title":"Novel Metrics for Evaluation and Validation of Regression-based Supervised Learning","year":2022,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Francis Xavier University","funders":"","keywords":"Machine learning; Artificial intelligence; Computer science; MNIST database; Consistency (knowledge bases); Regression; Random forest; Metric (unit); Regression analysis; Sample (material); Deep learning; Data mining; Statistics; Mathematics","score_opus":0.058619853697456405,"score_gpt":0.32686733025605735,"score_spread":0.26824747655860093,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362681872","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":[0.039833788,0.00004690532,0.9584715,0.00092050363,0.0000789708,0.00022948493,0.0000050612084,0.00005647007,0.0003573434],"genre_scores_gemma":[0.90914536,0.0000014061475,0.090427704,0.00006220881,0.000008734402,0.0000714151,0.00016310532,0.0000039678116,0.00011612853],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990312,0.0001578878,0.00015023154,0.00021083507,0.0003783306,0.00007152238],"domain_scores_gemma":[0.99912226,0.00035789813,0.00013289708,0.00020919848,0.00015424733,0.000023510416],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017617702,0.000050351522,0.00007222422,0.00019011281,0.00023683162,0.00003916961,0.00020551361,0.000016351878,0.00004801567],"category_scores_gemma":[0.00071689725,0.000045026092,0.000022518121,0.0004542863,0.000009003073,0.00015456171,0.00009672559,0.000084336156,4.9514904e-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":[0.0000711652,0.00031838412,0.024490066,0.000113596114,0.00002001856,1.5727758e-7,0.00095718756,0.14033835,0.06264071,0.057360474,0.00092208886,0.71276784],"study_design_scores_gemma":[0.0007940807,0.00012213422,0.0031725317,0.0000032907783,0.000008794806,8.0007277e-7,0.00007061271,0.9888697,0.004316795,0.00025837007,0.0023261216,0.000056766734],"about_ca_topic_score_codex":0.000031412823,"about_ca_topic_score_gemma":6.5039944e-7,"teacher_disagreement_score":0.8693116,"about_ca_system_score_codex":0.000032378946,"about_ca_system_score_gemma":0.000079683836,"threshold_uncertainty_score":0.18361108},"labels":[],"label_agreement":null},{"id":"W4367727818","doi":"10.1109/access.2023.3272556","title":"Bio-Inspired Feature Selection Algorithms With Their Applications: A Systematic Literature Review","year":2023,"lang":"en","type":"article","venue":"IEEE Access","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":61,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Feature selection; Machine learning; Artificial intelligence; Metaheuristic; Particle swarm optimization; Algorithm; Support vector machine; Feature (linguistics); Data mining","score_opus":0.023262878129273017,"score_gpt":0.3053787232636258,"score_spread":0.2821158451343528,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367727818","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":[0.00017089682,0.023957264,0.96444714,0.007023348,0.00024238364,0.0020004625,0.000021331716,0.0016582222,0.0004789425],"genre_scores_gemma":[0.6744182,0.14551248,0.09857942,0.023963807,0.004065981,0.029002042,0.004285989,0.0004611971,0.019710874],"study_design_codex":"systematic_review","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99871844,0.0001605328,0.0002080235,0.00045536447,0.00026186058,0.00019578807],"domain_scores_gemma":[0.9986568,0.00009314792,0.00021232452,0.00079163775,0.00018225248,0.00006384514],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004523754,0.00016398967,0.0002447733,0.00017948005,0.00020281522,0.00063195766,0.0011684072,0.000074095544,0.0000019045677],"category_scores_gemma":[0.000046820245,0.00010614551,0.00004562368,0.0036389332,0.000016384744,0.0009019835,0.000081907056,0.0002382865,0.00009309178],"study_design_candidate":"systematic_review","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":[0.000034118195,0.00047706577,0.0062605646,0.45101804,0.000502962,0.000102117934,0.0028328763,0.0010838332,0.0024692402,0.027262768,0.20615438,0.30180207],"study_design_scores_gemma":[0.0017961928,0.00047417323,0.022818504,0.22512197,0.0003720628,0.0010816831,0.00011360756,0.6153697,0.003134197,0.002943241,0.12405105,0.0027236054],"about_ca_topic_score_codex":0.000006253643,"about_ca_topic_score_gemma":0.000007359962,"teacher_disagreement_score":0.86586773,"about_ca_system_score_codex":0.000031481624,"about_ca_system_score_gemma":0.000046000503,"threshold_uncertainty_score":0.60939825},"labels":[],"label_agreement":null},{"id":"W4379383388","doi":"10.1016/j.ins.2023.119219","title":"INFER: Distilling knowledge from human-generated rules with uncertainty for STINs","year":2023,"lang":"en","type":"article","venue":"Information Sciences","topic":"Machine Learning and Data Classification","field":"Computer Science","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":"Simon Fraser University","funders":"","keywords":"Computer science; Artificial intelligence; Machine learning; Process (computing); Human intelligence; Set (abstract data type); Knowledge extraction; Data mining","score_opus":0.064384667922655,"score_gpt":0.3379413348105341,"score_spread":0.2735566668878791,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4379383388","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":[0.20422643,0.00001561359,0.7885901,0.000976025,0.00022755368,0.0001979731,0.00008158075,0.0005663399,0.005118398],"genre_scores_gemma":[0.9789711,0.0000060709754,0.020043796,0.00012548802,0.00005831062,0.000047728427,0.0006331108,0.0000024527603,0.00011194509],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99907637,0.0000326564,0.00025346142,0.0001847263,0.0002607075,0.00019210808],"domain_scores_gemma":[0.9991572,0.00022326753,0.00016749854,0.0002315108,0.0001696013,0.000050942646],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00073397584,0.00008704785,0.000085980304,0.00021859919,0.00068505254,0.0006885691,0.0006623641,0.00003055545,0.000009191752],"category_scores_gemma":[0.00019089424,0.00006199783,0.000020432864,0.000982129,0.000104127495,0.0022850807,0.00008937676,0.000060288006,0.00025595355],"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":[0.000018885232,0.000051452123,0.0109706065,0.00006702475,0.000026146265,6.6882285e-7,0.014147709,0.07361988,0.0009993862,0.45089144,0.008819366,0.44038746],"study_design_scores_gemma":[0.00022168076,0.00007486779,0.019374814,0.000021135133,0.0000026313414,5.859838e-7,0.00027503335,0.9215586,0.00024352504,0.002634405,0.05546147,0.0001312574],"about_ca_topic_score_codex":0.00022770141,"about_ca_topic_score_gemma":0.00009389803,"teacher_disagreement_score":0.8479387,"about_ca_system_score_codex":0.000021482178,"about_ca_system_score_gemma":0.00012623833,"threshold_uncertainty_score":0.66398877},"labels":[],"label_agreement":null},{"id":"W4379511426","doi":"10.21428/594757db.6ee355e7","title":"Exploring Preferential Label Smoothing for Neural Network-based Classifiers","year":2023,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke; University of Alberta","funders":"","keywords":"Overfitting; Smoothing; Ground truth; Computer science; Regularization (linguistics); Artificial intelligence; Machine learning; Artificial neural network; Noise (video); Binary classification; Generalization; Pattern recognition (psychology); Mathematics; Support vector machine","score_opus":0.26845584679131046,"score_gpt":0.31943994072303866,"score_spread":0.0509840939317282,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4379511426","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":[0.03488498,0.000008578719,0.95638216,0.004210822,0.0011259082,0.0001988487,0.0000032388648,0.001429339,0.0017561578],"genre_scores_gemma":[0.9376735,0.000006879749,0.0601073,0.0004577507,0.00033853276,0.00018510381,0.00012317454,0.000018171148,0.0010895979],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99887145,0.000058192,0.00017090153,0.00036445592,0.00018002844,0.0003549664],"domain_scores_gemma":[0.9991566,0.00023182345,0.00006225096,0.00043326468,0.000040748884,0.00007530417],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043892473,0.00010383082,0.00009914281,0.00010369274,0.0002524866,0.00023050193,0.0005338942,0.000035497225,0.000009022968],"category_scores_gemma":[0.00009254497,0.000093276394,0.000048872564,0.0005096856,0.000014836637,0.00061856967,0.00012239952,0.00013126718,0.00007833893],"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":[0.000045520963,0.00006357365,0.0026004566,0.000088283494,0.00002889583,0.0000039025276,0.00045519284,0.11047112,0.0016334716,0.23657364,0.049202353,0.5988336],"study_design_scores_gemma":[0.00038375217,0.000046350957,0.005583778,0.000009800134,0.0000038636936,3.535453e-7,0.000016651356,0.971724,0.00020034454,0.00053505,0.021372054,0.00012403767],"about_ca_topic_score_codex":0.000025746009,"about_ca_topic_score_gemma":0.000013230093,"teacher_disagreement_score":0.9027885,"about_ca_system_score_codex":0.00001922002,"about_ca_system_score_gemma":0.00003771254,"threshold_uncertainty_score":0.3803701},"labels":[],"label_agreement":null},{"id":"W4381137345","doi":"10.22214/ijraset.2023.54035","title":"Decision Tree Learning Based Feature Selection and Evaluation for Image Classification","year":2023,"lang":"en","type":"article","venue":"International Journal for Research in Applied Science and Engineering Technology","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Institute for Advanced Research","keywords":"Artificial intelligence; Decision tree; Computer science; Classifier (UML); Machine learning; Decision tree learning; Pattern recognition (psychology); Incremental decision tree; ID3 algorithm; Feature selection; Logistic model tree; Contextual image classification; Data mining; Image (mathematics)","score_opus":0.07829141481452324,"score_gpt":0.4331141711061334,"score_spread":0.3548227562916102,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4381137345","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":[0.08600093,0.000043277138,0.8979024,0.014903387,0.00036475007,0.0004849365,0.0000020081277,0.0001941683,0.00010411766],"genre_scores_gemma":[0.9163179,0.00006136102,0.08329748,0.000011550348,0.000062499406,0.00021436688,0.00001083072,0.0000068531717,0.000017149916],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983849,0.000022363847,0.00015850498,0.00035389166,0.0007758652,0.00030447554],"domain_scores_gemma":[0.9985208,0.0004209782,0.000058637706,0.00011854461,0.00082009943,0.00006092352],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0077321464,0.00007021482,0.000075282,0.0025807335,0.00038909825,0.00043707064,0.0006575136,0.00008676818,6.028007e-7],"category_scores_gemma":[0.0024690884,0.000066541135,0.000013567315,0.0018067277,0.000108117885,0.00035280126,0.00014162184,0.00045974358,0.0000023817122],"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":[0.000038701048,0.00001572094,0.00038219537,0.0000143152865,0.0000048530646,0.0000013836393,0.00006624985,0.008480374,0.14623822,0.07372014,0.00039820743,0.77063966],"study_design_scores_gemma":[0.0005437312,0.00007773428,0.0059688324,0.00003110515,0.0000012777738,0.000026581878,0.00007826488,0.9679361,0.001306351,0.015780272,0.00818437,0.00006536136],"about_ca_topic_score_codex":0.0000019341537,"about_ca_topic_score_gemma":0.0000048013994,"teacher_disagreement_score":0.9594557,"about_ca_system_score_codex":0.00023757691,"about_ca_system_score_gemma":0.00019025737,"threshold_uncertainty_score":0.42146823},"labels":[],"label_agreement":null},{"id":"W4381618813","doi":"10.1016/j.knosys.2023.110732","title":"SSS-Net: A shadowed-sets-based semi-supervised sample selection network for classification on noise labeled images","year":2023,"lang":"en","type":"article","venue":"Knowledge-Based Systems","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":15,"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","funders":"Tongji University; National Natural Science Foundation of China; Natural Science Foundation of Shanghai","keywords":"Sample (material); Computer science; Selection (genetic algorithm); Artificial intelligence; Pattern recognition (psychology); Data mining; Similarity (geometry); Noise (video); Set (abstract data type); Cluster analysis; Machine learning; Sample size determination; Image (mathematics); Mathematics; Statistics","score_opus":0.04507762784135625,"score_gpt":0.30844043386584885,"score_spread":0.2633628060244926,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4381618813","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":[0.0075422195,0.00028642602,0.9827026,0.0019082056,0.002026605,0.0018245896,0.00021458829,0.0024032283,0.0010915184],"genre_scores_gemma":[0.98509556,0.000008142878,0.009558558,0.00023128245,0.00064767123,0.0014077772,0.0019733438,0.000079864854,0.0009978184],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9963306,0.00067390385,0.00068163296,0.0011094061,0.00046696345,0.00073747773],"domain_scores_gemma":[0.9957369,0.0019418189,0.00037332767,0.0012156679,0.0005160631,0.00021621052],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0020390507,0.00040212882,0.00044192455,0.0005024479,0.000693164,0.0005355587,0.0009510115,0.00024420122,0.000015120561],"category_scores_gemma":[0.0007047204,0.00038596577,0.00019287271,0.0023854407,0.00005273437,0.0003003945,0.00006011908,0.00031454174,0.0006910914],"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":[0.00082834344,0.0017029851,0.044627257,0.0029406622,0.00022429656,0.000009682855,0.0012222481,0.29736266,0.05647853,0.069349565,0.41438314,0.11087063],"study_design_scores_gemma":[0.0015404648,0.00032671547,0.010371001,0.0002287283,0.000025116437,0.0000013690445,0.000034224337,0.9363226,0.0008959134,0.0002186925,0.049622707,0.00041241816],"about_ca_topic_score_codex":0.00019756424,"about_ca_topic_score_gemma":0.00010340449,"teacher_disagreement_score":0.9775533,"about_ca_system_score_codex":0.0002884433,"about_ca_system_score_gemma":0.00044957758,"threshold_uncertainty_score":0.9998592},"labels":[],"label_agreement":null},{"id":"W4381801098","doi":"10.5267/j.ijiec.2023.4.004","title":"Extending the hypergradient descent technique to reduce the time of optimal solution achieved in hyperparameter optimization algorithms","year":2023,"lang":"en","type":"article","venue":"International Journal of Industrial Engineering Computations","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Hyperparameter; Machine learning; Computer science; Artificial intelligence; Hyperparameter optimization; Algorithm; Bayesian optimization; Support vector machine","score_opus":0.03418958972268212,"score_gpt":0.28851649353066855,"score_spread":0.25432690380798645,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4381801098","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":[0.03386927,0.00001733949,0.955955,0.008965506,0.0009218662,0.00020696623,0.0000059375393,0.000045374432,0.000012708696],"genre_scores_gemma":[0.90448713,0.000017373884,0.09505867,0.000049425995,0.00031451051,0.000022543702,0.00001936859,0.000011111096,0.000019832152],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986826,0.00010762602,0.0005143305,0.00012912163,0.00042982624,0.00013644838],"domain_scores_gemma":[0.99884653,0.00039565546,0.00026603517,0.0001734728,0.0002718121,0.000046498717],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011205944,0.000093859875,0.00012599952,0.00051873486,0.00006786814,0.000114789014,0.0009559317,0.00005342443,0.0000033475965],"category_scores_gemma":[0.0007039215,0.00006624087,0.00007078481,0.00088264607,0.000021659615,0.00031496407,0.00015115291,0.00034509777,0.0000071183617],"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":[0.000014402571,0.000030478674,0.000063158026,0.0000010189957,0.000028290055,0.0000046446107,0.00033206682,0.977451,0.0023000645,0.0011464292,0.00027773393,0.018350713],"study_design_scores_gemma":[0.00037401434,0.00006623882,0.0022096813,0.00010618951,0.000007100592,0.00006764421,0.000030645624,0.99554765,0.0007641345,0.000050461804,0.00070761755,0.00006860393],"about_ca_topic_score_codex":0.000023318411,"about_ca_topic_score_gemma":5.258906e-7,"teacher_disagreement_score":0.87061787,"about_ca_system_score_codex":0.00013718718,"about_ca_system_score_gemma":0.000095027135,"threshold_uncertainty_score":0.27012244},"labels":[],"label_agreement":null},{"id":"W4381856792","doi":"10.1007/s10845-023-02153-w","title":"Production quality prediction of cross-specification products using dynamic deep transfer learning network","year":2023,"lang":"en","type":"article","venue":"Journal of Intelligent Manufacturing","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":19,"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 Guelph","funders":"National Natural Science Foundation of China","keywords":"Computer science; Transfer of learning; Adaptability; Quality (philosophy); Domain (mathematical analysis); Process (computing); Artificial intelligence; Production (economics); Domain adaptation; Data mining; Machine learning; Mathematics","score_opus":0.06617760022358855,"score_gpt":0.3334831305166272,"score_spread":0.26730553029303866,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4381856792","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":[0.52851903,0.00010025085,0.47002712,0.00027795119,0.00087108836,0.00009769816,7.9782325e-7,0.00007368984,0.000032357628],"genre_scores_gemma":[0.9922274,0.0003280818,0.006856929,0.0000064757915,0.00040397863,0.0000019339489,0.00001805409,0.0000145819495,0.00014261411],"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","domain_scores_codex":[0.9976529,0.00026346926,0.0009974228,0.00031797742,0.0005270247,0.00024121978],"domain_scores_gemma":[0.9984135,0.00009783012,0.0006564877,0.0003890279,0.00038025153,0.00006287696],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026069195,0.00014155792,0.00024000555,0.00032898565,0.00020704149,0.00013514915,0.00045417965,0.00007293467,0.000009045171],"category_scores_gemma":[0.00040882683,0.00012756223,0.000109049026,0.0005483246,0.000046887435,0.000962317,0.00006426585,0.00047491377,0.000013200859],"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":[0.00006818117,0.00006995989,0.007935832,0.00015760378,0.000057041747,0.0000037635095,0.0014915187,0.8461118,0.043290805,0.00068587734,0.00004978112,0.100077875],"study_design_scores_gemma":[0.00026873063,0.00019144727,0.36598614,0.00026237723,0.000039152124,0.00012210269,0.00028355743,0.2789342,0.34883523,0.00094477984,0.0038752942,0.0002569773],"about_ca_topic_score_codex":0.000012284607,"about_ca_topic_score_gemma":0.0000028131544,"teacher_disagreement_score":0.56717753,"about_ca_system_score_codex":0.00014639841,"about_ca_system_score_gemma":0.000061623614,"threshold_uncertainty_score":0.5201837},"labels":[],"label_agreement":null},{"id":"W4381929460","doi":"10.1016/j.dam.2023.05.024","title":"Minimum consistent subset of simple graph classes","year":2023,"lang":"en","type":"article","venue":"Discrete Applied Mathematics","topic":"Machine Learning and Data Classification","field":"Computer Science","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":"Carleton University","funders":"","keywords":"Combinatorics; Mathematics; Vertex (graph theory); Undirected graph; Graph; Feedback vertex set; Discrete mathematics; Simple graph; Planar graph","score_opus":0.028685704390450494,"score_gpt":0.28005047055770643,"score_spread":0.25136476616725595,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4381929460","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":[0.10552139,0.00004195568,0.8542376,0.001220851,0.00016452481,0.0005327741,0.00007783114,0.0009675203,0.03723551],"genre_scores_gemma":[0.93775076,0.00003026733,0.061750386,0.00006434433,0.00001976511,0.000040351515,0.00016958965,0.00001615232,0.00015837909],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99885905,0.000017940623,0.0003510853,0.0002562325,0.00030017726,0.00021551203],"domain_scores_gemma":[0.99859446,0.00026531643,0.00021893173,0.0008160963,0.000042137184,0.00006303172],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003475127,0.00012727838,0.0002230226,0.0001387688,0.00007738185,0.00006444344,0.0005937053,0.000051385396,0.000013473165],"category_scores_gemma":[0.000081746024,0.0001081802,0.00006685757,0.00064508495,0.0000673712,0.00008777756,0.00021808519,0.00009331186,0.00017536314],"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":[0.0000030832161,0.000063428044,0.00017442046,0.00025091114,0.000028185063,0.000002402842,0.0012320961,0.000102317885,0.010846289,0.97682446,0.0065814583,0.0038909498],"study_design_scores_gemma":[0.0014332876,0.00017783581,0.009879305,0.00012791253,0.00010790895,0.000019863686,0.0038317316,0.38892066,0.019398384,0.55053467,0.024465954,0.0011025089],"about_ca_topic_score_codex":0.000005100226,"about_ca_topic_score_gemma":0.0000031185887,"teacher_disagreement_score":0.8322294,"about_ca_system_score_codex":0.000008454122,"about_ca_system_score_gemma":0.000031012467,"threshold_uncertainty_score":0.44114605},"labels":[],"label_agreement":null},{"id":"W4382201038","doi":"10.1145/3589883.3589884","title":"AI2: a novel explainable machine learning framework using an NLP interface","year":2023,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":5,"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 Trois-Rivières","funders":"Canadian Network for Research and Innovation in Machining Technology, Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Scripting language; Python (programming language); Artificial intelligence; Exploit; Machine learning; Coding (social sciences); Natural language processing; Programming language","score_opus":0.0672463347180058,"score_gpt":0.331916429499517,"score_spread":0.2646700947815112,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4382201038","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":[0.03803804,0.00003499065,0.95764965,0.0010232505,0.00021418552,0.00007354675,0.0000018884396,0.0012256358,0.0017387968],"genre_scores_gemma":[0.7924392,0.000010203065,0.20429727,0.000167324,0.00007337783,0.000006512526,0.000033272237,0.000017883644,0.0029549478],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986291,0.000106160434,0.00019381568,0.0004900363,0.00023916931,0.00034171055],"domain_scores_gemma":[0.99892193,0.00015188596,0.00008896401,0.00067251595,0.000050419803,0.00011429065],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00065803877,0.00013943677,0.00013177868,0.00019310576,0.0003362748,0.00034722243,0.0007789406,0.00008101232,0.000079979836],"category_scores_gemma":[0.00034016866,0.00012669581,0.00003462856,0.0009800936,0.000022285334,0.00083751144,0.0004171387,0.00044416572,0.00035294326],"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":[0.00003577266,0.00054610934,0.020630486,0.000119854776,0.00006308608,0.00004503876,0.009124924,0.2713848,0.053809855,0.51125526,0.0016581855,0.13132663],"study_design_scores_gemma":[0.00012178245,0.00006810861,0.0014500248,0.000025608964,0.0000028051738,0.000013460483,0.00019165661,0.9778246,0.0005763071,0.0010443373,0.018508317,0.00017296015],"about_ca_topic_score_codex":0.0004269942,"about_ca_topic_score_gemma":0.000014122941,"teacher_disagreement_score":0.75440115,"about_ca_system_score_codex":0.000038868613,"about_ca_system_score_gemma":0.00003943946,"threshold_uncertainty_score":0.51665056},"labels":[],"label_agreement":null},{"id":"W4382202917","doi":"10.1609/aaai.v37i9.26264","title":"USDNL: Uncertainty-Based Single Dropout in Noisy Label Learning","year":2023,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Wuhan University; National Natural Science Foundation of China","keywords":"Computer science; Dropout (neural networks); Machine learning; Artificial intelligence; Entropy (arrow of time); Computation; Artificial neural network; Cross entropy; Overhead (engineering); Deep neural networks; Selection (genetic algorithm); Algorithm; Pattern recognition (psychology)","score_opus":0.10593084394319452,"score_gpt":0.3191468016734711,"score_spread":0.21321595773027657,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4382202917","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":[0.87989575,0.000028545086,0.057874594,0.03091299,0.0009991261,0.0009425808,0.000010962243,0.0012044242,0.028131027],"genre_scores_gemma":[0.99755967,0.000013225988,0.0016866596,0.00016651175,0.000037917922,0.000027705997,0.0000049715964,0.000013907393,0.0004894562],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979813,0.000051568008,0.0005027947,0.00055626285,0.00050724804,0.00040081836],"domain_scores_gemma":[0.99871534,0.00020652666,0.0003423408,0.00033315347,0.0003292375,0.000073381576],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00097401295,0.00020032903,0.000234761,0.00033285626,0.00020503315,0.00027903426,0.00177182,0.000094190334,0.000031204225],"category_scores_gemma":[0.0012301765,0.00016111453,0.0000707473,0.0019267207,0.00016979151,0.00032593907,0.00031497344,0.00052338815,0.00032322775],"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":[0.00006350002,0.0002231797,0.0057107625,0.00007259072,0.000007384115,0.0000018024264,0.0016018747,0.0055855513,0.10096126,0.7194287,0.00023243812,0.16611096],"study_design_scores_gemma":[0.00005943537,0.0002162084,0.001260837,0.00023069409,0.0000044699987,0.0000011127078,0.00047046572,0.8738568,0.09238393,0.030466244,0.00081941526,0.00023041343],"about_ca_topic_score_codex":0.00015646774,"about_ca_topic_score_gemma":0.000049515624,"teacher_disagreement_score":0.86827123,"about_ca_system_score_codex":0.00007274436,"about_ca_system_score_gemma":0.00011670487,"threshold_uncertainty_score":0.65700597},"labels":[],"label_agreement":null},{"id":"W4382203144","doi":"10.1609/aaai.v37i8.26169","title":"ProxyBO: Accelerating Neural Architecture Search via Bayesian Optimization with Zero-Cost Proxies","year":2023,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute; HEC Montréal","funders":"","keywords":"Computer science; Bayesian optimization; Bayesian probability; Architecture; Task (project management); Search cost; Generalization; Machine learning; Reliability (semiconductor); Artificial intelligence; Engineering; Mathematics; Power (physics)","score_opus":0.02590065413059057,"score_gpt":0.26978281876199867,"score_spread":0.2438821646314081,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4382203144","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":[0.0033111179,0.0000042654715,0.9877695,0.0051497803,0.000054405617,0.00037953697,0.0000015134359,0.00091156317,0.0024183276],"genre_scores_gemma":[0.7221763,0.000002684715,0.2760598,0.0001686707,0.000059363483,0.00006436929,0.00012281326,0.00001705902,0.001328923],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986458,0.00012268947,0.00015724261,0.0004341285,0.00033734104,0.0003027923],"domain_scores_gemma":[0.99921674,0.000071131995,0.000057593108,0.00049190305,0.000080996564,0.00008163267],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032877154,0.00013313656,0.00010196351,0.00018065287,0.0002923189,0.0004449847,0.00053459,0.000043763917,0.000026216841],"category_scores_gemma":[0.000050878065,0.000094481795,0.000021049567,0.0010513406,0.00002707789,0.00048341558,0.00018188015,0.0002548841,0.000048630664],"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":[0.000014923348,0.000031191343,0.00617774,0.00004402359,0.000010714507,0.00001030193,0.0012276858,0.76710993,0.0007761942,0.008134542,0.00054475036,0.21591799],"study_design_scores_gemma":[0.0001639418,0.00007969893,0.004843115,0.000011743207,0.000001997955,0.000019624124,0.000033606888,0.9937593,0.00043498896,0.00014432799,0.0003699273,0.00013778004],"about_ca_topic_score_codex":0.000058699217,"about_ca_topic_score_gemma":0.000022297147,"teacher_disagreement_score":0.7188652,"about_ca_system_score_codex":0.000017545883,"about_ca_system_score_gemma":0.000052061045,"threshold_uncertainty_score":0.4290998},"labels":[],"label_agreement":null},{"id":"W4382237530","doi":"10.1609/aaai.v37i7.26004","title":"A Gift from Label Smoothing: Robust Training with Adaptive Label Smoothing via Auxiliary Classifier under Label Noise","year":2023,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"Defense Acquisition Program Administration; Agency for Defense Development","keywords":"Computer science; Smoothing; Artificial intelligence; Overfitting; Regularization (linguistics); Robustness (evolution); Lipschitz continuity; Machine learning; Classifier (UML); Extractor; Pattern recognition (psychology); Computation; Trimming; Artificial neural network; Algorithm; Mathematics; Computer vision; Engineering","score_opus":0.18662960904574635,"score_gpt":0.309557591752239,"score_spread":0.12292798270649266,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4382237530","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":[0.31898585,0.00006619797,0.63844097,0.023587324,0.0010687629,0.0011015785,0.00006810632,0.0013563441,0.015324869],"genre_scores_gemma":[0.9748106,0.00003256602,0.023683941,0.0005808224,0.00013138352,0.00005881586,0.000013140846,0.00004393395,0.00064480293],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9964621,0.00007505976,0.00071592565,0.001116923,0.0009562342,0.0006737443],"domain_scores_gemma":[0.99739915,0.00040583644,0.00068764994,0.00066199986,0.00065227627,0.00019307046],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010665613,0.0004455876,0.00045691605,0.00029828283,0.0005573501,0.00057992066,0.002613412,0.00020600767,0.0000452543],"category_scores_gemma":[0.0004963296,0.00033549182,0.0000849524,0.001782856,0.0004048316,0.0010397277,0.00061168236,0.00095686316,0.0002566156],"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":[0.0002520896,0.00029205912,0.00066941243,0.000051395866,0.00009536206,0.00000531658,0.010066883,0.0010307442,0.06672517,0.7229439,0.00044562374,0.19742201],"study_design_scores_gemma":[0.00019754404,0.0003657974,0.001619259,0.00048484164,0.000044181692,0.000006253431,0.0035477974,0.87890214,0.026090547,0.08797271,0.00021503726,0.00055386557],"about_ca_topic_score_codex":0.00047904992,"about_ca_topic_score_gemma":0.00012694807,"teacher_disagreement_score":0.8778714,"about_ca_system_score_codex":0.000093640025,"about_ca_system_score_gemma":0.00027354542,"threshold_uncertainty_score":0.9999097},"labels":[],"label_agreement":null},{"id":"W4382318343","doi":"10.1609/aaai.v37i12.26751","title":"Rethinking Label Refurbishment: Model Robustness under Label Noise","year":2023,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Machine Learning and Data Classification","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":"McMaster University","funders":"","keywords":"Robustness (evolution); Generalization; Computer science; Regularization (linguistics); Deep neural networks; Artificial neural network; Artificial intelligence; Noise (video); Machine learning; Pattern recognition (psychology); Mathematics","score_opus":0.1653035614116124,"score_gpt":0.3342900065389262,"score_spread":0.1689864451273138,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4382318343","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":[0.53834546,0.0000452152,0.37938228,0.05169322,0.001251165,0.0009935828,0.000026573493,0.0015632992,0.026699224],"genre_scores_gemma":[0.98871464,0.0000612398,0.009533771,0.00033971862,0.000052524163,0.000033016924,0.00000435122,0.000018609997,0.001242151],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9976751,0.000029933126,0.00052398595,0.0006568528,0.0006915856,0.00042254792],"domain_scores_gemma":[0.99830216,0.00011097065,0.00040753715,0.00054834376,0.0005338556,0.000097130076],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010546594,0.00023684629,0.0002377114,0.00021328536,0.00036989886,0.00038957983,0.0025690577,0.00012577891,0.0000177412],"category_scores_gemma":[0.00046663452,0.00018501276,0.000069575566,0.0014263872,0.0001816247,0.00061182375,0.0006861153,0.00048060893,0.00019832003],"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":[0.000024935573,0.00008695798,0.000081475286,0.00004336516,0.000010650671,3.9629913e-7,0.0013252213,0.006330182,0.029078115,0.9057194,0.00045788984,0.05684143],"study_design_scores_gemma":[0.000032122327,0.000049630988,0.00012745407,0.00013304388,0.000007504163,0.0000015825332,0.00015661775,0.73112583,0.045424256,0.22274536,0.000028874741,0.00016772177],"about_ca_topic_score_codex":0.000030996165,"about_ca_topic_score_gemma":0.000008871837,"teacher_disagreement_score":0.72479564,"about_ca_system_score_codex":0.000057955647,"about_ca_system_score_gemma":0.00012441343,"threshold_uncertainty_score":0.7544601},"labels":[],"label_agreement":null},{"id":"W4382318681","doi":"10.1609/aaai.v37i13.26810","title":"Recent Developments in Data-Driven Algorithms for Discrete Optimization","year":2023,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Heuristics; Algorithm; Computer science; Integer programming; Heuristic; Suite; Mathematical optimization; Artificial intelligence; Machine learning; Mathematics","score_opus":0.19927631671507248,"score_gpt":0.36832322605371776,"score_spread":0.16904690933864527,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4382318681","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":[0.008096433,0.000023327326,0.95975953,0.024358975,0.0009820363,0.0014067179,0.000075092306,0.00037003084,0.004927856],"genre_scores_gemma":[0.89448714,0.0005019366,0.1041325,0.00016819792,0.00006884186,0.00011302595,0.00010836163,0.00001957091,0.00040042985],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984331,0.000017686023,0.00043344646,0.00053494435,0.00032163862,0.0002591845],"domain_scores_gemma":[0.99884963,0.000097385164,0.00026596128,0.0004182075,0.0003224585,0.000046384142],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00079827505,0.00013243422,0.0001546513,0.00018092603,0.00014073194,0.00019339465,0.0024347452,0.000057595935,0.000011279263],"category_scores_gemma":[0.000869451,0.00010367092,0.00002828335,0.0011299837,0.00006698987,0.0005421483,0.0006446484,0.00015954366,0.000048602633],"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":[0.00004524402,0.00006727592,0.0005815682,0.00004409164,0.000010991029,2.639304e-7,0.0010522101,0.009630027,0.0021216774,0.410427,0.0007042505,0.5753154],"study_design_scores_gemma":[0.000032791315,0.000040938365,0.00062321627,0.000095344716,0.000003481179,5.5712337e-7,0.00017310465,0.97605395,0.009667598,0.011453527,0.0017253349,0.00013016703],"about_ca_topic_score_codex":0.000016313299,"about_ca_topic_score_gemma":0.000015121026,"teacher_disagreement_score":0.9664239,"about_ca_system_score_codex":0.000039915016,"about_ca_system_score_gemma":0.00010115216,"threshold_uncertainty_score":0.4524403},"labels":[],"label_agreement":null},{"id":"W4382469227","doi":"10.1609/aaai.v37i1.25088","title":"Denoising after Entropy-Based Debiasing a Robust Training Method for Dataset Bias with Noisy Labels","year":2023,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Machine Learning and Data Classification","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":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"Institute for Information and Communications Technology Promotion; Ministry of Science and ICT, South Korea","keywords":"Debiasing; Computer science; Artificial intelligence; Noise reduction; Machine learning; Generalization; Entropy (arrow of time); Sampling bias; Sample (material); Pattern recognition (psychology); Statistics; Mathematics; Sample size determination; Psychology","score_opus":0.2141292935997887,"score_gpt":0.3536692546631078,"score_spread":0.1395399610633191,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4382469227","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":[0.033149637,0.000009125968,0.95849127,0.006945554,0.0001842493,0.0005522905,0.00014715889,0.0002331136,0.00028760132],"genre_scores_gemma":[0.85437214,0.0000046221676,0.14493333,0.0003885544,0.00006363282,0.00010192329,0.000051292198,0.000021617336,0.00006287035],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978948,0.000049134556,0.00046261062,0.0006665423,0.00047697237,0.00044994397],"domain_scores_gemma":[0.99817,0.0004599534,0.0004213365,0.00043951505,0.00041396217,0.000095220144],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014536015,0.0002410972,0.00027189357,0.00024002718,0.00031026022,0.00050952035,0.001468897,0.00007712375,0.000017940025],"category_scores_gemma":[0.00096979184,0.00017234722,0.00008126881,0.0011306445,0.00013757803,0.0004705526,0.00021306609,0.00027306174,0.000043444088],"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":[0.00058823056,0.00015593827,0.0010326225,0.00027164517,0.000055617726,0.0000037121297,0.004659869,0.005878971,0.06990818,0.55965215,0.0010841154,0.35670894],"study_design_scores_gemma":[0.00008418405,0.00024587812,0.00039360992,0.00040668604,0.000031969197,0.0000055737723,0.000621366,0.84914386,0.13357471,0.014081602,0.0011120086,0.00029856924],"about_ca_topic_score_codex":0.000052879477,"about_ca_topic_score_gemma":0.000029235243,"teacher_disagreement_score":0.8432649,"about_ca_system_score_codex":0.00003898314,"about_ca_system_score_gemma":0.00017501292,"threshold_uncertainty_score":0.70281154},"labels":[],"label_agreement":null},{"id":"W4382795963","doi":"10.1007/978-981-99-3157-6_11","title":"Learning Evaluation for Intelligence","year":2023,"lang":"en","type":"book-chapter","venue":"Advanced technologies and societal change","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":2,"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":"Popularity; Quarter (Canadian coin); Field (mathematics); Artificial intelligence; Computer science; Data science; Psychology; History; Mathematics","score_opus":0.11534005963692061,"score_gpt":0.33551453134064285,"score_spread":0.22017447170372223,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4382795963","genre_codex":"methods","genre_gemma":"other","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":[0.00019009082,0.019634634,0.86931646,0.019878855,0.0019459947,0.0053571947,0.0001288722,0.016746756,0.06680114],"genre_scores_gemma":[0.13195111,0.08517685,0.19036141,0.0005255127,0.0006479616,0.0042600334,0.0018304732,0.0003746959,0.58487195],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9987755,0.00001040669,0.00018355504,0.0005742906,0.00024204886,0.00021423865],"domain_scores_gemma":[0.9990226,0.00017404383,0.00021828547,0.00043415197,0.00012896278,0.000021974185],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00040942477,0.0002130397,0.00021631223,0.00012040145,0.00025055459,0.000083899424,0.00050722377,0.00035522753,0.00000313258],"category_scores_gemma":[0.0003221995,0.00020288986,0.00008852741,0.000086894084,0.00011001884,0.0002919194,0.00042861176,0.00043839964,0.00002815778],"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":[0.0000011289858,0.0000015999598,0.000002378723,0.000034983266,0.000009458078,4.562883e-7,0.00015938953,0.00001234286,0.000013441584,0.29423243,0.000066546905,0.70546585],"study_design_scores_gemma":[0.00022366701,0.0004795222,0.00006979646,0.00021376158,0.000049741964,0.0000054912957,0.0011052776,0.11591333,0.00011313778,0.6235907,0.25760812,0.0006274481],"about_ca_topic_score_codex":0.0000027852539,"about_ca_topic_score_gemma":0.0000073741294,"teacher_disagreement_score":0.7048384,"about_ca_system_score_codex":0.00005435691,"about_ca_system_score_gemma":0.00002082677,"threshold_uncertainty_score":0.8273608},"labels":[],"label_agreement":null},{"id":"W4382993052","doi":"10.54364/aaiml.2023.1167","title":"Evolutionary Augmentation Policy Optimization for Self-Supervised Learning","year":2023,"lang":"en","type":"article","venue":"Advances in Artificial Intelligence and Machine Learning","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Pretext; Computer science; Task (project management); Artificial intelligence; Machine learning; Evolutionary algorithm; Encoding (memory)","score_opus":0.037648791224953224,"score_gpt":0.3341446743973398,"score_spread":0.29649588317238657,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4382993052","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":[0.0026818465,0.00075838686,0.9929873,0.0019378237,0.00018370281,0.00028035976,0.0000027439353,0.0006336067,0.0005342825],"genre_scores_gemma":[0.86699826,0.0051106936,0.1268028,0.00013473861,0.00020784137,0.0001306529,0.00034400498,0.000026621132,0.00024441094],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983805,0.00019187861,0.00039002657,0.0004985419,0.0001987523,0.00034029954],"domain_scores_gemma":[0.9991176,0.00040613906,0.00015414265,0.00017756002,0.00007687155,0.00006765158],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00069507887,0.00016207648,0.00016200576,0.0005132767,0.0004792184,0.00014992627,0.00029070702,0.00006825293,0.000013510683],"category_scores_gemma":[0.00081575534,0.0001692515,0.00004145834,0.0012881182,0.0000433675,0.001249839,0.00013763118,0.00033363618,0.00003784546],"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":[0.000015099076,0.000021120335,0.0025731805,0.00002831742,0.0000028930222,0.0000012173894,0.000766332,0.53320736,0.00010522902,0.05398106,0.0000036106749,0.4092946],"study_design_scores_gemma":[0.00008348639,0.0001461724,0.00060972146,0.00002900656,0.0000042567535,0.000003623088,0.00041526437,0.97700006,0.00020379935,0.011555749,0.009763675,0.00018521595],"about_ca_topic_score_codex":0.000106493215,"about_ca_topic_score_gemma":0.000041394716,"teacher_disagreement_score":0.8661845,"about_ca_system_score_codex":0.00006621644,"about_ca_system_score_gemma":0.00005689357,"threshold_uncertainty_score":0.6901876},"labels":[],"label_agreement":null},{"id":"W4384024880","doi":"10.1145/3583131.3590391","title":"MOAZ: A Multi-Objective AutoML-Zero Framework","year":2023,"lang":"en","type":"article","venue":"Proceedings of the Genetic and Evolutionary Computation Conference","topic":"Machine Learning and Data Classification","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":"McMaster University","funders":"","keywords":"Computer science; Artificial intelligence; Machine learning; Architecture; Pareto principle; Feature (linguistics); Mathematical optimization; Mathematics","score_opus":0.026907332893805543,"score_gpt":0.26998070453079687,"score_spread":0.24307337163699133,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384024880","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":[0.17425479,0.00013559684,0.8215551,0.0027228184,0.00022886076,0.00021714333,0.0000062223567,0.00026407602,0.00061543344],"genre_scores_gemma":[0.8823047,0.000054668566,0.117303744,0.000062773724,0.00002353023,0.000017404642,0.0000040572622,0.000005190948,0.00022393449],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99901724,0.00002126028,0.00021204173,0.00033155514,0.00025472417,0.00016315441],"domain_scores_gemma":[0.99919266,0.0001103677,0.00018962436,0.00012313761,0.00033109816,0.000053140066],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018547053,0.00010930123,0.00011523903,0.00011479787,0.0002469287,0.00008985928,0.0005026478,0.00006279141,0.0000035222608],"category_scores_gemma":[0.0002211283,0.000088627196,0.0000364852,0.0006958059,0.00011589106,0.0002335338,0.0003641514,0.00015357415,0.000025154983],"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":[0.000040662577,0.00022281281,0.1671567,0.000341943,0.00009620526,0.0000014324937,0.009700167,0.014939245,0.0057349754,0.57980114,0.010747804,0.21121691],"study_design_scores_gemma":[0.0000957725,0.000024633458,0.4497286,0.00003917042,0.000004487619,0.000007342469,0.00007197493,0.4948913,0.00005380977,0.054841198,0.00017327188,0.00006845777],"about_ca_topic_score_codex":0.000019549196,"about_ca_topic_score_gemma":4.76444e-7,"teacher_disagreement_score":0.7080499,"about_ca_system_score_codex":0.000021537177,"about_ca_system_score_gemma":0.00007731092,"threshold_uncertainty_score":0.3614112},"labels":[],"label_agreement":null},{"id":"W4384030641","doi":"10.5220/0012090400003555","title":"Automated Feature Engineering for AutoML Using Genetic Algorithms","year":2023,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","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 Windsor","funders":"","keywords":"Computer science; Feature (linguistics); Feature engineering; Genetic algorithm; Algorithm; Artificial intelligence; Machine learning; Deep learning","score_opus":0.025534566936643764,"score_gpt":0.2909624500239157,"score_spread":0.26542788308727194,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384030641","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":[0.0049151587,0.00002212135,0.98901236,0.0010122679,0.00028873677,0.00011731071,0.000004153677,0.004522481,0.000105403364],"genre_scores_gemma":[0.052604795,0.000003982655,0.9459579,0.00008578005,0.0000997723,0.00002033209,0.00004739342,0.000015161271,0.0011648693],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99934155,0.000012848644,0.00009038532,0.0002437745,0.0001081634,0.00020328014],"domain_scores_gemma":[0.9995029,0.000066872075,0.000030318262,0.00031807847,0.000034127963,0.000047702626],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015678434,0.00007880747,0.000072399744,0.00012519803,0.000087345514,0.00012855917,0.00033370318,0.000048855458,0.000003369886],"category_scores_gemma":[0.00007064464,0.00007096359,0.0000308487,0.0005473092,0.0000045900047,0.00014926604,0.00008879398,0.00006658838,0.00005395464],"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":[0.000005338984,0.00006020925,0.0014011599,0.00023540879,0.00007996848,0.00003234533,0.00082802156,0.4898658,0.04290571,0.04981516,0.08123614,0.33353475],"study_design_scores_gemma":[0.00010495265,0.000013287707,0.015568594,0.000006930518,0.0000026891719,0.000007960548,0.000003984046,0.9701063,0.00025562794,0.00005784083,0.013776892,0.00009496238],"about_ca_topic_score_codex":0.000016728038,"about_ca_topic_score_gemma":5.873843e-7,"teacher_disagreement_score":0.48024046,"about_ca_system_score_codex":0.000020538224,"about_ca_system_score_gemma":0.000027801138,"threshold_uncertainty_score":0.28938112},"labels":[],"label_agreement":null},{"id":"W4384575244","doi":"10.23952/jano.5.2023.2.04","title":"IdentifyMix: An efficient two-stage learning approach to combating label noise","year":2023,"lang":"en","type":"article","venue":"Journal of Applied and Numerical Optimization","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Natural Science Foundation of Fujian Province; National Natural Science Foundation of China","keywords":"Artificial intelligence; Computer science; Machine learning; Margin (machine learning); Noise (video); Generalization; Sample (material); Artificial neural network; Selection (genetic algorithm); Supervised learning; Process (computing); Pattern recognition (psychology); Deep learning; Stability (learning theory); Mathematics","score_opus":0.02130369396280206,"score_gpt":0.28307913250964417,"score_spread":0.2617754385468421,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384575244","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":[0.032822873,0.000010101951,0.964647,0.00028968917,0.000087388406,0.00008777161,5.626941e-7,0.00009860006,0.001955996],"genre_scores_gemma":[0.7188635,0.000012219363,0.2808405,0.00011217318,0.000073042844,0.000003853795,0.0000203603,0.0000100506995,0.000064313055],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99885267,0.00007831474,0.00034050108,0.00023243907,0.0003263784,0.00016971228],"domain_scores_gemma":[0.9991852,0.00007171869,0.00030490317,0.00016172306,0.00009664761,0.0001798176],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008094303,0.00010032199,0.00017628612,0.00022440289,0.00020435029,0.00025008526,0.00030076268,0.000037152953,0.0000035688117],"category_scores_gemma":[0.00010076718,0.0000856493,0.000025265374,0.0007597396,0.000015249225,0.00024412527,0.00012197557,0.00025146623,0.00001283428],"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":[0.000021900581,0.00010397602,0.000103807426,0.000009678008,0.0000058218693,0.0000015594884,0.00081109325,0.9697666,0.0009849477,0.009652938,0.000047294227,0.018490352],"study_design_scores_gemma":[0.0004462821,0.00013893686,0.0009949395,0.000009257437,0.000007025433,0.000008300688,0.00016953963,0.9974414,0.00007342035,0.000059823244,0.00054824835,0.000102839585],"about_ca_topic_score_codex":0.00000475079,"about_ca_topic_score_gemma":5.127884e-8,"teacher_disagreement_score":0.68604064,"about_ca_system_score_codex":0.000023655006,"about_ca_system_score_gemma":0.000025597032,"threshold_uncertainty_score":0.34926772},"labels":[],"label_agreement":null},{"id":"W4385248297","doi":"10.1145/3571724","title":"The Principles of Data-Centric AI","year":2023,"lang":"en","type":"article","venue":"Communications of the ACM","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":91,"is_retracted":false,"has_abstract":true,"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; TRACE (psycholinguistics); Data science; Philosophy","score_opus":0.17989544972823113,"score_gpt":0.3795690690161228,"score_spread":0.19967361928789168,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385248297","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00847356,0.0030172404,0.013654364,0.9624579,0.0003945488,0.00051812804,0.00011006921,0.0003507428,0.011023441],"genre_scores_gemma":[0.913794,0.0017579802,0.08327096,0.00013209211,0.000014086134,0.00001581369,0.00011499512,0.0000065628265,0.000893549],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992136,0.00023732646,0.0002064021,0.000110578025,0.00015188352,0.00008021826],"domain_scores_gemma":[0.9348066,0.00091267744,0.0001961891,0.06399283,0.00007850934,0.000013191903],"candidate_categories":["metaresearch","open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.00096455077,0.0000385003,0.000059093858,0.000042384152,0.00035897794,0.00003888305,0.07968687,0.00001668948,8.974995e-7],"category_scores_gemma":[0.008738233,0.000022220174,0.000028047027,0.00083191117,0.00017113889,0.00019599366,0.056227833,0.00013540695,0.000030752755],"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":[0.0000025980573,0.00009285302,0.010497283,0.000019961075,0.000034041997,4.3412278e-8,0.0005613671,0.00028637983,0.00069007906,0.8259072,0.075252295,0.08665591],"study_design_scores_gemma":[0.000106732885,0.000009358263,0.12368643,0.000027262515,0.000011894508,0.0000013470991,0.00007431437,0.22796063,0.00031518418,0.033291586,0.61445516,0.00006008918],"about_ca_topic_score_codex":0.000044247477,"about_ca_topic_score_gemma":0.00003313091,"teacher_disagreement_score":0.9623258,"about_ca_system_score_codex":0.0000069958464,"about_ca_system_score_gemma":0.00006127952,"threshold_uncertainty_score":0.99961156},"labels":[],"label_agreement":null},{"id":"W4385466175","doi":"10.1007/978-3-031-37742-6_47","title":"Weakly Supervised Medical Image Segmentation with Soft Labels and Noise Robust Loss","year":2023,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Machine Learning and Data Classification","field":"Computer Science","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":"University of Alberta; Alberta Bone and Joint Health Institute; University of Calgary","funders":"","keywords":"Computer science; Artificial intelligence; Segmentation; Cross entropy; Deep learning; Probabilistic logic; Ground truth; Pattern recognition (psychology); Medical diagnosis; Noise (video); Image segmentation; Binary classification; Machine learning; Image (mathematics); Support vector machine","score_opus":0.01713412965787675,"score_gpt":0.2517878722043876,"score_spread":0.23465374254651084,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385466175","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":[0.00033127633,0.000090658425,0.99367416,0.004150393,0.00047989705,0.0002760777,0.000009261764,0.00030327137,0.0006849937],"genre_scores_gemma":[0.064251505,0.00025799352,0.930716,0.0025521782,0.00062200526,0.000032920336,0.00013222401,0.00010066422,0.0013345301],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99622726,0.000059455226,0.00038071806,0.0014338065,0.0014362563,0.00046252884],"domain_scores_gemma":[0.99782014,0.000540893,0.00020500134,0.000989838,0.00018830504,0.00025581167],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011478413,0.00039960828,0.00036268125,0.00053841004,0.0002800104,0.0007091864,0.0019089546,0.00025858972,0.000029649498],"category_scores_gemma":[0.00020083829,0.00032246267,0.000041352938,0.00062042044,0.0007744175,0.0007744443,0.00093466963,0.0008093873,0.00007434359],"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":[0.000016208498,0.00003751349,0.0007636109,0.00012307292,0.000018317542,0.00028171606,0.0011845382,0.008696948,0.0004305475,0.01303305,0.00007624573,0.9753382],"study_design_scores_gemma":[0.00056889333,0.0002214666,0.0019117846,0.0005029179,0.000012832115,0.00016681277,8.316481e-7,0.9831129,0.00027266025,0.012138132,0.00044896672,0.00064184703],"about_ca_topic_score_codex":0.00005284895,"about_ca_topic_score_gemma":0.00016161462,"teacher_disagreement_score":0.9746964,"about_ca_system_score_codex":0.00010646267,"about_ca_system_score_gemma":0.0005140569,"threshold_uncertainty_score":0.99992275},"labels":[],"label_agreement":null},{"id":"W4385569148","doi":"10.1016/j.anscip.2023.04.064","title":"O63 Drowning in data, thirsting for knowledge","year":2023,"lang":"en","type":"article","venue":"Animal - science proceedings","topic":"Machine Learning and Data Classification","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 Guelph","funders":"","keywords":"Data science; Computer science","score_opus":0.10512643548131734,"score_gpt":0.367997448282477,"score_spread":0.26287101280115965,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385569148","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":[0.89401245,0.00012978225,0.057353113,0.009285605,0.00069873943,0.00083190587,0.00001749782,0.002004978,0.03566595],"genre_scores_gemma":[0.97135127,0.0000064230408,0.028231043,0.000073600175,0.00009339914,0.000030634408,0.0000124699745,0.000007730033,0.00019344463],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99801075,0.0000058020814,0.00022705902,0.0008962724,0.00032442968,0.000535697],"domain_scores_gemma":[0.99912745,0.0001511557,0.000105358245,0.00034193147,0.00017867934,0.00009540686],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003720626,0.00010814332,0.00011473439,0.00047203497,0.00048426044,0.00062195066,0.003042548,0.00003701639,0.0000016822186],"category_scores_gemma":[0.0021176047,0.00010191293,0.000018060025,0.003790317,0.00014222563,0.0033066985,0.0013025439,0.00016514324,0.00011923886],"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":[0.000020680694,0.0000851103,0.033881694,0.0001687579,0.0000034624525,0.0000033429417,0.010061001,0.000015965494,0.1782124,0.65030736,0.008186193,0.119054005],"study_design_scores_gemma":[0.00018146605,0.000080022764,0.059775006,0.000052056854,0.0000018631067,0.0000062042723,0.00051430985,0.92517835,0.0012712437,0.0020865123,0.010672016,0.00018092769],"about_ca_topic_score_codex":0.000025792426,"about_ca_topic_score_gemma":0.000007829634,"teacher_disagreement_score":0.92516243,"about_ca_system_score_codex":0.00005166394,"about_ca_system_score_gemma":0.00016400946,"threshold_uncertainty_score":0.59974843},"labels":[],"label_agreement":null},{"id":"W4385571084","doi":"10.18653/v1/2023.acl-srw.43","title":"LECO: Improving Early Exiting via Learned Exits and Comparison-based Exiting Mechanism","year":2023,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Speedup; Computer science; Inference; Mechanism (biology); Look-ahead; Artificial intelligence; Computer architecture; Parallel computing; Algorithm","score_opus":0.042381350944768,"score_gpt":0.2930484622193053,"score_spread":0.25066711127453734,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385571084","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":[0.12210564,0.000021857219,0.8714976,0.0019710434,0.00015382268,0.00012471483,0.0000013266034,0.0012890887,0.0028349056],"genre_scores_gemma":[0.94778836,0.000002102388,0.051294185,0.00023888695,0.000064373555,0.000016031809,0.000024134659,0.00001730158,0.000554654],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99827707,0.00013130704,0.00031187636,0.00059101067,0.00028746744,0.0004012565],"domain_scores_gemma":[0.9988236,0.00033306613,0.00017665482,0.00048382563,0.00005796771,0.00012489095],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009246877,0.00016314661,0.00018571861,0.00021308556,0.00040648316,0.00048286226,0.00048646223,0.00007221224,0.00001925711],"category_scores_gemma":[0.00024541802,0.00015803357,0.000038474132,0.0005750866,0.000029350525,0.00043079074,0.00031119617,0.0002678594,0.00020504862],"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":[0.000008830002,0.00004470179,0.011648573,0.00010557321,0.00001511842,0.000018053326,0.0011735264,0.00055861025,0.035564784,0.17638193,0.00034437227,0.77413595],"study_design_scores_gemma":[0.00030431335,0.00006730945,0.015540789,0.000023694294,0.000004289727,0.0000038741687,0.000120977165,0.97643465,0.003687958,0.0031934988,0.00040165285,0.00021702048],"about_ca_topic_score_codex":0.00039869093,"about_ca_topic_score_gemma":0.000025472866,"teacher_disagreement_score":0.97587603,"about_ca_system_score_codex":0.000023311895,"about_ca_system_score_gemma":0.000052771476,"threshold_uncertainty_score":0.6444422},"labels":[],"label_agreement":null},{"id":"W4385571422","doi":"10.18653/v1/2023.findings-acl.426","title":"“Low-Resource” Text Classification: A Parameter-Free Classification Method with Compressors","year":2023,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":67,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Global Water Futures; Canada First Research Excellence Fund","keywords":"Computer science; Artificial intelligence; Classifier (UML); Deep neural networks; Parametric statistics; Artificial neural network; k-nearest neighbors algorithm; Machine learning; Data mining; Pattern recognition (psychology)","score_opus":0.044134728120425064,"score_gpt":0.30741481133996235,"score_spread":0.2632800832195373,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385571422","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":[0.0037292896,0.000017724547,0.94908375,0.016245587,0.00014838777,0.000331965,0.00001126772,0.0020587347,0.028373284],"genre_scores_gemma":[0.6089689,0.000029628913,0.38110968,0.00092424906,0.0001987834,0.00029064456,0.00041875077,0.00005564478,0.008003681],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997129,0.000414863,0.00041776925,0.0009561974,0.0006395392,0.00044262406],"domain_scores_gemma":[0.99586546,0.00076908484,0.00027101612,0.0027629174,0.00014196277,0.00018956864],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0010061803,0.00026126893,0.00025316936,0.00036159717,0.00033808986,0.000445592,0.0021424321,0.00012543454,0.00006837613],"category_scores_gemma":[0.00033563518,0.0002048506,0.00007389439,0.0019935463,0.00009281799,0.00060551043,0.00036520878,0.00032880498,0.0008706848],"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":[0.000054304026,0.00024660575,0.0034053072,0.00007272586,0.00007372149,0.000014573954,0.0010279428,0.0012687836,0.008469033,0.49311402,0.09028828,0.4019647],"study_design_scores_gemma":[0.0006004988,0.00011359054,0.088561244,0.000028679928,0.000014926247,0.000022088792,0.00031289613,0.78581184,0.00092083955,0.0020932637,0.1211684,0.00035175812],"about_ca_topic_score_codex":0.00004022863,"about_ca_topic_score_gemma":0.000021119744,"teacher_disagreement_score":0.78454304,"about_ca_system_score_codex":0.00005533688,"about_ca_system_score_gemma":0.00008202644,"threshold_uncertainty_score":0.99990726},"labels":[],"label_agreement":null},{"id":"W4385571912","doi":"10.18653/v1/2023.findings-acl.356","title":"LABO: Towards Learning Optimal Label Regularization via Bi-level Optimization","year":2023,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo; Université de Montréal; Huawei Technologies (Canada)","funders":"","keywords":"Regularization (linguistics); Computer science; Smoothing; Artificial intelligence; Normalization (sociology); Machine learning; Deep neural networks; Artificial neural network; Mathematical optimization; Mathematics","score_opus":0.039586587494584595,"score_gpt":0.2820888890739697,"score_spread":0.24250230157938507,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385571912","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":[0.0015261817,0.000010959909,0.98875296,0.0034216603,0.00021047561,0.00009993346,0.0000025380778,0.0014857018,0.0044895583],"genre_scores_gemma":[0.15070361,0.00008662661,0.8129803,0.0003219337,0.00018183778,0.000033092358,0.0009206658,0.00003611099,0.034735817],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99861395,0.0001407925,0.00022498527,0.00043365173,0.00033270544,0.0002539261],"domain_scores_gemma":[0.9991798,0.00004123539,0.000113256574,0.0004485206,0.0001406564,0.00007653011],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00058582186,0.00012802209,0.000111798705,0.00024674775,0.0002688977,0.0002681361,0.00051090564,0.00008907728,0.000076383556],"category_scores_gemma":[0.00026067594,0.00012128648,0.000028362338,0.0015589187,0.000021566158,0.0007274422,0.0002505517,0.000188948,0.00042906404],"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":[0.00000471465,0.000049455914,0.0005175022,0.000016668482,0.000012363704,0.0000044810963,0.000389098,0.7165078,0.0018955031,0.0424291,0.0018501235,0.23632322],"study_design_scores_gemma":[0.00024028552,0.000047392343,0.0077478043,0.000007664948,0.000003761671,0.0000041764147,0.000025628271,0.9862752,0.00040138015,0.00021605508,0.004872572,0.00015809671],"about_ca_topic_score_codex":0.000072095325,"about_ca_topic_score_gemma":0.0000027111803,"teacher_disagreement_score":0.2697674,"about_ca_system_score_codex":0.00003367159,"about_ca_system_score_gemma":0.000061586856,"threshold_uncertainty_score":0.5514893},"labels":[],"label_agreement":null},{"id":"W4385573553","doi":"10.18653/v1/2022.emnlp-main.57","title":"DropMix: A Textual Data Augmentation Combining Dropout with Mixup","year":2022,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Fundamental Research Funds for the Central Universities; State Key Laboratory of Software Development Environment; Leverhulme Trust","keywords":"Overfitting; Dropout (neural networks); Computer science; Regularization (linguistics); Artificial intelligence; Machine learning; Curse of dimensionality; Deep neural networks; Deep learning; Artificial neural network","score_opus":0.03726976908270862,"score_gpt":0.28314147580183274,"score_spread":0.24587170671912412,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385573553","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":[0.009663345,0.00002217809,0.9692967,0.0035233852,0.00013654503,0.00013250462,0.00002864683,0.000350371,0.016846312],"genre_scores_gemma":[0.9554904,0.0000014957035,0.041158624,0.00054167054,0.000021037506,0.000022067357,0.00090438605,0.0000067990172,0.001853508],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987939,0.00013188117,0.00012774993,0.00043194828,0.00037578825,0.00013872334],"domain_scores_gemma":[0.9986745,0.00006473225,0.00008419645,0.0011115847,0.000019789872,0.00004517207],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00044171853,0.00007465352,0.0000699503,0.000072490875,0.00038595562,0.0001544689,0.0014172189,0.000009845334,0.0002384029],"category_scores_gemma":[0.000023020415,0.000063332016,0.00000881714,0.00033186807,0.000020962834,0.00056108844,0.0010966127,0.00017237352,0.00005654146],"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":[0.00007171506,0.00047788222,0.02466184,0.00002132873,0.000066928464,0.00004159159,0.0032907694,0.0023322874,0.0016462508,0.61561954,0.06652153,0.28524834],"study_design_scores_gemma":[0.0007134964,0.0002688674,0.0041241013,0.000004068726,0.00000815898,0.000059270005,0.0012920001,0.91541344,0.00006201353,0.0003183262,0.077533066,0.00020321179],"about_ca_topic_score_codex":0.0002261084,"about_ca_topic_score_gemma":0.0000247002,"teacher_disagreement_score":0.94582707,"about_ca_system_score_codex":0.00003564651,"about_ca_system_score_gemma":0.00007641657,"threshold_uncertainty_score":0.29684976},"labels":[],"label_agreement":null},{"id":"W4386075939","doi":"10.1109/cvpr52729.2023.01542","title":"Class Adaptive Network Calibration","year":2023,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Smoothing; Machine learning; Artificial intelligence; Class (philosophy); Code (set theory); Scalability; Artificial neural network; Calibration; Contextual image classification; Data mining; Image (mathematics); Mathematics; Computer vision","score_opus":0.03016431155759341,"score_gpt":0.26199188754361985,"score_spread":0.23182757598602644,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386075939","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":[0.00057978486,0.000007678179,0.967414,0.004649409,0.00021444226,0.000046886646,5.9479527e-7,0.00090718555,0.026179975],"genre_scores_gemma":[0.9418456,0.000013294074,0.04854,0.0007974611,0.0002434919,0.000016703825,0.00007054558,0.000006899232,0.008466034],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99943185,0.000055060806,0.00008029343,0.00018296666,0.00011490057,0.00013491706],"domain_scores_gemma":[0.9995532,0.00006709908,0.00002963366,0.00029721466,0.000017464694,0.00003537521],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022352448,0.000043922202,0.000042281903,0.00004005617,0.00009285031,0.00008949667,0.00027572093,0.000026065773,0.000021644117],"category_scores_gemma":[0.000026247044,0.000037049795,0.000015660255,0.00061561074,0.0000084889225,0.00032533382,0.000105379506,0.00006376428,0.0006014838],"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":[0.0000013719775,0.0000044625003,0.0011553958,0.0000011292794,0.0000027931205,0.0000017078419,0.00007621939,0.005316192,0.0000640841,0.8627365,0.0922609,0.038379226],"study_design_scores_gemma":[0.000044177796,0.000019438163,0.011318735,0.0000020471323,6.236174e-7,0.0000011421379,0.000011210448,0.93884224,0.000025945463,0.0054470734,0.044234756,0.000052601346],"about_ca_topic_score_codex":0.000024461704,"about_ca_topic_score_gemma":0.000013306039,"teacher_disagreement_score":0.94126576,"about_ca_system_score_codex":0.000008295671,"about_ca_system_score_gemma":0.000019949466,"threshold_uncertainty_score":0.7731058},"labels":[],"label_agreement":null},{"id":"W4386096173","doi":"10.32388/zznn5z","title":"Review of: \"Causality in Machine Learning: Innovating Model Generalization through Inference of Causal Relationships from Observational Data\"","year":2023,"lang":"en","type":"peer-review","venue":"","topic":"Machine Learning and Data Classification","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 Laval","funders":"","keywords":"Causal inference; Causality (physics); Generalization; Observational study; Inference; Causal model; Artificial intelligence; Machine learning; Computer science; Econometrics; Psychology; Epistemology; Mathematics; Statistics; Philosophy","score_opus":0.43486252950250126,"score_gpt":0.4282925925146826,"score_spread":0.006569936987818659,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386096173","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":[0.00002909296,0.05987923,0.9018262,0.033423625,0.0004749786,0.0006371033,0.0020087848,0.0002290292,0.0014919328],"genre_scores_gemma":[0.0011830962,0.27925283,0.37722412,0.0056689642,0.00022239625,0.00011811708,0.32026398,0.00008777032,0.015978726],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99471056,0.000997472,0.0021140028,0.0010134974,0.00093474635,0.0002297151],"domain_scores_gemma":[0.99354005,0.0011472345,0.0019948701,0.0023283698,0.0009452753,0.000044197754],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0042117867,0.00034204146,0.00095394056,0.00021679592,0.00010524746,0.00004584818,0.0022273585,0.00024805046,0.00009567985],"category_scores_gemma":[0.0128977625,0.0003228772,0.000074222626,0.0025807277,0.00005934047,0.0010245912,0.0013011358,0.0012387579,0.000022738555],"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":[0.0000059956947,0.00020549935,0.029092235,0.053338252,0.000106519474,0.000002452007,0.00029908,0.018995471,0.00005981601,0.18277682,0.69541425,0.019703608],"study_design_scores_gemma":[0.00013653593,0.00001672544,0.0043911897,0.027231459,0.00005715291,7.0658365e-7,0.0000023835025,0.8461446,0.000004093175,0.0037577534,0.117950395,0.00030695944],"about_ca_topic_score_codex":0.005806355,"about_ca_topic_score_gemma":0.0009861679,"teacher_disagreement_score":0.82714915,"about_ca_system_score_codex":0.00007524576,"about_ca_system_score_gemma":0.0007693912,"threshold_uncertainty_score":0.99992234},"labels":[],"label_agreement":null},{"id":"W4386213601","doi":"10.1117/12.2687397","title":"Multimodal medical data statistical system based on machine learning algorithm","year":2023,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Big data; Machine learning; Artificial intelligence; Statistic; Decision tree; Algorithm; Online machine learning; Data mining; Unsupervised learning; Mathematics","score_opus":0.03435537855713543,"score_gpt":0.3094493824961634,"score_spread":0.27509400393902794,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386213601","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":[0.000035933226,0.00000599106,0.98914784,0.003547705,0.0002613297,0.00007953794,0.00011656448,0.001617542,0.005187583],"genre_scores_gemma":[0.61577606,0.000010028128,0.37475082,0.0007248197,0.00025071893,0.000022189493,0.006981363,0.000032759966,0.0014512565],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997543,0.00033125916,0.0002474867,0.00067493797,0.00091289246,0.00029046595],"domain_scores_gemma":[0.997566,0.0008178399,0.0000599755,0.0012994539,0.00003266568,0.00022405114],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0016738566,0.00013200114,0.00015318416,0.0001570747,0.00020125549,0.00015748218,0.0017279356,0.00008245453,0.00017245552],"category_scores_gemma":[0.0007798242,0.000104423896,0.000019549889,0.0004921276,0.000036257985,0.00021324542,0.0006471283,0.00044873045,0.0016501752],"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":[0.000008069481,0.00007824541,0.0015489252,0.000048273738,0.000010677101,0.00017351881,0.000038045364,0.0016787149,0.000009761837,0.0949728,0.010721063,0.8907119],"study_design_scores_gemma":[0.00035589494,0.00006380619,0.0042207846,0.000027371985,0.000003117531,0.000009943048,0.000016974038,0.9726948,0.0000060865445,0.000018920851,0.022457901,0.0001243941],"about_ca_topic_score_codex":0.00032809257,"about_ca_topic_score_gemma":0.000015597516,"teacher_disagreement_score":0.9710161,"about_ca_system_score_codex":0.00003641413,"about_ca_system_score_gemma":0.0001366563,"threshold_uncertainty_score":0.99912715},"labels":[],"label_agreement":null},{"id":"W4386454182","doi":"10.36244/icj.2023.5.2","title":"Deep Learning from Noisy Labels with Some Adjustments of a Recent Method","year":2023,"lang":"en","type":"article","venue":"Híradástechnika/Infocommunications journal","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"European Social Fund; European Commission; Canadian Institute for Advanced Research","keywords":"Softmax function; Computer science; Extension (predicate logic); Artificial intelligence; Noise (video); Artificial neural network; Pattern recognition (psychology); Function (biology); Machine learning; Image (mathematics)","score_opus":0.05406486913937391,"score_gpt":0.3355921552952093,"score_spread":0.2815272861558354,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386454182","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":[0.0035681082,0.0008375904,0.98419,0.0065398337,0.00012651915,0.00030791538,0.000007596273,0.00067811867,0.0037443032],"genre_scores_gemma":[0.1946567,0.0063241026,0.79791087,0.00021619175,0.00008883213,0.00009885236,0.00021755215,0.00004312463,0.0004437766],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975538,0.0006604919,0.0006202845,0.00029680514,0.00053934177,0.00032925108],"domain_scores_gemma":[0.9963301,0.00056194456,0.00072273856,0.0019072391,0.00032016853,0.00015779756],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014088516,0.00019629013,0.00028971749,0.0005223969,0.00064255984,0.00022202409,0.002584812,0.00010520571,0.00007821381],"category_scores_gemma":[0.0003300884,0.0001667733,0.000079828525,0.0016623363,0.0000823821,0.0009596978,0.0006451931,0.0010541679,0.00013351694],"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":[0.00004362197,0.0003640315,0.005771565,0.00002812932,0.0002669226,0.0000190956,0.0036959015,0.013419348,0.00864351,0.082586676,0.0016200749,0.8835411],"study_design_scores_gemma":[0.003110724,0.0007438609,0.09663954,0.00043543486,0.00017351125,0.00041473925,0.0017346991,0.57460123,0.003238998,0.021896891,0.29595885,0.001051535],"about_ca_topic_score_codex":0.00008935296,"about_ca_topic_score_gemma":0.000019763182,"teacher_disagreement_score":0.88248956,"about_ca_system_score_codex":0.00009888886,"about_ca_system_score_gemma":0.00014441706,"threshold_uncertainty_score":0.6800818},"labels":[],"label_agreement":null},{"id":"W4386566644","doi":"10.18653/v1/2023.eacl-main.188","title":"How Many and Which Training Points Would Need to be Removed to Flip this Prediction?","year":2023,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Army Research Office; Atomic Energy of Canada Limited","keywords":"Robustness (evolution); Computer science; Text categorization; Cardinality (data modeling); Categorization; Training set; Simple (philosophy); Machine learning; Artificial intelligence; Set (abstract data type); Regular polygon; Algorithm; Data mining; Mathematics","score_opus":0.05024372021815765,"score_gpt":0.27727465639309307,"score_spread":0.22703093617493542,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386566644","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":[0.06682457,0.000007414253,0.53447336,0.38165995,0.00040765895,0.00028597488,0.000016486518,0.0013367663,0.01498782],"genre_scores_gemma":[0.8753262,0.000012233,0.08323118,0.0070061134,0.00016278653,0.000043590877,0.000056970857,0.000019588839,0.034141287],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998871,0.00005605923,0.00012857949,0.0004542476,0.0002491674,0.00024094696],"domain_scores_gemma":[0.99911296,0.00007893458,0.000031480606,0.000505032,0.00006826369,0.00020333198],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00052597554,0.000101875725,0.00010791993,0.00022660362,0.00015994246,0.00042876432,0.00039303786,0.00008093095,0.000026907854],"category_scores_gemma":[0.00046146932,0.000091205744,0.000016518581,0.0011984956,0.000008004743,0.00035986037,0.00026779185,0.00020315549,0.00016714555],"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":[0.00003654152,0.00005258728,0.009038311,0.000037734542,0.000045367036,0.000014056196,0.02727228,0.00037150818,0.019909445,0.11223996,0.3194075,0.51157475],"study_design_scores_gemma":[0.0004298893,0.00018582291,0.2052413,0.000032373468,0.000007203682,0.000016657063,0.0014968088,0.45205244,0.00043800302,0.00052022084,0.3392536,0.00032570073],"about_ca_topic_score_codex":0.00006049117,"about_ca_topic_score_gemma":0.00003918499,"teacher_disagreement_score":0.80850166,"about_ca_system_score_codex":0.000019144229,"about_ca_system_score_gemma":0.000028398443,"threshold_uncertainty_score":0.41345844},"labels":[],"label_agreement":null},{"id":"W4386707565","doi":"10.32920/24132882","title":"Quantifying Deep Learning Model Uncertainty in Conformal Prediction","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; Toronto Metropolitan University","funders":"","keywords":"Uncertainty quantification; Probabilistic logic; Machine learning; Artificial intelligence; Context (archaeology); Conformal map; Computer science; Sensitivity analysis; Uncertainty analysis; Bayesian probability; Artificial neural network; Measurement uncertainty; Data mining; Mathematics; Statistics","score_opus":0.0937607704171857,"score_gpt":0.32281739581051927,"score_spread":0.22905662539333357,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386707565","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":[0.007360579,0.000049555892,0.9855137,0.0007489395,0.0005654313,0.00020250806,0.0000071633694,0.0012972472,0.0042548906],"genre_scores_gemma":[0.9659773,0.00021378831,0.031233137,0.00007276485,0.00007467156,0.00007041065,0.00056185265,0.000022271004,0.0017737903],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980093,0.0001435486,0.0004596962,0.000719338,0.00034947382,0.00031862184],"domain_scores_gemma":[0.99878985,0.000111856694,0.0002210581,0.0007340539,0.000072115356,0.00007106016],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011177207,0.00021391292,0.00023487868,0.00037081313,0.0001348424,0.00035371125,0.0009482561,0.00026565045,0.0000092645605],"category_scores_gemma":[0.00024189254,0.00020859308,0.00007287732,0.00030322268,0.00002254866,0.00039448033,0.0014064969,0.0014594776,0.00012844846],"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":[0.0000038826224,0.000013399001,0.0062763654,0.0000692023,0.000006677647,0.0000025992385,0.00067092216,0.9432352,0.000023388737,0.021988029,0.00013206038,0.027578238],"study_design_scores_gemma":[0.0001576697,0.000016588747,0.0134895425,0.00008569781,0.0000038959674,0.000001864553,0.00008472762,0.98367333,0.0000059890313,0.0016919329,0.000593036,0.00019571064],"about_ca_topic_score_codex":0.0008683115,"about_ca_topic_score_gemma":0.00049567135,"teacher_disagreement_score":0.95861673,"about_ca_system_score_codex":0.00011885392,"about_ca_system_score_gemma":0.00014869007,"threshold_uncertainty_score":0.8506179},"labels":[],"label_agreement":null},{"id":"W4386708427","doi":"10.32920/24132882.v1","title":"Quantifying Deep Learning Model Uncertainty in Conformal Prediction","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Machine Learning and Data Classification","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":"Vector Institute; Toronto Metropolitan University","funders":"","keywords":"Uncertainty quantification; Probabilistic logic; Conformal map; Machine learning; Artificial intelligence; Context (archaeology); Computer science; Sensitivity analysis; Uncertainty analysis; Bayesian probability; Artificial neural network; Data mining; Mathematics; Simulation","score_opus":0.0937607704171857,"score_gpt":0.32281739581051927,"score_spread":0.22905662539333357,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386708427","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":[0.007360579,0.000049555892,0.9855137,0.0007489395,0.0005654313,0.00020250806,0.0000071633694,0.0012972472,0.0042548906],"genre_scores_gemma":[0.9659773,0.00021378831,0.031233137,0.00007276485,0.00007467156,0.00007041065,0.00056185265,0.000022271004,0.0017737903],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980093,0.0001435486,0.0004596962,0.000719338,0.00034947382,0.00031862184],"domain_scores_gemma":[0.99878985,0.000111856694,0.0002210581,0.0007340539,0.000072115356,0.00007106016],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011177207,0.00021391292,0.00023487868,0.00037081313,0.0001348424,0.00035371125,0.0009482561,0.00026565045,0.0000092645605],"category_scores_gemma":[0.00024189254,0.00020859308,0.00007287732,0.00030322268,0.00002254866,0.00039448033,0.0014064969,0.0014594776,0.00012844846],"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":[0.0000038826224,0.000013399001,0.0062763654,0.0000692023,0.000006677647,0.0000025992385,0.00067092216,0.9432352,0.000023388737,0.021988029,0.00013206038,0.027578238],"study_design_scores_gemma":[0.0001576697,0.000016588747,0.0134895425,0.00008569781,0.0000038959674,0.000001864553,0.00008472762,0.98367333,0.0000059890313,0.0016919329,0.000593036,0.00019571064],"about_ca_topic_score_codex":0.0008683115,"about_ca_topic_score_gemma":0.00049567135,"teacher_disagreement_score":0.95861673,"about_ca_system_score_codex":0.00011885392,"about_ca_system_score_gemma":0.00014869007,"threshold_uncertainty_score":0.8506179},"labels":[],"label_agreement":null},{"id":"W4387207464","doi":"","title":"Sample Boosting Algorithm (SamBA) -An Interpretable Greedy Ensemble Classifier Based On Local Expertise For Fat Data","year":2023,"lang":"en","type":"preprint","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Université Laval","funders":"Fonds Québécois de la Recherche sur la Nature et les Technologies; Natural Sciences and Engineering Research Council of Canada; Institut de Valorisation des Données; Compute Canada; Canadian Institute for Advanced Research; Aix-Marseille Université","keywords":"Boosting (machine learning); Classifier (UML); Greedy algorithm; Artificial intelligence; Computer science; Pattern recognition (psychology); Machine learning; Algorithm","score_opus":0.06381920132074156,"score_gpt":0.29599905735353305,"score_spread":0.23217985603279148,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387207464","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":[0.00029640066,0.00012874806,0.98395675,0.010019555,0.00062456884,0.0006686428,0.00075155654,0.00093900296,0.0026147596],"genre_scores_gemma":[0.20310228,0.00007322283,0.77838194,0.00043002027,0.000089282024,0.00028350076,0.013959138,0.00010845261,0.0035721832],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9919681,0.003862488,0.0007183131,0.0021660503,0.00068278064,0.0006022963],"domain_scores_gemma":[0.98473823,0.0044060736,0.00064834097,0.008681376,0.0012209647,0.00030502977],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0073162275,0.000478138,0.00047742986,0.0003436092,0.00065278204,0.0013209392,0.006143487,0.00035916452,0.00002956522],"category_scores_gemma":[0.004902675,0.00050492084,0.00017671392,0.0004910977,0.0001779359,0.00063697406,0.004226105,0.00089082087,0.00006812623],"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":[0.00002315376,0.000655174,0.00034433836,0.00017895224,0.000052031883,0.0000050012454,0.0027073584,0.001756786,0.00053870934,0.03806458,0.006056175,0.94961774],"study_design_scores_gemma":[0.00045303535,0.0000027110405,0.0005615637,0.0009788532,0.000027059577,0.000002464542,0.00007447222,0.97061634,0.002818217,0.00314852,0.020823564,0.000493178],"about_ca_topic_score_codex":0.0036871517,"about_ca_topic_score_gemma":0.0015837811,"teacher_disagreement_score":0.96885955,"about_ca_system_score_codex":0.00022790348,"about_ca_system_score_gemma":0.00040811655,"threshold_uncertainty_score":0.99974024},"labels":[],"label_agreement":null},{"id":"W4388198609","doi":"10.5753/eniac.2023.233874","title":"Surrogate-based constrained multi-objective optimization for the compression of CNNs","year":2023,"lang":"pt","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Universidade Federal de Ouro Preto; Conselho Nacional de Desenvolvimento Científico e Tecnológico; Coordenação de Aperfeiçoamento de Pessoal de Nível Superior","keywords":"Computer science; Physics; Algorithm","score_opus":0.06400395393608184,"score_gpt":0.32640829665879545,"score_spread":0.2624043427227136,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388198609","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":[0.0005240712,0.00005237151,0.99301416,0.0045090155,0.00051296013,0.000750533,0.00012381004,0.00023887331,0.00027418524],"genre_scores_gemma":[0.93629193,0.000032952026,0.060611654,0.00017363483,0.00005017073,0.00007321243,0.00041180622,0.000019386187,0.002335241],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984374,0.0002383761,0.00037054124,0.0004267414,0.00026995706,0.0002569673],"domain_scores_gemma":[0.99683124,0.0018046022,0.00031876448,0.00065316015,0.0003304511,0.000061806204],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009305736,0.00016712605,0.00020426081,0.00016161066,0.0003710937,0.00011987073,0.0006416693,0.00010107025,0.00009244124],"category_scores_gemma":[0.00054443814,0.000115218645,0.000112566435,0.0008552726,0.0001553541,0.00018322979,0.00013976423,0.00015027143,0.000037919326],"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":[0.00008037697,0.00018209475,0.0013201248,0.00013411362,0.000048116028,8.3470206e-7,0.001177067,0.9525661,0.0010268954,0.007404463,0.0035551693,0.03250463],"study_design_scores_gemma":[0.0014015444,0.00012459946,0.0074605225,0.0000712664,0.000029869874,5.780119e-7,0.0004543692,0.98809224,0.0013847115,0.000020872474,0.0008254993,0.00013392264],"about_ca_topic_score_codex":0.00016805546,"about_ca_topic_score_gemma":0.000036309455,"teacher_disagreement_score":0.9357679,"about_ca_system_score_codex":0.00002535139,"about_ca_system_score_gemma":0.00019421047,"threshold_uncertainty_score":0.46984798},"labels":[],"label_agreement":null},{"id":"W4388521737","doi":"10.1609/aaaiss.v1i1.27492","title":"Quantifying Deep Learning Model Uncertainty in Conformal Prediction","year":2023,"lang":"en","type":"article","venue":"Proceedings of the AAAI Symposium Series","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; Toronto Metropolitan University","funders":"","keywords":"Uncertainty quantification; Machine learning; Artificial intelligence; Probabilistic logic; Computer science; Conformal map; Context (archaeology); Sensitivity analysis; Uncertainty analysis; Bayesian probability; Artificial neural network; Data mining; Mathematics","score_opus":0.022766537524749286,"score_gpt":0.25097553267995865,"score_spread":0.22820899515520937,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388521737","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":[0.9740704,0.00004590815,0.004871748,0.007885068,0.00040592597,0.00034190743,0.0000063287544,0.0008778461,0.011494854],"genre_scores_gemma":[0.9973531,0.0001016153,0.0015859435,0.000034007626,0.000029086312,0.000025600113,0.000008586716,0.000009712941,0.00085239444],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988921,0.0000143576235,0.0002925584,0.00026338006,0.00028900648,0.00024854072],"domain_scores_gemma":[0.9994204,0.000036170037,0.00021745503,0.0001634532,0.00012838752,0.000034116936],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006785023,0.00011645241,0.00014081599,0.00016941933,0.00022808627,0.00015050876,0.0007857981,0.00006302823,0.000001454387],"category_scores_gemma":[0.00019197936,0.00009112858,0.00005067354,0.00085116876,0.00006420441,0.0014118631,0.00042251978,0.0002755879,0.00001331337],"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":[0.00009745991,0.00005652518,0.18764362,0.00047118674,0.000026306334,6.618738e-7,0.016902052,0.31911886,0.17283739,0.2949265,0.00068113796,0.0072383215],"study_design_scores_gemma":[0.00016346587,0.00004864406,0.019062635,0.0000665385,0.0000049624614,0.0000067141004,0.00048293913,0.9747,0.0033715093,0.0010753035,0.00091812253,0.000099196244],"about_ca_topic_score_codex":0.000043500317,"about_ca_topic_score_gemma":0.000011411038,"teacher_disagreement_score":0.6555811,"about_ca_system_score_codex":0.000036763682,"about_ca_system_score_gemma":0.00003283133,"threshold_uncertainty_score":0.3716116},"labels":[],"label_agreement":null},{"id":"W4388706525","doi":"10.1016/j.inffus.2023.102145","title":"A dynamic multiple classifier system using graph neural network for high dimensional overlapped data","year":2023,"lang":"en","type":"article","venue":"Information Fusion","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure; Université du Québec à Montréal","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada; Fonds de recherche du Québec; Fundação de Amparo à Ciência e Tecnologia do Estado de Pernambuco; Conselho Nacional de Desenvolvimento Científico e Tecnológico; Coordenação de Aperfeiçoamento de Pessoal de Nível Superior","keywords":"Computer science; Classifier (UML); Artificial intelligence; Curse of dimensionality; Machine learning; Artificial neural network; Locality; Graph; Pattern recognition (psychology); Data mining; Theoretical computer science","score_opus":0.038601665051433344,"score_gpt":0.27896109910976896,"score_spread":0.24035943405833562,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388706525","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":[0.11294641,0.000014879538,0.8830955,0.00079931575,0.0014033773,0.0004933159,0.00024481304,0.0008599904,0.00014237023],"genre_scores_gemma":[0.9401326,0.000004876806,0.051568724,0.00022583228,0.00008685482,0.000025830053,0.007883748,0.000009221251,0.0000623082],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99866045,0.00006269799,0.0004090008,0.00025079297,0.0003448501,0.0002722186],"domain_scores_gemma":[0.99845034,0.00018455116,0.00027684253,0.0009098566,0.00011229429,0.00006612201],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006880437,0.0001260007,0.00012937687,0.00020676317,0.00045906423,0.00023791558,0.00074005005,0.00008154058,0.000003818216],"category_scores_gemma":[0.00014303591,0.00011261289,0.000038205933,0.0007228944,0.000016974436,0.002597389,0.00058536313,0.00011726528,0.00013617183],"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":[0.0002014416,0.00005930758,0.004125054,0.0005498184,0.000055262804,0.0000052806927,0.0009226672,0.5257682,0.0022908312,0.08868738,0.07510583,0.30222893],"study_design_scores_gemma":[0.00047874486,0.000023810282,0.014921085,0.00004637474,0.0000067537326,0.000009081569,0.000043827506,0.9751894,0.0000058604287,0.00020315513,0.008939185,0.00013273304],"about_ca_topic_score_codex":0.00011986272,"about_ca_topic_score_gemma":0.000019215715,"teacher_disagreement_score":0.8315268,"about_ca_system_score_codex":0.00005764258,"about_ca_system_score_gemma":0.00005338079,"threshold_uncertainty_score":0.45922202},"labels":[],"label_agreement":null},{"id":"W4388933883","doi":"10.21203/rs.3.rs-3626886/v1","title":"Measuring the Prediction Difficulty of Individual Cases in a Dataset using Machine Learning","year":2023,"lang":"en","type":"preprint","venue":"Research Square","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Machine learning; Metric (unit); Artificial intelligence; Artificial neural network; Data mining; Key (lock); Perspective (graphical); Predictive modelling; Variety (cybernetics)","score_opus":0.30751642992099687,"score_gpt":0.4225685595853316,"score_spread":0.11505212966433476,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388933883","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":[0.9185212,0.0018986448,0.056180157,0.0038565893,0.000915541,0.002819287,0.014864044,0.0007788076,0.00016568265],"genre_scores_gemma":[0.9908228,0.0002007495,0.0014149278,0.0000058815112,0.000121966616,0.00007621186,0.0072808457,0.00002419344,0.000052409647],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99466693,0.001952187,0.00045359807,0.0007252481,0.0017496392,0.00045240734],"domain_scores_gemma":[0.99701613,0.0011308166,0.00022852304,0.0013198558,0.00022444384,0.000080245234],"candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.005928112,0.00018463215,0.00025384445,0.00072115357,0.0003798536,0.00041408296,0.0021027143,0.00017770921,0.000008071623],"category_scores_gemma":[0.003026703,0.00014005194,0.00006542086,0.0011230959,0.00012263513,0.00023621607,0.004828581,0.00283045,0.000020737263],"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":[0.00015052668,0.00080199,0.53439033,0.004569486,0.00028892054,0.00042609463,0.013200739,0.3661631,0.0036487267,0.0047685225,0.0065274374,0.06506413],"study_design_scores_gemma":[0.00024997775,0.00010327129,0.21906997,0.00088725524,0.000011661752,0.00002161041,0.00041904332,0.7762718,0.00016783609,0.0003653391,0.0022554747,0.00017671728],"about_ca_topic_score_codex":0.006238045,"about_ca_topic_score_gemma":0.00079224166,"teacher_disagreement_score":0.41010875,"about_ca_system_score_codex":0.00016538834,"about_ca_system_score_gemma":0.00031169358,"threshold_uncertainty_score":0.99947006},"labels":[],"label_agreement":null},{"id":"W4389072684","doi":"10.48550/arxiv.2311.14214","title":"Extending Variability-Aware Model Selection with Bias Detection in Machine Learning Projects","year":2023,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Heuristics; Selection (genetic algorithm); Model selection; Machine learning; Selection bias; Process (computing); Feature selection; Artificial intelligence; Data mining; Sample (material); Code (set theory); Statistics; Mathematics","score_opus":0.13341738042047066,"score_gpt":0.21547752602944953,"score_spread":0.08206014560897887,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389072684","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":[0.16443701,0.0000049760415,0.83393514,0.00007475303,0.00014771015,0.0003050383,0.0000052882497,0.0007896292,0.0003004672],"genre_scores_gemma":[0.9955151,0.00006152975,0.002957862,0.000011674181,0.000040148792,0.00000625026,0.00007775106,0.000031297972,0.0012983611],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972958,0.000546229,0.0002266286,0.0014439699,0.00014148837,0.00034587123],"domain_scores_gemma":[0.99852055,0.00019079121,0.0003278103,0.00073966006,0.00013079107,0.00009039102],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011076151,0.00030029664,0.00027642798,0.00072179444,0.00026619274,0.00017668869,0.0007770973,0.0002671197,0.000004045722],"category_scores_gemma":[0.00022648742,0.00032013722,0.000076649514,0.0016318442,0.00004149076,0.0005437798,0.0007910023,0.0015220563,0.00003296669],"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":[0.00004359576,0.000054582353,0.041185968,0.00010361273,0.000020604419,0.000034075507,0.0002542314,0.94748557,0.00008539536,0.0079307305,0.000004548074,0.0027971156],"study_design_scores_gemma":[0.00033010714,0.000081253536,0.007529756,0.00011504261,0.000025470461,0.000006704461,0.00004477374,0.9859505,0.0000878766,0.0054336623,0.0000512472,0.00034356033],"about_ca_topic_score_codex":0.0012645728,"about_ca_topic_score_gemma":0.0013486972,"teacher_disagreement_score":0.8310781,"about_ca_system_score_codex":0.00046878727,"about_ca_system_score_gemma":0.00023637907,"threshold_uncertainty_score":0.9999251},"labels":[],"label_agreement":null},{"id":"W4389382319","doi":"10.33965/mccsis2023_202305r004","title":"TOWARDS EXPLAINABLE MACHINE LEARNING OPERATIONS (MLOPS)","year":2023,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Field (mathematics); Artificial intelligence; Machine learning","score_opus":0.027145874328496227,"score_gpt":0.27820472101358273,"score_spread":0.2510588466850865,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389382319","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":[0.0040770564,0.000039312967,0.92925006,0.010183126,0.00020316617,0.00009367458,0.0000022251725,0.0020060008,0.05414536],"genre_scores_gemma":[0.89126295,0.000093404014,0.05553452,0.00040351108,0.000080918006,0.000047387064,0.00023064736,0.0000143669495,0.052332327],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990823,0.0000926173,0.00013512299,0.0002880899,0.000186804,0.00021505597],"domain_scores_gemma":[0.9994133,0.00004715611,0.000021093356,0.00040168845,0.000049059123,0.000067666144],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0004760034,0.000082055536,0.0000779894,0.00014876072,0.00036446407,0.00026541098,0.0005024703,0.000033701555,0.00014849096],"category_scores_gemma":[0.00022720092,0.000070059934,0.000028062574,0.00084796525,0.000012344215,0.0005057164,0.00024398054,0.00018268531,0.0016847984],"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":[0.0000023612558,0.00004415624,0.0036134154,0.000016410067,0.000013664968,0.00001793842,0.0011643337,0.029529102,0.001446744,0.7343292,0.009989621,0.21983302],"study_design_scores_gemma":[0.00010202544,0.000029604284,0.0051872795,0.0000028423458,0.0000012779415,0.000004904425,0.00006088879,0.85188514,0.00025930782,0.00052126765,0.14184628,0.00009919228],"about_ca_topic_score_codex":0.00037913537,"about_ca_topic_score_gemma":0.00004210058,"teacher_disagreement_score":0.8871859,"about_ca_system_score_codex":0.000019346138,"about_ca_system_score_gemma":0.0000501327,"threshold_uncertainty_score":0.9990925},"labels":[],"label_agreement":null},{"id":"W4389728957","doi":"10.21203/rs.3.rs-3736323/v1","title":"Prediction Performance Metrics Considering the Difficulty of Individual Cases","year":2023,"lang":"en","type":"preprint","venue":"Research Square","topic":"Machine Learning and Data Classification","field":"Computer Science","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":"University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Machine learning; Metric (unit); Performance prediction; Performance metric; Artificial intelligence; Predictive modelling; Artificial neural network; Variety (cybernetics); Data mining; Simulation; Engineering","score_opus":0.2739598167954957,"score_gpt":0.4073426254268437,"score_spread":0.133382808631348,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389728957","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":[0.9416409,0.0011957656,0.04579402,0.0054208515,0.0013766527,0.0016880045,0.00082522485,0.0009004458,0.0011581467],"genre_scores_gemma":[0.99708056,0.00061264087,0.0014792682,0.0000085588645,0.00014196304,0.0001090829,0.00028527784,0.0000149822445,0.00026765437],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.996385,0.0006275579,0.00033658213,0.0005317195,0.0017634627,0.00035569683],"domain_scores_gemma":[0.9960496,0.0018005995,0.00018094848,0.0013896405,0.00050208386,0.00007711578],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0040894914,0.00014138913,0.00018823965,0.0005983823,0.00039279013,0.0003940057,0.0018943195,0.00016517245,0.000007638457],"category_scores_gemma":[0.002839525,0.00009975444,0.00007491017,0.0013789894,0.00016642017,0.00018452662,0.0036558122,0.0015876057,0.000051858286],"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":[0.000074518335,0.00061053556,0.33766422,0.008131634,0.00046856052,0.00013354686,0.014101058,0.060630973,0.00064592506,0.03450841,0.058205362,0.48482525],"study_design_scores_gemma":[0.00016902575,0.00021842336,0.69623333,0.00053433294,0.000014392836,0.000020335807,0.00048451955,0.29565984,0.00049646484,0.0006822137,0.0053069843,0.00018015396],"about_ca_topic_score_codex":0.00028044503,"about_ca_topic_score_gemma":0.000025503216,"teacher_disagreement_score":0.4846451,"about_ca_system_score_codex":0.000084919266,"about_ca_system_score_gemma":0.00032254227,"threshold_uncertainty_score":0.68974453},"labels":[],"label_agreement":null},{"id":"W4390906038","doi":"10.1109/transai60598.2023.00048","title":"Feature Selection via Independent Domination","year":2023,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Feature selection; Selection (genetic algorithm); Computer science; Feature (linguistics); Artificial intelligence; Pattern recognition (psychology)","score_opus":0.011074451459804775,"score_gpt":0.2612648775403473,"score_spread":0.2501904260805425,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390906038","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":[0.0048097963,0.0000046524065,0.9769447,0.010633375,0.00021620914,0.00006362011,3.4497282e-7,0.0008808054,0.0064464933],"genre_scores_gemma":[0.97177386,0.0000070429996,0.01307606,0.00016424716,0.0000682649,0.000012278326,0.00005155229,0.000004291157,0.0148423845],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994276,0.00004223032,0.00005161773,0.00019924293,0.00017664295,0.00010267446],"domain_scores_gemma":[0.9996786,0.000029203122,0.000033755514,0.0001895789,0.000039659066,0.000029214112],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027471493,0.000046979916,0.000038007023,0.00013000373,0.000097161756,0.00009922131,0.00022844234,0.000044847064,0.000019095698],"category_scores_gemma":[0.000037700003,0.000040236326,0.00001640388,0.0007035457,0.000004316486,0.00031997278,0.0000672144,0.00010574391,0.0007205542],"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":[0.0000045115275,0.000034606404,0.0066007026,0.000012487734,0.000009548227,0.0000034062475,0.00034360625,0.0005627509,0.015852926,0.16490084,0.08419105,0.7274836],"study_design_scores_gemma":[0.000142731,0.000027801514,0.17501605,0.0000024089295,0.0000015716602,0.000011081232,0.00001247248,0.7677644,0.0016748805,0.0019022237,0.053354345,0.00009003769],"about_ca_topic_score_codex":0.000023872755,"about_ca_topic_score_gemma":0.000022350847,"teacher_disagreement_score":0.96696407,"about_ca_system_score_codex":0.00002446669,"about_ca_system_score_gemma":0.000014621407,"threshold_uncertainty_score":0.9261507},"labels":[],"label_agreement":null},{"id":"W4391093893","doi":"10.1109/bigdata59044.2023.10386105","title":"Extending Variability-Aware Model Selection with Bias Detection in Machine Learning Projects","year":2023,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","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":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Machine learning; Heuristics; Selection (genetic algorithm); Model selection; Artificial intelligence; Process (computing); Feature selection; Selection bias; Data mining; Key (lock); Data modeling; Feature engineering; Deep learning; Database","score_opus":0.04510676513135061,"score_gpt":0.273076250363951,"score_spread":0.22796948523260038,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391093893","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":[0.081123725,0.000002580184,0.91583526,0.00034923534,0.00004979578,0.0001669509,5.627479e-7,0.0011013616,0.0013705454],"genre_scores_gemma":[0.98597854,0.0000090161175,0.012848885,0.000027441014,0.000023174545,0.00004450221,0.000026232405,0.000012068483,0.0010301111],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99859095,0.00024499153,0.00018176717,0.0004971054,0.00023299866,0.00025219555],"domain_scores_gemma":[0.9994104,0.00014033889,0.000082193365,0.0002690137,0.00005330005,0.000044788892],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012842473,0.00011950179,0.00011030363,0.00040300435,0.00020292806,0.00013986195,0.00023328992,0.00005894697,0.000006851787],"category_scores_gemma":[0.00025749565,0.000097277916,0.000020080632,0.0019822824,0.000012717604,0.00058787136,0.00009884621,0.00037607446,0.000046938832],"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":[0.00005118146,0.00011000708,0.14222528,0.00008959033,0.000013601835,0.000008974945,0.0014875216,0.55620986,0.0073812823,0.015597326,0.00006191476,0.27676344],"study_design_scores_gemma":[0.00020593798,0.000090134876,0.016912667,0.0000156342,0.0000021942465,0.000012001258,0.000037562968,0.9810008,0.00083473884,0.00051335304,0.00024443594,0.00013053007],"about_ca_topic_score_codex":0.0003946157,"about_ca_topic_score_gemma":0.0005564966,"teacher_disagreement_score":0.90485483,"about_ca_system_score_codex":0.000094274954,"about_ca_system_score_gemma":0.00006405341,"threshold_uncertainty_score":0.39668784},"labels":[],"label_agreement":null},{"id":"W4391094351","doi":"10.1109/bigdata59044.2023.10386503","title":"GPT in Data Science: A Practical Exploration of Model Selection","year":2023,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Selection (genetic algorithm); Computer science; Data modeling; Data science; Artificial intelligence; Software engineering","score_opus":0.2597187824055493,"score_gpt":0.4325973325874891,"score_spread":0.17287855018193982,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391094351","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":[0.006720069,0.0000011500717,0.98523235,0.0050366772,0.00004723959,0.00005892139,0.0000014966043,0.00015341045,0.002748687],"genre_scores_gemma":[0.89941496,0.00001258096,0.10022296,0.00003369994,0.0000105618365,0.0000052211844,0.000041566585,0.0000019932204,0.00025646016],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99910915,0.000036778765,0.00014105483,0.00031486756,0.00028294255,0.000115204144],"domain_scores_gemma":[0.9992274,0.00005298258,0.00005304174,0.0005781766,0.00006108424,0.000027297085],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013869597,0.000035597946,0.00004901766,0.00028039492,0.000058351026,0.000073521805,0.0006102531,0.000020294234,0.0000033309461],"category_scores_gemma":[0.0005652954,0.000031552838,0.000004937426,0.0021247468,0.00003823172,0.004650418,0.00035585134,0.00008452068,0.000049583112],"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":[0.000008223008,0.00011687721,0.0021074777,0.000015609932,0.0000019167994,0.0000012969972,0.0009829105,0.035635512,0.021259964,0.89088404,0.004926235,0.044059925],"study_design_scores_gemma":[0.00006512809,0.0000123350055,0.003229986,0.0000031229595,6.254046e-7,0.0000012761765,0.00004488679,0.9924026,0.000667719,0.003183715,0.0003526842,0.00003589384],"about_ca_topic_score_codex":0.00005365555,"about_ca_topic_score_gemma":0.000054133652,"teacher_disagreement_score":0.95676714,"about_ca_system_score_codex":0.000019961462,"about_ca_system_score_gemma":0.0002476571,"threshold_uncertainty_score":0.33714408},"labels":[],"label_agreement":null},{"id":"W4391584324","doi":"10.1145/3631802.3631808","title":"Common Errors in Machine Learning Projects: A Second Look","year":2023,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"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; Artificial intelligence; Machine learning","score_opus":0.02974817013960254,"score_gpt":0.2831867102519455,"score_spread":0.25343854011234296,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391584324","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":[0.7620557,0.00016836016,0.08001934,0.011290269,0.0004962269,0.00063024,0.000008527419,0.0043359273,0.14099541],"genre_scores_gemma":[0.98420256,0.000012384034,0.003731522,0.00022754712,0.000018677674,0.000019975045,0.00007167914,0.00000889418,0.011706749],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989596,0.00014713677,0.00018293186,0.00032315735,0.00015804404,0.00022913562],"domain_scores_gemma":[0.9993967,0.000104759136,0.000057672543,0.00038093462,0.000014551314,0.000045371817],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00061481574,0.00009072177,0.00011303997,0.00028197851,0.00008802491,0.000100451616,0.00049088453,0.000041916817,0.00010881411],"category_scores_gemma":[0.00010254692,0.00007900584,0.00002400473,0.0010189438,0.000016033166,0.00032398128,0.00023898616,0.0003189821,0.0006443338],"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":[0.000022447959,0.00019068437,0.60660934,0.00014792994,0.00002209913,0.0001839273,0.0071140006,0.004430731,0.0029169896,0.10257339,0.01305537,0.2627331],"study_design_scores_gemma":[0.00027677874,0.000056081015,0.08268703,0.0000140338025,8.625829e-7,0.000010444031,0.00014446375,0.8647333,0.0001680886,0.0005750264,0.051187195,0.00014671365],"about_ca_topic_score_codex":0.00037247935,"about_ca_topic_score_gemma":0.0010067066,"teacher_disagreement_score":0.86030257,"about_ca_system_score_codex":0.00002532416,"about_ca_system_score_gemma":0.000033235443,"threshold_uncertainty_score":0.82818216},"labels":[],"label_agreement":null},{"id":"W4391719686","doi":"10.1016/j.cor.2024.106579","title":"An improved column-generation-based matheuristic for learning classification trees","year":2024,"lang":"en","type":"article","venue":"Computers & Operations Research","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Group for Research in Decision Analysis; Polytechnique Montréal","funders":"","keywords":"Column generation; Scalability; Computer science; Heuristic; Decision tree; Machine learning; Column (typography); Artificial intelligence; Integer programming; Mathematical optimization; Relaxation (psychology); Multiclass classification; Mathematics; Algorithm; Support vector machine; Database","score_opus":0.12618182425428445,"score_gpt":0.42385054819990986,"score_spread":0.2976687239456254,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391719686","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":[0.0058897883,0.00017251862,0.98667777,0.0052935,0.0005010881,0.0006905473,0.000016995955,0.00058193284,0.00017583813],"genre_scores_gemma":[0.8578656,0.000015728994,0.1393201,0.0000919237,0.00043736197,0.00045996453,0.00083291734,0.000027774442,0.00094866386],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973244,0.0006528596,0.0003372019,0.0008476545,0.00043937325,0.00039851925],"domain_scores_gemma":[0.9976871,0.00066950696,0.000024671317,0.0008681565,0.0005887169,0.00016187523],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0020744253,0.0001565059,0.00014094838,0.00056171796,0.0012809851,0.0034013658,0.0010035599,0.00009687734,0.000019389843],"category_scores_gemma":[0.00038970058,0.00015290984,0.00006876331,0.0010101992,0.00009817281,0.0008986908,0.00009139582,0.0005062029,0.000115557894],"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":[0.000017331038,0.00032090832,0.00017410677,0.00012180362,0.00003966369,0.0000057381667,0.001411728,0.18073697,0.14091057,0.26476204,0.0106549915,0.40084416],"study_design_scores_gemma":[0.00020572943,0.00035363005,0.0011638217,0.000030801453,0.000005400488,0.0000031900186,0.0000498034,0.97593224,0.0005559091,0.00020317611,0.021324702,0.00017158937],"about_ca_topic_score_codex":0.00009768935,"about_ca_topic_score_gemma":0.00013150522,"teacher_disagreement_score":0.85197574,"about_ca_system_score_codex":0.00015997747,"about_ca_system_score_gemma":0.000579442,"threshold_uncertainty_score":0.9976332},"labels":[],"label_agreement":null},{"id":"W4391785473","doi":"10.1007/s00778-024-00835-2","title":"Assisted design of data science pipelines","year":2024,"lang":"en","type":"article","venue":"The VLDB Journal","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Berlin Center for Machine Learning; Banting and Best Diabetes Centre, University of Toronto; Technische Universität Berlin","keywords":"Pipeline transport; Computer science; Data science; Engineering; Mechanical engineering","score_opus":0.16349691109568132,"score_gpt":0.37462525822397275,"score_spread":0.21112834712829143,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391785473","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":[0.0006856071,0.00086341816,0.9917012,0.005618825,0.00049519056,0.00003366468,0.000003287732,0.000056814763,0.00054201065],"genre_scores_gemma":[0.89051443,0.00018734258,0.10866622,0.0000932461,0.00026020006,7.1178437e-7,0.0000031787415,0.000005283742,0.0002693949],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99895376,0.00013635158,0.00019434822,0.00019920067,0.00038380953,0.00013251058],"domain_scores_gemma":[0.9986504,0.0002050954,0.00008977019,0.0009136459,0.00009133512,0.0000497529],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0041198144,0.000052507774,0.00006370874,0.00013746011,0.00026296818,0.0005952428,0.0034386772,0.000013257358,0.000014937489],"category_scores_gemma":[0.00030155343,0.000028850958,0.000017348751,0.00078485644,0.00014908712,0.0014314261,0.0004341691,0.00024720273,0.000040270177],"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":[0.0000067517467,0.00003288495,0.00013432487,0.000016986665,0.000014749796,0.000017550132,0.0005671554,0.0008319439,0.03005883,0.040804103,0.012541042,0.9149737],"study_design_scores_gemma":[0.00005696119,0.00003392768,0.004316045,0.000058795817,0.0000106392,0.0005171837,0.000024260667,0.97239566,0.000577574,0.0025925243,0.019357288,0.000059167498],"about_ca_topic_score_codex":0.000007981723,"about_ca_topic_score_gemma":4.7902034e-7,"teacher_disagreement_score":0.9715637,"about_ca_system_score_codex":0.000016071077,"about_ca_system_score_gemma":0.00035978557,"threshold_uncertainty_score":0.6389975},"labels":[],"label_agreement":null},{"id":"W4392157622","doi":"10.1109/tnnls.2024.3366615","title":"Meta-Scaler: A Meta-Learning Framework for the Selection of Scaling Techniques","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Neural Networks and Learning Systems","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure","funders":"Fundação de Amparo à Ciência e Tecnologia do Estado de Pernambuco; Conselho Nacional de Desenvolvimento Científico e Tecnológico; Coordenação de Aperfeiçoamento de Pessoal de Nível Superior","keywords":"Computer science; Preprocessor; Artificial intelligence; Normalization (sociology); Classifier (UML); Machine learning; Data pre-processing; Meta learning (computer science); Pipeline (software); Data mining; Pattern recognition (psychology)","score_opus":0.05172056130541656,"score_gpt":0.292002743580519,"score_spread":0.24028218227510242,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392157622","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":[0.0003931597,0.005456693,0.9915815,0.0007538552,0.00075914245,0.00039784377,0.0000029035357,0.0006274241,0.000027465861],"genre_scores_gemma":[0.991257,0.00035013683,0.007119924,0.000044030483,0.00019652,0.00037211622,0.0000028959169,0.000028492914,0.000628852],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99809575,0.000559104,0.00039231652,0.0004720318,0.00023223323,0.00024856438],"domain_scores_gemma":[0.99701214,0.0024211882,0.00016875811,0.00025738002,0.00008202053,0.00005853147],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014302823,0.00022197017,0.000410865,0.00016147381,0.00076831685,0.00052128173,0.00027789795,0.00015082757,0.000012858102],"category_scores_gemma":[0.000035170622,0.00013926953,0.00035933987,0.000586607,0.000051253282,0.00029896025,0.000004544171,0.0013299919,0.0000016116987],"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":[0.000014512983,0.000015648187,0.00001345821,0.00010063436,0.0013276008,6.814796e-7,0.00021362565,0.87760955,0.000104138584,0.004156992,0.000041996333,0.11640116],"study_design_scores_gemma":[0.000047201585,0.00021283522,0.000025860758,0.00007574926,0.0016853776,0.000033003897,0.00007166536,0.9851665,0.00018064403,0.00005313091,0.0123056285,0.00014240309],"about_ca_topic_score_codex":0.00013615408,"about_ca_topic_score_gemma":0.0000050909466,"teacher_disagreement_score":0.99086386,"about_ca_system_score_codex":0.000019707912,"about_ca_system_score_gemma":0.00001630535,"threshold_uncertainty_score":0.590935},"labels":[],"label_agreement":null},{"id":"W4392297233","doi":"10.3390/eng5010021","title":"Fundamental Components and Principles of Supervised Machine Learning Workflows with Numerical and Categorical Data","year":2024,"lang":"en","type":"article","venue":"Eng—Advances in Engineering","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"General Fusion (Canada)","funders":"","keywords":"Categorical variable; Workflow; Computer science; Machine learning; Artificial intelligence; Supervised learning; Data science; Artificial neural network","score_opus":0.023185337911759644,"score_gpt":0.2550979615735789,"score_spread":0.23191262366181925,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392297233","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":[0.10737876,0.015391331,0.8764014,0.00019567361,0.00016938709,0.00009852913,0.000009104993,0.00020662665,0.00014918091],"genre_scores_gemma":[0.9522188,0.00072545646,0.046937715,0.0000041167846,0.000026229434,0.0000051952147,0.000053600128,0.000011221933,0.000017722983],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99911517,0.00003247228,0.00017114794,0.0003791695,0.00015058089,0.00015147978],"domain_scores_gemma":[0.99944425,0.00018248394,0.000026199088,0.00028549423,0.000006845089,0.0000547481],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00023597309,0.000116854804,0.00015106182,0.000115413815,0.00003495411,0.00008885101,0.00031644155,0.000026509848,0.0000023314124],"category_scores_gemma":[0.000059868038,0.0000974321,0.00000759607,0.00028105438,0.000028637327,0.00075371895,0.00034202522,0.00029818722,0.000001057013],"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":[0.000058750527,0.00014414376,0.20665939,0.0013956506,0.000069031325,0.00014156285,0.0026490628,0.2797958,0.005563287,0.06669283,0.000006991831,0.4368235],"study_design_scores_gemma":[0.0001737833,0.000045802575,0.012437509,0.000104581195,0.0000036363665,0.000032181422,0.000016847234,0.965425,0.000037579037,0.000021203228,0.02158894,0.00011294814],"about_ca_topic_score_codex":0.000029351577,"about_ca_topic_score_gemma":0.0000067889073,"teacher_disagreement_score":0.84484,"about_ca_system_score_codex":0.000020456071,"about_ca_system_score_gemma":0.000011012414,"threshold_uncertainty_score":0.3973166},"labels":[],"label_agreement":null},{"id":"W4392931294","doi":"10.1109/icassp48485.2024.10446280","title":"Leveraging Noisy Labels of Nearest Neighbors for Label Correction and Sample Selection","year":2024,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","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":"Toronto Metropolitan University","funders":"","keywords":"Computer science; Benchmark (surveying); Artificial intelligence; Context (archaeology); Pattern recognition (psychology); Feature selection; Representation (politics); Sample (material); Selection (genetic algorithm); Feature (linguistics); Machine learning; Noise (video); Data mining; Image (mathematics)","score_opus":0.026278782564371665,"score_gpt":0.29022141613892743,"score_spread":0.2639426335745558,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392931294","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":[0.013390328,0.00008877561,0.98418117,0.0009046671,0.0005321253,0.00009551128,0.0000044455273,0.00022630137,0.00057668594],"genre_scores_gemma":[0.9248282,0.00001836497,0.07402323,0.0000691128,0.000058313493,0.0000130815115,0.000018105291,0.0000065067075,0.00096513267],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99946237,0.000024326979,0.00011269879,0.00023141797,0.0000783278,0.00009085918],"domain_scores_gemma":[0.9994146,0.00035957564,0.000030865907,0.00011872431,0.000049749135,0.000026446744],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002265001,0.000056353543,0.00006427256,0.0000929124,0.0000847211,0.0001555482,0.00009709965,0.00002906546,0.000009731314],"category_scores_gemma":[0.00015978825,0.000049742564,0.000015314234,0.00029259012,0.000012292153,0.00032204099,0.00003595925,0.00007054243,0.000004269554],"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":[0.0000109770335,0.00004506089,0.00792841,0.00016198629,0.000023677663,3.1746174e-7,0.00093315897,0.00035018573,0.010003771,0.1260312,0.008353873,0.8461574],"study_design_scores_gemma":[0.00011199189,0.00007872149,0.0054920423,0.000023218827,0.0000056524095,0.00000671614,0.000023616405,0.9718165,0.0018604565,0.0017962182,0.018719628,0.00006528346],"about_ca_topic_score_codex":0.00045399094,"about_ca_topic_score_gemma":0.00004348081,"teacher_disagreement_score":0.97146624,"about_ca_system_score_codex":0.00001861761,"about_ca_system_score_gemma":0.000034544086,"threshold_uncertainty_score":0.20284429},"labels":[],"label_agreement":null},{"id":"W4393021455","doi":"10.2139/ssrn.4765615","title":"Technical Analysis with Machine Learning Classification Algorithms: Can it Still ‘Beat’ the Buy-and-Hold Strategy?","year":2024,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Machine Learning and Data Classification","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":"Carleton University","funders":"","keywords":"Computer science; Beat (acoustics); Machine learning; Artificial intelligence; Algorithm","score_opus":0.01855319034340787,"score_gpt":0.27496209020093276,"score_spread":0.2564088998575249,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393021455","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":[0.005700222,0.00914398,0.94787455,0.034775477,0.00025188376,0.00040758116,0.00003001351,0.00049050146,0.001325815],"genre_scores_gemma":[0.98928607,0.0054510166,0.0025751218,0.00011761786,0.00029647956,0.000046201087,0.0002015415,0.00004539333,0.0019805657],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9955014,0.0005474704,0.00061135204,0.0010579827,0.0007802054,0.0015016196],"domain_scores_gemma":[0.9977434,0.00017520691,0.0006376211,0.0010886239,0.00019243003,0.00016271514],"candidate_categories":["metaepi_narrow","scholarly_communication","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0041338997,0.00046539612,0.0004850338,0.0005884198,0.00050589896,0.0014318508,0.0018111602,0.00029444782,0.000010878267],"category_scores_gemma":[0.000118934004,0.0002952533,0.0002525264,0.0012582259,0.0001425488,0.00018431542,0.0009073415,0.013385899,0.00001896863],"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":[0.000067479144,0.00015873152,0.006070431,0.00010669318,0.003118125,0.000039104198,0.0011038703,0.030775428,0.00025863267,0.59230727,0.0002580157,0.36573625],"study_design_scores_gemma":[0.0003253145,0.00046342087,0.006938804,0.00011649176,0.001394238,0.0008752737,0.00074014324,0.88958514,0.000007778896,0.094143696,0.004774397,0.00063533173],"about_ca_topic_score_codex":0.0007279674,"about_ca_topic_score_gemma":0.004632773,"teacher_disagreement_score":0.98358583,"about_ca_system_score_codex":0.00088625215,"about_ca_system_score_gemma":0.002822125,"threshold_uncertainty_score":0.99994993},"labels":[],"label_agreement":null},{"id":"W4393147232","doi":"10.1609/aaai.v38i13.29404","title":"Scaling Up Semi-supervised Learning with Unconstrained Unlabelled Data","year":2024,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Mitacs","keywords":"Scaling; Artificial intelligence; Computer science; Machine learning; Semi-supervised learning; Mathematics","score_opus":0.10527602704660391,"score_gpt":0.31731090033649584,"score_spread":0.21203487328989193,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393147232","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":[0.15994099,0.0003468825,0.76529807,0.02771968,0.0019608135,0.0012174333,0.000047758695,0.0017230952,0.04174531],"genre_scores_gemma":[0.99342895,0.000047004916,0.0055895215,0.00008522287,0.00008144856,0.000012582388,0.000012452976,0.000018439972,0.00072440604],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99775964,0.000039933137,0.00045946226,0.0008606156,0.00055496546,0.0003253998],"domain_scores_gemma":[0.99842215,0.00024747936,0.00020779014,0.00067869143,0.00035145646,0.00009245171],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001008161,0.00024018751,0.00023326122,0.00016047238,0.00028712652,0.0008319628,0.0032093746,0.000082087005,0.00006952405],"category_scores_gemma":[0.00072896964,0.0001601406,0.000056191995,0.0010802791,0.0002453375,0.000883963,0.0007184174,0.0006576537,0.00012918562],"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":[0.000044694647,0.000037163307,0.0002537219,0.000104880586,0.000030974257,0.0000014346797,0.0014384802,0.00019805918,0.020880226,0.6636298,0.00019940581,0.31318116],"study_design_scores_gemma":[0.000036937792,0.00013245705,0.00006630883,0.0006702936,0.000026519048,0.000015052103,0.00081449136,0.9252207,0.056876782,0.014308658,0.001572303,0.00025947572],"about_ca_topic_score_codex":0.000054550797,"about_ca_topic_score_gemma":0.0000082773895,"teacher_disagreement_score":0.92502266,"about_ca_system_score_codex":0.0000335615,"about_ca_system_score_gemma":0.00022731774,"threshold_uncertainty_score":0.8022637},"labels":[],"label_agreement":null},{"id":"W4393169604","doi":"10.23977/acss.2024.080201","title":"ReCurricularFace: Revisiting CurricularFace for Hard Sample Mining","year":2024,"lang":"en","type":"article","venue":"Advances in Computer Signals and Systems","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Sample (material); Data mining; Computer science; Chemistry; Chromatography","score_opus":0.025569428204295676,"score_gpt":0.31202424610318413,"score_spread":0.28645481789888844,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393169604","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":[0.0043844576,0.060216006,0.93331224,0.00038086897,0.0011271551,0.00030017685,0.000013182215,0.00018721164,0.000078700905],"genre_scores_gemma":[0.57739687,0.0014878875,0.419899,0.00013399997,0.0008074582,0.0001377471,0.000044233097,0.000024122946,0.00006867835],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99841624,0.00014255305,0.00037800203,0.0006230396,0.00018019594,0.00025998647],"domain_scores_gemma":[0.99862266,0.00085493893,0.00009502486,0.00030795086,0.000055485787,0.000063915526],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009870064,0.00015924436,0.0002506933,0.00012753576,0.00012086281,0.0007501694,0.0003514752,0.000052412965,0.0000012540288],"category_scores_gemma":[0.00007153404,0.00013430716,0.000051613166,0.00035779466,0.000018221266,0.00090891327,0.00012251738,0.00012536491,0.0000053591366],"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":[0.000002945271,0.000015289403,0.0030804372,0.0009216322,0.00001722919,0.000017274526,0.0007374835,0.025088588,0.00013050728,0.06713696,0.00064467354,0.90220696],"study_design_scores_gemma":[0.000117512194,0.000054327236,0.0001945125,0.0007656751,0.0000038323906,0.00002666405,0.000040515046,0.8486987,0.000014179898,0.00087398547,0.14904453,0.0001655922],"about_ca_topic_score_codex":0.000027314809,"about_ca_topic_score_gemma":0.0000016027574,"teacher_disagreement_score":0.9020414,"about_ca_system_score_codex":0.000028032122,"about_ca_system_score_gemma":0.000022842965,"threshold_uncertainty_score":0.7233901},"labels":[],"label_agreement":null},{"id":"W4393396017","doi":"10.1016/j.asoc.2024.111518","title":"SPINEX: Similarity-based predictions with explainable neighbors exploration for regression and classification","year":2024,"lang":"en","type":"article","venue":"Applied Soft Computing","topic":"Machine Learning and Data Classification","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 Guelph; University of Manitoba","funders":"","keywords":"Similarity (geometry); Regression; Artificial intelligence; Computer science; Pattern recognition (psychology); Machine learning; Statistics; Mathematics; Image (mathematics)","score_opus":0.030467660819479225,"score_gpt":0.2814340144765215,"score_spread":0.2509663536570423,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393396017","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":[0.002520161,0.0001028467,0.9920899,0.002961043,0.00015592578,0.00041529577,0.0000045726238,0.00082325574,0.0009269937],"genre_scores_gemma":[0.80177456,0.0000043246014,0.19768345,0.0001397779,0.00010347623,0.000086565866,0.0001497708,0.000016992559,0.000041088337],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987396,0.000037296904,0.0002227294,0.0005883503,0.00019703142,0.00021498975],"domain_scores_gemma":[0.99904084,0.00033547642,0.000104099214,0.00037661608,0.00007133902,0.00007162823],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047851287,0.00015597796,0.0001258898,0.00016521537,0.0005035647,0.0004950394,0.00022434533,0.0000739441,0.0000013091338],"category_scores_gemma":[0.00004984594,0.00012832045,0.000025794547,0.0004471213,0.00004102151,0.00049331546,0.00006780639,0.00019021217,0.00000829613],"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":[0.000042898202,0.00007522214,0.000490889,0.00037291253,0.000025571755,0.000002816975,0.001400662,0.020137683,0.0038769543,0.68491423,0.0021376826,0.2865225],"study_design_scores_gemma":[0.00029315436,0.0000800245,0.001439289,0.00012088844,0.000014995404,0.0000038219223,0.00013106345,0.9804194,0.00029073807,0.003447367,0.013600671,0.00015858361],"about_ca_topic_score_codex":0.0000060782363,"about_ca_topic_score_gemma":0.0000030167766,"teacher_disagreement_score":0.9602817,"about_ca_system_score_codex":0.00004824656,"about_ca_system_score_gemma":0.000094180206,"threshold_uncertainty_score":0.52327555},"labels":[],"label_agreement":null},{"id":"W4393440160","doi":"10.5281/zenodo.1067991","title":"Countwordserror","year":2017,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science","score_opus":0.045259652020450056,"score_gpt":0.29380195701520495,"score_spread":0.24854230499475488,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393440160","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000039170363,0.000096778276,0.01616486,0.0014318118,0.00046195622,0.00032286518,0.9575631,0.001046078,0.022908648],"genre_scores_gemma":[0.00022695445,0.00020725117,0.0005181904,0.00017252921,0.0002838226,4.3072372e-8,0.9970439,0.00054025155,0.0010070568],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9975529,0.00040448585,0.00027717478,0.0007884977,0.0005790243,0.00039793388],"domain_scores_gemma":[0.9959587,0.00002901554,0.00039493525,0.0029509335,0.00047077294,0.00019565815],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0010404259,0.00023711537,0.00022610117,0.00029423417,0.004214151,0.004227248,0.007439375,0.00017795082,0.004279178],"category_scores_gemma":[0.0011288071,0.00024555562,0.000068466434,0.00027197754,0.00014859278,0.0005831277,0.0037485082,0.00071503426,0.039974295],"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":[0.0000065402114,0.000061139646,9.3214844e-8,0.00006299146,0.000019941775,0.000012821455,0.000058710273,0.000004443167,0.00001731666,0.0011016096,0.94038737,0.05826701],"study_design_scores_gemma":[0.00020640921,0.00010357987,0.00009231745,0.000048507016,0.000013976456,0.000091157686,0.000009963976,0.0006978114,0.0000036480203,0.00010227138,0.99836373,0.0002666185],"about_ca_topic_score_codex":0.00008689825,"about_ca_topic_score_gemma":0.0000015753778,"teacher_disagreement_score":0.05800039,"about_ca_system_score_codex":0.0001289391,"about_ca_system_score_gemma":0.000010685136,"threshold_uncertainty_score":0.99999964},"labels":[],"label_agreement":null},{"id":"W4393512592","doi":"10.5281/zenodo.3769289","title":"Example DWI Dataset including minimally preprocessed and co-registered data","year":2020,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Machine Learning and Data Classification","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":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Artificial intelligence; Pattern recognition (psychology); Data mining","score_opus":0.19170812723171443,"score_gpt":0.33734286289932003,"score_spread":0.1456347356676056,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393512592","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000072585244,0.000098480064,0.013583628,0.0013283334,0.00007612983,0.0003574017,0.98245716,0.00057810254,0.0015135098],"genre_scores_gemma":[0.0002131333,0.00030837648,0.0016606518,0.00038820697,0.0001832526,7.1050245e-8,0.9967369,0.00042699018,0.00008244233],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9964254,0.0005576712,0.0004238928,0.0016304039,0.0005890509,0.0003736207],"domain_scores_gemma":[0.9952539,0.00008518515,0.00040333663,0.003745929,0.00022150441,0.0002901374],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["open_science","insufficient_payload"],"category_scores_codex":[0.0013426195,0.00028419253,0.00029246268,0.00025273982,0.0019002854,0.0031717392,0.008038645,0.00013993224,0.0011462359],"category_scores_gemma":[0.0021913366,0.00030307577,0.000022902845,0.00057256,0.00016380246,0.0009976516,0.01330993,0.0006560674,0.0074524176],"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":[0.000024532428,0.00006051098,4.4309868e-7,0.00028990192,0.000033988046,0.000020367024,0.00014808518,0.0000017401295,0.00013061482,0.0001882988,0.9688408,0.030260755],"study_design_scores_gemma":[0.0003478801,0.00014280535,0.00006760239,0.00005446922,0.000026546195,0.00009952127,0.000029655801,0.0032616407,0.000010517121,0.00002662769,0.99562126,0.00031149914],"about_ca_topic_score_codex":0.00019708037,"about_ca_topic_score_gemma":0.0000033248198,"teacher_disagreement_score":0.029949255,"about_ca_system_score_codex":0.00006527204,"about_ca_system_score_gemma":0.00001941991,"threshold_uncertainty_score":0.9999421},"labels":[],"label_agreement":null},{"id":"W4393541531","doi":"10.5281/zenodo.5948876","title":"Task-Informed Meta-Learning data","year":2022,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Task (project management); Computer science; Meta learning (computer science); Psychology; Engineering","score_opus":0.10960800253417868,"score_gpt":0.30499137407897614,"score_spread":0.19538337154479746,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393541531","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000011554589,0.00025625445,0.014994797,0.0013715304,0.00029616588,0.00040811137,0.9703842,0.0015016142,0.010786216],"genre_scores_gemma":[0.000062379186,0.0005171652,0.00086633547,0.00025459434,0.0001424372,1.8071347e-7,0.9966144,0.0006502365,0.0008922491],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99547213,0.0012526751,0.0004796758,0.0012601804,0.0010173378,0.00051800837],"domain_scores_gemma":[0.99470514,0.00012363445,0.00048523865,0.0041541005,0.00030095832,0.00023091832],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["open_science","insufficient_payload"],"category_scores_codex":[0.0022697677,0.00032791882,0.0003923915,0.000525129,0.0043650786,0.0027884196,0.01283511,0.00013594137,0.12273023],"category_scores_gemma":[0.0030846987,0.0003291329,0.000109853085,0.0010663598,0.00010561335,0.0010372658,0.018888459,0.0015897847,0.009398699],"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":[0.000009623985,0.00007748951,7.531176e-8,0.00009105656,0.00023190012,0.000018057674,0.0001059868,0.00008388206,0.000010887488,0.0008176296,0.958145,0.04040841],"study_design_scores_gemma":[0.00021863724,0.00017180997,0.000014784475,0.000009765482,0.00017560372,0.00012563184,0.000050880528,0.0027071957,0.0000015716546,0.000034988047,0.99614567,0.00034344677],"about_ca_topic_score_codex":0.00011557786,"about_ca_topic_score_gemma":0.0000016418879,"teacher_disagreement_score":0.113331534,"about_ca_system_score_codex":0.00020441032,"about_ca_system_score_gemma":0.000027434522,"threshold_uncertainty_score":0.9999161},"labels":[],"label_agreement":null},{"id":"W4393585426","doi":"10.5281/zenodo.3767047","title":"Example DWI Dataset including minimally preprocessed and co-registered data","year":2020,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Artificial intelligence","score_opus":0.19170812723171443,"score_gpt":0.33734286289932003,"score_spread":0.1456347356676056,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393585426","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000072585244,0.000098480064,0.013583628,0.0013283334,0.00007612983,0.0003574017,0.98245716,0.00057810254,0.0015135098],"genre_scores_gemma":[0.0002131333,0.00030837648,0.0016606518,0.00038820697,0.0001832526,7.1050245e-8,0.9967369,0.00042699018,0.00008244233],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9964254,0.0005576712,0.0004238928,0.0016304039,0.0005890509,0.0003736207],"domain_scores_gemma":[0.9952539,0.00008518515,0.00040333663,0.003745929,0.00022150441,0.0002901374],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["open_science","insufficient_payload"],"category_scores_codex":[0.0013426195,0.00028419253,0.00029246268,0.00025273982,0.0019002854,0.0031717392,0.008038645,0.00013993224,0.0011462359],"category_scores_gemma":[0.0021913366,0.00030307577,0.000022902845,0.00057256,0.00016380246,0.0009976516,0.01330993,0.0006560674,0.0074524176],"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":[0.000024532428,0.00006051098,4.4309868e-7,0.00028990192,0.000033988046,0.000020367024,0.00014808518,0.0000017401295,0.00013061482,0.0001882988,0.9688408,0.030260755],"study_design_scores_gemma":[0.0003478801,0.00014280535,0.00006760239,0.00005446922,0.000026546195,0.00009952127,0.000029655801,0.0032616407,0.000010517121,0.00002662769,0.99562126,0.00031149914],"about_ca_topic_score_codex":0.00019708037,"about_ca_topic_score_gemma":0.0000033248198,"teacher_disagreement_score":0.029949255,"about_ca_system_score_codex":0.00006527204,"about_ca_system_score_gemma":0.00001941991,"threshold_uncertainty_score":0.9999421},"labels":[],"label_agreement":null},{"id":"W4393650089","doi":"10.5281/zenodo.3767048","title":"Example DWI Dataset including minimally preprocessed and co-registered data","year":2020,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Artificial intelligence","score_opus":0.19170812723171443,"score_gpt":0.33734286289932003,"score_spread":0.1456347356676056,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393650089","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000072585244,0.000098480064,0.013583628,0.0013283334,0.00007612983,0.0003574017,0.98245716,0.00057810254,0.0015135098],"genre_scores_gemma":[0.0002131333,0.00030837648,0.0016606518,0.00038820697,0.0001832526,7.1050245e-8,0.9967369,0.00042699018,0.00008244233],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9964254,0.0005576712,0.0004238928,0.0016304039,0.0005890509,0.0003736207],"domain_scores_gemma":[0.9952539,0.00008518515,0.00040333663,0.003745929,0.00022150441,0.0002901374],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["open_science","insufficient_payload"],"category_scores_codex":[0.0013426195,0.00028419253,0.00029246268,0.00025273982,0.0019002854,0.0031717392,0.008038645,0.00013993224,0.0011462359],"category_scores_gemma":[0.0021913366,0.00030307577,0.000022902845,0.00057256,0.00016380246,0.0009976516,0.01330993,0.0006560674,0.0074524176],"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":[0.000024532428,0.00006051098,4.4309868e-7,0.00028990192,0.000033988046,0.000020367024,0.00014808518,0.0000017401295,0.00013061482,0.0001882988,0.9688408,0.030260755],"study_design_scores_gemma":[0.0003478801,0.00014280535,0.00006760239,0.00005446922,0.000026546195,0.00009952127,0.000029655801,0.0032616407,0.000010517121,0.00002662769,0.99562126,0.00031149914],"about_ca_topic_score_codex":0.00019708037,"about_ca_topic_score_gemma":0.0000033248198,"teacher_disagreement_score":0.029949255,"about_ca_system_score_codex":0.00006527204,"about_ca_system_score_gemma":0.00001941991,"threshold_uncertainty_score":0.9999421},"labels":[],"label_agreement":null},{"id":"W4393743360","doi":"10.5281/zenodo.6089828","title":"Task-Informed Meta-Learning data","year":2022,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Task (project management); Computer science; Psychology; Engineering","score_opus":0.10960800253417868,"score_gpt":0.30499137407897614,"score_spread":0.19538337154479746,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393743360","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000011554589,0.00025625445,0.014994797,0.0013715304,0.00029616588,0.00040811137,0.9703842,0.0015016142,0.010786216],"genre_scores_gemma":[0.000062379186,0.0005171652,0.00086633547,0.00025459434,0.0001424372,1.8071347e-7,0.9966144,0.0006502365,0.0008922491],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99547213,0.0012526751,0.0004796758,0.0012601804,0.0010173378,0.00051800837],"domain_scores_gemma":[0.99470514,0.00012363445,0.00048523865,0.0041541005,0.00030095832,0.00023091832],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["open_science","insufficient_payload"],"category_scores_codex":[0.0022697677,0.00032791882,0.0003923915,0.000525129,0.0043650786,0.0027884196,0.01283511,0.00013594137,0.12273023],"category_scores_gemma":[0.0030846987,0.0003291329,0.000109853085,0.0010663598,0.00010561335,0.0010372658,0.018888459,0.0015897847,0.009398699],"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":[0.000009623985,0.00007748951,7.531176e-8,0.00009105656,0.00023190012,0.000018057674,0.0001059868,0.00008388206,0.000010887488,0.0008176296,0.958145,0.04040841],"study_design_scores_gemma":[0.00021863724,0.00017180997,0.000014784475,0.000009765482,0.00017560372,0.00012563184,0.000050880528,0.0027071957,0.0000015716546,0.000034988047,0.99614567,0.00034344677],"about_ca_topic_score_codex":0.00011557786,"about_ca_topic_score_gemma":0.0000016418879,"teacher_disagreement_score":0.113331534,"about_ca_system_score_codex":0.00020441032,"about_ca_system_score_gemma":0.000027434522,"threshold_uncertainty_score":0.9999161},"labels":[],"label_agreement":null},{"id":"W4393769005","doi":"10.5281/zenodo.1009659","title":"Countwordserror","year":2017,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science","score_opus":0.045259652020450056,"score_gpt":0.29380195701520495,"score_spread":0.24854230499475488,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393769005","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000039170363,0.000096778276,0.01616486,0.0014318118,0.00046195622,0.00032286518,0.9575631,0.001046078,0.022908648],"genre_scores_gemma":[0.00022695445,0.00020725117,0.0005181904,0.00017252921,0.0002838226,4.3072372e-8,0.9970439,0.00054025155,0.0010070568],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9975529,0.00040448585,0.00027717478,0.0007884977,0.0005790243,0.00039793388],"domain_scores_gemma":[0.9959587,0.00002901554,0.00039493525,0.0029509335,0.00047077294,0.00019565815],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0010404259,0.00023711537,0.00022610117,0.00029423417,0.004214151,0.004227248,0.007439375,0.00017795082,0.004279178],"category_scores_gemma":[0.0011288071,0.00024555562,0.000068466434,0.00027197754,0.00014859278,0.0005831277,0.0037485082,0.00071503426,0.039974295],"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":[0.0000065402114,0.000061139646,9.3214844e-8,0.00006299146,0.000019941775,0.000012821455,0.000058710273,0.000004443167,0.00001731666,0.0011016096,0.94038737,0.05826701],"study_design_scores_gemma":[0.00020640921,0.00010357987,0.00009231745,0.000048507016,0.000013976456,0.000091157686,0.000009963976,0.0006978114,0.0000036480203,0.00010227138,0.99836373,0.0002666185],"about_ca_topic_score_codex":0.00008689825,"about_ca_topic_score_gemma":0.0000015753778,"teacher_disagreement_score":0.05800039,"about_ca_system_score_codex":0.0001289391,"about_ca_system_score_gemma":0.000010685136,"threshold_uncertainty_score":0.99999964},"labels":[],"label_agreement":null},{"id":"W4394082051","doi":"10.6084/m9.figshare.21485874","title":"Dataset - variable selection","year":2023,"lang":"en","type":"dataset","venue":"Figshare","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ministère des Ressources naturelles et des Forêts","funders":"","keywords":"Selection (genetic algorithm); Variable (mathematics); Feature selection; Computer science; Artificial intelligence; Mathematics","score_opus":0.046092925445056464,"score_gpt":0.29934253331554345,"score_spread":0.253249607870487,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394082051","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[9.736719e-10,0.000026033373,0.0002809887,0.0001116604,0.00022937998,0.00011992008,0.9988476,0.0003034357,0.0000809794],"genre_scores_gemma":[2.1823393e-8,0.0000063741377,0.0012390522,0.00025803252,0.0002712245,0.0001608632,0.99762917,0.000013584931,0.00042166474],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985639,0.00008831273,0.0001894648,0.00060398347,0.00030307108,0.00025129574],"domain_scores_gemma":[0.99822646,0.00016884106,0.00020002078,0.001259078,0.00006416724,0.000081409984],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00011913479,0.00019598185,0.00016309494,0.00017898875,0.00015695993,0.0004140533,0.001784739,0.00023325461,0.029723138],"category_scores_gemma":[0.0014203115,0.00019589782,0.000031556585,0.0007315158,0.0000021606747,0.00036484693,0.0007107714,0.00051174744,0.1473129],"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":[5.284735e-7,0.000014002357,1.0946729e-7,0.00016140334,0.000009186005,0.0000063585903,0.0000010987586,0.000024522076,5.8215875e-7,0.000036292353,0.9990591,0.00068682677],"study_design_scores_gemma":[0.000052624742,0.00002123944,0.00004460438,0.0003455934,0.0000063892653,0.000010504259,3.4196142e-7,0.0044306526,0.0000015579863,0.00005655207,0.99481314,0.00021678921],"about_ca_topic_score_codex":0.00030586054,"about_ca_topic_score_gemma":0.000064988475,"teacher_disagreement_score":0.11758976,"about_ca_system_score_codex":0.00004592987,"about_ca_system_score_gemma":0.00018041243,"threshold_uncertainty_score":0.9711638},"labels":[],"label_agreement":null},{"id":"W4394168734","doi":"10.6084/m9.figshare.1450804.v1","title":"Cobre for machine learning","year":2015,"lang":"en","type":"dataset","venue":"Figshare","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Artificial intelligence","score_opus":0.07403695984826873,"score_gpt":0.31040024906537766,"score_spread":0.23636328921710892,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394168734","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[5.856525e-9,0.00048251293,0.00047693896,0.00023443239,0.00015302727,0.00025672175,0.9979428,0.00021261116,0.00024097078],"genre_scores_gemma":[0.0000011887516,0.000008867666,0.0011410919,0.00020468504,0.0002903904,0.00029264265,0.9971256,0.000016362763,0.00091913104],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985814,0.00009211338,0.00020842893,0.0005462105,0.00030920477,0.00026263774],"domain_scores_gemma":[0.9981438,0.00024702342,0.00029679068,0.0009543797,0.00022282694,0.00013516354],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00018131442,0.00023773151,0.00023896495,0.00012517544,0.00015864019,0.00031446392,0.0017670193,0.0002406924,0.013580452],"category_scores_gemma":[0.003865225,0.00022217294,0.0000844435,0.000193786,0.000003274423,0.000223486,0.0005374137,0.00059654133,0.0059983516],"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":[0.0000024360868,0.000014791489,5.276841e-7,0.00023203944,0.000008545512,0.0000038984663,0.000008495945,0.000028044851,1.9806966e-7,0.000016620404,0.99407876,0.005605669],"study_design_scores_gemma":[0.00018603358,0.00008052156,0.000009974785,0.0003563391,0.000007647825,0.000009107682,0.0000011333055,0.017813874,0.0000015162059,0.000042201595,0.9812292,0.00026248355],"about_ca_topic_score_codex":0.000039196064,"about_ca_topic_score_gemma":0.00003322545,"teacher_disagreement_score":0.01778583,"about_ca_system_score_codex":0.000051597905,"about_ca_system_score_gemma":0.00020898599,"threshold_uncertainty_score":0.9947756},"labels":[],"label_agreement":null},{"id":"W4394501563","doi":"10.6084/m9.figshare.22581739","title":"Estimated code","year":2023,"lang":"en","type":"dataset","venue":"Figshare","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Food Inspection Agency","funders":"","keywords":"Code (set theory); Computer science; Programming language","score_opus":0.10523763243898027,"score_gpt":0.3419248561579997,"score_spread":0.23668722371901946,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394501563","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[7.1860597e-9,0.000055216675,0.00004802169,0.00024620374,0.00018563197,0.00009617727,0.9985766,0.00065927854,0.00013286163],"genre_scores_gemma":[2.2202778e-7,0.000009754364,0.0003808522,0.00016778188,0.00011378109,0.000117757576,0.998687,0.000013344592,0.00050950673],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99883366,0.00005349029,0.00016453462,0.00047377753,0.0002647543,0.00020981269],"domain_scores_gemma":[0.9981907,0.00017409073,0.00016863785,0.0013230818,0.00006531065,0.00007818468],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00006216321,0.00017434363,0.00015551149,0.00013881054,0.00009490257,0.00030277568,0.0019484465,0.00019338219,0.016618377],"category_scores_gemma":[0.001878464,0.0001665009,0.00004746838,0.0004181624,0.0000025625566,0.00015960843,0.0006749515,0.00039726912,0.23920913],"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":[2.9296072e-7,0.0000082141605,1.7099845e-7,0.00013012542,0.0000056292947,0.000026999156,0.000002338337,0.000016664992,2.0330309e-7,0.000008609857,0.99766505,0.0021357012],"study_design_scores_gemma":[0.00004667237,0.000012662438,0.00031180045,0.0007614918,0.0000033966298,0.0000059638164,3.1929136e-7,0.009934328,0.0000014845252,0.00002045938,0.9887141,0.0001873231],"about_ca_topic_score_codex":0.00006664374,"about_ca_topic_score_gemma":0.000048710885,"teacher_disagreement_score":0.22259076,"about_ca_system_score_codex":0.000026881191,"about_ca_system_score_gemma":0.000108393004,"threshold_uncertainty_score":0.9842806},"labels":[],"label_agreement":null},{"id":"W4394688228","doi":"10.1016/j.eswa.2024.123923","title":"One-step abductive multi-target learning with diverse noisy samples and its application to tumour segmentation for breast cancer","year":2024,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":18,"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":"Computer science; Segmentation; Artificial intelligence; Machine learning; Breast cancer; Pattern recognition (psychology); Cancer; Computer vision; Medicine; Internal medicine","score_opus":0.02848520687439513,"score_gpt":0.30339922850753454,"score_spread":0.2749140216331394,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394688228","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":[0.00096996943,0.0011587905,0.99250036,0.0022179023,0.000062068604,0.002477949,0.00016260357,0.00040617253,0.000044199587],"genre_scores_gemma":[0.8411977,0.00006101979,0.14319676,0.00008675329,0.00026142446,0.014614699,0.00019006434,0.000036230558,0.00035533615],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9985055,0.00005942318,0.00021467592,0.0007638879,0.00023800142,0.00021855913],"domain_scores_gemma":[0.9990383,0.00011480006,0.00012591032,0.0003471005,0.00022919434,0.00014469626],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020549892,0.00018268997,0.00017331145,0.00015593809,0.00042158394,0.00031924312,0.00028974013,0.000049342372,0.0000034693983],"category_scores_gemma":[0.000010291017,0.00015125012,0.000021171125,0.00053091714,0.000027515081,0.0005100544,0.000062526786,0.00013042218,0.000039010698],"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":[0.00029461726,0.00061385956,0.009208514,0.001667198,0.00055840577,0.0000033129097,0.022750186,0.051511776,0.15878995,0.34573004,0.0022905883,0.40658155],"study_design_scores_gemma":[0.00081313966,0.0002041132,0.0110295685,0.0003535296,0.000053351738,0.000066109445,0.0026082417,0.8856149,0.001592489,0.000059912774,0.09697014,0.0006345065],"about_ca_topic_score_codex":0.00065319514,"about_ca_topic_score_gemma":0.00010408619,"teacher_disagreement_score":0.8493036,"about_ca_system_score_codex":0.00012553409,"about_ca_system_score_gemma":0.000089403504,"threshold_uncertainty_score":0.6167801},"labels":[],"label_agreement":null},{"id":"W4394993814","doi":"10.1007/s42519-024-00376-5","title":"On the Capability of Classification Trees and Random Forests to Estimate Probabilities","year":2024,"lang":"en","type":"article","venue":"Journal of Statistical Theory and Practice","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"HEC Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Mathematics; Random forest; Statistics; Artificial intelligence","score_opus":0.0296397589164158,"score_gpt":0.3635069484470442,"score_spread":0.3338671895306284,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394993814","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":[0.027340282,0.00028849064,0.9563127,0.014471199,0.00010014277,0.000111032954,0.000013360355,0.000011973328,0.0013508144],"genre_scores_gemma":[0.9727797,0.00004409232,0.02694858,0.00015154835,0.000026392529,0.000003538068,8.742669e-7,0.000002979228,0.000042287298],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9981579,0.0011663826,0.00027772857,0.00013555164,0.00019192655,0.00007048499],"domain_scores_gemma":[0.9689729,0.030535987,0.00014400903,0.00016801,0.00011252906,0.00006656285],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0062913974,0.00006405756,0.00012344155,0.000051737665,0.00007720165,0.00018141956,0.00015268414,0.000023787492,0.000015181284],"category_scores_gemma":[0.020073254,0.00003578133,0.000018326049,0.00010804391,0.00014116391,0.00045663645,0.000038923892,0.0002197538,0.0000042338092],"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":[0.00061047386,0.000036722202,0.00007169215,0.000052613614,0.000018648008,0.000004742089,0.0008123173,0.000042389474,0.00017103115,0.9438689,0.0004074292,0.053903062],"study_design_scores_gemma":[0.00025689093,0.0006170366,0.030809546,0.00012489068,0.00006321282,0.00021517374,0.00039791776,0.026741559,0.00006682637,0.93297386,0.007656793,0.00007630088],"about_ca_topic_score_codex":0.000004313637,"about_ca_topic_score_gemma":0.0000024885887,"teacher_disagreement_score":0.9454394,"about_ca_system_score_codex":0.000011749431,"about_ca_system_score_gemma":0.00004941935,"threshold_uncertainty_score":0.9881811},"labels":[],"label_agreement":null},{"id":"W4396628646","doi":"10.1016/b978-0-443-13829-4.00004-0","title":"Case studies in machine learning artificial intelligence","year":2024,"lang":"en","type":"book-chapter","venue":"Elsevier eBooks","topic":"Machine Learning and Data Classification","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":"McMaster University","funders":"","keywords":"Artificial intelligence; Computer science; Machine learning","score_opus":0.07978515612210121,"score_gpt":0.32638496051284926,"score_spread":0.24659980439074805,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396628646","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":[0.000018201124,0.006784343,0.0024648302,0.00036708682,0.00094509183,0.00028259854,0.000013131645,0.00036100138,0.9887637],"genre_scores_gemma":[0.013929381,0.0003905437,0.0024364383,0.0000957316,0.00027301104,0.000031868887,0.000029425528,0.000055816952,0.9827578],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9978381,0.00007365236,0.00062787556,0.00086763786,0.00030760872,0.00028513625],"domain_scores_gemma":[0.9986645,0.00021321051,0.00021570173,0.0007431353,0.000080493824,0.00008298302],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00076349336,0.00039819113,0.00045723293,0.00044763242,0.00015545537,0.00021484704,0.00061961927,0.00020356107,0.000033599794],"category_scores_gemma":[0.000119304954,0.00035981214,0.00013194093,0.000065186905,0.00014265437,0.000112409834,0.00063183263,0.0015068761,0.00081760454],"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":[0.0000022324684,0.0000039381603,0.0000021215958,0.00010011511,0.000031861273,0.0029968752,0.0008905114,0.000026764365,0.0000028514175,0.29806653,0.000010930233,0.69786525],"study_design_scores_gemma":[0.000031352203,0.00008212524,7.2234025e-7,0.0005739386,0.000043131527,0.0018116657,0.000056939545,0.026552342,0.000016346798,0.18575814,0.7845557,0.0005176317],"about_ca_topic_score_codex":0.000004201769,"about_ca_topic_score_gemma":0.000192168,"teacher_disagreement_score":0.78454477,"about_ca_system_score_codex":0.00013063016,"about_ca_system_score_gemma":0.000074601645,"threshold_uncertainty_score":0.99996036},"labels":[],"label_agreement":null},{"id":"W4396694063","doi":"10.1038/s41598-024-61284-z","title":"Measuring the prediction difficulty of individual cases in a dataset using machine learning","year":2024,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Machine Learning and Data Classification","field":"Computer Science","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":"University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Metric (unit); Machine learning; Artificial intelligence; Artificial neural network; Perspective (graphical); Data mining; Key (lock); Variety (cybernetics)","score_opus":0.06299436719122843,"score_gpt":0.2899077230452051,"score_spread":0.2269133558539767,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396694063","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":[0.9548698,0.0011742628,0.03745778,0.0004048872,0.0051924717,0.00029529314,0.00018928082,0.0002670906,0.00014915668],"genre_scores_gemma":[0.99753207,0.0000041846497,0.0013281766,0.0000060851476,0.00003648869,0.0000060212847,0.000976934,0.000005793861,0.000104243474],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99803567,0.00016336983,0.00041789046,0.0005947784,0.00061298476,0.0001752894],"domain_scores_gemma":[0.99884754,0.00011680181,0.00017428491,0.0007786322,0.000044014992,0.00003870059],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0030606734,0.00009165923,0.00010231887,0.00026430754,0.00027487118,0.0007708353,0.00040140824,0.000033455024,0.000009821157],"category_scores_gemma":[0.00046407737,0.00006306133,0.00003637269,0.0010333095,0.00010120362,0.00056476996,0.0002853625,0.00027304204,0.000005037263],"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":[0.000028215909,0.0006598148,0.37289983,0.0009078313,0.00020423908,0.0048659076,0.02087123,0.09621721,0.22525486,0.008159289,0.030343693,0.23958789],"study_design_scores_gemma":[0.00008034237,0.00003276628,0.023556352,0.00022184469,0.00002675903,0.001400311,0.00012489688,0.90428644,0.0037728196,0.00070008304,0.065633744,0.00016362855],"about_ca_topic_score_codex":0.0003231075,"about_ca_topic_score_gemma":0.000094028925,"teacher_disagreement_score":0.8080692,"about_ca_system_score_codex":0.000038971437,"about_ca_system_score_gemma":0.00012320187,"threshold_uncertainty_score":0.7433183},"labels":[],"label_agreement":null},{"id":"W4396723302","doi":"10.1145/3589334.3645474","title":"Whole Page Unbiased Learning to Rank","year":2024,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","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":false,"ca_institutions":"Wilfrid Laurier University","funders":"","keywords":"Computer science; Learning to rank; Information retrieval; Ranking (information retrieval)","score_opus":0.017618708289845224,"score_gpt":0.2787650035453022,"score_spread":0.26114629525545696,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396723302","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":[0.003942718,0.000080916514,0.95321953,0.0131045915,0.00026030772,0.000060325245,8.7514593e-7,0.0010638564,0.028266875],"genre_scores_gemma":[0.9486474,0.0000037258694,0.025603654,0.000637087,0.00007551463,0.000009259248,0.000017298544,0.0000076110387,0.024998447],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99925596,0.000060376624,0.00009521731,0.0003085039,0.00014175518,0.00013820009],"domain_scores_gemma":[0.9994923,0.00009267209,0.000010484784,0.00031097577,0.000017081175,0.00007647726],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003150011,0.00006406743,0.000056298166,0.00010510914,0.00008065067,0.0004470111,0.00035992588,0.00002335987,0.00008799779],"category_scores_gemma":[0.00010162831,0.00005239641,0.000026962092,0.00045142617,0.000006148651,0.00026958028,0.000116802075,0.00016737184,0.0032444578],"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":[0.0000032729586,0.000024020836,0.0005186682,0.00003806454,0.000012588243,0.000032180822,0.0016888714,0.001499985,0.02436597,0.20882158,0.055473663,0.70752114],"study_design_scores_gemma":[0.00004236158,0.000033921424,0.001857837,0.000016582999,0.0000014436805,0.000003370058,0.000025544905,0.36055025,0.00032654885,0.00024830963,0.6368117,0.000082123894],"about_ca_topic_score_codex":0.00004058494,"about_ca_topic_score_gemma":0.0000061758337,"teacher_disagreement_score":0.9447047,"about_ca_system_score_codex":0.000016015692,"about_ca_system_score_gemma":0.000028238908,"threshold_uncertainty_score":0.99753165},"labels":[],"label_agreement":null},{"id":"W4396939046","doi":"10.1371/journal.pone.0299989","title":"Simulation study to evaluate when Plasmode simulation is superior to parametric simulation in estimating the mean squared error of the least squares estimator in linear regression","year":2024,"lang":"en","type":"article","venue":"PLoS ONE","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"Technische Universität Dortmund; Deutsche Forschungsgemeinschaft","keywords":"Estimator; Parametric statistics; Mean squared error; Context (archaeology); Computer science; Resampling; Statistics; Outcome (game theory); Algorithm; Mathematics","score_opus":0.10280042601457218,"score_gpt":0.36529113523200213,"score_spread":0.26249070921742995,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396939046","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":[0.80026114,0.000032227228,0.19643778,0.0017259555,0.000111967915,0.0013180175,0.0000081230355,0.00009590416,0.000008905259],"genre_scores_gemma":[0.97081846,2.7030114e-7,0.028910743,0.00008526232,0.000049655326,0.000063727704,0.000010876945,0.000021539665,0.00003948585],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99704754,0.00055189646,0.0006344159,0.00058237935,0.00095202384,0.00023172496],"domain_scores_gemma":[0.9970668,0.0016721876,0.00015700418,0.0008595187,0.00017941147,0.000065060616],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014403823,0.00019473415,0.00026823505,0.0005601631,0.00016873052,0.00020952153,0.0006510581,0.00006205177,0.000012911157],"category_scores_gemma":[0.0032210017,0.00012937626,0.000047317983,0.0021600402,0.000019790523,0.00051019754,0.00027777045,0.0003011273,0.000044474145],"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":[0.00004728206,0.0005175251,0.021896109,0.00007320526,0.000014612493,0.0000010790533,0.015484388,0.95222515,0.0004346347,0.000037321293,0.000004439888,0.009264284],"study_design_scores_gemma":[0.00032309073,0.00018677817,0.06073964,0.00066380354,0.000030942403,1.2245262e-7,0.00023769152,0.9372117,0.0002380168,0.00021735398,0.000010488306,0.00014038652],"about_ca_topic_score_codex":0.0003176198,"about_ca_topic_score_gemma":0.00017731705,"teacher_disagreement_score":0.17055732,"about_ca_system_score_codex":0.0001560513,"about_ca_system_score_gemma":0.00008118205,"threshold_uncertainty_score":0.5275811},"labels":[],"label_agreement":null},{"id":"W4398275946","doi":"10.7910/dvn/2ceywv/p7hovg","title":"Raúl_Labrador.jpg","year":2019,"lang":"gl","type":"dataset","venue":"Harvard Dataverse","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Replication (statistics); Computer science; Information retrieval; Cartography; Biology; Geography","score_opus":0.024594279433611716,"score_gpt":0.2638907917282827,"score_spread":0.239296512294671,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4398275946","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000016334747,0.00001111974,0.018356372,0.00013059124,0.004711375,0.0006792052,0.97354347,0.00022342315,0.0023280887],"genre_scores_gemma":[0.00019454224,0.0010334735,0.0043873517,0.0013038261,0.00077455834,0.0000307919,0.9835117,0.000056220815,0.008707535],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9936013,0.00062125846,0.0009997546,0.0024534771,0.0012635292,0.0010606776],"domain_scores_gemma":[0.9882621,0.00040656695,0.0010018795,0.009638725,0.00021718474,0.00047353387],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0013301194,0.00096145744,0.00094340416,0.0005248688,0.0004543997,0.0014282531,0.0065119523,0.00073460786,0.046755705],"category_scores_gemma":[0.0008647396,0.00096816814,0.00029846365,0.00082115113,0.00021460018,0.0019557606,0.0034172703,0.0018091464,0.80898744],"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":[0.000045931192,0.0002455648,0.000076752236,0.00028990515,0.00010821382,0.000117242074,0.00008890168,0.00006177742,0.000041463973,0.0020863912,0.98861796,0.008219886],"study_design_scores_gemma":[0.0009077072,0.00018369414,0.00048601054,0.00026210633,0.00017533771,0.00007476699,0.00004433249,0.016889427,0.000012740983,0.00003922968,0.9798522,0.0010724674],"about_ca_topic_score_codex":0.00073760044,"about_ca_topic_score_gemma":0.00007240232,"teacher_disagreement_score":0.7622317,"about_ca_system_score_codex":0.00019926135,"about_ca_system_score_gemma":0.0006210766,"threshold_uncertainty_score":0.99960834},"labels":[],"label_agreement":null},{"id":"W4399156410","doi":"10.1145/3654934","title":"Data Acquisition for Improving Model Confidence","year":2024,"lang":"en","type":"article","venue":"Proceedings of the ACM on Management of Data","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; York University","funders":"","keywords":"Computer science; Data acquisition; Machine learning; Context (archaeology); Knowledge acquisition; Range (aeronautics); Process (computing); Artificial intelligence; Data mining; Data quality; Data science; Engineering","score_opus":0.11260369583204238,"score_gpt":0.3468254042837654,"score_spread":0.23422170845172302,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399156410","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":[0.0027182763,0.0003063394,0.974722,0.015931413,0.0003309291,0.0008520631,0.0012750288,0.00023078268,0.0036331268],"genre_scores_gemma":[0.62564075,0.000080178856,0.37315205,0.000120386336,0.000050254985,0.000018359338,0.00037222716,0.000012951394,0.000552868],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99868435,0.0000042319725,0.00023161886,0.0006214407,0.00033404658,0.0001243129],"domain_scores_gemma":[0.99609834,0.00007027651,0.00018179264,0.0035595775,0.000070145616,0.000019870557],"candidate_categories":["open_science"],"consensus_categories":["open_science"],"category_scores_codex":[0.0011490313,0.00009036245,0.00009823619,0.00007872344,0.00006875848,0.00019938836,0.014609128,0.000023551314,0.000001692036],"category_scores_gemma":[0.0002313609,0.00006692661,0.000024181172,0.00026336298,0.000034642075,0.0019137475,0.011780305,0.000085884545,0.000004472566],"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":[0.000021010768,0.000058156147,0.000045295405,0.0023185683,0.000060150633,2.0074788e-7,0.00007290684,0.000106074105,0.0043035196,0.7822855,0.04631901,0.1644096],"study_design_scores_gemma":[0.00010981779,0.000034672372,0.00022085689,0.00029293227,0.000056645742,9.412082e-7,0.00004675375,0.967835,0.0008870623,0.026107129,0.00433099,0.00007721037],"about_ca_topic_score_codex":0.000007010779,"about_ca_topic_score_gemma":3.367759e-7,"teacher_disagreement_score":0.9677289,"about_ca_system_score_codex":0.000012683863,"about_ca_system_score_gemma":0.000018403727,"threshold_uncertainty_score":0.99621224},"labels":[],"label_agreement":null},{"id":"W4399615587","doi":"10.1007/s10664-024-10450-y","title":"How far are we with automated machine learning? characterization and challenges of AutoML toolkits","year":2024,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University; University of Calgary","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Characterization (materials science); Computer science; Artificial intelligence; Machine learning; Nanotechnology; Materials science","score_opus":0.02592931027558718,"score_gpt":0.24558559859600892,"score_spread":0.21965628832042175,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399615587","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":[0.029161748,0.0049816626,0.952388,0.009592379,0.00013919537,0.00009105576,0.000011382222,0.0036266427,0.000007954043],"genre_scores_gemma":[0.97888863,0.0011996294,0.019524593,0.000030119882,0.00006344818,0.000015651602,0.000059715898,0.000032273423,0.00018594065],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99906987,0.00004085178,0.00014113325,0.00036692285,0.0002054617,0.00017578522],"domain_scores_gemma":[0.9994222,0.00016882237,0.00006421043,0.00022419477,0.000041217576,0.00007934346],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014771099,0.00016235912,0.00018268128,0.00015249483,0.00005001102,0.0002205696,0.00020132218,0.00007431487,0.0000024743806],"category_scores_gemma":[0.00022984171,0.0001303305,0.00002600879,0.000376779,0.000017871294,0.00047103205,0.000099865494,0.00025887118,0.00000381],"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":[0.00003161925,0.00018132785,0.12231929,0.005054217,0.00028682328,0.00017547865,0.005417316,0.019307535,0.007794795,0.016526071,0.0003328328,0.8225727],"study_design_scores_gemma":[0.00009175236,0.00008491086,0.15071067,0.00020599514,0.000008148154,0.000026438775,0.000008380929,0.768507,0.00013766754,0.0000075117105,0.08004882,0.00016268887],"about_ca_topic_score_codex":0.0000033228703,"about_ca_topic_score_gemma":0.0000013760347,"teacher_disagreement_score":0.9497269,"about_ca_system_score_codex":0.000024623087,"about_ca_system_score_gemma":0.000022126032,"threshold_uncertainty_score":0.5314724},"labels":[],"label_agreement":null},{"id":"W4399714937","doi":"10.1007/978-3-031-62700-2_16","title":"Shapley-Based Data Valuation Method for the Machine Learning Data Markets (MLDM)","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Machine Learning and Data Classification","field":"Computer Science","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":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Computer science; Valuation (finance); Artificial intelligence; Machine learning; Data mining; Finance","score_opus":0.09770049559368323,"score_gpt":0.35377676369661865,"score_spread":0.25607626810293543,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399714937","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":[3.5947082e-7,0.00211343,0.9842589,0.0097815655,0.0017352531,0.0007094809,0.0002719088,0.00029309496,0.00083601],"genre_scores_gemma":[0.003976262,0.00009548885,0.9897989,0.0014903501,0.0007704391,0.00002658721,0.0024265249,0.00006384556,0.0013515869],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9944799,0.00017436,0.0005828959,0.0030267094,0.0011992578,0.0005369026],"domain_scores_gemma":[0.987774,0.004410494,0.00039557516,0.0070985104,0.00021036365,0.00011106383],"candidate_categories":["metaepi_narrow","scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.0094346525,0.0005040504,0.00041118564,0.00057759346,0.00063395716,0.0015775063,0.014947836,0.00024447267,0.000027936821],"category_scores_gemma":[0.0013822113,0.0003639728,0.00008368469,0.0007086281,0.0003003826,0.0010222734,0.006549335,0.0014715266,0.000056235018],"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":[0.000011316653,0.000013736407,0.000019919571,0.00008345524,0.000022026934,0.000007205739,0.00011656682,0.047517918,0.00003648343,0.01819932,0.00025308455,0.933719],"study_design_scores_gemma":[0.00018593766,0.0000628193,0.000074232164,0.00019161258,0.000048316655,0.00001896106,1.4116479e-7,0.83911586,0.000027481834,0.037099514,0.122812316,0.00036281184],"about_ca_topic_score_codex":0.00009679941,"about_ca_topic_score_gemma":0.00020538132,"teacher_disagreement_score":0.93335617,"about_ca_system_score_codex":0.00014517104,"about_ca_system_score_gemma":0.0007820789,"threshold_uncertainty_score":0.9998812},"labels":[],"label_agreement":null},{"id":"W4399760063","doi":"10.26434/chemrxiv-2024-q17mn","title":"Machine Learning Enables a Top-Down Approach to Mechanistic Elucidation","year":2024,"lang":"en","type":"preprint","venue":"ChemRxiv","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Natural Sciences and Engineering Research Council of Canada; University of British Columbia; Canada Foundation for Innovation","keywords":"Top-down and bottom-up design; Computer science; Mechanism (biology); Data science; Artificial intelligence; Machine learning; Cognitive science; Computational biology; Biology; Psychology; Software engineering; Epistemology; Philosophy","score_opus":0.02515048713725662,"score_gpt":0.2610494616066192,"score_spread":0.23589897446936256,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399760063","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":[0.0024342919,0.0008520054,0.96224004,0.002538702,0.0008241719,0.0004184713,0.000008326876,0.0011455942,0.02953841],"genre_scores_gemma":[0.9213205,0.00006184209,0.071171194,0.00026970732,0.00034534643,0.00021827623,0.00072529726,0.000049055223,0.0058387606],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974695,0.00013557874,0.0003679358,0.001300288,0.0003925432,0.00033415147],"domain_scores_gemma":[0.9982068,0.000074500465,0.00018299394,0.0012681037,0.00009454894,0.0001730653],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007809958,0.00034981087,0.0003191193,0.0003267621,0.00016590029,0.0008341935,0.001405908,0.0002449759,0.000022434418],"category_scores_gemma":[0.0003990919,0.0003304945,0.00012319977,0.00047782392,0.00001949696,0.00011255216,0.0028589354,0.0013992359,0.0006313963],"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":[0.00002419526,0.0003471146,0.0003567663,0.0026828216,0.00018851206,0.000028952816,0.0048878053,0.025329327,0.010221204,0.71016353,0.008605612,0.23716417],"study_design_scores_gemma":[0.0001175089,0.00004613234,0.00014501919,0.0001946071,0.000049669987,0.000017200688,0.00004980613,0.8902454,0.0047392617,0.025881458,0.07791347,0.0006004608],"about_ca_topic_score_codex":0.00017296655,"about_ca_topic_score_gemma":0.000005010727,"teacher_disagreement_score":0.91888624,"about_ca_system_score_codex":0.00012792421,"about_ca_system_score_gemma":0.00015513677,"threshold_uncertainty_score":0.9999147},"labels":[],"label_agreement":null},{"id":"W4400302466","doi":"10.1002/smr.2710","title":"On the value of instance selection for bug resolution prediction performance","year":2024,"lang":"en","type":"article","venue":"Journal of Software Evolution and Process","topic":"Machine Learning and Data Classification","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":false,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Computer science; Selection (genetic algorithm); Value (mathematics); Resolution (logic); Artificial intelligence; Machine learning; Data mining","score_opus":0.012080885809297288,"score_gpt":0.2595333875728785,"score_spread":0.24745250176358125,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400302466","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":[0.16483812,0.0008449998,0.8328951,0.0008830058,0.00034165804,0.00009150816,0.0000058745054,0.000050251627,0.00004948515],"genre_scores_gemma":[0.9953518,0.00012791366,0.00427745,0.00004115806,0.00011928331,0.000007460884,0.0000025240013,0.0000044635563,0.000067969224],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992484,0.00005021357,0.00026042503,0.00012461118,0.00023411527,0.000082259234],"domain_scores_gemma":[0.9991798,0.0002094267,0.00021641684,0.00008894074,0.00027716515,0.000028246202],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00082880707,0.00006383007,0.000083050974,0.00013819456,0.00016224432,0.00006754138,0.00017332268,0.0000453584,0.000001945135],"category_scores_gemma":[0.0003398331,0.000042290558,0.000037270096,0.0003581421,0.000031164207,0.0006402847,0.000012625053,0.00019193602,0.0000011190394],"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":[0.00068604684,0.0002507942,0.042578865,0.002491729,0.0001354195,0.0000012560066,0.0032828546,0.051678553,0.0021702475,0.62598455,0.0130924275,0.25764725],"study_design_scores_gemma":[0.00029498708,0.00082716724,0.061787117,0.00061702635,0.000025760926,0.00008813756,0.000053309614,0.9120723,0.00068470166,0.017743029,0.005717303,0.00008918996],"about_ca_topic_score_codex":0.0000027663602,"about_ca_topic_score_gemma":9.66055e-7,"teacher_disagreement_score":0.8603937,"about_ca_system_score_codex":0.000063593914,"about_ca_system_score_gemma":0.00013614203,"threshold_uncertainty_score":0.17245589},"labels":[],"label_agreement":null},{"id":"W4400530140","doi":"10.1145/3626772.3657903","title":"Unbiased Validation of Technology-Assisted Review for eDiscovery","year":2024,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","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":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science","score_opus":0.026457597882547052,"score_gpt":0.3177730236927362,"score_spread":0.29131542581018915,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400530140","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":[0.00034346792,0.0041672015,0.9771046,0.015461087,0.0001988832,0.00020349048,0.0000072218645,0.00036740222,0.0021466617],"genre_scores_gemma":[0.7396568,0.0021375553,0.252843,0.0008845243,0.000102662074,0.00018019881,0.0003106038,0.000018382747,0.003866281],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9994601,0.000018329265,0.00016751685,0.00019801759,0.00008837049,0.00006765873],"domain_scores_gemma":[0.999443,0.00008535486,0.00004640563,0.00035821128,0.000053631422,0.000013385086],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000320224,0.000048057187,0.00008979298,0.0001245269,0.000024515557,0.000047337075,0.0002841471,0.000033236014,0.000015907164],"category_scores_gemma":[0.00018587307,0.00003688597,0.000042614993,0.00056571886,0.000015184198,0.00024634617,0.000046082434,0.00005152266,0.000024381086],"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":[0.0000014105037,0.000028654706,0.000096730764,0.0015260612,0.0000140804395,5.8438445e-7,0.000015360178,0.0000061328033,0.0050929193,0.44224402,0.031071573,0.51990247],"study_design_scores_gemma":[0.00034963206,0.0002441907,0.00168507,0.0036909303,0.000080512,0.000024473424,0.000019996807,0.18180811,0.047288064,0.016587017,0.7478758,0.0003462095],"about_ca_topic_score_codex":0.000004742985,"about_ca_topic_score_gemma":6.460273e-7,"teacher_disagreement_score":0.7393133,"about_ca_system_score_codex":0.000011602668,"about_ca_system_score_gemma":0.000051060866,"threshold_uncertainty_score":0.15041661},"labels":[],"label_agreement":null},{"id":"W4400681662","doi":"10.1109/saner60148.2024.00019","title":"Refining GPT-3 Embeddings with a Siamese Structure for Technical Post Duplicate Detection","year":2024,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Refining (metallurgy); Computer science; Artificial intelligence; Materials science; Metallurgy","score_opus":0.007164724710223737,"score_gpt":0.2590984125606616,"score_spread":0.25193368785043785,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400681662","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":[0.008588016,0.000043832926,0.9849412,0.0038684064,0.000109705754,0.00011338367,0.000009214004,0.0009980005,0.001328227],"genre_scores_gemma":[0.8897953,0.0000012391699,0.1090653,0.00020144082,0.00006308753,0.000035024543,0.000025924612,0.000012846655,0.00079981465],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99908894,0.000017533675,0.00012701348,0.0004583616,0.00014011379,0.00016800509],"domain_scores_gemma":[0.9993466,0.000106167914,0.000036733796,0.00039573925,0.000062408246,0.000052360887],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018520308,0.00010509716,0.00008535217,0.00011096314,0.000119486824,0.00037790267,0.00033633015,0.00006839936,0.000011906231],"category_scores_gemma":[0.0000758463,0.000071906186,0.000034318207,0.00038484563,0.000022127735,0.0003834781,0.00007477697,0.00020666834,0.000023473835],"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":[0.000048727325,0.000033487024,0.00013033397,0.00011333314,0.00002476703,0.000007284653,0.00025678586,0.0001334053,0.16625722,0.20630048,0.0012843624,0.62540984],"study_design_scores_gemma":[0.0005348207,0.00067960325,0.0043722875,0.00010430733,0.000027989565,0.00031280096,0.00003923094,0.80080795,0.010696136,0.0027263763,0.17925881,0.00043966758],"about_ca_topic_score_codex":0.0000440278,"about_ca_topic_score_gemma":0.00009795502,"teacher_disagreement_score":0.8812073,"about_ca_system_score_codex":0.00003461773,"about_ca_system_score_gemma":0.00004187892,"threshold_uncertainty_score":0.36441243},"labels":[],"label_agreement":null},{"id":"W4400769068","doi":"10.1016/j.patcog.2024.110803","title":"Dynamic selection for reconstructing instance-dependent noisy labels","year":2024,"lang":"en","type":"article","venue":"Pattern Recognition","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":7,"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 Calgary","funders":"National Natural Science Foundation of China","keywords":"Selection (genetic algorithm); Computer science; Artificial intelligence; Pattern recognition (psychology)","score_opus":0.02621654168521104,"score_gpt":0.2861119032924488,"score_spread":0.25989536160723775,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400769068","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":[0.05910333,0.000101606274,0.93737924,0.00089868496,0.0010150596,0.00021849973,0.00004493269,0.00055862824,0.0006800174],"genre_scores_gemma":[0.96844745,0.000043510874,0.03066652,0.00014351083,0.00012679343,0.000112027075,0.0002516605,0.000017463184,0.0001910621],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99898446,0.000060587474,0.00020591044,0.00043401192,0.0001341771,0.00018083963],"domain_scores_gemma":[0.99951357,0.00013381625,0.00007271199,0.00016213366,0.000079415135,0.000038380687],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036340617,0.00010472864,0.000085364685,0.00015439827,0.00013985691,0.00034960711,0.00017525919,0.000060978753,0.000035923986],"category_scores_gemma":[0.000065452536,0.00010591471,0.000047741676,0.00023995775,0.000010546642,0.0006349029,0.00003393582,0.00017192488,0.00024413144],"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":[0.0000026034545,0.000012120978,0.0009276634,0.00009130965,0.000011486604,9.978635e-7,0.00012976101,0.00001005417,0.0020209232,0.00024926805,0.00011481023,0.996429],"study_design_scores_gemma":[0.00027124092,0.00008786065,0.0013744066,0.00021961806,0.000019431296,0.00009033457,0.000041934298,0.9834923,0.0023313947,0.007603703,0.0042198803,0.00024787014],"about_ca_topic_score_codex":0.00003698641,"about_ca_topic_score_gemma":0.00009467031,"teacher_disagreement_score":0.99618113,"about_ca_system_score_codex":0.00009212718,"about_ca_system_score_gemma":0.000038962553,"threshold_uncertainty_score":0.43190765},"labels":[],"label_agreement":null},{"id":"W4400909907","doi":"10.1109/icde60146.2024.00146","title":"FeatAug: Automatic Feature Augmentation From One-to-Many Relationship Tables","year":2024,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Feature (linguistics); Artificial intelligence; Pattern recognition (psychology); Data mining","score_opus":0.02920513358580999,"score_gpt":0.2927907284485727,"score_spread":0.2635855948627627,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400909907","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":[0.012357566,0.00024659245,0.9577131,0.020389723,0.00041901026,0.00016464366,0.00002172563,0.0011486653,0.0075389193],"genre_scores_gemma":[0.7790029,0.000005481784,0.21204415,0.0004907571,0.00011028955,0.000029414845,0.00034522574,0.000010809587,0.007960957],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989496,0.00008384252,0.00015119235,0.00041654738,0.00025712597,0.00014169239],"domain_scores_gemma":[0.99901503,0.0003162046,0.00003202574,0.00052681327,0.000026461432,0.0000834833],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00023622293,0.00010145995,0.00008621011,0.00016241307,0.00013513089,0.0007237121,0.00042288037,0.0000599967,0.00018964997],"category_scores_gemma":[0.0001279616,0.00008881387,0.000031337688,0.0005926529,0.000009683229,0.00077138987,0.00010519605,0.00018598931,0.0016343645],"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":[0.0000029710632,0.00005070598,0.0061334325,0.00006492988,0.0000383442,0.000008660058,0.0018043342,0.0003491442,0.002007653,0.6640652,0.09221112,0.23326354],"study_design_scores_gemma":[0.00011866746,0.000032580403,0.21080534,0.00011270448,0.000018803752,0.0000040635346,0.000060934177,0.73835313,0.0003234909,0.013541177,0.036430556,0.00019853776],"about_ca_topic_score_codex":0.00021635559,"about_ca_topic_score_gemma":0.000047934875,"teacher_disagreement_score":0.7666454,"about_ca_system_score_codex":0.00006013977,"about_ca_system_score_gemma":0.000052919135,"threshold_uncertainty_score":0.999143},"labels":[],"label_agreement":null},{"id":"W4400985571","doi":"10.54254/2755-2721/79/20241399","title":"Label noise learning with the combination of CausalNL and CGAN models","year":2024,"lang":"en","type":"article","venue":"Applied and Computational Engineering","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Overfitting; Artificial intelligence; Computer science; Noise (video); Artificial neural network; Machine learning; Transfer of learning; Set (abstract data type); Training set; Deep learning; Algorithm; Pattern recognition (psychology); Image (mathematics)","score_opus":0.007219495042634706,"score_gpt":0.19885643849389767,"score_spread":0.19163694345126298,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400985571","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":[0.04516335,0.00026537286,0.9532169,0.0007598045,0.000019224759,0.00005560801,6.9913034e-7,0.00014459949,0.00037444977],"genre_scores_gemma":[0.97734064,0.000012348098,0.022574753,0.000018865405,0.000011644725,0.000008571636,0.000011181707,0.000005516498,0.00001650229],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996076,0.0000075849357,0.00006988321,0.00014145183,0.00011484278,0.000058608504],"domain_scores_gemma":[0.9997227,0.00015507427,0.000020334777,0.000059525853,0.00002127082,0.000021102054],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012336008,0.000059699243,0.000054252116,0.00005411825,0.00006028772,0.000099671925,0.00007458353,0.000015459083,3.012876e-7],"category_scores_gemma":[0.0000031544962,0.000042901444,0.0000050311696,0.00015145901,0.000015014184,0.00014317286,0.00004249324,0.0001084172,8.8157674e-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":[9.922647e-7,0.0000052606442,0.000017029883,0.000036875525,0.000009770804,4.1866315e-7,0.00046443514,0.364949,0.00029435853,0.6183519,0.0000068905465,0.015863104],"study_design_scores_gemma":[0.00012085446,0.00002299026,0.0029325567,0.000018348448,0.0000052360683,0.000009010494,0.000019169329,0.9928166,0.000024186658,0.0035812843,0.00039464637,0.00005511645],"about_ca_topic_score_codex":0.0000045714155,"about_ca_topic_score_gemma":2.4249303e-7,"teacher_disagreement_score":0.93217725,"about_ca_system_score_codex":0.000005701604,"about_ca_system_score_gemma":0.000015389278,"threshold_uncertainty_score":0.17494701},"labels":[],"label_agreement":null},{"id":"W4401011528","doi":"10.1016/b978-0-443-24010-2.00003-2","title":"Classification","year":2024,"lang":"en","type":"book-chapter","venue":"Elsevier eBooks","topic":"Machine Learning and Data Classification","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 Calgary","funders":"","keywords":"Computer science","score_opus":0.02533283003194519,"score_gpt":0.26476683120612954,"score_spread":0.23943400117418434,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401011528","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":[3.7156587e-7,0.0010619677,0.0022643204,0.0011510119,0.0007908331,0.0002108387,0.000014726024,0.0005910817,0.99391484],"genre_scores_gemma":[0.0005996041,0.00008704659,0.0028154466,0.00024095076,0.0003422548,0.000026973368,0.00009442724,0.000053502357,0.9957398],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99827874,0.000020809988,0.00035977675,0.0007752356,0.0003684577,0.00019698686],"domain_scores_gemma":[0.99815714,0.000053268843,0.00020198962,0.0014117202,0.00007376847,0.00010212279],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00029257598,0.00030756145,0.000252624,0.00023260797,0.000100136735,0.00034129067,0.0009913369,0.0002726676,0.000069497284],"category_scores_gemma":[0.000016279651,0.0002808989,0.00015438601,0.000026405252,0.00006002659,0.000111886286,0.00029171942,0.0006721002,0.004769546],"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":[4.4335022e-7,0.000001339043,5.9174516e-7,0.000029952604,0.000013560288,0.0000058572455,0.00004440296,1.0672335e-7,0.000014458885,0.4757042,0.0004964634,0.5236886],"study_design_scores_gemma":[0.000041187726,0.000021083923,0.000039801896,0.00016199492,0.000030161682,0.000015752305,0.0000011799978,0.0023319183,0.0000036830393,0.10324153,0.8938405,0.00027122005],"about_ca_topic_score_codex":2.7019877e-7,"about_ca_topic_score_gemma":0.0000039453757,"teacher_disagreement_score":0.89334404,"about_ca_system_score_codex":0.00008730345,"about_ca_system_score_gemma":0.00011309215,"threshold_uncertainty_score":0.9999643},"labels":[],"label_agreement":null},{"id":"W4401011540","doi":"10.1016/b978-0-443-24010-2.00006-8","title":"Semisupervised learning methods","year":2024,"lang":"en","type":"book-chapter","venue":"Elsevier eBooks","topic":"Machine Learning and Data Classification","field":"Computer Science","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 Calgary","funders":"","keywords":"Psychology; Computer science; Artificial intelligence","score_opus":0.024571782030373187,"score_gpt":0.30933901268721803,"score_spread":0.28476723065684484,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401011540","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":[2.9561798e-7,0.0024802575,0.031285454,0.00041265096,0.0006927222,0.0001874152,0.000004762477,0.0007858215,0.9641506],"genre_scores_gemma":[0.000043520995,0.000112375536,0.06950611,0.00020560579,0.00030785793,0.000021703869,0.00005389856,0.00007743868,0.92967147],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9978872,0.00012371378,0.00041883474,0.00092470506,0.00035854577,0.0002870252],"domain_scores_gemma":[0.99823415,0.00019271478,0.00019277554,0.0011563494,0.00007902279,0.00014497411],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0009637457,0.00041513616,0.00041711278,0.00025942485,0.00016888393,0.000411542,0.0011251776,0.00032798742,0.000149496],"category_scores_gemma":[0.00006412733,0.00037933988,0.00024097935,0.000036502093,0.00006052949,0.00011061476,0.00061658025,0.001490623,0.0017457248],"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":[8.998871e-7,0.0000015382119,8.991569e-7,0.00009814481,0.00003842574,0.000017193976,0.00020486004,0.0000021620474,0.00007514668,0.23008479,0.00014498267,0.769331],"study_design_scores_gemma":[0.00006869303,0.000038345606,0.000004633412,0.0003021579,0.00005096372,0.000026747537,0.000003010577,0.0068965494,0.000029898629,0.043119002,0.94906414,0.00039583843],"about_ca_topic_score_codex":5.771722e-7,"about_ca_topic_score_gemma":0.0000016062432,"teacher_disagreement_score":0.9489192,"about_ca_system_score_codex":0.00007489721,"about_ca_system_score_gemma":0.00012056401,"threshold_uncertainty_score":0.99986583},"labels":[],"label_agreement":null},{"id":"W4401014350","doi":"10.5194/egusphere-2024-1609-ac2","title":"Reply on RC1","year":2024,"lang":"en","type":"peer-review","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Canadian Avalanche Association; Simon Fraser University","funders":"","keywords":"Chemistry","score_opus":0.042805713276592355,"score_gpt":0.3383457709466101,"score_spread":0.2955400576700178,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401014350","genre_codex":"commentary","genre_gemma":"other","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":[2.9836457e-8,0.012475437,0.03061165,0.57565403,0.00390956,0.00014182313,0.00003443474,0.00061771285,0.37655532],"genre_scores_gemma":[0.0000063170232,0.0021242872,0.0049855122,0.05126851,0.00037536412,0.000027797008,0.0007541254,0.00001610769,0.94044197],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982949,0.00007944327,0.00025206307,0.0007770613,0.0004355416,0.00016100657],"domain_scores_gemma":[0.99786925,0.000096543394,0.00010210092,0.0018029269,0.00006458091,0.00006460732],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00055032724,0.00019894697,0.00025155366,0.00012868393,0.000045671466,0.00025078133,0.0012464303,0.0000933779,0.00042403524],"category_scores_gemma":[0.00022870251,0.00014364735,0.00011247936,0.00032529637,0.000011750773,0.000083293395,0.00031200418,0.00064239313,0.009228329],"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":[1.8371848e-7,0.000008231151,1.6196141e-7,0.0006626246,0.000006989537,0.0000064090127,0.000005307255,5.999599e-7,2.7927345e-7,0.046349954,0.8407131,0.11224618],"study_design_scores_gemma":[0.000018468016,0.00003876566,0.000008894133,0.001749815,0.000017526982,0.000008957326,2.6361866e-7,0.0028385883,0.0000022363208,0.0007187916,0.9944247,0.00017301447],"about_ca_topic_score_codex":0.00015205755,"about_ca_topic_score_gemma":0.000010949491,"teacher_disagreement_score":0.56388664,"about_ca_system_score_codex":0.00004022257,"about_ca_system_score_gemma":0.0001215596,"threshold_uncertainty_score":0.9915431},"labels":[],"label_agreement":null},{"id":"W4401726091","doi":"10.1109/tbiom.2024.3446964","title":"Large-Scale Fully-Unsupervised Re-Identification","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Biometrics Behavior and Identity Science","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Fundação de Amparo à Pesquisa do Estado de São Paulo","keywords":"Identification (biology); Scale (ratio); Computer science; Artificial intelligence; Geography; Cartography; Biology; Ecology","score_opus":0.029697618136944475,"score_gpt":0.323513884743391,"score_spread":0.2938162666064465,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401726091","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":[0.15117696,0.0001629628,0.8457356,0.00044065499,0.0018060516,0.00016531139,0.00005077983,0.00032546365,0.00013623432],"genre_scores_gemma":[0.99485534,0.0002514218,0.004144791,0.000056180495,0.00002486879,0.000041225565,0.000006770851,0.000008870392,0.00061052974],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99757445,0.000050784707,0.0002985603,0.00085984985,0.00088517606,0.00033116207],"domain_scores_gemma":[0.9987889,0.0000848854,0.000053895754,0.0007121352,0.00016484161,0.00019535393],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001561752,0.00014758493,0.000117614676,0.0029283315,0.00084197306,0.0024874303,0.0010094328,0.000075533775,0.000040266787],"category_scores_gemma":[0.00003842184,0.0001428216,0.000072048366,0.011469217,0.00022570581,0.0038249092,0.000016518967,0.00028680178,0.00022774513],"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":[0.00000951843,0.0012467107,0.002608287,0.00014268493,0.000016035856,0.000031669097,0.003082444,0.00015540347,0.18362479,0.01373018,0.00049691665,0.79485536],"study_design_scores_gemma":[0.0009948208,0.00055848825,0.3321965,0.00014636357,0.00023886887,0.00014387205,0.0009505973,0.5657693,0.0813582,0.0014993934,0.014613578,0.0015299743],"about_ca_topic_score_codex":0.000076496355,"about_ca_topic_score_gemma":0.00004924471,"teacher_disagreement_score":0.8436784,"about_ca_system_score_codex":0.00011482692,"about_ca_system_score_gemma":0.00012098104,"threshold_uncertainty_score":0.9985481},"labels":[],"label_agreement":null},{"id":"W4401900459","doi":"10.1007/s41060-024-00624-8","title":"A nearest neighbor-based approach for improving the reliability of multiclass probabilistic classifiers","year":2024,"lang":"en","type":"article","venue":"International Journal of Data Science and Analytics","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Probabilistic logic; Probabilistic classification; k-nearest neighbors algorithm; Reliability (semiconductor); Artificial intelligence; Computer science; Benchmark (surveying); Multiclass classification; Machine learning; Multivariate statistics; Class (philosophy); Pattern recognition (psychology); Support vector machine; Data mining; Naive Bayes classifier","score_opus":0.059764479937032586,"score_gpt":0.34094200030587785,"score_spread":0.28117752036884525,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401900459","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":[0.0057668067,0.00010863691,0.9880603,0.0053952485,0.0003652295,0.00009804415,0.00008280197,0.000012568171,0.00011036804],"genre_scores_gemma":[0.914734,0.000015362923,0.08501385,0.00009924276,0.00010209553,0.0000014968116,0.000018959776,0.0000029771252,0.000012030925],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983611,0.00003813604,0.0003755935,0.00031035423,0.0007933027,0.00012151043],"domain_scores_gemma":[0.99769026,0.0004831797,0.00025436332,0.00054476806,0.0009614111,0.000066028275],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0036692799,0.0000716389,0.000107135915,0.00020761741,0.000109183384,0.0006113321,0.0030305008,0.00002348657,0.0000010893024],"category_scores_gemma":[0.0027533243,0.000043241576,0.000042353426,0.0004799801,0.00044815513,0.0017352575,0.00035112465,0.00017939325,3.7903695e-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":[0.00015898413,0.00065671536,0.0073965457,0.000651634,0.00017692258,0.000026396416,0.0013063473,0.04273214,0.016884938,0.24918751,0.003157773,0.6776641],"study_design_scores_gemma":[0.00015391885,0.00006578201,0.0012812959,0.00003554012,0.000024523406,0.000019940864,0.00008165255,0.99381787,0.00013049014,0.0006849658,0.00365354,0.000050483166],"about_ca_topic_score_codex":0.000024381532,"about_ca_topic_score_gemma":0.0000024445883,"teacher_disagreement_score":0.95108575,"about_ca_system_score_codex":0.00007124379,"about_ca_system_score_gemma":0.000858118,"threshold_uncertainty_score":0.58950895},"labels":[],"label_agreement":null},{"id":"W4402169893","doi":"10.32920/26883781","title":"Stochastic-Based Hyperparameter Selection and Learnability Analysis in Supervised and Unsupervised Learning","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Learnability; Hyperparameter; Machine learning; Artificial intelligence; Computer science; Selection (genetic algorithm); Statistical learning; Unsupervised learning; Supervised learning; Artificial neural network","score_opus":0.016730722462555386,"score_gpt":0.26788233561171443,"score_spread":0.251151613149159,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402169893","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":[0.5347889,0.00030750586,0.46248582,0.0015529925,0.00008473675,0.00023719242,0.000004122728,0.00032865224,0.00021006314],"genre_scores_gemma":[0.9740131,0.000021348478,0.025530145,0.0000827673,0.000026986736,0.000049620034,0.000087798486,0.000016215172,0.00017205233],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99723285,0.00046413473,0.00040283112,0.0013634025,0.00027307638,0.0002636725],"domain_scores_gemma":[0.99877954,0.00033124283,0.000094654344,0.00058974174,0.00008367878,0.00012115119],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010831718,0.0003066535,0.00047149954,0.00096009654,0.000120037155,0.0007589824,0.00036131174,0.00026842175,0.000034931745],"category_scores_gemma":[0.000322048,0.00028081072,0.00011125588,0.0011871487,0.00006324456,0.00014839071,0.0010204836,0.0015062129,0.000012218352],"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":[0.000065648186,0.00020683988,0.23926993,0.0009769173,0.00047465976,0.000011053491,0.0019611244,0.57329524,0.0006972238,0.0063741803,0.000045939054,0.17662123],"study_design_scores_gemma":[0.00022186806,0.000049522725,0.08701354,0.000042987074,0.00015576348,0.0000022379038,0.000032490356,0.91010785,0.000020563692,0.0020117438,0.00006998333,0.00027142162],"about_ca_topic_score_codex":0.0013690523,"about_ca_topic_score_gemma":0.0005483264,"teacher_disagreement_score":0.43922415,"about_ca_system_score_codex":0.00008890963,"about_ca_system_score_gemma":0.00014622425,"threshold_uncertainty_score":0.9999644},"labels":[],"label_agreement":null},{"id":"W4402189204","doi":"10.32920/26883781.v1","title":"Stochastic-Based Hyperparameter Selection and Learnability Analysis in Supervised and Unsupervised Learning","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Learnability; Hyperparameter; Machine learning; Artificial intelligence; Unsupervised learning; Computer science; Selection (genetic algorithm); Supervised learning; Natural language processing; Artificial neural network","score_opus":0.016730722462555386,"score_gpt":0.26788233561171443,"score_spread":0.251151613149159,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402189204","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":[0.5347889,0.00030750586,0.46248582,0.0015529925,0.00008473675,0.00023719242,0.000004122728,0.00032865224,0.00021006314],"genre_scores_gemma":[0.9740131,0.000021348478,0.025530145,0.0000827673,0.000026986736,0.000049620034,0.000087798486,0.000016215172,0.00017205233],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99723285,0.00046413473,0.00040283112,0.0013634025,0.00027307638,0.0002636725],"domain_scores_gemma":[0.99877954,0.00033124283,0.000094654344,0.00058974174,0.00008367878,0.00012115119],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010831718,0.0003066535,0.00047149954,0.00096009654,0.000120037155,0.0007589824,0.00036131174,0.00026842175,0.000034931745],"category_scores_gemma":[0.000322048,0.00028081072,0.00011125588,0.0011871487,0.00006324456,0.00014839071,0.0010204836,0.0015062129,0.000012218352],"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":[0.000065648186,0.00020683988,0.23926993,0.0009769173,0.00047465976,0.000011053491,0.0019611244,0.57329524,0.0006972238,0.0063741803,0.000045939054,0.17662123],"study_design_scores_gemma":[0.00022186806,0.000049522725,0.08701354,0.000042987074,0.00015576348,0.0000022379038,0.000032490356,0.91010785,0.000020563692,0.0020117438,0.00006998333,0.00027142162],"about_ca_topic_score_codex":0.0013690523,"about_ca_topic_score_gemma":0.0005483264,"teacher_disagreement_score":0.43922415,"about_ca_system_score_codex":0.00008890963,"about_ca_system_score_gemma":0.00014622425,"threshold_uncertainty_score":0.9999644},"labels":[],"label_agreement":null},{"id":"W4402745439","doi":"10.1101/2024.09.19.613953","title":"Discovering Governing Equations of Biological Systems through Representation Learning and Sparse Model Discovery","year":2024,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Machine Learning and Data Classification","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":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Representation (politics); Computer science; Sparse approximation; Data science; Artificial intelligence; Machine learning; Political science","score_opus":0.04477838576575742,"score_gpt":0.277032341100858,"score_spread":0.23225395533510057,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402745439","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":[0.2910931,0.0019667803,0.70513666,0.00021828068,0.0006679152,0.0003296702,0.000118312535,0.00042469712,0.000044597407],"genre_scores_gemma":[0.9791172,0.0006241406,0.01989388,0.000015899715,0.00017055158,0.00010249998,0.000003067895,0.000047238536,0.000025504703],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970638,0.0002791155,0.00064413477,0.0012379489,0.00043813308,0.00033686135],"domain_scores_gemma":[0.9978069,0.00026103097,0.000633096,0.001028287,0.0001701896,0.00010051474],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00072836806,0.0003858478,0.00049257255,0.00018982662,0.00019670685,0.0010260236,0.00064502965,0.00031625666,0.0000015378948],"category_scores_gemma":[0.000703728,0.00036729235,0.00011224031,0.0005026267,0.00011352424,0.0007876975,0.0019483882,0.0011214224,0.000019571833],"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":[0.000025740663,0.00014780893,0.017254239,0.001682511,0.0002487302,0.0000319231,0.00032894828,0.22784488,0.39883092,0.35345986,0.00011104521,0.000033395634],"study_design_scores_gemma":[0.00017380586,0.000044939978,0.0072060614,0.0007158272,0.000064538064,4.9759993e-8,0.000022147007,0.98525405,0.0054132044,0.000105085644,0.0004888258,0.00051145116],"about_ca_topic_score_codex":0.00026250153,"about_ca_topic_score_gemma":0.0000015177245,"teacher_disagreement_score":0.7574092,"about_ca_system_score_codex":0.00014487554,"about_ca_system_score_gemma":0.00032605662,"threshold_uncertainty_score":0.9998779},"labels":[],"label_agreement":null},{"id":"W4402747738","doi":"10.1371/journal.pdig.0000299","title":"Boosting efficiency in a clinical literature surveillance system with LightGBM","year":2024,"lang":"en","type":"article","venue":"PLOS Digital Health","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; Impact","funders":"Mitacs","keywords":"Boosting (machine learning); Computer science; Artificial intelligence","score_opus":0.022648504160431033,"score_gpt":0.3076604598499421,"score_spread":0.2850119556895111,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402747738","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":[0.37181908,0.017918332,0.52772206,0.025838312,0.0019755487,0.0016878125,0.00023412325,0.0055478234,0.047256935],"genre_scores_gemma":[0.9981646,0.000028679793,0.0013442276,0.00013817518,0.000104990795,0.000009508359,0.00004650959,0.000011375492,0.00015192923],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982917,0.00013724969,0.00044418752,0.00055480964,0.0002689027,0.00030319925],"domain_scores_gemma":[0.998948,0.000344029,0.00009399473,0.0004354265,0.00004169631,0.00013686194],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007664636,0.0001227086,0.0002126676,0.00013129228,0.00007652452,0.0010277078,0.00039108325,0.000051170457,4.6388854e-7],"category_scores_gemma":[0.00011202132,0.000088176,0.000034712757,0.00093522493,0.000024647894,0.0007163024,0.000085612526,0.00040490096,0.000080837606],"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":[0.00005856879,0.00076017145,0.21597326,0.005328368,0.000048498176,0.00050199404,0.004517256,0.00017529058,0.000008506008,0.25361836,0.0015014361,0.51750827],"study_design_scores_gemma":[0.0005070365,0.00095732615,0.11496833,0.005780135,0.0000023009281,0.00021822829,0.00011615474,0.8667079,0.000003794976,0.00017718285,0.010109607,0.00045195853],"about_ca_topic_score_codex":0.000022526994,"about_ca_topic_score_gemma":0.000022815175,"teacher_disagreement_score":0.8665327,"about_ca_system_score_codex":0.000100664976,"about_ca_system_score_gemma":0.000288786,"threshold_uncertainty_score":0.99102104},"labels":[],"label_agreement":null},{"id":"W4402781705","doi":"10.1109/ieeedata.2024.3421108","title":"Editorial: Enhancing Reproducibility Through Understanding Datasets","year":2024,"lang":"en","type":"editorial","venue":"IEEE data descriptions.","topic":"Machine Learning and Data Classification","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":"Simon Fraser University","funders":"","keywords":"Reproducibility; Computer science; Data science; Chemistry; Chromatography","score_opus":0.10656442367567341,"score_gpt":0.349820396448238,"score_spread":0.24325597277256455,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402781705","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[2.1197403e-7,0.0004932541,0.36262515,0.00050702115,0.6189731,0.00020794515,0.016238017,0.0006690194,0.00028628702],"genre_scores_gemma":[0.00005927156,0.00048814208,0.013404718,0.000049814276,0.87985957,0.000035721885,0.10559794,0.00006400466,0.0004407912],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99095756,0.00044716394,0.00094226864,0.0052837967,0.001784321,0.00058487715],"domain_scores_gemma":[0.97823334,0.000930408,0.00043118987,0.020041477,0.000209335,0.00015427335],"candidate_categories":["metaresearch","metaepi_narrow","scholarly_communication","open_science","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.006379049,0.0005498502,0.0005481589,0.00025036518,0.0005151907,0.0024482955,0.006814239,0.0008575649,0.000025103795],"category_scores_gemma":[0.008469668,0.0005389613,0.000103387516,0.00089180336,0.00013864659,0.004238645,0.0026433524,0.0025420666,0.0010406497],"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":[0.0000075547887,0.00005992672,0.0000010542052,0.0002510437,0.000057519544,0.00001106876,0.00016836793,0.0000058548712,0.00017832784,0.003219983,0.99536484,0.00067442725],"study_design_scores_gemma":[0.00016029432,0.000033750643,0.0000011366207,0.00029942978,0.00011402391,0.000004919723,0.000047022153,0.0033259213,0.000029592342,0.007347045,0.98809636,0.0005404967],"about_ca_topic_score_codex":0.00094466924,"about_ca_topic_score_gemma":0.00043137383,"teacher_disagreement_score":0.34922042,"about_ca_system_score_codex":0.00076492043,"about_ca_system_score_gemma":0.001074278,"threshold_uncertainty_score":0.9998824},"labels":[],"label_agreement":null},{"id":"W4402863272","doi":"10.1037/xge0001655","title":"Different methods elicit different belief distributions.","year":2024,"lang":"en","type":"article","venue":"Journal of Experimental Psychology General","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Booth University College","funders":"","keywords":"Psychology; Cognitive psychology; Social psychology","score_opus":0.03750134573984761,"score_gpt":0.433913119916343,"score_spread":0.3964117741764954,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402863272","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":[0.26106036,0.006249467,0.72400445,0.004235613,0.0033592149,0.000056873327,0.000006253604,0.00007025182,0.00095753255],"genre_scores_gemma":[0.94358367,0.00013648652,0.05489504,0.0004949816,0.00055275805,0.000008552605,0.000019303629,0.000012096293,0.000297094],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9982897,0.00044449075,0.00049500004,0.00031529486,0.00022567461,0.00022986149],"domain_scores_gemma":[0.9991447,0.00009754084,0.00016973948,0.00039904166,0.00004369575,0.00014530339],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00046585736,0.00017788283,0.00025383133,0.00019698574,0.00011764598,0.00018157136,0.00070042745,0.00008710625,0.0001050098],"category_scores_gemma":[0.000032725653,0.00012399664,0.00019118139,0.00018442338,0.00006183621,0.00029429115,0.00013765595,0.00050311117,0.00003012876],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000041661777,0.0006867847,0.00085466704,0.000009958209,0.00014222393,0.00006723945,0.0006083142,0.0000131347415,0.77643955,0.0905827,0.026000697,0.10455305],"study_design_scores_gemma":[0.0033090217,0.0038639647,0.14530899,0.00021723215,0.00011738348,0.00388904,0.00020198204,0.06331475,0.47219464,0.016223267,0.2901613,0.0011984435],"about_ca_topic_score_codex":0.0000033318483,"about_ca_topic_score_gemma":3.8875314e-7,"teacher_disagreement_score":0.6825233,"about_ca_system_score_codex":0.00010142575,"about_ca_system_score_gemma":0.000025140722,"threshold_uncertainty_score":0.5056436},"labels":[],"label_agreement":null},{"id":"W4403069814","doi":"10.1007/978-3-031-72117-5_19","title":"Detecting Noisy Labels with Repeated Cross-Validations","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Machine Learning and Data Classification","field":"Computer Science","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":"Sunnybrook Hospital; University of Toronto","funders":"","keywords":"Computer science; Artificial intelligence; Speech recognition; Computer vision","score_opus":0.019106172318709445,"score_gpt":0.2828571323118246,"score_spread":0.26375095999311515,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403069814","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":[0.0002703976,0.00024707938,0.98715883,0.001112829,0.00093435944,0.00025459388,0.000009432824,0.0005480767,0.009464409],"genre_scores_gemma":[0.46080095,0.00003123239,0.53131783,0.0008624782,0.0006667173,0.000026034933,0.000058900598,0.00009265886,0.0061431816],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99634165,0.00003236652,0.0004697321,0.001785326,0.0008612682,0.000509635],"domain_scores_gemma":[0.9971607,0.0003888501,0.00027746856,0.0017391089,0.0002926788,0.00014123623],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0010105375,0.0004420379,0.00033994278,0.0008046374,0.00042208927,0.0019500556,0.0024039608,0.00023953746,0.00002187589],"category_scores_gemma":[0.00016843362,0.00035739946,0.00007509415,0.0010796153,0.00048531202,0.0007506652,0.0009368806,0.0011913965,0.00017929502],"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":[0.000009902273,0.000030116213,0.00064748724,0.00012667084,0.0000328399,0.00019610039,0.0011391881,0.0648354,0.00053699204,0.09499523,0.000023724542,0.83742636],"study_design_scores_gemma":[0.0002849321,0.00026068446,0.0007838272,0.0008485552,0.00002223925,0.00025259503,2.5655555e-7,0.9100974,0.0018171336,0.076543115,0.0081244605,0.0009647918],"about_ca_topic_score_codex":0.000048994963,"about_ca_topic_score_gemma":0.00011310663,"teacher_disagreement_score":0.845262,"about_ca_system_score_codex":0.00022724994,"about_ca_system_score_gemma":0.00043114094,"threshold_uncertainty_score":0.9998878},"labels":[],"label_agreement":null},{"id":"W4403421377","doi":"10.1109/iiai-aai63651.2024.00052","title":"Minimizing Model Misclassification Using Regularized Loss Interpretability","year":2024,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Interpretability; Computer science; Artificial intelligence","score_opus":0.03906841556291794,"score_gpt":0.3097947442682105,"score_spread":0.27072632870529256,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403421377","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":[0.013835008,0.00011319109,0.97743386,0.0027613088,0.00023835477,0.000090788,0.0000022883307,0.0006787752,0.00484641],"genre_scores_gemma":[0.7282426,0.0000057910806,0.2708508,0.00007952176,0.000028714077,0.000005998175,0.0000112376,0.0000073574815,0.0007680049],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987607,0.00009206222,0.00024358876,0.0005409623,0.00019411322,0.00016857036],"domain_scores_gemma":[0.9989792,0.00009245487,0.000042688254,0.0007733789,0.0000490875,0.000063152336],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00056314934,0.00011087994,0.00010453739,0.00011403757,0.00009959801,0.00047620595,0.000517722,0.000062330735,0.000022598077],"category_scores_gemma":[0.00009575998,0.00009411045,0.000063879845,0.00034619248,0.000040575447,0.0007743875,0.00015142081,0.0001731475,0.00006188241],"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":[0.000012538474,0.000075903576,0.000552892,0.0001417726,0.000030247302,0.0000069553835,0.0015769454,0.0076129516,0.0745563,0.746246,0.00090331916,0.16828422],"study_design_scores_gemma":[0.00005755388,0.0000066251755,0.00029045175,0.000032934997,0.00000705368,0.000011954099,0.000015551304,0.9901289,0.00079155946,0.0064355796,0.0021046621,0.00011717762],"about_ca_topic_score_codex":0.00003262952,"about_ca_topic_score_gemma":0.0000032156013,"teacher_disagreement_score":0.98251593,"about_ca_system_score_codex":0.000085513646,"about_ca_system_score_gemma":0.000115419476,"threshold_uncertainty_score":0.4592065},"labels":[],"label_agreement":null},{"id":"W4403580911","doi":"10.48550/arxiv.2410.13577","title":"Generalization Bounds via Meta-Learned Model Representations: PAC-Bayes and Sample Compression Hypernetworks","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Generalization; Sample (material); Compression (physics); Artificial intelligence; Computer science; Mathematics; Physics; Mathematical analysis","score_opus":0.1479020429098674,"score_gpt":0.24657071544103237,"score_spread":0.09866867253116499,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403580911","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":[0.016884388,0.000734929,0.9799543,0.00061303476,0.00028992153,0.00023142388,0.000045745684,0.0004366048,0.0008096466],"genre_scores_gemma":[0.9732374,0.00082473573,0.023474421,0.000109985514,0.00008066318,0.0000052141686,0.00036805889,0.000025374915,0.0018741409],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977326,0.00028296516,0.00024656055,0.0013642445,0.00013583482,0.00023780305],"domain_scores_gemma":[0.99802387,0.00021790821,0.0002453151,0.0012471182,0.00012675721,0.00013904306],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00033998385,0.00030317405,0.00034823283,0.00027647728,0.00027125448,0.00047587263,0.0008400736,0.00026578046,0.000026822083],"category_scores_gemma":[0.00009074001,0.00030080107,0.00017059363,0.00050291704,0.000089056484,0.00038465238,0.0022388527,0.00064292084,0.000028163204],"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":[0.000008335491,0.00003413042,0.0008516784,0.00007884279,0.00022673991,0.000011908976,0.0002202683,0.80985516,0.000054391097,0.1855313,0.00092516193,0.0022020624],"study_design_scores_gemma":[0.00012677292,0.000012865939,0.00031594577,0.000033058735,0.0003574219,0.000002861834,0.000014221813,0.77187574,0.000016610544,0.22645724,0.0005492055,0.00023807272],"about_ca_topic_score_codex":0.0006160666,"about_ca_topic_score_gemma":0.000066629254,"teacher_disagreement_score":0.9564799,"about_ca_system_score_codex":0.00008147372,"about_ca_system_score_gemma":0.00010562343,"threshold_uncertainty_score":0.9999444},"labels":[],"label_agreement":null},{"id":"W4403640253","doi":"10.2139/ssrn.4995227","title":"Fedelr: When Federated Learning Meets Learning with Noisy Labels","year":2024,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Machine Learning and Data Classification","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":"Western University","funders":"","keywords":"Computer science; Federated learning; Artificial intelligence; Machine learning","score_opus":0.010078825890084655,"score_gpt":0.24800777930658957,"score_spread":0.2379289534165049,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403640253","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":[0.04360099,0.015751226,0.9053299,0.02131795,0.0014087617,0.000514709,0.000004692374,0.0019833415,0.0100884205],"genre_scores_gemma":[0.9749038,0.002967824,0.005050577,0.000100008765,0.0005918283,0.000028415972,0.00010829112,0.000108027874,0.016141182],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9939631,0.0007722825,0.0006018353,0.0011489427,0.0008572781,0.00265652],"domain_scores_gemma":[0.99807537,0.00012793155,0.0007061602,0.0005901613,0.00029370256,0.00020670122],"candidate_categories":["metaepi_narrow","scholarly_communication","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.003869737,0.00058049173,0.0005227042,0.0004455384,0.0010462527,0.002910884,0.0016421258,0.00036421893,0.000028048335],"category_scores_gemma":[0.00024076819,0.00047582004,0.00019274802,0.00042751266,0.000056054512,0.00038468477,0.001421246,0.022914706,0.0002743785],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014573705,0.00018413154,0.0032132433,0.0003277209,0.0017233404,0.00019937144,0.0034608997,0.059895456,0.0008884069,0.44100598,0.0012637279,0.48769197],"study_design_scores_gemma":[0.0016358519,0.002073777,0.0005666002,0.0014874748,0.0003509611,0.0038318834,0.0016334517,0.4701711,0.00016435546,0.41820756,0.09746518,0.002411798],"about_ca_topic_score_codex":0.00027354746,"about_ca_topic_score_gemma":0.00066028454,"teacher_disagreement_score":0.93130285,"about_ca_system_score_codex":0.0012974964,"about_ca_system_score_gemma":0.005795278,"threshold_uncertainty_score":0.9998409},"labels":[],"label_agreement":null},{"id":"W4403786036","doi":"10.2139/ssrn.5000604","title":"Large-Scale Multi-Objective Feature Selection: A Multi-Phase Search Space Shrinking Approach","year":2024,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brock University; University of Ontario Institute of Technology","funders":"","keywords":"Scale (ratio); Feature selection; Selection (genetic algorithm); Feature (linguistics); Resizing; Space (punctuation); Computer science; Phase (matter); Scale space; Pattern recognition (psychology); Artificial intelligence; Mathematical optimization; Algorithm; Mathematics; Data mining; Physics; Geography; Cartography; Economics","score_opus":0.02129647725193712,"score_gpt":0.316415797269649,"score_spread":0.2951193200177119,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403786036","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":[0.0049028625,0.0074313246,0.9820301,0.0028697622,0.0008939165,0.0004918624,0.000025976347,0.0005105907,0.00084360567],"genre_scores_gemma":[0.73696196,0.0022853506,0.24244997,0.00013109653,0.001778708,0.00011153606,0.00022589548,0.00015564603,0.015899817],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.993481,0.0006665479,0.00045573534,0.0015041815,0.00081933243,0.0030732357],"domain_scores_gemma":[0.9980469,0.00006754586,0.0003756033,0.00092558283,0.00034272237,0.00024166808],"candidate_categories":["metaepi_narrow","scholarly_communication","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.004538423,0.0005871129,0.0005141037,0.00065016,0.00074534025,0.0013138395,0.002026051,0.00058196863,0.00000926506],"category_scores_gemma":[0.00011260975,0.0005320905,0.00038161347,0.00093903596,0.000056242396,0.00035791704,0.0019491803,0.021143826,0.00010705315],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00036348528,0.005938219,0.003269148,0.0012604493,0.0033316927,0.00014273517,0.042573765,0.025740752,0.0018900338,0.6955885,0.0032870953,0.21661407],"study_design_scores_gemma":[0.0019125666,0.00028766217,0.00045230932,0.00019489393,0.00010264423,0.0015315468,0.0024044074,0.958244,0.00010044239,0.030729879,0.0033157016,0.0007239321],"about_ca_topic_score_codex":0.00013269931,"about_ca_topic_score_gemma":0.0007257674,"teacher_disagreement_score":0.9325033,"about_ca_system_score_codex":0.0022670056,"about_ca_system_score_gemma":0.0057003275,"threshold_uncertainty_score":0.9999364},"labels":[],"label_agreement":null},{"id":"W4403850457","doi":"10.1145/3700791","title":"AugmenToxic: Leveraging Reinforcement Learning to Optimize LLM Instruction Fine-Tuning for Data Augmentation to Enhance Toxicity Detection","year":2024,"lang":"en","type":"article","venue":"ACM Transactions on the Web","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Concordia University","funders":"Canada Research Chairs","keywords":"Computer science; Reinforcement learning; Human–computer interaction; Machine learning","score_opus":0.04766722686026172,"score_gpt":0.32306940240138293,"score_spread":0.27540217554112123,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403850457","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":[0.011748782,0.000018282706,0.9732627,0.012966989,0.0007946905,0.00061045034,0.000013747829,0.0004393369,0.00014498056],"genre_scores_gemma":[0.93168145,0.000022820686,0.06622511,0.00044664793,0.00009545508,0.00024720942,0.00006422222,0.000020461146,0.0011966075],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983237,0.00012453261,0.00029757968,0.00068254076,0.0003118733,0.00025980276],"domain_scores_gemma":[0.9980989,0.0003784693,0.00007005772,0.0012967637,0.00005930321,0.0000964994],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00093793974,0.00017307095,0.00011441295,0.00029023446,0.000742303,0.0005067751,0.0011333008,0.00005168262,0.000056018842],"category_scores_gemma":[0.0002523222,0.00014934703,0.0000567878,0.00077806064,0.000014029315,0.00087321457,0.00007930736,0.00034771248,0.00012030121],"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":[0.000049506732,0.000026210877,0.0000018203825,0.000029088347,0.00003644472,4.5488622e-7,0.0011963932,0.25133714,0.05837989,0.00047655567,0.0004053351,0.6880612],"study_design_scores_gemma":[0.00016439095,0.00025507106,0.0000310963,0.00010078192,0.000026730597,0.000007119275,0.00019454792,0.9225933,0.051145263,0.00019449256,0.025098855,0.00018834604],"about_ca_topic_score_codex":0.00009639153,"about_ca_topic_score_gemma":0.000108380336,"teacher_disagreement_score":0.91993266,"about_ca_system_score_codex":0.00020745154,"about_ca_system_score_gemma":0.000065915854,"threshold_uncertainty_score":0.6090196},"labels":[],"label_agreement":null},{"id":"W4403889819","doi":"10.1007/978-3-031-72754-2_3","title":"Federated Learning with Local Openset Noisy Labels","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Machine Learning and Data Classification","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":"Vector Institute; University of British Columbia","funders":"","keywords":"Computer science; Artificial intelligence","score_opus":0.014118104488706065,"score_gpt":0.25032610768997604,"score_spread":0.23620800320126997,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403889819","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":[0.000042959982,0.00039768175,0.98410726,0.0019888354,0.0007457901,0.00025470197,0.0000050986905,0.00045994626,0.011997748],"genre_scores_gemma":[0.7240472,0.000076282515,0.26225808,0.0019112112,0.0006132644,0.000023459008,0.00011481624,0.0001259225,0.010829806],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99609864,0.0000550172,0.0004103164,0.0018695323,0.00097299635,0.0005934776],"domain_scores_gemma":[0.99813116,0.00033427792,0.00022244937,0.0009060558,0.00022636236,0.00017972697],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0009076838,0.00053198216,0.00045122686,0.0006794013,0.00042106287,0.001835894,0.0021255752,0.00027571406,0.00003108811],"category_scores_gemma":[0.00007170017,0.00041721045,0.00006720388,0.00089047564,0.00061244925,0.0006237927,0.0011702077,0.0018752349,0.00035192806],"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":[0.0000107559545,0.00001882605,0.00007643803,0.00006598876,0.000019545194,0.00025229246,0.00041928887,0.06959972,0.00008601543,0.04067275,0.00006556238,0.8887128],"study_design_scores_gemma":[0.00021794082,0.000327832,0.000111409216,0.00061336363,0.000012310839,0.00019182822,4.1123613e-7,0.9572393,0.00028607858,0.019533606,0.020786688,0.0006792629],"about_ca_topic_score_codex":0.00006580443,"about_ca_topic_score_gemma":0.00016880831,"teacher_disagreement_score":0.88803357,"about_ca_system_score_codex":0.00024964436,"about_ca_system_score_gemma":0.0005879631,"threshold_uncertainty_score":0.999828},"labels":[],"label_agreement":null},{"id":"W4404145701","doi":"10.1007/978-3-031-73125-9_16","title":"A Comparative Study of Machine Learning Algorithms on Datasets of Varying Sizes","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in networks and systems","topic":"Machine Learning and Data Classification","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":"Dalhousie University","funders":"","keywords":"Computer science; Machine learning; Artificial intelligence; Algorithm","score_opus":0.03255842546738884,"score_gpt":0.2865262340275536,"score_spread":0.25396780856016477,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404145701","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":[0.001495484,0.048680034,0.91546154,0.00016608383,0.00235358,0.002419165,0.00040179555,0.00026479806,0.028757524],"genre_scores_gemma":[0.9979297,0.00020551613,0.00032923158,0.000011981231,0.0001683856,0.000012559894,0.00032683663,0.000023074283,0.0009927457],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99815065,0.00015764656,0.00059205556,0.0005959398,0.00032406749,0.00017965405],"domain_scores_gemma":[0.99804974,0.0008242815,0.00046910648,0.0005649747,0.000047557653,0.00004432381],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005708615,0.0003080514,0.00078482536,0.00025412903,0.00007395496,0.00010876833,0.00041252736,0.00021468672,0.0000040377504],"category_scores_gemma":[0.000040649924,0.00024044748,0.000049920083,0.00014633147,0.000046519464,0.000070656475,0.0002544556,0.0009832518,0.0000026146809],"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":[0.000056473535,0.000108646294,0.000591148,0.0005229013,0.0002514565,0.000048048634,0.003580226,0.9268421,0.000017543269,0.03067932,0.00011422713,0.037187893],"study_design_scores_gemma":[0.0003013546,0.000596574,0.000073547366,0.0011145389,0.000038927785,0.0000118775615,0.000022541339,0.9928004,0.0000036853812,0.0007453079,0.004067922,0.00022329201],"about_ca_topic_score_codex":0.0004589912,"about_ca_topic_score_gemma":0.00012965733,"teacher_disagreement_score":0.9964342,"about_ca_system_score_codex":0.000032924712,"about_ca_system_score_gemma":0.000023805642,"threshold_uncertainty_score":0.9805164},"labels":[],"label_agreement":null},{"id":"W4404200958","doi":"10.1007/978-3-031-71452-8_10","title":"Performance Metrics of Binary Classifiers","year":2024,"lang":"en","type":"book-chapter","venue":"","topic":"Machine Learning and Data Classification","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":"Jewish General Hospital","funders":"","keywords":"Binary number; Artificial intelligence; Computer science; Pattern recognition (psychology); Mathematics; Arithmetic","score_opus":0.03069373376124343,"score_gpt":0.2505954583085049,"score_spread":0.21990172454726145,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404200958","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":[0.00002202177,0.0006213546,0.01413954,0.000534915,0.0005222532,0.00007615927,0.000010132096,0.00023557518,0.983838],"genre_scores_gemma":[0.017562278,0.00063711713,0.008664511,0.00006826256,0.000069312126,0.0000026418716,0.000052203017,0.000023508539,0.9729202],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987783,0.0000075745074,0.0002998632,0.00043025418,0.00035732772,0.00012669973],"domain_scores_gemma":[0.9987705,0.000075875505,0.00017207868,0.000847567,0.00007567748,0.00005834538],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002470713,0.00018930448,0.00022335729,0.0005282735,0.000040036,0.00006626231,0.00084038475,0.00019292174,0.00013554873],"category_scores_gemma":[0.000019739677,0.00015667758,0.00009974474,0.00018024984,0.000055515,0.00019276878,0.0003347645,0.00041631729,0.0008777524],"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":[0.0000014502909,0.000005467339,0.000019623436,0.00015003791,0.00002442352,0.0000044822195,0.000028453507,0.000016058322,0.000035378092,0.9273167,0.012310504,0.060087424],"study_design_scores_gemma":[0.000059862792,0.0001392333,0.00023519911,0.00015501147,0.00003196471,0.000009576488,0.0000031042607,0.18709931,0.0000651771,0.006351148,0.805571,0.00027942017],"about_ca_topic_score_codex":0.000006838979,"about_ca_topic_score_gemma":9.3219086e-7,"teacher_disagreement_score":0.92096555,"about_ca_system_score_codex":0.00004239726,"about_ca_system_score_gemma":0.000090814276,"threshold_uncertainty_score":0.99990016},"labels":[],"label_agreement":null},{"id":"W4404307781","doi":"10.36227/techrxiv.173152638.87399189/v1","title":"Unified Bayesian representation for high-dimensional multi-modal biomedical data for small-sample classification","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Agencia Estatal de Investigación; Canadian Institutes of Health Research; Genentech; National Institutes of Health; Northern California Institute for Research and Education; Servier; BioClinica; U.S. Department of Defense; Alzheimer's Disease Neuroimaging Initiative; University of Southern California; Bristol-Myers Squibb; Eli Lilly and Company; Biogen; Eisai; Alzheimer's Association","keywords":"Modal; Bayesian probability; Computer science; Representation (politics); Sample (material); Pattern recognition (psychology); Artificial intelligence; Small data; Data mining; Machine learning; Materials science; Physics","score_opus":0.15135621558474255,"score_gpt":0.37842567332340016,"score_spread":0.2270694577386576,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404307781","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":[0.00023866676,0.00007615494,0.97388566,0.018222755,0.0023230654,0.0016588875,0.0028164007,0.00067286217,0.00010556597],"genre_scores_gemma":[0.07179409,0.000014556176,0.8540186,0.00022123587,0.0005624042,0.0006166376,0.071566515,0.00004654588,0.0011593726],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9959807,0.00015463997,0.00074083323,0.0022978815,0.00044867233,0.00037727857],"domain_scores_gemma":[0.9943067,0.0011953387,0.0003706023,0.0036515323,0.00028930663,0.00018653744],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0013351875,0.00035238353,0.00037416827,0.00035960914,0.00023334534,0.00063784525,0.002822769,0.00044505202,0.000022782897],"category_scores_gemma":[0.001536479,0.00031709435,0.00013630178,0.00032943764,0.00009159888,0.0002586096,0.0034166758,0.00057402626,0.000038254202],"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":[0.00010735439,0.00047939105,0.000093061855,0.0009376286,0.00021524094,0.0000027028384,0.00018754567,0.00077475945,0.0021431867,0.7017949,0.066718005,0.22654621],"study_design_scores_gemma":[0.0006347198,0.00006664421,0.0012405841,0.00007020725,0.00007289464,0.0000030483804,0.000020525104,0.9187003,0.00011375527,0.06447006,0.014263263,0.00034402029],"about_ca_topic_score_codex":0.0010612172,"about_ca_topic_score_gemma":0.00017750295,"teacher_disagreement_score":0.91792554,"about_ca_system_score_codex":0.00011561271,"about_ca_system_score_gemma":0.0006033749,"threshold_uncertainty_score":0.9999281},"labels":[],"label_agreement":null},{"id":"W4404373849","doi":"10.1145/3702985","title":"A Machine Learning Approach for Automated Filling of Categorical Fields in Data Entry Forms—RCR Report","year":2024,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"BNP Paribas Cardif","keywords":"Computer science; Categorical variable; Artificial intelligence; Software engineering; Machine learning; Programming language; Data mining","score_opus":0.10919899534806334,"score_gpt":0.34966833276716797,"score_spread":0.24046933741910465,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404373849","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":[0.00084969925,0.00055745867,0.9971245,0.00033353624,0.00024978226,0.0001134023,0.000019875106,0.0007417748,0.000009993619],"genre_scores_gemma":[0.19632281,0.00011855621,0.8032177,0.0000147222445,0.000018429186,0.000034250752,0.00016847468,0.000012550043,0.00009250091],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988801,0.00011301072,0.00028612933,0.00045895853,0.00008284274,0.00017898099],"domain_scores_gemma":[0.9974139,0.0018295202,0.000042703665,0.0006469266,0.000021966993,0.000045012897],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013151463,0.000117787924,0.00021985176,0.00026576928,0.000056192,0.000035986974,0.000428891,0.00013254421,0.0000024106241],"category_scores_gemma":[0.0016075625,0.00010756443,0.000039491784,0.00033054344,0.000015613934,0.00019914149,0.000036679376,0.0004293141,4.967367e-7],"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":[0.00004217134,0.00011895179,0.0004663901,0.00085585075,0.00011753615,0.00004929236,0.0011454328,0.64542603,0.00050220615,0.006406961,0.00011310841,0.3447561],"study_design_scores_gemma":[0.00016878643,0.00006536105,0.00030989834,0.000029467808,0.000018681721,0.00018572401,0.0000139706635,0.9932702,0.00018790831,0.00028293798,0.005359815,0.00010723438],"about_ca_topic_score_codex":0.00007725381,"about_ca_topic_score_gemma":0.0000057494144,"teacher_disagreement_score":0.3478442,"about_ca_system_score_codex":0.000019138199,"about_ca_system_score_gemma":0.000041129606,"threshold_uncertainty_score":0.43863502},"labels":[],"label_agreement":null},{"id":"W4404554853","doi":"10.32388/cyzn0g","title":"Sample Compression Hypernetworks: From Generalization Bounds to Meta-Learning","year":2024,"lang":"en","type":"preprint","venue":"Qeios","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Generalization; Sample (material); Set (abstract data type); Computer science; Compression (physics); Data compression; Artificial intelligence; Machine learning; Theoretical computer science; Mathematics","score_opus":0.04949213236746966,"score_gpt":0.30202128412540924,"score_spread":0.25252915175793955,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404554853","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":[0.0053103017,0.002082135,0.9853815,0.0031459173,0.0017448907,0.00028411526,0.000082890685,0.00088168756,0.001086578],"genre_scores_gemma":[0.73920745,0.00017059206,0.25181046,0.001019566,0.0013623894,0.00026101506,0.0036644638,0.0000795446,0.0024245095],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99747545,0.0003428446,0.0003736965,0.0011052509,0.00043871545,0.00026405064],"domain_scores_gemma":[0.9981161,0.0002360498,0.00019612738,0.0012108274,0.00008915724,0.00015176805],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00041782964,0.00031753548,0.0004169873,0.00019380914,0.0001833314,0.0011084285,0.0012310651,0.00025063567,0.0001581814],"category_scores_gemma":[0.000235199,0.00027309745,0.0001882143,0.00034038152,0.000015841542,0.00013068113,0.0032057976,0.0010444472,0.00046770347],"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":[0.00001611209,0.00012464702,0.0027961605,0.00026872035,0.0012975981,0.000018813531,0.0043244786,0.6508856,0.0015235612,0.074655324,0.08043706,0.18365195],"study_design_scores_gemma":[0.000061092614,0.000023573708,0.0012042419,0.000112888614,0.0002351971,0.0000011409398,0.000008790685,0.7801943,0.00010074596,0.01724739,0.20048812,0.00032255283],"about_ca_topic_score_codex":0.0014773095,"about_ca_topic_score_gemma":0.00004386453,"teacher_disagreement_score":0.73389715,"about_ca_system_score_codex":0.00008175794,"about_ca_system_score_gemma":0.00009487355,"threshold_uncertainty_score":0.9999721},"labels":[],"label_agreement":null},{"id":"W4404573441","doi":"10.48550/arxiv.2411.11983","title":"The occlusion process: improving sampler performance with parallel computation and variational approximation","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Engineering and Physical Sciences Research Council; Natural Sciences and Engineering Research Council of Canada; UK Research and Innovation","keywords":"Computation; Process (computing); Computer science; Mathematical optimization; Mathematics; Algorithm","score_opus":0.03453653353446975,"score_gpt":0.19306684774955532,"score_spread":0.15853031421508557,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404573441","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":[0.12666517,0.000061983104,0.8716364,0.0005251598,0.00014406127,0.00024148391,0.0000052495734,0.00018249925,0.00053798384],"genre_scores_gemma":[0.98824346,0.000087786946,0.0112197315,0.000027705491,0.000046657886,0.000002785155,0.00009697323,0.00001011506,0.00026480577],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988076,0.00008464093,0.00014180857,0.0006788846,0.00012986934,0.00015720064],"domain_scores_gemma":[0.99904156,0.00012787626,0.0002326696,0.00039502553,0.00015036415,0.000052524214],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037589384,0.00017224996,0.00011013179,0.00011272253,0.00046632392,0.00040520905,0.0005085959,0.00010298537,0.0000014000329],"category_scores_gemma":[0.000030304815,0.00013165546,0.000027182203,0.00032953915,0.000067039655,0.0003780454,0.0008367415,0.00046928544,0.0000160247],"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":[0.00005569772,0.00003228015,0.0034284112,0.00042144465,0.000045726665,0.0000103025395,0.00075707235,0.7144927,0.000013872549,0.25515243,0.0000676432,0.02552241],"study_design_scores_gemma":[0.00017476984,0.00003982856,0.011505696,0.000075013784,0.000029809276,0.000008025989,0.00004765414,0.9551439,0.000003577943,0.032697786,0.00010484492,0.00016908099],"about_ca_topic_score_codex":0.00005269328,"about_ca_topic_score_gemma":0.000019120704,"teacher_disagreement_score":0.8615783,"about_ca_system_score_codex":0.00008229938,"about_ca_system_score_gemma":0.00019070035,"threshold_uncertainty_score":0.53687537},"labels":[],"label_agreement":null},{"id":"W4404638964","doi":"10.1007/s11704-024-3575-5","title":"Soft-GNN: towards robust graph neural networks via self-adaptive data utilization","year":2024,"lang":"en","type":"article","venue":"Frontiers of Computer Science","topic":"Machine Learning and Data Classification","field":"Computer Science","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":"Computer science; Generality; Robustness (evolution); Graph; Data mining; Machine learning; Artificial intelligence; Noisy data; Training set; Artificial neural network; Pattern recognition (psychology); Theoretical computer science","score_opus":0.04234906727040412,"score_gpt":0.2712512761662814,"score_spread":0.2289022088958773,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404638964","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":[0.00026745038,0.0015985948,0.9923034,0.0008497007,0.004101082,0.0001533338,0.00000995601,0.0005312609,0.00018525358],"genre_scores_gemma":[0.45721617,0.000047888374,0.5423384,0.00013060737,0.00018740898,0.0000033792237,0.00004618105,0.000009469002,0.000020545793],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9972948,0.00010643337,0.00034429057,0.0011354745,0.00071426696,0.00040473288],"domain_scores_gemma":[0.99769366,0.000054476986,0.00014625116,0.0017562287,0.00019392309,0.00015543333],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012745712,0.0001959739,0.00021443126,0.00042861188,0.000262125,0.00070430007,0.0046404502,0.000065479566,0.000002291478],"category_scores_gemma":[0.000035934507,0.00017448983,0.000056674176,0.0024116822,0.0003289155,0.0033359905,0.0015387854,0.00026167367,0.000007646537],"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":[0.0000059953377,0.000061145634,0.0005306966,0.000024877958,0.000026592514,0.0000101243095,0.0005477588,0.05763434,0.00002586325,0.011053019,0.024099331,0.9059802],"study_design_scores_gemma":[0.00008552399,0.00009894855,0.0044612936,0.000024928837,0.0000124494645,0.00001795085,0.000008620893,0.9904623,0.00004216503,0.00069641357,0.0038984977,0.00019088427],"about_ca_topic_score_codex":0.000044478154,"about_ca_topic_score_gemma":0.0000033139193,"teacher_disagreement_score":0.932828,"about_ca_system_score_codex":0.00005894194,"about_ca_system_score_gemma":0.00026351455,"threshold_uncertainty_score":0.8623189},"labels":[],"label_agreement":null},{"id":"W4404660366","doi":"10.2139/ssrn.5031810","title":"Evaluating and Enhancing Segmentation Model Robustness with Metamorphic Testing","year":2024,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Machine Learning and Data Classification","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":"Polytechnique Montréal","funders":"","keywords":"Robustness (evolution); Segmentation; Computer science; Artificial intelligence; Robustness testing; Computer vision; Biology","score_opus":0.05007778346795639,"score_gpt":0.3265554576501277,"score_spread":0.27647767418217134,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404660366","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":[0.14130375,0.0030026578,0.8541294,0.0009404013,0.00015513065,0.00016215464,0.0000015039749,0.00014950408,0.00015554558],"genre_scores_gemma":[0.7961366,0.0003991366,0.20280787,0.000031662796,0.00019148731,0.000026776775,0.000016979548,0.0000332029,0.00035629683],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99707633,0.00021529988,0.00039301286,0.0006694839,0.0005312077,0.0011146365],"domain_scores_gemma":[0.9987329,0.00012556829,0.0004500246,0.00041228373,0.00019902275,0.00008015193],"candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.004708724,0.00027578094,0.00025197602,0.00024832986,0.00032307752,0.00087900704,0.00060257176,0.00011448091,0.000001126919],"category_scores_gemma":[0.00020895487,0.00022242719,0.000050013772,0.00029766053,0.000027767088,0.00032683287,0.0007126365,0.004925094,0.00000494401],"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":[0.000011184261,0.000019827961,0.00018429475,0.00016195496,0.00017131615,0.0000057475922,0.00052704255,0.6626183,0.0030405824,0.054820713,0.0000049902237,0.27843407],"study_design_scores_gemma":[0.000175611,0.0001422711,0.000059049024,0.0002658214,0.00010679848,0.000506231,0.00016100236,0.8442862,0.0000895217,0.15398364,0.0000016540225,0.0002222028],"about_ca_topic_score_codex":0.000059520557,"about_ca_topic_score_gemma":0.0002045678,"teacher_disagreement_score":0.65483284,"about_ca_system_score_codex":0.0006310992,"about_ca_system_score_gemma":0.004318886,"threshold_uncertainty_score":0.9973706},"labels":[],"label_agreement":null},{"id":"W4404672160","doi":"10.1007/978-3-031-73024-5_10","title":"Markov Knowledge Distillation: Make Nasty Teachers Trained by Self-undermining Knowledge Distillation Fully Distillable","year":2024,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Distillation; Computer science; Markov chain; Markov process; Artificial intelligence; Machine learning; Chromatography; Chemistry; Mathematics; Statistics","score_opus":0.014151228164921693,"score_gpt":0.2643206319185038,"score_spread":0.2501694037535821,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404672160","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":[0.00012084417,0.0025354915,0.94311,0.0012483723,0.002466766,0.00048113771,0.000053707674,0.000871302,0.04911237],"genre_scores_gemma":[0.79521716,0.00013592195,0.1831152,0.0002477845,0.001618816,0.00004575299,0.00043584997,0.00016950438,0.019014038],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99461395,0.000120569,0.0008963069,0.0026109426,0.0009021444,0.0008561079],"domain_scores_gemma":[0.99641174,0.00079147395,0.0004453479,0.0017249343,0.00030142898,0.00032505122],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0015302977,0.0008797704,0.0006916113,0.00085203245,0.0005854636,0.0014916421,0.0025930007,0.0005077593,0.000036690977],"category_scores_gemma":[0.00022174457,0.0008151941,0.00019588039,0.0013099584,0.0005338681,0.0006616663,0.0012839055,0.0013676285,0.00030710673],"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":[0.000008511692,0.000084452346,0.00025326232,0.00021971471,0.000039303388,0.000028397364,0.004126715,0.0026589737,0.00008143112,0.038996544,0.0008239798,0.95267874],"study_design_scores_gemma":[0.00031428775,0.00014337077,0.0009525529,0.0005124673,0.000038244518,0.000067304034,0.0000015308291,0.8405368,0.000040597737,0.02881814,0.12754247,0.001032289],"about_ca_topic_score_codex":0.000020154725,"about_ca_topic_score_gemma":0.00016040626,"teacher_disagreement_score":0.95164645,"about_ca_system_score_codex":0.00087323796,"about_ca_system_score_gemma":0.0008048204,"threshold_uncertainty_score":0.9995449},"labels":[],"label_agreement":null},{"id":"W4404736300","doi":"10.1080/03081079.2024.2430349","title":"SCNet: semi-supervised and contrastive learning against noisy labels with two selection strategy approach","year":2024,"lang":"en","type":"article","venue":"International Journal of General Systems","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Selection (genetic algorithm); Computer science; Artificial intelligence; Machine learning; Natural language processing","score_opus":0.013222997751265772,"score_gpt":0.26861583667591765,"score_spread":0.25539283892465187,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404736300","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":[0.13321146,0.0012855828,0.8615253,0.0005535908,0.0008803441,0.000095633346,0.000005311205,0.00007419659,0.0023685498],"genre_scores_gemma":[0.9947775,0.000066533474,0.0037299048,0.00004043752,0.00079869066,0.000004751343,0.00001760171,0.000010758014,0.00055383646],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986453,0.00017825433,0.0003296229,0.00022454794,0.00049822684,0.00012402084],"domain_scores_gemma":[0.9991729,0.00006085841,0.0002135315,0.0000715657,0.00039998817,0.00008113757],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005599967,0.000117879936,0.00015693065,0.00021963763,0.000071647,0.00086708856,0.00037179154,0.000039807466,0.0000027322142],"category_scores_gemma":[0.000031665197,0.00008561756,0.00003814902,0.00018844426,0.000025484214,0.0006977881,0.000042684063,0.00035176642,0.0000051575676],"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":[0.00014414002,0.00013035016,0.014270408,0.00011684483,0.0008956732,0.00021547731,0.0016547414,0.7015322,0.040090233,0.06533195,0.0012878132,0.17433019],"study_design_scores_gemma":[0.0005525774,0.00019519766,0.0018143245,0.00017765973,0.000012967103,0.0010115874,0.00011963721,0.99077713,0.00015919069,0.000061016948,0.0050014164,0.00011726668],"about_ca_topic_score_codex":0.000117499825,"about_ca_topic_score_gemma":0.0000054585007,"teacher_disagreement_score":0.861566,"about_ca_system_score_codex":0.00009626363,"about_ca_system_score_gemma":0.00012928288,"threshold_uncertainty_score":0.83613545},"labels":[],"label_agreement":null},{"id":"W4405444248","doi":"10.1145/3708473","title":"Leveraging Data Characteristics for Bug Localization in Deep Learning Programs","year":2024,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Machine Learning and Data Classification","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":"Polytechnique Montréal","funders":"Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research; National Science Foundation","keywords":"Computer science; Deep learning; Artificial intelligence; Software engineering; Data science; Machine learning","score_opus":0.13358464562709096,"score_gpt":0.344974517411349,"score_spread":0.21138987178425803,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405444248","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":[0.0015010833,0.00032902582,0.99653953,0.00035657934,0.0005388591,0.0001316402,0.0000068007885,0.0005949118,0.0000015954192],"genre_scores_gemma":[0.20884371,0.00016019093,0.790615,0.000045178796,0.00003918189,0.000056643494,0.00016852433,0.000019945888,0.000051588024],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99894506,0.00013951438,0.00019070198,0.00046075825,0.00006982564,0.00019411494],"domain_scores_gemma":[0.997949,0.0014338208,0.00002627827,0.0005209596,0.000024041374,0.000045921686],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010413924,0.0001174923,0.00015437376,0.00023619195,0.000092930975,0.00012432631,0.00040385197,0.000087091365,0.0000022880315],"category_scores_gemma":[0.001192179,0.00011970554,0.000023470693,0.00031037902,0.000014949035,0.00027037243,0.00002908226,0.00033543666,0.0000030341691],"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":[0.000006235698,0.000017984928,0.00040636124,0.00015032031,0.000016918295,0.0000036384733,0.00065452565,0.030301142,0.00008313989,0.0011649269,0.000005060024,0.9671897],"study_design_scores_gemma":[0.00013120858,0.00007110063,0.0013420578,0.00008102266,0.000015692991,0.000026596093,0.000030340187,0.96701145,0.00005035923,0.00032664518,0.030777667,0.00013585284],"about_ca_topic_score_codex":0.000021287968,"about_ca_topic_score_gemma":0.0000053365325,"teacher_disagreement_score":0.9670539,"about_ca_system_score_codex":0.000025912517,"about_ca_system_score_gemma":0.000022957583,"threshold_uncertainty_score":0.48814502},"labels":[],"label_agreement":null},{"id":"W4405686578","doi":"10.25071/1708-6701.40497","title":"Minutes of the 2023 CAML / ACMB Annual General Meeting","year":2024,"lang":"en","type":"article","venue":"CAML Review / Revue de l ACBM","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science","score_opus":0.015248706872321839,"score_gpt":0.2785776927881506,"score_spread":0.26332898591582876,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405686578","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":[0.019742845,0.7867175,0.06774551,0.094470106,0.0036404924,0.0013802714,0.00018619091,0.0006793156,0.025437796],"genre_scores_gemma":[0.43998048,0.20729123,0.21101828,0.018023288,0.0067969915,0.0006976723,0.0004626376,0.00027611578,0.115453295],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99868745,0.00023638946,0.00034093717,0.00034854445,0.00017941334,0.00020727466],"domain_scores_gemma":[0.9986855,0.00015344658,0.00014085008,0.00088106515,0.00008001952,0.000059135138],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00096892065,0.00012495028,0.00023115729,0.00004586966,0.00007951931,0.00009209806,0.0011030578,0.000048803642,0.000023567158],"category_scores_gemma":[0.00070671825,0.00008658479,0.00015233862,0.0006444144,0.00003860384,0.00021684647,0.00030914074,0.00025086285,0.00010220454],"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":[0.0000020114949,0.000048925227,0.0027950157,0.012498873,0.000060516282,0.00004152027,0.0013808941,0.00010957154,0.005315867,0.11077479,0.25794783,0.60902417],"study_design_scores_gemma":[0.000049882936,0.00002402667,0.0033995777,0.00538961,0.000050242874,0.000109311564,0.000011816028,0.02286594,0.00048573376,0.0003898115,0.96704906,0.00017497782],"about_ca_topic_score_codex":0.00005376972,"about_ca_topic_score_gemma":0.000010656916,"teacher_disagreement_score":0.70910126,"about_ca_system_score_codex":0.000040288993,"about_ca_system_score_gemma":0.00009778093,"threshold_uncertainty_score":0.3530825},"labels":[],"label_agreement":null},{"id":"W4405907339","doi":"10.1109/tpami.2024.3524377","title":"Hyper-YOLO: When Visual Object Detection Meets Hypergraph Computation","year":2024,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":237,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Natural Science Foundation of Beijing Municipality; National Natural Science Foundation of China","keywords":"Computer science; Artificial intelligence; Object detection; Hypergraph; Computer vision; Computation; Object (grammar); Cognitive neuroscience of visual object recognition; Visualization; Pattern recognition (psychology); Mathematics; Algorithm","score_opus":0.018397297134184042,"score_gpt":0.286248052880697,"score_spread":0.26785075574651296,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405907339","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":[0.0050210743,0.00035610117,0.9922403,0.0012719684,0.00046250774,0.000112520655,0.00002487471,0.00039136663,0.00011928728],"genre_scores_gemma":[0.99732214,0.00030182474,0.0018854388,0.00019056952,0.0000356034,0.000023778372,0.000028089595,0.000015459218,0.00019706567],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981511,0.00017226048,0.00037555996,0.000753581,0.00032751262,0.00021998964],"domain_scores_gemma":[0.9991883,0.00019687861,0.0000757747,0.00035698057,0.00006587543,0.000116164534],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036317794,0.00024018384,0.00025349774,0.0009971124,0.00030821355,0.0004833101,0.0003011856,0.00008735601,0.000069766334],"category_scores_gemma":[0.0000069559455,0.00020993936,0.0002411742,0.0014781822,0.00005345367,0.00045472177,0.0000068165277,0.00038342495,0.000104664905],"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":[0.000007250908,0.000061377636,0.0001626709,0.000025801966,0.0002712152,0.000005309592,0.00034976687,0.011013741,0.0015300533,0.00012715552,0.0000122794245,0.9864334],"study_design_scores_gemma":[0.00005477849,0.00016858424,0.0012349017,0.000031428477,0.0002989867,0.000028423523,0.00003174256,0.96048194,0.03599128,0.00039184935,0.0010287082,0.00025735795],"about_ca_topic_score_codex":0.0012958762,"about_ca_topic_score_gemma":0.0014968084,"teacher_disagreement_score":0.9923011,"about_ca_system_score_codex":0.00004412976,"about_ca_system_score_gemma":0.000023854678,"threshold_uncertainty_score":0.85610783},"labels":[],"label_agreement":null},{"id":"W4405967252","doi":"10.3390/a18010007","title":"A Closest Resemblance Classifier with Feature Interval Learning and Outranking Measures for Improved Performance","year":2024,"lang":"en","type":"article","venue":"Algorithms","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada","funders":"National Research Council Canada","keywords":"Interpretability; Overfitting; Artificial intelligence; Computer science; Support vector machine; Random forest; Machine learning; Naive Bayes classifier; Pairwise comparison; Pattern recognition (psychology); Robustness (evolution); Classifier (UML); Data mining; Artificial neural network","score_opus":0.01683321575566576,"score_gpt":0.27398368608844426,"score_spread":0.2571504703327785,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405967252","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":[0.0095076775,0.0018372635,0.9818135,0.0048711905,0.00036857728,0.00026832975,0.0000074381564,0.00048996834,0.0008360693],"genre_scores_gemma":[0.8851946,0.00024548444,0.11102735,0.00012216489,0.00029044936,0.000077158285,0.000034663673,0.0000294889,0.0029786504],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989247,0.00004809075,0.000120423814,0.0004996625,0.00015772216,0.00024940813],"domain_scores_gemma":[0.9994347,0.00014082881,0.00004858015,0.0002416491,0.00007274464,0.00006150122],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00044024992,0.00014783724,0.00014341192,0.00009639708,0.00021574758,0.00051578647,0.00029578747,0.00006996695,0.0000013953476],"category_scores_gemma":[0.00005969396,0.00010976902,0.000034146215,0.00025620285,0.000046447287,0.00054494204,0.0000779218,0.00042094724,0.0000066933744],"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":[0.000033466495,0.000012959209,0.001761919,0.0001452058,0.000039183353,0.000007371847,0.0006874758,0.000037929913,0.0013931816,0.0023754102,0.0007202191,0.9927857],"study_design_scores_gemma":[0.00026917196,0.0003062628,0.0034320368,0.00017193877,0.000013829623,0.00006899855,0.000041257725,0.82090867,0.00029359054,0.00012379033,0.17418885,0.00018158175],"about_ca_topic_score_codex":0.000013762764,"about_ca_topic_score_gemma":0.00001340881,"teacher_disagreement_score":0.9926041,"about_ca_system_score_codex":0.000025074627,"about_ca_system_score_gemma":0.000054617423,"threshold_uncertainty_score":0.49737406},"labels":[],"label_agreement":null},{"id":"W4405986911","doi":"10.1016/j.apenergy.2024.125258","title":"Zeolite-catalytic pyrolysis of waste plastics: Machine learning prediction, interpretation, and optimization","year":2025,"lang":"en","type":"article","venue":"Applied Energy","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":32,"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","funders":"Foundation of State Key Laboratory of Coal Combustion; Alliance of International Science Organizations; National Natural Science Foundation of China","keywords":"Zeolite; Interpretation (philosophy); Pyrolysis; Catalysis; Waste management; Process engineering; Chemical engineering; Engineering; Environmental science; Computer science; Chemistry; Organic chemistry","score_opus":0.004258632305308585,"score_gpt":0.20001849341904712,"score_spread":0.19575986111373853,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405986911","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":[0.0012196308,0.0001450045,0.9920978,0.0001899972,0.000082588725,0.00003670059,0.000005281265,0.00012200648,0.0061010187],"genre_scores_gemma":[0.9795603,0.000099200806,0.019536419,0.00008756639,0.000019877843,0.000018863137,0.00020603547,0.000006451487,0.0004652847],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991693,0.000040662293,0.0002660087,0.00029286768,0.00012554301,0.00010565745],"domain_scores_gemma":[0.99933445,0.00013463148,0.00013754901,0.0002891483,0.000068292786,0.000035946956],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014844697,0.00009934028,0.00013624933,0.00022064665,0.000104732135,0.00006177174,0.000239981,0.00005234952,0.0000057068055],"category_scores_gemma":[0.00009192726,0.00009773635,0.000020664516,0.0004522088,0.00004283211,0.00015371491,0.00014197137,0.00009573197,0.0000016982441],"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":[0.000017119311,0.000027869715,0.0009709405,0.000030712985,0.000034636963,1.6695458e-7,0.00024657356,0.69910705,0.0009104793,0.25013825,0.00011905383,0.048397154],"study_design_scores_gemma":[0.00024017303,0.000025648611,0.0005670349,0.000020068774,0.000022800326,9.582888e-7,0.00003757957,0.993692,0.0018861778,0.0011884702,0.0022480644,0.00007104816],"about_ca_topic_score_codex":0.00010780942,"about_ca_topic_score_gemma":0.000011766595,"teacher_disagreement_score":0.9783407,"about_ca_system_score_codex":0.000019174415,"about_ca_system_score_gemma":0.000030869465,"threshold_uncertainty_score":0.39855728},"labels":[],"label_agreement":null},{"id":"W4406031787","doi":"10.48550/arxiv.2501.00532","title":"Variability-Aware Machine Learning Model Selection: Feature Modeling, Instantiation, and Experimental Case Study","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Feature selection; Computer science; Selection (genetic algorithm); Feature (linguistics); Artificial intelligence; Model selection; Machine learning","score_opus":0.05974465071298773,"score_gpt":0.22696123008286395,"score_spread":0.16721657936987622,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406031787","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":[0.47956222,0.000117848154,0.5191584,0.00009631508,0.00015223185,0.0002480201,0.000011142173,0.00036942592,0.00028439664],"genre_scores_gemma":[0.9966443,0.000031154126,0.0021832013,0.000027142909,0.000057041074,0.0000036122435,0.000054552183,0.00002403184,0.0009749184],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99756247,0.00036770955,0.00019782262,0.0015322627,0.000121806195,0.00021795665],"domain_scores_gemma":[0.998755,0.000056411234,0.00014934561,0.00075793295,0.00014794154,0.0001333951],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005529192,0.0003293755,0.0002632202,0.00027757394,0.0004406136,0.00037324725,0.0005690288,0.0003215086,0.000008841436],"category_scores_gemma":[0.00004720725,0.0003634417,0.00008259142,0.0005352189,0.00003635686,0.00035952963,0.0022000945,0.0020538275,0.000011857888],"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":[0.000016196313,0.00018818695,0.0066405083,0.00007241854,0.0000697331,0.00057801907,0.0015959796,0.96712905,0.00001566918,0.023379382,0.00004165073,0.00027321736],"study_design_scores_gemma":[0.00033484542,0.00009290203,0.000040472303,0.000031321033,0.000080746286,0.0001794481,0.0007855353,0.99250454,0.000008275933,0.005554804,0.000043055083,0.00034405765],"about_ca_topic_score_codex":0.00066037773,"about_ca_topic_score_gemma":0.00014517878,"teacher_disagreement_score":0.51708215,"about_ca_system_score_codex":0.00021352904,"about_ca_system_score_gemma":0.00019063562,"threshold_uncertainty_score":0.99988174},"labels":[],"label_agreement":null},{"id":"W4406401421","doi":"10.1017/s147106842400036x","title":"On Lower Bounding Minimal Model Count","year":2024,"lang":"en","type":"article","venue":"Theory and Practice of Logic Programming","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"Ministry of Education, India; National Supercomputing Centre Singapore; University of Toronto; National Research Foundation Singapore; National Research Foundation","keywords":"Computer science; Bounding overwatch; Count data; Statistics; Artificial intelligence; Mathematics; Poisson distribution","score_opus":0.033015599651150904,"score_gpt":0.3339099828072208,"score_spread":0.30089438315606987,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406401421","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":[0.0038812575,0.00127552,0.9680239,0.0021975706,0.0002196368,0.000105248655,0.0000016714608,0.00021359274,0.02408161],"genre_scores_gemma":[0.92009556,0.000057371293,0.079279326,0.00027687263,0.000032743294,0.000008678579,0.0000036327026,0.0000056884614,0.0002401177],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99893904,0.0003189091,0.00014855762,0.00028017856,0.00016613724,0.00014715876],"domain_scores_gemma":[0.99690604,0.0026694662,0.00008820849,0.00025938655,0.000034292112,0.000042590706],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0037222763,0.000089533394,0.000091806294,0.00007191816,0.000115801646,0.000322939,0.000227035,0.00004499543,0.0000074096215],"category_scores_gemma":[0.0014961892,0.000070479626,0.000027678978,0.00016529094,0.00006642007,0.000803737,0.00008917894,0.00021752139,0.000016634598],"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":[0.0000986894,0.00004590618,0.0000021737735,0.000040180694,0.000011178157,0.000013206991,0.00060826703,0.00012005052,0.0002728272,0.7691452,0.000038303966,0.22960404],"study_design_scores_gemma":[0.0002096531,0.00076177577,0.000027855875,0.00021058378,0.00006960414,0.00019156553,0.0004943125,0.3623079,0.00015980628,0.5147851,0.120490104,0.00029169914],"about_ca_topic_score_codex":0.0000037628542,"about_ca_topic_score_gemma":2.0058036e-7,"teacher_disagreement_score":0.9162143,"about_ca_system_score_codex":0.000014186896,"about_ca_system_score_gemma":0.000040668245,"threshold_uncertainty_score":0.31141084},"labels":[],"label_agreement":null},{"id":"W4407601102","doi":"10.2139/ssrn.5139167","title":"Empirical Deduction and Analysis of Bug Evolution in Deep Learning and Non-Deep Learning Frameworks","year":2025,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Machine Learning and Data Classification","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":"Polytechnique Montréal","funders":"","keywords":"Deep learning; Artificial intelligence; Computer science; Machine learning; Natural language processing","score_opus":0.007618788415341462,"score_gpt":0.29197465612988605,"score_spread":0.2843558677145446,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407601102","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":[0.20894864,0.0054487553,0.7845006,0.0006826257,0.0001407322,0.00008560894,6.459138e-7,0.00004026186,0.00015216357],"genre_scores_gemma":[0.9870759,0.0085996445,0.0039323345,0.000016904178,0.00008634378,0.000007730372,0.000040844687,0.000009441106,0.00023080662],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99694574,0.00061165524,0.00056045514,0.00064576085,0.00032599195,0.00091037445],"domain_scores_gemma":[0.9986362,0.00021331472,0.0006272846,0.0002983305,0.00014334793,0.000081527214],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0029406503,0.00024373877,0.0005171528,0.0013786884,0.00026454334,0.00021592143,0.00044018577,0.0005268878,0.0000042689476],"category_scores_gemma":[0.00052199175,0.00024676925,0.00013761414,0.0012047567,0.00006541301,0.0002663608,0.0005363299,0.011339668,9.0690617e-7],"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":[0.000042819807,0.00007558519,0.6132944,0.00007887364,0.0007274502,0.0000022338672,0.0017954175,0.0871591,0.0000853814,0.017330876,0.0000025613058,0.27940527],"study_design_scores_gemma":[0.00024516633,0.00012799374,0.26735154,0.0001104008,0.00029397357,0.000041016523,0.0006972845,0.6987634,0.0000029627945,0.0320356,0.00011790624,0.00021275348],"about_ca_topic_score_codex":0.0002769438,"about_ca_topic_score_gemma":0.00077017286,"teacher_disagreement_score":0.78056824,"about_ca_system_score_codex":0.0007179299,"about_ca_system_score_gemma":0.0007689958,"threshold_uncertainty_score":0.99999845},"labels":[],"label_agreement":null},{"id":"W4408030800","doi":"10.1016/b978-0-44-332818-3.00009-5","title":"Basics of machine learning","year":2025,"lang":"en","type":"book-chapter","venue":"Elsevier eBooks","topic":"Machine Learning and Data Classification","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":"Carleton University","funders":"","keywords":"Computer science; Artificial intelligence","score_opus":0.014024369124600372,"score_gpt":0.24139694789700422,"score_spread":0.22737257877240385,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408030800","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":[5.0947335e-7,0.00096422323,0.010586982,0.00021172667,0.00025765528,0.00015929832,0.00002026153,0.00016714525,0.9876322],"genre_scores_gemma":[0.00048255426,0.00013116412,0.007363412,0.00013860162,0.000073686,0.000005318718,0.00008579637,0.000023332477,0.9916961],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99850357,0.00006137278,0.00043441422,0.0004970497,0.00032806362,0.00017556171],"domain_scores_gemma":[0.9982547,0.00014324092,0.00042484858,0.0010010831,0.00011098837,0.00006512117],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003774911,0.00027699253,0.00040909305,0.00023511302,0.00010433832,0.000063389416,0.0009857191,0.00021555898,0.000056474626],"category_scores_gemma":[0.00007725866,0.00026540656,0.00016287982,0.000027965982,0.00006453259,0.0000672813,0.00045159005,0.00077992264,0.00008054787],"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":[0.0000018380126,0.0000032497564,0.000023981767,0.000074136864,0.000024226172,0.0000037894158,0.000044228465,0.000003695982,0.000007429053,0.28077316,0.00009910401,0.71894115],"study_design_scores_gemma":[0.000115792325,0.00004600071,0.000035889618,0.0002729273,0.000031528423,0.0000043026585,6.931089e-7,0.003798527,0.000025712588,0.00734659,0.988101,0.00022102494],"about_ca_topic_score_codex":0.0000014756561,"about_ca_topic_score_gemma":0.000011172957,"teacher_disagreement_score":0.9880019,"about_ca_system_score_codex":0.00003635429,"about_ca_system_score_gemma":0.00020804288,"threshold_uncertainty_score":0.9999798},"labels":[],"label_agreement":null},{"id":"W4408240727","doi":"10.1016/j.neunet.2025.107275","title":"FedELR: When federated learning meets learning with noisy labels","year":2025,"lang":"en","type":"article","venue":"Neural Networks","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"National Natural Science Foundation of China","keywords":"Computer science; Artificial intelligence; Machine learning","score_opus":0.009106668695091812,"score_gpt":0.23827010918266545,"score_spread":0.22916344048757364,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408240727","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":[0.028412927,0.0005428183,0.9463025,0.008774569,0.00048956234,0.00023351991,3.9894255e-7,0.0012786074,0.013965135],"genre_scores_gemma":[0.9886688,0.000031517917,0.0044130385,0.0007548084,0.00010463005,0.00001817922,0.00005082056,0.000016898313,0.005941314],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981461,0.00036373394,0.00024497398,0.0005840703,0.00023775877,0.00042333597],"domain_scores_gemma":[0.9990569,0.0002201295,0.00015372846,0.0003683856,0.00010892726,0.000091982896],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035302204,0.00021645294,0.00021650118,0.00011343348,0.00077746314,0.00071709463,0.00058159314,0.000117198826,0.000021747863],"category_scores_gemma":[0.00011591341,0.00017974757,0.000043547127,0.00064312073,0.000042534142,0.0004526399,0.00024578525,0.0010531435,0.000024653053],"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":[0.0000592209,0.000048114285,0.03268972,0.000023650928,0.000050638395,0.000031617503,0.00028021468,0.58101124,0.00028531908,0.011085301,0.0045425436,0.36989242],"study_design_scores_gemma":[0.00038801707,0.0001328801,0.00632267,0.000055526692,0.000010789998,0.000011574402,0.000026825688,0.94875354,0.00003618731,0.000080489415,0.043984514,0.00019698465],"about_ca_topic_score_codex":0.000087246415,"about_ca_topic_score_gemma":0.000060397873,"teacher_disagreement_score":0.96025586,"about_ca_system_score_codex":0.000038776805,"about_ca_system_score_gemma":0.00004652049,"threshold_uncertainty_score":0.7329893},"labels":[],"label_agreement":null},{"id":"W4408352598","doi":"10.1109/icassp49660.2025.10889047","title":"Learning from Ambiguous Data with Hard Labels","year":2025,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","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":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Artificial intelligence","score_opus":0.034552064196515415,"score_gpt":0.2792409356508822,"score_spread":0.2446888714543668,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408352598","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":[0.009469145,0.000061499115,0.963396,0.0044969916,0.00009966688,0.000048459926,0.0000048980755,0.0003969476,0.022026377],"genre_scores_gemma":[0.8028298,0.000018954306,0.17692667,0.0009492372,0.00003973559,0.0000052782157,0.00040347248,0.000006101046,0.018820731],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991131,0.0000726237,0.0000990848,0.00045894345,0.00013481821,0.000121432655],"domain_scores_gemma":[0.99843204,0.00007153391,0.00004240086,0.0013902815,0.00003134275,0.00003239857],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020393713,0.000072626644,0.00008334124,0.00005396747,0.00012432407,0.00024494124,0.0013878427,0.00002773685,0.000041126073],"category_scores_gemma":[0.00010727272,0.00005436309,0.000007490827,0.00029366152,0.000018372844,0.00046426227,0.00056341494,0.00018580894,0.00013274742],"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":[0.000014821734,0.00007052426,0.040399358,0.000012841396,0.000059459668,0.0000101677415,0.00024296352,0.0005187105,0.0012538721,0.08475874,0.019359812,0.8532987],"study_design_scores_gemma":[0.00045745503,0.0000688134,0.16236189,0.000044106175,0.0000149522875,0.0000021180276,0.0000661782,0.5698636,0.00037142867,0.0010041939,0.26554814,0.00019713026],"about_ca_topic_score_codex":0.0012389942,"about_ca_topic_score_gemma":0.00007251799,"teacher_disagreement_score":0.8531016,"about_ca_system_score_codex":0.000010179934,"about_ca_system_score_gemma":0.000061927465,"threshold_uncertainty_score":0.257898},"labels":[],"label_agreement":null},{"id":"W4408353457","doi":"10.1109/icassp49660.2025.10888230","title":"Federated Domain Generalization with Label Smoothing and Balanced Decentralized Training","year":2025,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","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":false,"ca_institutions":"Queen's University","funders":"","keywords":"Generalization; Computer science; Smoothing; Domain (mathematical analysis); Training (meteorology); Artificial intelligence; Mathematics; Computer vision","score_opus":0.01614742587461864,"score_gpt":0.26547677908226486,"score_spread":0.2493293532076462,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408353457","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":[0.04460514,0.000062098996,0.94516426,0.003376386,0.000051956285,0.00008247683,5.063835e-7,0.00023158557,0.006425578],"genre_scores_gemma":[0.79143715,0.000027300572,0.20670296,0.0010911585,0.000008389961,0.0000087475055,0.00002960587,0.0000043362975,0.0006903198],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992974,0.000077569064,0.00011926117,0.00026643442,0.00009571754,0.00014366598],"domain_scores_gemma":[0.9996804,0.00004153715,0.00004554328,0.00015215093,0.000041543066,0.0000388015],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020406526,0.000080941994,0.00009418895,0.00006948783,0.00020695175,0.0003368246,0.00013951275,0.000033319862,0.0000072532634],"category_scores_gemma":[0.000034505476,0.000062484316,0.000006407676,0.0003686584,0.000019329369,0.00028592438,0.000046817073,0.00007072121,0.0000019757292],"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":[0.00003087652,0.0000401891,0.012657015,0.00002926614,0.000033737164,0.000004190162,0.0015089217,0.0002451286,0.010531994,0.76834846,0.00092432083,0.20564589],"study_design_scores_gemma":[0.002265185,0.000052054096,0.02532518,0.00007475564,0.000009099751,0.000010322555,0.0002137873,0.9541012,0.00093928265,0.0038937873,0.01287462,0.00024070221],"about_ca_topic_score_codex":0.000056059333,"about_ca_topic_score_gemma":0.00004616532,"teacher_disagreement_score":0.9538561,"about_ca_system_score_codex":0.00001668403,"about_ca_system_score_gemma":0.00005686407,"threshold_uncertainty_score":0.32480073},"labels":[],"label_agreement":null},{"id":"W4408404791","doi":"10.1080/01621459.2025.2474266","title":"Positive and Unlabeled Data: Model, Estimation, Inference, and Classification","year":2025,"lang":"en","type":"article","venue":"Journal of the American Statistical Association","topic":"Machine Learning and Data Classification","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":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; University of Waterloo","keywords":"Inference; Estimation; Artificial intelligence; Computer science; Statistics; Econometrics; Mathematics; Pattern recognition (psychology); Machine learning; Data mining; Economics","score_opus":0.01785442230205226,"score_gpt":0.33019765773690907,"score_spread":0.3123432354348568,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408404791","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":[0.018674945,0.000037165148,0.9675252,0.013318936,0.00007583479,0.000056519315,0.00004353088,0.000011611396,0.00025630122],"genre_scores_gemma":[0.89765096,0.00007987376,0.101634,0.0004609972,0.000016899712,0.00000113307,0.000016861393,0.0000023282546,0.00013694022],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989254,0.00025175526,0.00030068672,0.00016184544,0.0002671469,0.00009319229],"domain_scores_gemma":[0.9975491,0.0010568666,0.00083961425,0.00027972832,0.00023119964,0.000043464344],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00081040704,0.00006695437,0.00016844658,0.000080749014,0.00014095643,0.00017813254,0.0004096506,0.000024764116,5.623769e-7],"category_scores_gemma":[0.003408154,0.000047819467,0.000012506943,0.00034228642,0.00007957174,0.00046616947,0.00020817736,0.0002056412,0.0000011660387],"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":[0.00003530562,0.000081984115,0.067730986,0.000017630266,0.00010029812,8.2074854e-7,0.0002643789,0.00075878977,0.00069631846,0.4565068,0.009321543,0.46448514],"study_design_scores_gemma":[0.00011854225,0.000027380705,0.4039524,0.000014846393,0.000030096215,0.0000021729559,0.000016119919,0.580351,0.0000063984166,0.015221317,0.00022709339,0.000032613432],"about_ca_topic_score_codex":0.000028176572,"about_ca_topic_score_gemma":0.000006722823,"teacher_disagreement_score":0.878976,"about_ca_system_score_codex":0.000116213705,"about_ca_system_score_gemma":0.00013832381,"threshold_uncertainty_score":0.40801248},"labels":[],"label_agreement":null},{"id":"W4408511407","doi":"10.3386/w33566","title":"A Quest for AI Knowledge","year":2025,"lang":"en","type":"report","venue":"National Bureau of Economic Research","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Computer science","score_opus":0.40455140239041565,"score_gpt":0.5866357707658248,"score_spread":0.1820843683754092,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408511407","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":[0.0000064293604,0.0009889653,0.012506327,0.0050539877,0.00096037163,0.0005995743,0.00016574089,0.0000510202,0.9796676],"genre_scores_gemma":[0.2671886,0.0034258096,0.030738614,0.00027539543,0.006061609,0.0021772252,0.010991674,0.00011637681,0.6790247],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9975646,0.00018825682,0.00052887213,0.00065780676,0.0007772292,0.00028321505],"domain_scores_gemma":[0.99387056,0.0019050853,0.00022975136,0.0006227469,0.0033029532,0.00006889278],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007364651,0.00014408038,0.0003223885,0.0010504395,0.00016182079,0.0001697551,0.0015380996,0.00027720325,0.000041910305],"category_scores_gemma":[0.003100228,0.00014754279,0.00014339603,0.00026920167,0.00009539723,0.00023509719,0.00040615734,0.00061806774,0.00012506434],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000061851806,0.000042505377,0.000050984367,0.0002074095,0.00003500235,1.5987032e-7,0.000019883935,0.00003719319,0.00000992834,0.6540601,0.32526118,0.020269457],"study_design_scores_gemma":[0.00021181093,0.000060633916,0.00029036868,0.0001145331,0.0000044419608,0.0000036339252,0.0000028587424,0.026211893,0.00004367005,0.20946035,0.76347405,0.00012174581],"about_ca_topic_score_codex":0.00054991327,"about_ca_topic_score_gemma":0.00016821029,"teacher_disagreement_score":0.44459978,"about_ca_system_score_codex":0.001173308,"about_ca_system_score_gemma":0.0103669455,"threshold_uncertainty_score":0.9952434},"labels":[],"label_agreement":null},{"id":"W4408538279","doi":"10.2139/ssrn.5181302","title":"A Quest for AI Knowledge","year":2025,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Machine Learning and Data Classification","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 Toronto","funders":"","keywords":"Psychology","score_opus":0.007382179542127534,"score_gpt":0.30399835865409275,"score_spread":0.2966161791119652,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408538279","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":[0.00046609368,0.0021552166,0.9817028,0.010117097,0.00033052315,0.00007987919,6.454517e-7,0.00007370752,0.005074037],"genre_scores_gemma":[0.97788376,0.0006522788,0.0042667505,0.00056670903,0.00023912966,0.000020598593,0.0000073025017,0.000008164747,0.016355285],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99860346,0.000067659596,0.00015696006,0.00018968244,0.00007259787,0.00090966595],"domain_scores_gemma":[0.9994624,0.00007585559,0.00006551493,0.00025709765,0.000103851526,0.000035243287],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014248494,0.000076254066,0.00008737687,0.00013515097,0.00024676727,0.00016116159,0.0006631079,0.000039860814,0.0000018391828],"category_scores_gemma":[0.00013637681,0.00006610406,0.00006232699,0.00025775962,0.000013300898,0.00026149594,0.00006031919,0.0008385293,0.000027975208],"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":[0.0000048538504,0.000026918651,0.00023649547,0.000004412353,0.000018415916,1.0778612e-7,0.000040346844,0.000005974691,0.00007156504,0.8148897,0.0016203931,0.1830808],"study_design_scores_gemma":[0.00056183664,0.00016446348,0.0009267698,0.000023983317,0.000012703305,0.00006461557,0.00006250164,0.030044714,0.00008231819,0.6686331,0.2993065,0.00011645479],"about_ca_topic_score_codex":0.000011858998,"about_ca_topic_score_gemma":0.00021277463,"teacher_disagreement_score":0.97743607,"about_ca_system_score_codex":0.0003140341,"about_ca_system_score_gemma":0.0021909694,"threshold_uncertainty_score":0.38866857},"labels":[],"label_agreement":null},{"id":"W4408694014","doi":"10.1038/s41586-025-08905-3","title":"Author Correction: AI models collapse when trained on recursively generated data","year":2025,"lang":"en","type":"erratum","venue":"Nature","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; University of Toronto","funders":"","keywords":"Computer science","score_opus":0.039116636036608705,"score_gpt":0.31890218175764923,"score_spread":0.27978554572104053,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408694014","genre_codex":"methods","genre_gemma":"other","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":[0.000002239963,0.005397112,0.40687686,0.13604501,0.22819154,0.0010076785,0.0023793194,0.0015207694,0.21857947],"genre_scores_gemma":[0.00042376455,0.00016798291,0.010286708,0.008421461,0.0023374818,0.000032488926,0.025323715,0.000037993632,0.9529684],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99660295,0.0003402258,0.00035415552,0.0016323599,0.0007236583,0.00034662493],"domain_scores_gemma":[0.995377,0.0001446434,0.00031611495,0.0036140098,0.0004169251,0.0001313196],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.0005861444,0.0004358086,0.00043375892,0.00040251092,0.0003330255,0.00055146014,0.0042827018,0.004089954,0.00004657698],"category_scores_gemma":[0.0008289044,0.00039911372,0.00008280504,0.0009779434,0.00003479759,0.0006407984,0.0006997578,0.010908573,0.000058888698],"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":[0.000025780533,0.000054423384,5.2337623e-7,0.000041763356,0.000045336645,0.000018800727,0.0001464818,0.0003345646,0.000005414259,0.014463328,0.9547978,0.03006577],"study_design_scores_gemma":[0.00014524256,0.0000461813,0.000026017431,0.00016893138,0.00002423983,0.000008731412,0.000005064643,0.4177871,0.0000060218376,0.0013401407,0.58021134,0.00023100436],"about_ca_topic_score_codex":0.000059990805,"about_ca_topic_score_gemma":0.00008137761,"teacher_disagreement_score":0.73438895,"about_ca_system_score_codex":0.0001662397,"about_ca_system_score_gemma":0.0012216368,"threshold_uncertainty_score":0.9998461},"labels":[],"label_agreement":null},{"id":"W4408791657","doi":"10.1109/access.2025.3554093","title":"Understanding the Role of Diversity in Ensemble-Based AutoML Methods for Classification Tasks","year":2025,"lang":"en","type":"article","venue":"IEEE Access","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"H2020 Marie Skłodowska-Curie Actions; Ontario Ministry of Research and Innovation; Ministerio de Ciencia e Innovación; Eusko Jaurlaritza; European Commission","keywords":"Computer science; Diversity (politics); Artificial intelligence; Machine learning; Political science","score_opus":0.22214572461060786,"score_gpt":0.4265519126365056,"score_spread":0.20440618802589774,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408791657","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":[0.0021247487,0.000054145545,0.9930333,0.0020054807,0.00020714653,0.00021003411,0.0000029449907,0.000050591254,0.002311631],"genre_scores_gemma":[0.97289366,0.0000030165638,0.02685783,0.00016806634,0.0000100756715,0.000023150835,0.000006973158,0.00000234617,0.000034889377],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99917555,0.00021820885,0.00016612602,0.00022743076,0.00009711009,0.000115576826],"domain_scores_gemma":[0.9986355,0.0007027511,0.00012952433,0.000464688,0.000051466825,0.000016124271],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001030442,0.0000631675,0.000099125304,0.00016502239,0.00022048088,0.00011192751,0.0011708841,0.000047646594,0.0000014462511],"category_scores_gemma":[0.00014387268,0.000050256072,0.000037821,0.0005741345,0.000037246715,0.00030989706,0.00019484415,0.00010294483,7.211637e-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":[0.00004820941,0.00011718326,0.07876293,0.00008947748,0.000023916618,2.4569204e-7,0.0008141493,0.0033374184,0.016798224,0.60503614,0.0007584975,0.29421356],"study_design_scores_gemma":[0.00031895848,0.000013851192,0.05513343,0.000025332156,0.000010043797,1.0713106e-7,0.00010816869,0.86934394,0.009877764,0.06341428,0.0016883073,0.000065825705],"about_ca_topic_score_codex":0.00015467365,"about_ca_topic_score_gemma":0.00004974333,"teacher_disagreement_score":0.9707689,"about_ca_system_score_codex":0.00009750315,"about_ca_system_score_gemma":0.00008336011,"threshold_uncertainty_score":0.21758135},"labels":[],"label_agreement":null},{"id":"W4408813631","doi":"10.5731/pdajpst.2024-003020","title":"Phase-Incremental Decision Trees for Multi-Phase Feature Selection and Interaction in Biologics Manufacturing","year":2025,"lang":"en","type":"article","venue":"PDA Journal of Pharmaceutical Science and Technology","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Roche (Canada)","funders":"","keywords":"Phase (matter); Feature selection; Selection (genetic algorithm); Decision tree; Computer science; Feature (linguistics); Artificial intelligence; Machine learning; Chemistry","score_opus":0.050187309051697694,"score_gpt":0.438773905189776,"score_spread":0.3885865961380783,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408813631","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":[0.601502,0.00029065151,0.39379483,0.0041158767,0.00016470756,0.000093406845,9.857766e-7,0.00002236208,0.000015198338],"genre_scores_gemma":[0.9396459,0.00020501488,0.06000781,0.00011568934,0.000014512665,0.0000035408964,5.437237e-7,0.0000012680002,0.000005743853],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992298,0.000026669966,0.00020943655,0.0002310633,0.00012817155,0.00017485209],"domain_scores_gemma":[0.99951315,0.00012161936,0.000116377974,0.000075763324,0.0001170869,0.000055992426],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010101113,0.0000737572,0.00012337689,0.00074704847,0.00018103891,0.00010062393,0.00033661426,0.00007698704,0.0000017134486],"category_scores_gemma":[0.0005042769,0.000055284247,0.000015253192,0.0007062221,0.00017122735,0.0005340149,0.00014159152,0.00033948402,3.0879337e-7],"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":[0.00007385486,0.00018330185,0.0011589518,0.0000067080377,0.0000040890436,0.0000023757957,0.000023298908,0.0000034305178,0.13166113,0.004527354,0.000039609575,0.8623159],"study_design_scores_gemma":[0.007961281,0.0011944567,0.0033985563,0.00011295645,0.000024429866,0.00027664902,0.000242275,0.51351327,0.43544433,0.006392197,0.03128189,0.00015773471],"about_ca_topic_score_codex":0.0000024261467,"about_ca_topic_score_gemma":0.000012372214,"teacher_disagreement_score":0.8621582,"about_ca_system_score_codex":0.00007757467,"about_ca_system_score_gemma":0.000063552274,"threshold_uncertainty_score":0.2254426},"labels":[],"label_agreement":null},{"id":"W4409150274","doi":"10.1145/3690624.3709290","title":"On the Necessity of World Knowledge for Mitigating Missing Labels in Extreme Classification","year":2025,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","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":false,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute","funders":"","keywords":"Computer science; Data science; Artificial intelligence; Knowledge management","score_opus":0.10967752470100078,"score_gpt":0.3328740019953946,"score_spread":0.2231964772943938,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409150274","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":[0.01651217,0.00007761876,0.89593846,0.020851295,0.00013268163,0.00025843785,0.0000018375614,0.000075076496,0.0661524],"genre_scores_gemma":[0.9770236,0.0000015844091,0.019845614,0.00033091463,0.000011941001,0.000027087415,0.0000066257094,0.0000026332327,0.0027500007],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992092,0.00013610027,0.00023248508,0.00023130307,0.00007866277,0.00011222356],"domain_scores_gemma":[0.9981653,0.0012016062,0.00010981704,0.00044153907,0.00006541722,0.000016296726],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00084664056,0.000065820685,0.00009172667,0.00016360004,0.00012694475,0.000073310955,0.0004878213,0.000026853833,0.000008430214],"category_scores_gemma":[0.0005429021,0.000046168243,0.000028988514,0.00071493816,0.000029280907,0.00014230161,0.00006819327,0.000113231385,0.000005100111],"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":[0.0000037938585,0.000057348538,0.0032188355,0.000030425183,0.0000025714776,3.517489e-8,0.00018325678,0.000017329976,0.005038621,0.8496531,0.0018925165,0.13990213],"study_design_scores_gemma":[0.0003493796,0.000023490564,0.10116196,0.00025465828,0.0000045238644,1.4244594e-7,0.000094735406,0.83544075,0.008945602,0.046747234,0.0068706563,0.00010688336],"about_ca_topic_score_codex":0.000033431414,"about_ca_topic_score_gemma":0.00015091326,"teacher_disagreement_score":0.96051145,"about_ca_system_score_codex":0.000034394,"about_ca_system_score_gemma":0.00006872148,"threshold_uncertainty_score":0.18826863},"labels":[],"label_agreement":null},{"id":"W4409223223","doi":"10.1109/access.2025.3558218","title":"Variability-Aware Machine Learning Model Selection: Feature Modeling, Instantiation, and Experimental Case Study","year":2025,"lang":"en","type":"article","venue":"IEEE Access","topic":"Machine Learning and Data Classification","field":"Computer Science","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":"University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Feature selection; Artificial intelligence; Selection (genetic algorithm); Machine learning; Feature (linguistics); Data modeling; Software engineering","score_opus":0.029730099083008294,"score_gpt":0.34132482943116077,"score_spread":0.3115947303481525,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409223223","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":[0.3542248,0.000084351705,0.64458543,0.00031400856,0.00012659919,0.0001760914,0.0000018688231,0.00017898725,0.0003078303],"genre_scores_gemma":[0.9959444,0.000005346714,0.0034685412,0.00013464954,0.00003362535,0.00003842396,0.000010584881,0.000007457205,0.00035697973],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987275,0.0002140485,0.00019358467,0.00054485555,0.00016952559,0.00015046154],"domain_scores_gemma":[0.9993231,0.000056725396,0.00007580341,0.00037757977,0.00011393949,0.000052804222],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045621803,0.00014511768,0.0001409205,0.00014962068,0.00052877783,0.00054667477,0.00046070945,0.000067576344,0.0000043556443],"category_scores_gemma":[0.00006154873,0.00013795639,0.000022337961,0.0005323833,0.000016019563,0.0010290655,0.00025677477,0.00036337905,0.0000014756638],"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":[0.000035150864,0.00075770676,0.18227974,0.000070823735,0.00007662823,0.000095909105,0.004521071,0.7925534,0.00072985346,0.005712418,0.0006790048,0.012488259],"study_design_scores_gemma":[0.00042521505,0.000049187365,0.00046581027,0.000009015122,0.0000123553555,0.00008693662,0.00023967602,0.99793017,0.00020095354,0.00035045858,0.00009915227,0.00013106962],"about_ca_topic_score_codex":0.00060574483,"about_ca_topic_score_gemma":0.00013938874,"teacher_disagreement_score":0.6417196,"about_ca_system_score_codex":0.00005619958,"about_ca_system_score_gemma":0.0000827973,"threshold_uncertainty_score":0.56256986},"labels":[],"label_agreement":null},{"id":"W4409348085","doi":"10.1609/aaai.v39i23.34697","title":"Error Diversity Matters: An Error-Resistant Ensemble Method for Unsupervised Dependency Parsing","year":2025,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Machine Learning and Data Classification","field":"Computer Science","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":"Northern Alberta Institute of Technology; Mila - Quebec Artificial Intelligence Institute; Queen's University; University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada; Alliance de recherche numérique du Canada; Alberta Innovates; DeepMind","keywords":"Dependency (UML); Dependency grammar; Computer science; Diversity (politics); Ensemble learning; Parsing; Artificial intelligence; Natural language processing; Statistics; Mathematics; Sociology","score_opus":0.11819926005001369,"score_gpt":0.36268660632610566,"score_spread":0.24448734627609198,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409348085","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":[0.03085725,0.000018965053,0.94870716,0.01532684,0.0004401445,0.0005914492,0.000016643799,0.00015712295,0.003884428],"genre_scores_gemma":[0.9459001,0.0000067149267,0.052951436,0.0007466443,0.000030139194,0.00002834943,0.0000040307373,0.000008457938,0.00032412956],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99811256,0.000060953025,0.0004549671,0.000660972,0.00037512768,0.00033539147],"domain_scores_gemma":[0.9983588,0.00021367152,0.0003097106,0.0004845817,0.0005486166,0.00008460411],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010948252,0.00021267134,0.00026134233,0.00018287513,0.0006767713,0.00031588125,0.0024598178,0.000108074884,0.000022131167],"category_scores_gemma":[0.00045946756,0.00017292456,0.00011147598,0.00057990826,0.000111953,0.00059700705,0.000700523,0.00027150684,0.000017707214],"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":[0.00014740716,0.00012507993,0.00037012564,0.00008996718,0.000016423608,1.9521936e-7,0.0013018587,0.00006111195,0.09022473,0.7506543,0.0003336926,0.15667512],"study_design_scores_gemma":[0.00008033933,0.00024643968,0.0010104736,0.0002580432,0.000044261786,0.000001670933,0.0011331899,0.5221568,0.21150506,0.2624236,0.00084946456,0.00029071324],"about_ca_topic_score_codex":0.00025016675,"about_ca_topic_score_gemma":0.000087149965,"teacher_disagreement_score":0.9150429,"about_ca_system_score_codex":0.00006233383,"about_ca_system_score_gemma":0.00011883417,"threshold_uncertainty_score":0.70516586},"labels":[],"label_agreement":null},{"id":"W4409373994","doi":"10.1016/b978-0-443-15888-9.00028-5","title":"More advanced machine learning schemes","year":2025,"lang":"en","type":"book-chapter","venue":"Elsevier eBooks","topic":"Machine Learning and Data Classification","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":"Polytechnique Montréal","funders":"","keywords":"Computer science; Artificial intelligence","score_opus":0.011521215430135191,"score_gpt":0.2543790732767027,"score_spread":0.24285785784656755,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409373994","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":[0.0000019873953,0.0021814038,0.005427317,0.00078124646,0.0003559248,0.0002624349,0.000016500559,0.00052800076,0.9904452],"genre_scores_gemma":[0.00023299459,0.0002036407,0.01855506,0.00046405115,0.000115846124,0.00002651654,0.00017673291,0.000040088053,0.9801851],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99798036,0.000054278586,0.00041729593,0.00085003127,0.00039995433,0.0002980826],"domain_scores_gemma":[0.9980427,0.00011814903,0.00035090727,0.0012589176,0.00011684572,0.000112495516],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002887089,0.00043742036,0.00044967476,0.00027351215,0.00025950532,0.00017812199,0.0012369334,0.0002663398,0.0000734569],"category_scores_gemma":[0.00011143041,0.00041747533,0.00018482131,0.000039901675,0.00007689506,0.00014737128,0.00061788404,0.0011984073,0.00022338684],"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":[0.0000038988283,0.0000036894185,0.000011512274,0.00006250323,0.000031948275,0.000010252301,0.00008044914,0.000005366022,0.000024639314,0.14890693,0.00013604703,0.8507228],"study_design_scores_gemma":[0.00020814604,0.000039948798,0.000024054943,0.0003343748,0.000028660814,0.000008075876,0.0000022368235,0.0049109817,0.00002750761,0.0036422415,0.99037546,0.0003983222],"about_ca_topic_score_codex":9.9561e-7,"about_ca_topic_score_gemma":0.000005960048,"teacher_disagreement_score":0.9902394,"about_ca_system_score_codex":0.0000730767,"about_ca_system_score_gemma":0.00017942049,"threshold_uncertainty_score":0.9998277},"labels":[],"label_agreement":null},{"id":"W4409921902","doi":"10.1007/s10994-025-06766-5","title":"Imbalanced regression pipeline recommendation","year":2025,"lang":"en","type":"article","venue":"Machine Learning","topic":"Machine Learning and Data Classification","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":"École de Technologie Supérieure; Université du Québec à Montréal","funders":"Fundação de Amparo à Ciência e Tecnologia do Estado de Pernambuco; Conselho Nacional de Desenvolvimento Científico e Tecnológico","keywords":"Pipeline (software); Regression; Computer science; Artificial intelligence; Machine learning; Regression analysis; Statistics; Mathematics","score_opus":0.011448653263013342,"score_gpt":0.28772038332406075,"score_spread":0.2762717300610474,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409921902","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":[0.0016250262,0.00028268562,0.9454324,0.014513139,0.0004161572,0.00009760314,0.0000015029714,0.0006614194,0.03697007],"genre_scores_gemma":[0.9600199,0.00009600853,0.024578478,0.0008892648,0.00007898203,0.000017405742,0.0003249298,0.00001189085,0.013983126],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998705,0.00027362676,0.00025502744,0.00041813587,0.00013743623,0.00021075476],"domain_scores_gemma":[0.9991719,0.0001419046,0.00015135462,0.0004256195,0.00006111763,0.00004808444],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00062014465,0.00014255031,0.00015138465,0.00021470046,0.00034019043,0.00016985665,0.0005004138,0.00006478665,0.00008249613],"category_scores_gemma":[0.00048411908,0.0001212864,0.000046377023,0.0005946498,0.00001588344,0.00033948894,0.00026599225,0.00043556772,0.00008482773],"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":[0.000014499475,0.00004145648,0.02564126,0.000017131331,0.000009553194,0.0000017978932,0.00011721931,0.00067484,0.0017732325,0.018944694,0.0061494755,0.94661486],"study_design_scores_gemma":[0.00034189995,0.00002416881,0.011475686,0.000044028653,0.000004910955,0.0000025508853,0.000008597541,0.6163336,0.00036550258,0.0006188532,0.3706671,0.0001131045],"about_ca_topic_score_codex":0.000076955264,"about_ca_topic_score_gemma":0.000014215722,"teacher_disagreement_score":0.9583949,"about_ca_system_score_codex":0.00004623597,"about_ca_system_score_gemma":0.000036918183,"threshold_uncertainty_score":0.4945916},"labels":[],"label_agreement":null},{"id":"W4410264349","doi":"10.1016/j.jss.2025.112460","title":"Unboxing Default Argument Breaking Changes in 1 + 2 data science libraries","year":2025,"lang":"en","type":"article","venue":"Journal of Systems and Software","topic":"Machine Learning and Data Classification","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":"École de Technologie Supérieure; Ontario Tech University","funders":"Fundação de Amparo à Pesquisa do Estado de Minas Gerais; Conselho Nacional de Desenvolvimento Científico e Tecnológico","keywords":"Argument (complex analysis); Computer science; Information retrieval; Chemistry","score_opus":0.028757512252001072,"score_gpt":0.2923493893611655,"score_spread":0.26359187710916443,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410264349","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":[0.06752132,0.009004897,0.91547555,0.0057067783,0.0016027079,0.00015778422,0.0000098059145,0.00006687241,0.00045427773],"genre_scores_gemma":[0.9831226,0.00012205984,0.016495422,0.00009033987,0.00006933653,0.0000012389559,0.0000022113545,0.0000024352319,0.00009436385],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99913186,0.00005368489,0.00026789468,0.00019796731,0.0002178793,0.00013074082],"domain_scores_gemma":[0.9990729,0.00013012088,0.00023654322,0.00042090705,0.0000911913,0.00004832444],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014338566,0.00006284805,0.00015209735,0.00033774067,0.00015224917,0.0006017905,0.0010307961,0.000027359249,6.1042294e-7],"category_scores_gemma":[0.0004232976,0.000048034304,0.000009586062,0.0005018546,0.000053129254,0.0015447822,0.0004659892,0.00015177386,5.575517e-7],"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":[0.0000269404,0.00012847887,0.2824623,0.00074838556,0.000052915893,0.00010127596,0.0038509928,0.0011204241,0.0020226242,0.19741523,0.0025351485,0.50953525],"study_design_scores_gemma":[0.0021366752,0.00030107223,0.4433413,0.006782944,0.00005013502,0.0007426307,0.0031544787,0.33847916,0.0005746663,0.0051923958,0.19853236,0.00071215944],"about_ca_topic_score_codex":0.00009994718,"about_ca_topic_score_gemma":0.000033067507,"teacher_disagreement_score":0.91560125,"about_ca_system_score_codex":0.000035317582,"about_ca_system_score_gemma":0.00017796922,"threshold_uncertainty_score":0.58030796},"labels":[],"label_agreement":null},{"id":"W4410319941","doi":"10.1016/j.neucom.2025.130360","title":"Generative neural architecture search","year":2025,"lang":"en","type":"article","venue":"Neurocomputing","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Bishop's University","funders":"Natural Science Foundation of Shandong Province; Fonds Québécois de la Recherche sur la Nature et les Technologies; National Natural Science Foundation of China; McGill University","keywords":"Computer science; Architecture; Artificial intelligence; Generative grammar; Generative model; Artificial neural network; Machine learning; Pattern recognition (psychology)","score_opus":0.015479871382477785,"score_gpt":0.28675727019316793,"score_spread":0.27127739881069013,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410319941","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":[0.04530752,0.000046341676,0.938202,0.008344161,0.0003132643,0.000103632956,5.140294e-7,0.00031786528,0.0073646726],"genre_scores_gemma":[0.949901,0.000001379805,0.047581747,0.0019356149,0.00010592513,0.0000034965046,0.000005088448,0.000005057906,0.00046068267],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988723,0.00019716605,0.00014710407,0.0004070262,0.00015169219,0.0002247162],"domain_scores_gemma":[0.9992712,0.00017322603,0.000038854352,0.00042884191,0.000045332978,0.000042538057],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020443452,0.00010018546,0.00009346232,0.00014262073,0.00026296795,0.00022035661,0.0006901089,0.000031189375,0.000002671234],"category_scores_gemma":[0.00007549146,0.00009067907,0.000037172606,0.00052614545,0.00001725363,0.000112376496,0.00040218674,0.00036301053,0.000021258293],"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":[0.000003946214,0.000032908385,0.00421112,0.000025178715,0.000008687567,0.000013001677,0.0006882701,0.02802177,0.006036195,0.12241851,0.001268137,0.8372723],"study_design_scores_gemma":[0.00016089797,0.000027824173,0.027414836,0.000014044217,0.0000019632928,0.000011640879,0.000011448573,0.9577144,0.001068129,0.00085742655,0.012618863,0.000098532895],"about_ca_topic_score_codex":0.000015693451,"about_ca_topic_score_gemma":0.0000018124108,"teacher_disagreement_score":0.9296926,"about_ca_system_score_codex":0.000014456618,"about_ca_system_score_gemma":0.00004636338,"threshold_uncertainty_score":0.3697785},"labels":[],"label_agreement":null},{"id":"W4410552841","doi":"10.1109/saner64311.2025.00053","title":"Evaluating the Effectiveness and Efficiency of Demonstration Retrievers in RAG for Coding Tasks","year":2025,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University; University of Manitoba","funders":"","keywords":"Computer science; Coding (social sciences); Mathematics; Statistics","score_opus":0.03623371557916335,"score_gpt":0.36805999315101207,"score_spread":0.33182627757184874,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410552841","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":[0.23618868,0.000028865285,0.7619802,0.00041318667,0.00004941516,0.00021313061,4.4508943e-7,0.000014743188,0.0011113731],"genre_scores_gemma":[0.9897498,0.000002865882,0.010167436,0.000028635854,0.0000029069122,0.000016283833,0.0000017563602,8.6023647e-7,0.0000294766],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.999417,0.00018062723,0.000118652126,0.00014828406,0.00007335024,0.00006205447],"domain_scores_gemma":[0.99852735,0.0012173373,0.000047360314,0.00016120219,0.000039965038,0.0000067717183],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023330282,0.000035450597,0.00005926023,0.00006131694,0.00008220827,0.00003885529,0.00016863686,0.000020892492,5.186661e-7],"category_scores_gemma":[0.000881068,0.000024639125,0.000011394141,0.00032841705,0.000025267298,0.00010976705,0.000045413955,0.00005225783,1.7578152e-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":[0.00005174548,0.000030803792,0.029853778,0.00012242621,0.0000056518243,8.241312e-8,0.00030224046,0.0015082429,0.029660255,0.64289784,0.000026011989,0.29554093],"study_design_scores_gemma":[0.00035130238,0.00007138862,0.15476812,0.00004368812,0.000003344721,3.8048267e-7,0.00004426962,0.83670753,0.0051814583,0.002768669,0.000028558079,0.000031296786],"about_ca_topic_score_codex":0.00004325647,"about_ca_topic_score_gemma":0.000009296522,"teacher_disagreement_score":0.8351993,"about_ca_system_score_codex":0.000014387392,"about_ca_system_score_gemma":0.000047703717,"threshold_uncertainty_score":0.105478436},"labels":[],"label_agreement":null},{"id":"W4410632692","doi":"10.22215/etd/2024-16393","title":"Learning with Limited Datasets: From Deep-Learning to Traditional Machine-Learning","year":2024,"lang":"en","type":"dissertation","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","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":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Artificial intelligence; Deep learning; Computer science; Machine learning","score_opus":0.018468319019022898,"score_gpt":0.25494258844940243,"score_spread":0.23647426943037952,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410632692","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":[0.107795276,0.004907618,0.7303085,0.007003356,0.00535722,0.0025665849,0.0013333985,0.014326189,0.1264019],"genre_scores_gemma":[0.4569439,0.0003045911,0.09311956,0.00069307676,0.0009890064,0.00030099382,0.39003932,0.0003482303,0.05726132],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99556434,0.00048158536,0.0005894411,0.0017734603,0.0010406674,0.0005505251],"domain_scores_gemma":[0.99773586,0.00058422453,0.000383729,0.00079744414,0.00015408525,0.00034463484],"candidate_categories":["metaepi_narrow","scholarly_communication","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005544895,0.00066454784,0.00052060466,0.000703433,0.00066134386,0.0014013915,0.0014309732,0.00034706542,0.0005699563],"category_scores_gemma":[0.00056435115,0.0005781517,0.00013464916,0.0011760474,0.00002575285,0.00072961464,0.00021643167,0.0034403,0.0017332982],"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":[0.0006813156,0.00046471093,0.006298646,0.00081783475,0.0011779254,0.0005137679,0.028909381,0.07081144,0.0030867208,0.048206892,0.018939681,0.82009166],"study_design_scores_gemma":[0.0005213554,0.00080646906,0.013407412,0.00070341356,0.00017848205,0.000032664222,0.001979703,0.60915935,0.00018637629,0.00047662633,0.37112138,0.0014267652],"about_ca_topic_score_codex":0.0009264594,"about_ca_topic_score_gemma":0.00093461527,"teacher_disagreement_score":0.8186649,"about_ca_system_score_codex":0.0001327075,"about_ca_system_score_gemma":0.00019008991,"threshold_uncertainty_score":0.999667},"labels":[],"label_agreement":null},{"id":"W4410743021","doi":"10.1007/978-3-031-91524-6_2","title":"Understanding AI and ML","year":2025,"lang":"en","type":"book-chapter","venue":"Progress in IS","topic":"Machine Learning and Data Classification","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":"National Research Council Canada; McGill University; MacEwan University; York University; University of Toronto","funders":"","keywords":"Computer science","score_opus":0.07465505201584716,"score_gpt":0.30921291886343366,"score_spread":0.2345578668475865,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410743021","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":[0.0000025754741,0.0057039135,0.24491231,0.011441003,0.00035641223,0.0002429929,0.000016195214,0.00020203501,0.73712254],"genre_scores_gemma":[0.11187494,0.002392983,0.04073904,0.0032603394,0.00028192834,0.00007466834,0.00014983336,0.000072206356,0.84115404],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991659,0.000014417336,0.00015208429,0.0003973161,0.00015175667,0.000118553085],"domain_scores_gemma":[0.9994055,0.000047991023,0.00008396983,0.00041237692,0.00001851026,0.000031652162],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016809523,0.00013113905,0.00014661161,0.00020441903,0.00006113274,0.00018657981,0.0003615416,0.0001350864,0.000022680284],"category_scores_gemma":[0.0000128134625,0.0001281695,0.000023035669,0.000050902745,0.0000667681,0.00013056849,0.00027450896,0.0003341109,0.000014680334],"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":[0.0000013203638,0.0000036693295,0.0018351568,0.000052939136,0.0000068379522,0.000006154013,0.00013401377,1.8246753e-7,5.2804236e-8,0.81288606,0.003291017,0.18178257],"study_design_scores_gemma":[0.00033904568,0.000053371743,0.0010913584,0.0008931248,0.000018401115,0.000009837809,0.000008980954,0.04341778,0.000005635005,0.29955247,0.6541424,0.00046763185],"about_ca_topic_score_codex":0.0000041614053,"about_ca_topic_score_gemma":0.0000069743505,"teacher_disagreement_score":0.65085137,"about_ca_system_score_codex":0.00007356479,"about_ca_system_score_gemma":0.000046410645,"threshold_uncertainty_score":0.5226601},"labels":[],"label_agreement":null},{"id":"W4410802186","doi":"10.1117/12.3053835","title":"A bibliometric review of machine learning applications in multidomain operations: a decade of progress","year":2025,"lang":"en","type":"review","venue":"","topic":"Machine Learning and Data Classification","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":false,"ca_institutions":"McMaster University","funders":"","keywords":"Computer science; Data science; Artificial intelligence","score_opus":0.04171308528816181,"score_gpt":0.38820070579400284,"score_spread":0.34648762050584103,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410802186","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":[6.193722e-8,0.84772444,0.14996608,0.00009468093,0.00002102891,0.0013874703,0.00002597576,0.00006211429,0.0007181396],"genre_scores_gemma":[0.0000042937527,0.94010484,0.05824615,0.000023201497,0.000009104351,0.0007689975,0.00045777683,0.0000105617555,0.00037508985],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9970064,0.00062186667,0.0013294588,0.00053355715,0.00033701234,0.00017170458],"domain_scores_gemma":[0.9973605,0.0007561006,0.000613072,0.0010131819,0.00020778384,0.00004933339],"candidate_categories":["bibliometrics"],"consensus_categories":["bibliometrics"],"category_scores_codex":[0.0014015174,0.000257607,0.0013777015,0.025023097,0.00005721281,0.000046996207,0.0014686298,0.00014362978,0.000021915372],"category_scores_gemma":[0.0012353632,0.00019523846,0.00024066973,0.09911106,0.000051614865,0.00019777218,0.00038827144,0.00047395617,0.000010096312],"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":[1.7210886e-7,0.00009722301,0.00012386267,0.12699251,0.000016081085,2.6396992e-7,0.000008837762,0.00000552553,1.1624047e-7,0.0108601935,0.000047772854,0.86184746],"study_design_scores_gemma":[0.000106258056,0.00003109612,0.00008247421,0.09640069,0.00010854252,0.0000042906954,0.0000024378212,0.005893141,0.0000010967487,0.00001854577,0.8971611,0.0001903163],"about_ca_topic_score_codex":0.000122010184,"about_ca_topic_score_gemma":0.000019773526,"teacher_disagreement_score":0.8971133,"about_ca_system_score_codex":0.00004834704,"about_ca_system_score_gemma":0.00046320327,"threshold_uncertainty_score":0.9860274},"labels":[{"model":"gemma","categories":["bibliometrics"],"domain":null,"study_design":"not_applicable","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":["bibliometrics"],"domain":null,"study_design":"observational","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W4411271784","doi":"10.1109/msr66628.2025.00110","title":"TriGraph: A Probabilistic Subgraph-Based Model for Visual Code Completion in Pure Data","year":2025,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","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":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Probabilistic logic; Code (set theory); Programming language; Artificial intelligence","score_opus":0.07307220060830805,"score_gpt":0.3594769382670126,"score_spread":0.28640473765870456,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411271784","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":[0.0020830384,0.000024546584,0.9920398,0.004553302,0.000063544554,0.00043237416,0.00006569485,0.00016887975,0.0005688284],"genre_scores_gemma":[0.90767854,0.0000024570206,0.09046803,0.000560321,0.000009289649,0.00008516412,0.00086788007,0.0000045397514,0.0003237869],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99884045,0.00007305609,0.00023751344,0.00053838396,0.00013541938,0.00017515461],"domain_scores_gemma":[0.9986449,0.00021486035,0.000057581456,0.0009862182,0.00006351522,0.00003291406],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00064165716,0.00009752711,0.00013411748,0.0002750105,0.00008773756,0.00012276213,0.0010888716,0.000051772487,0.000003212216],"category_scores_gemma":[0.0002625406,0.000086644635,0.000031171046,0.0006582883,0.000031985535,0.00027719222,0.00016139759,0.00010933841,0.0000034773418],"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":[0.00008171048,0.00047752116,0.007091502,0.00019085774,0.000011781349,8.0306995e-7,0.00008993683,0.039310772,0.00044520633,0.9102643,0.013855578,0.028180027],"study_design_scores_gemma":[0.00064244674,0.000030623156,0.0051485375,0.000023227569,0.00000578488,2.2433139e-7,0.000004681196,0.98006874,0.000017321867,0.011021056,0.0029438478,0.0000934911],"about_ca_topic_score_codex":0.000075811935,"about_ca_topic_score_gemma":0.0013390834,"teacher_disagreement_score":0.940758,"about_ca_system_score_codex":0.000025626412,"about_ca_system_score_gemma":0.00016244325,"threshold_uncertainty_score":0.35332656},"labels":[],"label_agreement":null},{"id":"W4411358394","doi":"10.1016/j.asoc.2025.113266","title":"Multi-granularity ensemble sample selection and label correction for classification with noisy labels","year":2025,"lang":"en","type":"article","venue":"Applied Soft Computing","topic":"Machine Learning and Data Classification","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 Alberta","funders":"National Key Research and Development Program of China; Key Technologies Research and Development Program; Natural Science Foundation of Jiangxi Province; National Natural Science Foundation of China","keywords":"Granularity; Computer science; Artificial intelligence; Selection (genetic algorithm); Pattern recognition (psychology); Sample (material); Ensemble learning; Machine learning; Feature selection; Chromatography","score_opus":0.023933881220577234,"score_gpt":0.2868405027664851,"score_spread":0.2629066215459079,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411358394","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":[0.01850955,0.000028617806,0.97956187,0.00046632302,0.00022464295,0.00042439377,0.000002382747,0.00040026353,0.00038198935],"genre_scores_gemma":[0.6493608,0.000002398414,0.35028523,0.0001584602,0.000028260458,0.00003215607,0.000044542598,0.000007147583,0.00008103328],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99883515,0.00004881547,0.00021852963,0.00054948713,0.00012234758,0.00022569842],"domain_scores_gemma":[0.99881244,0.00056623906,0.0001592091,0.0002862209,0.00013111469,0.00004479542],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00051050546,0.00014436079,0.00015707764,0.0001313989,0.0005968835,0.0002256751,0.00022336547,0.000085820546,4.924035e-7],"category_scores_gemma":[0.00015015651,0.00013991211,0.000017959657,0.0005271194,0.000029501416,0.0001608711,0.0000889963,0.0001989387,0.000003287545],"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":[0.000066837856,0.00019536153,0.014928915,0.0001157145,0.000041003917,1.6393561e-7,0.0005933641,0.001643508,0.03774395,0.119855024,0.00064538413,0.82417077],"study_design_scores_gemma":[0.0009089129,0.00004965496,0.030440211,0.00002928109,0.00001680882,0.0000035039025,0.000055308068,0.96324617,0.0011767091,0.001119834,0.0027995345,0.0001540551],"about_ca_topic_score_codex":0.00012581848,"about_ca_topic_score_gemma":0.00010476263,"teacher_disagreement_score":0.9616027,"about_ca_system_score_codex":0.00005988993,"about_ca_system_score_gemma":0.00006781399,"threshold_uncertainty_score":0.570545},"labels":[],"label_agreement":null},{"id":"W4411540031","doi":"10.1016/j.datak.2025.102482","title":"Domain knowledge in artificial intelligence: Using conceptual modeling to increase machine learning accuracy and explainability","year":2025,"lang":"en","type":"article","venue":"Data & Knowledge Engineering","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Artificial intelligence; Computer science; Domain (mathematical analysis); Machine learning; Domain knowledge; Artificial Intelligence System; Mathematics","score_opus":0.06691927417424057,"score_gpt":0.33926893247535406,"score_spread":0.27234965830111346,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411540031","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":[0.14754272,0.0011903007,0.8501359,0.00017862406,0.00028875415,0.000216162,0.000024834184,0.00019972427,0.00022295552],"genre_scores_gemma":[0.90180355,0.000024534358,0.09783458,0.000019140507,0.000096452146,0.000021813188,0.00015661566,0.000017307759,0.00002597387],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99785763,0.000208543,0.0005190331,0.0008911419,0.00012177945,0.00040184773],"domain_scores_gemma":[0.9980868,0.0005160269,0.000055156237,0.0010978455,0.00008466942,0.00015951133],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0016811909,0.00025636362,0.0002911777,0.0005122308,0.00019612595,0.00024418713,0.0013152265,0.00009464168,0.000006479631],"category_scores_gemma":[0.0017831986,0.00027979995,0.000025906767,0.0011879462,0.0000396167,0.00090265897,0.0021154578,0.0005805095,0.000026862193],"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":[0.000051187828,0.00033346922,0.0027645214,0.00035433183,0.000037532747,0.000016925658,0.008983845,0.107815444,0.005358594,0.27260888,0.00008330066,0.60159194],"study_design_scores_gemma":[0.000110384965,0.000019112756,0.00027021006,0.00015349292,0.000007396895,0.000004737663,0.00042251128,0.991344,0.00013192107,0.00058306305,0.006690996,0.0002621753],"about_ca_topic_score_codex":0.0003183823,"about_ca_topic_score_gemma":0.000246959,"teacher_disagreement_score":0.88352853,"about_ca_system_score_codex":0.00016382389,"about_ca_system_score_gemma":0.00016446077,"threshold_uncertainty_score":0.9999654},"labels":[],"label_agreement":null},{"id":"W4411552822","doi":"10.1109/icse55347.2025.00066","title":"Answering User Questions About Machine Learning Models Through Standardized Model Cards","year":2025,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","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":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Artificial intelligence; Machine learning; Natural language processing","score_opus":0.028470333698872627,"score_gpt":0.29926580179401663,"score_spread":0.270795468095144,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411552822","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":[0.0007745959,0.00037263494,0.9227877,0.0020104547,0.00013950207,0.00011141649,0.000010687631,0.0007439183,0.07304906],"genre_scores_gemma":[0.6904406,0.00019004072,0.2939449,0.00047428932,0.00002211937,0.000028630502,0.000039834646,0.000012406533,0.014847213],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99860924,0.00012319029,0.00026321036,0.0004744792,0.0002682734,0.00026159108],"domain_scores_gemma":[0.99898463,0.00007443816,0.000068271365,0.00069179403,0.00012587161,0.00005498112],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043317524,0.00016197118,0.00019775459,0.00012109706,0.00038413494,0.00029443557,0.0006251387,0.00007377085,0.000015735779],"category_scores_gemma":[0.000113735696,0.0001449718,0.00007346515,0.00045199372,0.0000322817,0.0010664258,0.00029988075,0.00037034476,0.000016499851],"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":[0.0000053783865,0.000017762675,0.00039353885,0.000012128336,0.0000152302355,7.912257e-7,0.00030188978,0.41325632,0.0002552311,0.57514095,0.0006927167,0.009908052],"study_design_scores_gemma":[0.00031156628,0.000013784732,0.00026182752,0.00003441238,0.000010320495,0.0000016201009,0.000018282964,0.9529563,0.00017000813,0.018964052,0.027108079,0.0001497531],"about_ca_topic_score_codex":0.0005560202,"about_ca_topic_score_gemma":0.00006415508,"teacher_disagreement_score":0.689666,"about_ca_system_score_codex":0.000075341944,"about_ca_system_score_gemma":0.00016661434,"threshold_uncertainty_score":0.5911778},"labels":[],"label_agreement":null},{"id":"W4411991166","doi":"10.1016/j.mlwa.2025.100696","title":"Feature engineering through two-level genetic algorithm","year":2025,"lang":"en","type":"article","venue":"Machine Learning with Applications","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary; University of Winnipeg","funders":"Mitacs","keywords":"Feature (linguistics); Genetic algorithm; Computer science; Algorithm; Artificial intelligence; Machine learning","score_opus":0.008721934370368313,"score_gpt":0.2498578987933728,"score_spread":0.2411359644230045,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411991166","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":[0.00011901663,0.00052636524,0.9882352,0.006181195,0.000056225777,0.00033035586,0.000010655561,0.0007163214,0.003824674],"genre_scores_gemma":[0.05397751,0.000038361286,0.93958163,0.00038889836,0.000089572415,0.00043633545,0.0001525973,0.000024172929,0.0053109424],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986811,0.000066651206,0.00016996924,0.0005784516,0.0002138482,0.00028995768],"domain_scores_gemma":[0.99873275,0.00013773088,0.000113414746,0.0008553015,0.0000921159,0.000068709116],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016493651,0.00021476508,0.00017308148,0.0001585706,0.00040722135,0.000217642,0.0008188589,0.00006811655,0.00000913719],"category_scores_gemma":[0.000054098295,0.00018793222,0.000043779823,0.0011712419,0.000034821416,0.00023075887,0.00018745546,0.000664076,0.000081397615],"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":[0.0000067493525,0.0001202666,0.0132682,0.000071228926,0.00008735287,0.0000058718097,0.00031426217,0.06482227,0.0006433047,0.23364563,0.0011691467,0.68584573],"study_design_scores_gemma":[0.00037776696,0.00003194367,0.020337407,0.0000278318,0.000019313422,0.000020999603,0.000009643776,0.5734981,0.000100190686,0.00056394964,0.40480557,0.00020733284],"about_ca_topic_score_codex":0.00012899651,"about_ca_topic_score_gemma":0.000014528171,"teacher_disagreement_score":0.68563837,"about_ca_system_score_codex":0.00004976614,"about_ca_system_score_gemma":0.00008106898,"threshold_uncertainty_score":0.76636535},"labels":[],"label_agreement":null},{"id":"W4412002212","doi":"10.1016/j.patter.2025.101317","title":"OpenML: Insights from 10 years and more than a thousand papers","year":2025,"lang":"en","type":"article","venue":"Patterns","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Leibniz-Gemeinschaft; HORIZON EUROPE Framework Programme; Tartu Ülikool; KU Leuven; Nederlandse Organisatie voor Wetenschappelijk Onderzoek; Technische Universiteit Eindhoven; Deutsche Forschungsgemeinschaft; Ludwig-Maximilians-Universität München; European Commission; Universiteit Leiden; Institut national de recherche en informatique et en automatique (INRIA)","keywords":"History; Data science; Computer science","score_opus":0.0109027440840229,"score_gpt":0.2630513411137447,"score_spread":0.25214859702972175,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412002212","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":[0.92650336,0.00031463226,0.060397476,0.003259759,0.00023147315,0.000106087406,0.000021393955,0.00015762594,0.009008207],"genre_scores_gemma":[0.997148,0.000036206922,0.0012070576,0.0005256742,0.000028041597,0.000007123202,0.00003215967,0.0000035456214,0.0010122156],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99942786,0.000044437675,0.000081249134,0.00027267312,0.00008844246,0.00008533717],"domain_scores_gemma":[0.9994794,0.000058991955,0.000030594252,0.0003817257,0.000011734254,0.00003753813],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00004492093,0.00006550614,0.00007497274,0.00005292376,0.00005819488,0.00015785576,0.00034206276,0.000032412554,0.000037827493],"category_scores_gemma":[0.000024797098,0.000057787438,0.000015461535,0.00010075972,0.000016675514,0.00014096881,0.00019933547,0.000081844766,0.000035746212],"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":[0.000015290621,0.00007628426,0.47578257,0.000037593123,0.00006098338,0.000032779833,0.004747795,0.000020689076,0.0034166528,0.019118574,0.0043142866,0.49237648],"study_design_scores_gemma":[0.00020362242,0.000012433635,0.9444973,0.00003396497,0.000005448127,7.69791e-7,0.000058980593,0.0072345864,0.00015490646,0.00057335594,0.04714142,0.00008324181],"about_ca_topic_score_codex":0.000519965,"about_ca_topic_score_gemma":0.00013223717,"teacher_disagreement_score":0.49229324,"about_ca_system_score_codex":0.000007983836,"about_ca_system_score_gemma":0.000018198667,"threshold_uncertainty_score":0.23565033},"labels":[],"label_agreement":null},{"id":"W4412190188","doi":"10.1007/978-981-96-8892-0_36","title":"Using Meta-Learning to Predict Work-in-Progress: An Approach for Small Datasets","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Machine Learning and Data Classification","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 Calgary","funders":"","keywords":"Computer science; Artificial intelligence; Machine learning; Work (physics); Data science","score_opus":0.073403482552982,"score_gpt":0.31593376757793945,"score_spread":0.24253028502495744,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412190188","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":[0.000029100445,0.0004621969,0.99696505,0.00048594325,0.0004967706,0.000829754,0.000053232812,0.00018739775,0.0004905373],"genre_scores_gemma":[0.011557478,0.000007882705,0.98693144,0.00065847737,0.0002219097,0.000063545034,0.00034514768,0.000028935023,0.0001851592],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99567616,0.00012878886,0.0005799498,0.0022906289,0.0006267467,0.0006977504],"domain_scores_gemma":[0.99697745,0.00046660742,0.00029411053,0.0018899566,0.00015688731,0.00021498413],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0021679637,0.0005343385,0.00069632306,0.0013088582,0.00032312065,0.0008777345,0.0040842853,0.00028158072,0.0000052347723],"category_scores_gemma":[0.00031113494,0.00047845466,0.00014011438,0.0012081347,0.00024157704,0.00063832744,0.0015076521,0.0009813608,0.0000041508297],"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":[0.000023155279,0.00006110863,0.00043241028,0.00009442517,0.00004250367,0.0000129172,0.00048343162,0.31614345,0.000018701165,0.006905738,0.000039802926,0.6757423],"study_design_scores_gemma":[0.0002150295,0.00014208574,0.00026311906,0.00020648944,0.00006263186,0.000011502253,4.17141e-7,0.9888541,0.000045815083,0.00385475,0.005827406,0.0005166314],"about_ca_topic_score_codex":0.000054120967,"about_ca_topic_score_gemma":0.00005365633,"teacher_disagreement_score":0.67522573,"about_ca_system_score_codex":0.00022264391,"about_ca_system_score_gemma":0.00045577248,"threshold_uncertainty_score":0.9997667},"labels":[],"label_agreement":null},{"id":"W4412217228","doi":"","title":"Zero-shot Clustering of Embeddings with Pretrained and Self-Supervised Learnt Encoders","year":2023,"lang":"en","type":"article","venue":"VBN Forskningsportal (Aalborg Universitet)","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Guelph; Vector Institute; Dalhousie University","funders":"","keywords":"Zero (linguistics); Cluster analysis; Shot (pellet); Encoder; Artificial intelligence; Computer science; Pattern recognition (psychology); Speech recognition; Chemistry","score_opus":0.011997495187589241,"score_gpt":0.21969979718894123,"score_spread":0.20770230200135198,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412217228","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":[0.856274,0.000036328394,0.13199101,0.0005967152,0.00010437929,0.00027106714,0.000012481956,0.0009994158,0.0097146025],"genre_scores_gemma":[0.97399735,0.00004528568,0.024445646,0.00005113521,0.000015942749,0.0000020847615,0.000072374045,0.00002027017,0.0013499098],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99863005,0.000036065674,0.00020671177,0.0004841661,0.00032741774,0.0003155811],"domain_scores_gemma":[0.99906754,0.00007683464,0.00019681123,0.0004254902,0.000089799985,0.00014354585],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002914559,0.0001894451,0.00022369988,0.0003749263,0.00019279982,0.0000745946,0.00051368965,0.00008259957,0.000024827672],"category_scores_gemma":[0.000034488814,0.00017855752,0.00005063976,0.0010492234,0.00008732281,0.0007411762,0.0002724747,0.00018980916,0.000021784952],"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":[0.00094756245,0.00093166594,0.4786053,0.002111065,0.0013195131,0.0014833456,0.14548376,0.029611897,0.03810455,0.18048646,0.014856897,0.10605797],"study_design_scores_gemma":[0.0018657823,0.00060385326,0.047731385,0.00016568974,0.00007298184,0.000058998852,0.0030310648,0.92962265,0.00071422546,0.0002432779,0.015255934,0.00063414726],"about_ca_topic_score_codex":0.00014394919,"about_ca_topic_score_gemma":0.000027642749,"teacher_disagreement_score":0.90001076,"about_ca_system_score_codex":0.000037771984,"about_ca_system_score_gemma":0.00007802945,"threshold_uncertainty_score":0.7281364},"labels":[],"label_agreement":null},{"id":"W4412444163","doi":"10.1016/j.jval.2025.04.1272","title":"MSR120 Estimating Sample Size for Training Ensemble Machine Learning Models","year":2025,"lang":"en","type":"article","venue":"Value in Health","topic":"Machine Learning and Data Classification","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":"Children's Hospital of Eastern Ontario","funders":"","keywords":"Training (meteorology); Ensemble learning; Computer science; Machine learning; Sample (material); Artificial intelligence; Sample size determination; Statistics; Mathematics; Geography; Chemistry; Chromatography","score_opus":0.11542284370992471,"score_gpt":0.34130861622580205,"score_spread":0.22588577251587733,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412444163","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":[0.0021489148,0.00032501252,0.9891714,0.0067028734,0.00029090417,0.00029771673,0.0000081107,0.00022296135,0.0008321247],"genre_scores_gemma":[0.40420738,0.000019769248,0.5949642,0.00051269215,0.000037283342,0.000037267575,0.00001971936,0.000008070671,0.000193645],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99830586,0.00028700865,0.00043812665,0.00042932678,0.00014732935,0.00039237062],"domain_scores_gemma":[0.9965425,0.0028098493,0.00017862386,0.00035718983,0.000036999776,0.00007481403],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020468927,0.00012047432,0.0002317781,0.00015927585,0.0003299208,0.00010872734,0.00042561284,0.000050033304,0.0000030318697],"category_scores_gemma":[0.0020357268,0.00012377017,0.000041943826,0.00047495324,0.000013606741,0.00027570053,0.000101983154,0.00031838284,0.0000036321592],"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":[0.000007438635,0.000026894424,0.001191304,0.00020973092,0.0000050285416,4.5718824e-7,0.002151968,0.6329671,0.000040657076,0.178125,0.00012497966,0.18514945],"study_design_scores_gemma":[0.0003503382,0.00006763106,0.0004920779,0.00015945955,0.0000016280987,0.0000016791838,0.000062568804,0.9339303,0.000010484074,0.061338603,0.003492929,0.00009229801],"about_ca_topic_score_codex":0.004665253,"about_ca_topic_score_gemma":0.00006230322,"teacher_disagreement_score":0.40205845,"about_ca_system_score_codex":0.00011682998,"about_ca_system_score_gemma":0.00036002434,"threshold_uncertainty_score":0.70524985},"labels":[],"label_agreement":null},{"id":"W4412604194","doi":"10.36227/techrxiv.175329122.29020847/v1","title":"A Survey of Next-Generation AI and Its Evolving Landscape","year":2025,"lang":"en","type":"preprint","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Pakistan Institute of Engineering and Applied Sciences","keywords":"Geography; Computer science; Environmental resource management; Environmental science","score_opus":0.08207158762354864,"score_gpt":0.31316338270315885,"score_spread":0.2310917950796102,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412604194","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":[0.014870036,0.0022518162,0.972789,0.0017996404,0.0005586647,0.00022414133,0.000058720485,0.00016059206,0.0072873808],"genre_scores_gemma":[0.990085,0.00013675915,0.007942626,0.00013052617,0.00003650126,0.0000090064,0.00035053815,0.0000028645643,0.0013061883],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988933,0.00022919859,0.00023381288,0.00041389116,0.00014451922,0.00008525146],"domain_scores_gemma":[0.9989433,0.00011446824,0.00014546052,0.0005241178,0.00023967493,0.000032949443],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007851154,0.00010930847,0.00017277793,0.00013584043,0.000049449558,0.00024891415,0.0004571518,0.000118122975,0.000022106386],"category_scores_gemma":[0.0004110013,0.00009856013,0.000021844915,0.0001729004,0.0000073059578,0.00022456162,0.00085930276,0.0002468391,0.0000043125765],"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":[0.000018666362,0.00025944362,0.209657,0.0016729905,0.00018676964,0.0000031495115,0.0017958978,0.007696573,0.005765819,0.16674532,0.055858627,0.55033976],"study_design_scores_gemma":[0.00005686435,0.000009337075,0.12578185,0.000037049052,0.00000420998,4.054643e-7,0.0000014815924,0.87353283,0.00018683726,0.00011170398,0.00019296446,0.00008447428],"about_ca_topic_score_codex":0.00076619,"about_ca_topic_score_gemma":0.00034391615,"teacher_disagreement_score":0.97521496,"about_ca_system_score_codex":0.000009749676,"about_ca_system_score_gemma":0.00016142055,"threshold_uncertainty_score":0.40191653},"labels":[],"label_agreement":null},{"id":"W4412689102","doi":"10.47297/taposatwsp2633-456911.20250605","title":"Optimizing Random Forest with Apache Spark: A Survey on Distributed Machine Learning and Big Data Scalability","year":2025,"lang":"en","type":"article","venue":"Theory and Practice of Science and Technology","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"SPARK (programming language); Scalability; Big data; Random forest; Computer science; Database; Operating system; Data science; Distributed computing; Machine learning; Programming language","score_opus":0.03292571789572647,"score_gpt":0.30944922155147464,"score_spread":0.2765235036557482,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412689102","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":[0.4004462,0.0010781713,0.5850613,0.010970126,0.0000867141,0.00026768807,0.000056454934,0.00017698974,0.0018563296],"genre_scores_gemma":[0.99178225,0.0003020955,0.007780851,0.000072428775,0.000003901116,0.0000027555407,0.0000276362,0.0000021637793,0.000025903058],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984354,0.000512807,0.00015059237,0.0005616254,0.00016506556,0.00017452812],"domain_scores_gemma":[0.99592197,0.0030731,0.00014345245,0.00064386136,0.00017237199,0.000045215707],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.011407244,0.000099560275,0.00017312224,0.000275116,0.00047030603,0.00013452982,0.00064628787,0.00006513117,7.281176e-7],"category_scores_gemma":[0.012816519,0.00007210388,0.00000380516,0.0013535878,0.002050256,0.0007711396,0.0007854177,0.00033717472,3.4828335e-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":[0.0014015904,0.00013758775,0.07874222,0.00005554616,0.00003225984,0.0000049157966,0.00031268937,0.00006869704,0.0018159698,0.47369358,0.000018265806,0.44371668],"study_design_scores_gemma":[0.010379719,0.0037671411,0.3663277,0.00064254383,0.00033587602,0.0006136883,0.0058777547,0.47880992,0.006582225,0.08951258,0.03572509,0.0014257464],"about_ca_topic_score_codex":0.00013700729,"about_ca_topic_score_gemma":0.00005668826,"teacher_disagreement_score":0.5913361,"about_ca_system_score_codex":0.000009254008,"about_ca_system_score_gemma":0.00011308071,"threshold_uncertainty_score":0.99549896},"labels":[],"label_agreement":null},{"id":"W4413052970","doi":"10.1016/j.datak.2025.102500","title":"Corrigendum to “Domain knowledge in artificial intelligence: Using conceptual modeling to increase machine learning accuracy and explainability” [Knowledge and Data Engineering Volume 160, November 2025, 102482]","year":2025,"lang":"en","type":"erratum","venue":"Data & Knowledge Engineering","topic":"Machine Learning and Data Classification","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":"Memorial University of Newfoundland","funders":"","keywords":"Computer science; Domain knowledge; Artificial intelligence; Domain (mathematical analysis); Volume (thermodynamics); Machine learning; Knowledge engineering; Mathematics","score_opus":0.08647812660475818,"score_gpt":0.3363630339300379,"score_spread":0.24988490732527974,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413052970","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":[0.0024787565,0.012756038,0.9694457,0.00027200315,0.011465122,0.0010827109,0.0012267901,0.0005604174,0.0007124765],"genre_scores_gemma":[0.18678826,0.0027982828,0.6892267,0.0003173668,0.013253903,0.00081647706,0.062424656,0.0014179047,0.042956457],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9929832,0.00035798372,0.001490739,0.0035198433,0.00040631366,0.0012419086],"domain_scores_gemma":[0.9934874,0.0006866326,0.00022810402,0.004539991,0.0002962784,0.00076157204],"candidate_categories":["metaepi_narrow","open_science","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0032577312,0.0011825225,0.0012783494,0.0018001433,0.00038197692,0.0008987782,0.005350573,0.0006334391,0.000033281438],"category_scores_gemma":[0.0063778316,0.0013823294,0.00007170892,0.002408631,0.00007915158,0.001907009,0.015189141,0.0030250177,0.00011389428],"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":[0.00020774324,0.0014005317,0.0011791424,0.0075163036,0.00054118806,0.00019906719,0.029208105,0.1134738,0.0021187908,0.025285376,0.20750576,0.6113642],"study_design_scores_gemma":[0.00015415435,0.000051315907,0.000086825,0.0010898544,0.00005186854,0.000020107107,0.00024438166,0.73562825,0.000009950872,0.000030481937,0.26166552,0.00096730184],"about_ca_topic_score_codex":0.00076442916,"about_ca_topic_score_gemma":0.0014051938,"teacher_disagreement_score":0.6221544,"about_ca_system_score_codex":0.0005121934,"about_ca_system_score_gemma":0.0008858722,"threshold_uncertainty_score":0.999275},"labels":[],"label_agreement":null},{"id":"W4413156257","doi":"10.1109/cvpr52734.2025.02363","title":"WISH: Weakly Supervised Instance Segmentation using Heterogeneous Labels","year":2025,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","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":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"National Research Foundation of Korea","keywords":"Computer science; Artificial intelligence; Segmentation; Image segmentation; Pattern recognition (psychology); Computer vision","score_opus":0.02255794911329053,"score_gpt":0.29487173563883456,"score_spread":0.27231378652554405,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413156257","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":[0.10136312,0.00009685456,0.8903801,0.0011283702,0.00022481718,0.00009931206,0.0000016383285,0.00021509166,0.0064907297],"genre_scores_gemma":[0.86772037,0.0000118952275,0.13008511,0.0009750491,0.000017212473,0.000006596236,0.00001585895,0.0000039741017,0.0011639204],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99922293,0.00006908681,0.00015850176,0.0002834796,0.00013048282,0.00013549527],"domain_scores_gemma":[0.9994068,0.000038684706,0.000044259625,0.00042906057,0.00004959626,0.000031557902],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014869339,0.000080102116,0.00007778474,0.00009388891,0.00013311625,0.00017478295,0.00039881407,0.000033795648,0.000023490793],"category_scores_gemma":[0.000029078079,0.00007503177,0.000023652969,0.00040345444,0.000015719059,0.00039827713,0.000108117754,0.000070767266,0.000031088355],"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":[0.000019772335,0.0001965125,0.016423631,0.000097102056,0.00006405337,0.000012596046,0.0007765185,0.008046365,0.22047442,0.28228942,0.0022255257,0.4693741],"study_design_scores_gemma":[0.0003769624,0.0000270015,0.0043501575,0.00003243275,0.000008208808,0.0000072343278,0.000039110353,0.96801114,0.018706406,0.0015101262,0.0067564943,0.00017471785],"about_ca_topic_score_codex":0.00008756654,"about_ca_topic_score_gemma":0.000024736295,"teacher_disagreement_score":0.9599648,"about_ca_system_score_codex":0.000051191142,"about_ca_system_score_gemma":0.00005971647,"threshold_uncertainty_score":0.30597067},"labels":[],"label_agreement":null},{"id":"W4413225605","doi":"10.18280/isi.300603","title":"Comparative Analysis of Four Programming Languages for Machine Learning","year":2025,"lang":"en","type":"article","venue":"Ingénierie des systèmes d information","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Programming language; Artificial intelligence; Natural language processing; Comparison of multi-paradigm programming languages; Fifth-generation programming language; Second-generation programming language; Programming paradigm","score_opus":0.021917926028794527,"score_gpt":0.2974338508695894,"score_spread":0.2755159248407949,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413225605","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":[0.016712727,0.00013086655,0.97625524,0.0001066428,0.000061590494,0.0002535441,0.000017408322,0.00016663087,0.0062953336],"genre_scores_gemma":[0.95302737,0.000006948492,0.04631102,0.000048401675,0.00000729994,0.000059862647,0.00039523534,0.0000016631515,0.00014217503],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991083,0.00007461155,0.00041195904,0.00012103278,0.00013710867,0.0001469832],"domain_scores_gemma":[0.9989161,0.00020122807,0.00034899375,0.00025274904,0.00025547066,0.000025445323],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005229553,0.00009801005,0.00025893364,0.00067548314,0.00020053209,0.0001976915,0.00032169945,0.000047864192,0.0000038079388],"category_scores_gemma":[0.00036711467,0.000090368994,0.00009691044,0.0014935858,0.00004340103,0.0013178457,0.00007664514,0.00009682169,0.000004459031],"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":[0.000042256434,0.00004429063,0.029680744,0.0005139231,0.0007766938,3.112077e-7,0.014362899,0.01855907,0.00031985267,0.1816687,0.00020082628,0.75383043],"study_design_scores_gemma":[0.0002639998,0.000074127056,0.03832985,0.00005948147,0.00015278015,0.000001027274,0.0009294937,0.9370164,0.0006744844,0.00057088665,0.021805579,0.00012186083],"about_ca_topic_score_codex":0.00013383367,"about_ca_topic_score_gemma":0.00004189007,"teacher_disagreement_score":0.93631464,"about_ca_system_score_codex":0.00006257991,"about_ca_system_score_gemma":0.000048413458,"threshold_uncertainty_score":0.36851406},"labels":[],"label_agreement":null},{"id":"W4413319364","doi":"10.1109/aitest66680.2025.00019","title":"CODEX: Testing Machine Learning with the Coverage of Data Explorer Tool","year":2025,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Systems Engineering Research Center; U.S. Department of Defense","keywords":"Computer science; Artificial intelligence","score_opus":0.05548895724841843,"score_gpt":0.28608901690307265,"score_spread":0.23060005965465422,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413319364","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":[0.0063017327,0.00006457366,0.9699128,0.0036796418,0.000032178155,0.00008581377,0.0000055377864,0.00014749616,0.019770198],"genre_scores_gemma":[0.9413292,0.000010367974,0.055964306,0.00040090756,0.000014222255,0.0000054962884,0.00006406087,0.000004479215,0.0022069777],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991782,0.00010301936,0.0001408205,0.0002992245,0.00016719098,0.000111551526],"domain_scores_gemma":[0.9981599,0.00047130123,0.000096971125,0.0011953317,0.00006202132,0.000014474068],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00058472215,0.000076118195,0.00009146797,0.00004772145,0.00016166652,0.00011378273,0.0013945196,0.00001804712,0.000013945126],"category_scores_gemma":[0.0003583112,0.000042581512,0.000009572495,0.00050164416,0.00003592991,0.00048816306,0.0006743176,0.00020592853,0.000010008982],"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":[0.000022742213,0.00007858613,0.096349515,0.000061200764,0.000050594597,0.0000041185526,0.00049685134,0.004445307,0.0015327353,0.14875296,0.004597767,0.74360764],"study_design_scores_gemma":[0.00025642785,0.000057637,0.020747626,0.000037065707,0.000010733516,0.00000438179,0.000051260784,0.9276636,0.00024388373,0.00026465717,0.050566304,0.00009639945],"about_ca_topic_score_codex":0.00016699599,"about_ca_topic_score_gemma":0.000028691062,"teacher_disagreement_score":0.9350274,"about_ca_system_score_codex":0.000007628565,"about_ca_system_score_gemma":0.00006670478,"threshold_uncertainty_score":0.25913876},"labels":[],"label_agreement":null},{"id":"W4413478130","doi":"10.36227/techrxiv.175606397.71672806/v1","title":"Evaluating Handwritten and Multimodal, Free-Style Responses in Algorithms and Data Structures: A RAG-LLM-Based Feedback Framework","year":2025,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Science North","funders":"University of North Carolina at Charlotte","keywords":"Computer science; Style (visual arts); Algorithm; Speech recognition; Artificial intelligence; Natural language processing; Art","score_opus":0.05574757992907353,"score_gpt":0.38565496345868666,"score_spread":0.32990738352961313,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413478130","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":[0.12419007,0.0006567591,0.865806,0.008378419,0.00012698841,0.00028462498,0.00005077524,0.00016118378,0.00034517213],"genre_scores_gemma":[0.40195203,0.000023362112,0.596979,0.0007261089,0.000023934595,0.000011357084,0.000052562988,0.0000057491807,0.00022588664],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99825996,0.00031218445,0.00025211164,0.00075452594,0.0002176048,0.00020360669],"domain_scores_gemma":[0.996993,0.0011654667,0.00007399672,0.0016595365,0.00004454982,0.00006344082],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012353598,0.00014386525,0.00017582111,0.0002178782,0.00017598296,0.0003948236,0.0010883791,0.000104666535,0.000016157503],"category_scores_gemma":[0.0027956527,0.00012227807,0.000011525516,0.00043183714,0.00007646891,0.000406179,0.0010143875,0.00029717656,0.0000025228903],"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":[0.00017596604,0.0001377461,0.04207748,0.00015188848,0.000031809832,0.000011712108,0.00088433287,0.00042330613,0.0011646952,0.026721433,0.0026608908,0.92555875],"study_design_scores_gemma":[0.0009331447,0.000058909063,0.12242919,0.0000952648,0.0000073832966,0.0000024872788,0.00008155085,0.86986595,0.00010935788,0.0052405926,0.0010422812,0.00013388654],"about_ca_topic_score_codex":0.0005255188,"about_ca_topic_score_gemma":0.00011845163,"teacher_disagreement_score":0.9254249,"about_ca_system_score_codex":0.00001904722,"about_ca_system_score_gemma":0.00013410547,"threshold_uncertainty_score":0.49863547},"labels":[],"label_agreement":null},{"id":"W4413943427","doi":"10.14778/3742728.3742754","title":"CatDB: Data-Catalog-Guided, LLM-Based Generation of Data-Centric ML Pipelines","year":2025,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Machine Learning and Data Classification","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":"Concordia University","funders":"","keywords":"Pipeline transport; Computer science; Environmental science","score_opus":0.10422959380219059,"score_gpt":0.32988666442145576,"score_spread":0.22565707061926515,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413943427","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":[0.12207971,0.0037642193,0.77877444,0.06870809,0.0040067737,0.003967969,0.0014612548,0.0008087559,0.016428798],"genre_scores_gemma":[0.9618042,0.00006762869,0.036685206,0.0003480705,0.000107081905,0.000020269816,0.0005647264,0.000008437706,0.00039434005],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982977,0.000022621556,0.00049220625,0.0005959546,0.00041173233,0.0001797687],"domain_scores_gemma":[0.9976485,0.000064514694,0.00045354362,0.001523611,0.0002728242,0.000037012956],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00097248756,0.0001416655,0.00019822606,0.00016919553,0.00012389537,0.000102159545,0.0045214887,0.00004703688,0.000005222705],"category_scores_gemma":[0.00051652576,0.0001019236,0.000038601127,0.0007505009,0.000063018095,0.00077889033,0.0018996816,0.00012732144,0.000006308883],"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":[0.000057692516,0.0014953341,0.040131994,0.0011893446,0.00020262419,6.73699e-7,0.0004949994,0.0010599345,0.18693104,0.19132194,0.38838005,0.18873438],"study_design_scores_gemma":[0.0010381844,0.00006313557,0.0048008813,0.00016291605,0.000113254464,0.000004536686,0.00005136023,0.78914046,0.13819465,0.000968196,0.06522674,0.00023571198],"about_ca_topic_score_codex":0.00025178306,"about_ca_topic_score_gemma":0.00001286109,"teacher_disagreement_score":0.83972454,"about_ca_system_score_codex":0.00004373011,"about_ca_system_score_gemma":0.0001504682,"threshold_uncertainty_score":0.8402126},"labels":[],"label_agreement":null},{"id":"W4414384679","doi":"10.1080/10618600.2025.2561900","title":"Concurrent Prediction of Multiple Survival Outcomes with a Refined Stacking Algorithm","year":2025,"lang":"en","type":"article","venue":"Journal of Computational and Graphical Statistics","topic":"Machine Learning and Data Classification","field":"Computer Science","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":"Western University; University of Saskatchewan; University of Victoria","funders":"Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Michael Smith Health Research BC","keywords":"Stacking; Minification; Identification (biology); Expectation–maximization algorithm","score_opus":0.014137165551512915,"score_gpt":0.2735001843192426,"score_spread":0.2593630187677297,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414384679","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":[0.009547869,0.00007453408,0.9889868,0.00097379717,0.00021082986,0.000039771632,0.00012716475,0.000010697018,0.000028570494],"genre_scores_gemma":[0.671135,0.000024147526,0.32871515,0.000060480274,0.000017910672,7.4054213e-7,0.00003123558,0.0000021594074,0.000013158214],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99893993,0.00008485964,0.00041546175,0.000110692796,0.00037194302,0.00007712679],"domain_scores_gemma":[0.9982087,0.0008647235,0.00033426625,0.000071777715,0.00046379105,0.000056722518],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003107498,0.00007848821,0.00020897597,0.00017259005,0.00007517487,0.00005139743,0.00015436154,0.00002913757,0.0000016522634],"category_scores_gemma":[0.00019433502,0.000055269407,0.00003114371,0.0002717563,0.00008016246,0.0001375089,0.000040899624,0.00017675431,1.6642883e-7],"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":[0.00003486446,0.00020186348,0.15715672,0.0000678338,0.00015316517,0.000010735348,0.0001154284,0.0057764417,0.00001932657,0.48310038,0.0005271326,0.3528361],"study_design_scores_gemma":[0.0008445606,0.00021354771,0.5999244,0.000048530066,0.000022260409,0.000013351238,0.000011912294,0.3574762,0.0000041781705,0.04053199,0.00086456264,0.000044516706],"about_ca_topic_score_codex":0.000009557272,"about_ca_topic_score_gemma":0.0000039948245,"teacher_disagreement_score":0.6615872,"about_ca_system_score_codex":0.0000118196485,"about_ca_system_score_gemma":0.00009895882,"threshold_uncertainty_score":0.2253821},"labels":[],"label_agreement":null},{"id":"W4414531862","doi":"10.1108/978-1-80262-963-720251012","title":"Towards Responsible Ecosystem Service Management Using Artificial Intelligence","year":2025,"lang":"en","type":"book-chapter","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"St. Clair College","funders":"","keywords":"Scope (computer science); Software deployment; Recreation; Ecosystem services; Sustainable development; Environmental monitoring; Data collection; Environmental data","score_opus":0.06415227923407596,"score_gpt":0.3015254745310863,"score_spread":0.23737319529701034,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414531862","genre_codex":"methods","genre_gemma":"other","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":[0.0000010660566,0.000029849254,0.5016698,0.001236183,0.0003398559,0.00015727166,0.000010449956,0.00018908273,0.49636644],"genre_scores_gemma":[0.0020183648,0.00022553075,0.38976046,0.0010921585,0.00025517942,0.000018368206,0.00012466098,0.000044900975,0.60646033],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9980432,0.00005812227,0.0004931636,0.0007753322,0.00040446655,0.00022570617],"domain_scores_gemma":[0.9980749,0.00007041314,0.00021921098,0.0014017582,0.00015915718,0.00007456315],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005622091,0.0002910573,0.0002745414,0.00044138145,0.00016625796,0.00033718353,0.001413699,0.0001993655,0.0001912697],"category_scores_gemma":[0.000017955277,0.00028049617,0.00008649026,0.0002140847,0.000010353261,0.0002078757,0.0008804868,0.0003193491,0.00057250593],"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":[0.00000593579,0.0000052137684,1.6743384e-7,0.00013840002,0.000026689493,0.000011983608,0.000022645501,0.00017428501,0.00000671237,0.7532939,0.00033209394,0.24598198],"study_design_scores_gemma":[0.000026672438,0.000025620044,0.0000043809796,0.0004143552,0.000047209945,0.000011299469,0.000021747988,0.42250708,0.00017091182,0.124501094,0.45185912,0.0004105208],"about_ca_topic_score_codex":0.00008232938,"about_ca_topic_score_gemma":0.00023877941,"teacher_disagreement_score":0.6287928,"about_ca_system_score_codex":0.00015205659,"about_ca_system_score_gemma":0.00025461885,"threshold_uncertainty_score":0.9999647},"labels":[],"label_agreement":null},{"id":"W4414754796","doi":"10.1093/nar/gkag335","title":"DNAi: an open-source AI tool for unbiased DNA fiber analysis","year":2025,"lang":"en","type":"article","venue":"Nucleic Acids Research","topic":"Machine Learning and Data Classification","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":"Hôpital Maisonneuve-Rosemont; Université de Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Segmentation; Fiber; Annotation; Deep learning; Pattern recognition (psychology); DNA","score_opus":0.06455442467865942,"score_gpt":0.41149805271896156,"score_spread":0.34694362804030215,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414754796","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":[0.05800008,0.00004584468,0.9058065,0.018699076,0.000097848526,0.0009146437,0.000030432551,0.00030007644,0.016105542],"genre_scores_gemma":[0.90115273,0.00001079234,0.044969734,0.0015779894,0.000104566505,0.00026160647,0.00025240198,0.000026718364,0.05164347],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99719524,0.0005941982,0.000276832,0.00082164945,0.00059345114,0.0005186444],"domain_scores_gemma":[0.9969494,0.00052406563,0.00005304582,0.0018896299,0.00045070788,0.00013315986],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0033356547,0.00012973176,0.00024324525,0.00076100935,0.0006613547,0.0014848174,0.0036184625,0.00011334165,0.0002464555],"category_scores_gemma":[0.00079336215,0.000119146294,0.00008858702,0.003503433,0.00010536367,0.0008688471,0.00119286,0.00045700028,0.00021466146],"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":[0.00015593413,0.00050049636,0.009559576,0.00008159731,0.00035810185,0.0000053040535,0.0007277345,0.000797111,0.004955474,0.11805042,0.12192398,0.7428843],"study_design_scores_gemma":[0.0005841418,0.00019809447,0.031733688,0.000014098474,0.00003709169,6.338332e-7,0.000047731235,0.36882144,0.00064969243,0.002265183,0.5954734,0.00017482197],"about_ca_topic_score_codex":0.00031658687,"about_ca_topic_score_gemma":0.000062297026,"teacher_disagreement_score":0.86083674,"about_ca_system_score_codex":0.00010467288,"about_ca_system_score_gemma":0.00025197677,"threshold_uncertainty_score":0.9995517},"labels":[],"label_agreement":null},{"id":"W4414809633","doi":"10.1007/978-3-032-05461-6_17","title":"Meta Subspace Analysis: Understanding Model (Mis)behavior in the Metafeature Space","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Machine Learning and Data Classification","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":"Dalhousie University","funders":"","keywords":"Subspace topology; Random forest; Naive Bayes classifier; Feature vector; Entropy (arrow of time); Feature (linguistics); Bayes' theorem; Perspective (graphical); Space (punctuation); Bayesian probability","score_opus":0.07203944131268429,"score_gpt":0.29621931323937095,"score_spread":0.22417987192668665,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414809633","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":[0.000010074537,0.0014046883,0.9849777,0.0067101833,0.00033543856,0.0004384279,0.000012630261,0.00011694595,0.0059938673],"genre_scores_gemma":[0.5309068,0.00017296801,0.46194485,0.0030891418,0.00017958775,0.00008055042,0.00006648453,0.000037045564,0.0035225567],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9956919,0.00017671281,0.00050280377,0.0017813642,0.0012472128,0.00060001476],"domain_scores_gemma":[0.99600464,0.0008310103,0.0003479252,0.002597619,0.00012120944,0.00009761618],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.002438043,0.00058083935,0.00084643706,0.0021668817,0.0003475884,0.0010408115,0.0051197493,0.00035359012,0.000011657837],"category_scores_gemma":[0.00012490411,0.00040410896,0.00040265685,0.0033988615,0.00035442485,0.0006187104,0.0007198636,0.0016652516,0.000007524151],"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":[0.000008468936,0.00007148033,0.0003001369,0.00004517081,0.00043418776,0.00008666956,0.002410145,0.45364654,0.00003460036,0.5031978,0.000114773255,0.03965003],"study_design_scores_gemma":[0.00013363901,0.000035572863,0.00032045224,0.000059476624,0.0009933716,0.000012739829,0.00000232127,0.9443535,0.000023819328,0.05302426,0.0006007033,0.0004401055],"about_ca_topic_score_codex":0.000086476124,"about_ca_topic_score_gemma":0.00094393117,"teacher_disagreement_score":0.5308967,"about_ca_system_score_codex":0.0004403887,"about_ca_system_score_gemma":0.0005265231,"threshold_uncertainty_score":0.9999962},"labels":[],"label_agreement":null},{"id":"W4415171628","doi":"10.2118/228102-ms","title":"Do We Really Need Hundreds of Machine Learning Models in Industry?","year":2025,"lang":"en","type":"article","venue":"SPE Annual Technical Conference and Exhibition","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary; University of British Columbia","funders":"","keywords":"Interpretability; Decision tree; Random forest; Tree (set theory); Structured prediction; Workflow; Field (mathematics); Incremental decision tree; Predictive modelling; Decision tree model","score_opus":0.03477523702766216,"score_gpt":0.29153479336688576,"score_spread":0.2567595563392236,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415171628","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":[0.07546838,0.0009047374,0.8644241,0.01922869,0.00010295558,0.00038590256,0.000036647587,0.00043140238,0.039017178],"genre_scores_gemma":[0.9954319,0.0005284983,0.0036289063,0.000082942584,0.000011434899,0.000010158847,0.000030792347,0.000003639879,0.0002716992],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988987,0.000110232744,0.0003118331,0.00034527417,0.0001645329,0.00016946933],"domain_scores_gemma":[0.99936897,0.0000743675,0.000099734556,0.00029808911,0.000109762805,0.000049109443],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00043919176,0.00011065729,0.00019219343,0.00025414492,0.0000644498,0.00007822727,0.00031028865,0.00023515441,0.000012442695],"category_scores_gemma":[0.00012599223,0.00010637151,0.000028874874,0.00054670667,0.00007488741,0.0005300109,0.00022314624,0.0006772563,0.0000032808096],"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":[0.00003542693,0.000101898404,0.0038839467,0.00005668614,0.000005286029,0.000004158698,0.00040092698,0.00046791183,0.0052744434,0.79856545,0.00044651533,0.19075735],"study_design_scores_gemma":[0.0018247854,0.00073200755,0.052845336,0.0013703613,0.000027846585,0.000023832888,0.000992141,0.47608936,0.0027235493,0.45201313,0.010688828,0.0006688233],"about_ca_topic_score_codex":0.00026882664,"about_ca_topic_score_gemma":0.0000814478,"teacher_disagreement_score":0.91996354,"about_ca_system_score_codex":0.000024285415,"about_ca_system_score_gemma":0.00008328235,"threshold_uncertainty_score":0.43377042},"labels":[],"label_agreement":null},{"id":"W4415233468","doi":"10.48550/arxiv.2507.18242","title":"Boosting Revisited: Benchmarking and Advancing LP-Based Ensemble Methods","year":2025,"lang":"en","type":"preprint","venue":"University of Twente Research Information","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Fonds de recherche du Québec – Nature et technologies; Alliance de recherche numérique du Canada; TKI DINALOG; Compute Canada","keywords":"Boosting (machine learning); Heuristics; Ensemble learning; Benchmarking; Decision tree; Hyperparameter; Gradient boosting; Margin (machine learning)","score_opus":0.0482439719890473,"score_gpt":0.37890847192298654,"score_spread":0.33066449993393926,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415233468","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":[0.00092115364,0.00013165626,0.98323256,0.0010539177,0.00010565473,0.00027439755,0.000022704766,0.000080716454,0.014177245],"genre_scores_gemma":[0.051655695,0.0004937675,0.94695514,0.000071628405,0.000029898667,0.0000010917715,0.00044099707,0.00000342499,0.00034834025],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981208,0.00063527585,0.00024735727,0.0002628909,0.00047592638,0.00025775982],"domain_scores_gemma":[0.99775964,0.00062308763,0.00033687372,0.0006134113,0.0005785464,0.000088455],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004601597,0.00011189342,0.00019767598,0.00096584385,0.00039491217,0.00019687721,0.0008515812,0.00014284595,0.000008538018],"category_scores_gemma":[0.00094282767,0.00013464948,0.000056343855,0.00047452585,0.000074819334,0.0011996394,0.002072047,0.00082004495,0.0000056448516],"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":[0.00003008161,0.000017319639,0.0012617742,0.001700458,0.000025756686,0.0000018441204,0.0018528701,0.0047373557,0.00015865946,0.010617621,0.0022737354,0.9773225],"study_design_scores_gemma":[0.00025626237,0.000041503696,0.0023264282,0.0008800635,0.00001021078,8.966969e-7,0.00038369364,0.9268838,0.00019362793,0.0006176956,0.06827694,0.00012883317],"about_ca_topic_score_codex":0.0006081312,"about_ca_topic_score_gemma":0.000013562236,"teacher_disagreement_score":0.9771937,"about_ca_system_score_codex":0.00017991754,"about_ca_system_score_gemma":0.00040364199,"threshold_uncertainty_score":0.54908466},"labels":[],"label_agreement":null},{"id":"W4415254920","doi":"10.1016/j.ins.2025.122804","title":"Federated domain generalization with source knowledge preservation via discriminative ensembles","year":2025,"lang":"en","type":"article","venue":"Information Sciences","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Institute for Information and Communications Technology Promotion; Information Technology Research Centre; Ministry of Science and ICT, South Korea; National Research Foundation of Korea; Ministry of Education, Ethiopia","keywords":"Discriminative model; Generalization; Regularization (linguistics); Benchmark (surveying); Ensemble learning; Feature (linguistics); Domain (mathematical analysis); Adversarial system; Labeled data","score_opus":0.01684071150768637,"score_gpt":0.2873510741744416,"score_spread":0.27051036266675527,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415254920","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":[0.012591243,0.000025796866,0.9493304,0.0026789166,0.00011919514,0.0001619566,0.0000013815211,0.00017911843,0.03491198],"genre_scores_gemma":[0.9756052,0.000005672651,0.022959286,0.0005103714,0.00001594119,0.000033582775,0.00007405388,0.0000017734029,0.000794149],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989786,0.0001150085,0.000267442,0.00018942414,0.0002955573,0.00015397609],"domain_scores_gemma":[0.99923414,0.00008733361,0.00019284053,0.0001789907,0.00027372123,0.000032959975],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00067470747,0.00009923685,0.00008285833,0.000323659,0.00068506127,0.00087137666,0.00048802528,0.00003855743,0.000006001838],"category_scores_gemma":[0.00011294086,0.000072385825,0.000015288599,0.0015607559,0.00011548127,0.0061664386,0.00010884462,0.0000699244,0.000045575],"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":[0.00001918241,0.00006329128,0.005918646,0.00006979848,0.000016447395,2.0140735e-7,0.0143058635,0.00958563,0.00079993333,0.47888657,0.002739548,0.48759487],"study_design_scores_gemma":[0.00028138352,0.00007590343,0.01672819,0.000043683078,0.000003816694,0.0000030198541,0.0006557194,0.92652303,0.0013325035,0.0042870096,0.049917795,0.00014794551],"about_ca_topic_score_codex":0.00011734027,"about_ca_topic_score_gemma":0.00007162479,"teacher_disagreement_score":0.96301395,"about_ca_system_score_codex":0.0000551564,"about_ca_system_score_gemma":0.00025392752,"threshold_uncertainty_score":0.8402705},"labels":[],"label_agreement":null},{"id":"W4415367189","doi":"10.1109/isit63088.2025.11195233","title":"Coded Deep Learning: Framework and Preliminary Results","year":2025,"lang":"","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Inference; Quantization (signal processing); Deep learning; Entropy (arrow of time); Probabilistic logic; Coding (social sciences); Differentiable function; Approximate inference","score_opus":0.013163437929925319,"score_gpt":0.2832258686205049,"score_spread":0.2700624306905796,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415367189","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":[0.0018589895,0.002396646,0.9018546,0.021430913,0.0007119832,0.00024764874,0.0000039838733,0.0003173105,0.07117794],"genre_scores_gemma":[0.8995786,0.0008779171,0.05952938,0.00084266317,0.00008797568,0.000012772373,0.000035941335,0.000011115257,0.039023675],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99702233,0.00050479325,0.0005996861,0.001153199,0.00029375823,0.00042623482],"domain_scores_gemma":[0.99714065,0.0011528379,0.0002377559,0.0011614404,0.00013815494,0.00016913521],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010526874,0.00028781052,0.0002881906,0.00024879898,0.0006546194,0.00074564025,0.0008397234,0.0003227566,0.000063581705],"category_scores_gemma":[0.0028130056,0.0002767656,0.000060606835,0.0009558509,0.0001809357,0.0004300851,0.0009494775,0.0011527048,0.00014675333],"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":[0.00038888992,0.00012619785,0.0031332797,0.000101161575,0.000040817315,0.000008483762,0.0018536058,0.00062140875,0.000035057947,0.31373635,0.0032160152,0.67673874],"study_design_scores_gemma":[0.0007127665,0.0006187787,0.060742952,0.00027392333,0.000040056937,0.000009276713,0.00023254506,0.8317342,0.000090324735,0.0068167737,0.09842218,0.00030622273],"about_ca_topic_score_codex":0.00009800549,"about_ca_topic_score_gemma":0.00000969895,"teacher_disagreement_score":0.89771956,"about_ca_system_score_codex":0.00003876951,"about_ca_system_score_gemma":0.00012555398,"threshold_uncertainty_score":0.99996847},"labels":[],"label_agreement":null},{"id":"W4415430853","doi":"10.47363/jaicc/2025(4)491","title":"A Method to Test the Ethics of Some AI Classifiers - The Example of School Dropouts Problem","year":2025,"lang":"","type":"article","venue":"Journal of Artificial Intelligence & Cloud Computing","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University Canada West","funders":"","keywords":"Emulation; Relation (database); Element (criminal law); Artificial neural network; Test (biology); Artifact (error); Dropout (neural networks)","score_opus":0.09432440352917293,"score_gpt":0.3986017413252179,"score_spread":0.304277337796045,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415430853","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":[0.010207665,0.00064650393,0.9308009,0.05559839,0.0019107867,0.00052690785,0.000007772048,0.00002304198,0.00027801047],"genre_scores_gemma":[0.89690155,0.000092258895,0.09988164,0.0020679955,0.0009204752,0.000004223601,9.920678e-7,0.000022267679,0.00010861817],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9907089,0.0026140276,0.0039178105,0.0006483384,0.0014515338,0.0006594006],"domain_scores_gemma":[0.9818179,0.010217256,0.0038130519,0.0014249192,0.0024622814,0.00026458988],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.020585172,0.0004204928,0.00089993555,0.00054309046,0.0010540214,0.0006181361,0.0043915184,0.00030522083,0.00003453602],"category_scores_gemma":[0.007560869,0.00027540454,0.000487907,0.0030230782,0.0005389991,0.00043901484,0.0011436077,0.0038504926,0.000024017692],"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":[0.0001278238,0.0005011273,0.00087385694,0.00021147986,0.00017090034,0.0000059778554,0.013828188,0.10790381,0.0070365034,0.3448984,0.000925012,0.5235169],"study_design_scores_gemma":[0.00010240949,0.0012071251,0.0012735315,0.0019321662,0.0002187854,0.000056643137,0.004086226,0.8750634,0.032521583,0.071598314,0.011596865,0.00034290826],"about_ca_topic_score_codex":0.0010443099,"about_ca_topic_score_gemma":0.00006911463,"teacher_disagreement_score":0.88669384,"about_ca_system_score_codex":0.00018214586,"about_ca_system_score_gemma":0.0022769624,"threshold_uncertainty_score":0.99996984},"labels":[],"label_agreement":null},{"id":"W4415491118","doi":"10.36227/techrxiv.175329122.29020847/v2","title":"A Survey of Next-Generation AI and Its Evolving Landscape","year":2025,"lang":"","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Pillar; Key (lock); Field (mathematics); Applications of artificial intelligence","score_opus":0.06290956501922752,"score_gpt":0.3057210691290316,"score_spread":0.24281150410980407,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415491118","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":[0.075793274,0.00924195,0.8976618,0.0054929717,0.000807287,0.0002707386,0.000023207233,0.00007577532,0.010633019],"genre_scores_gemma":[0.9948687,0.00029401018,0.0013393614,0.0003226163,0.000035102978,0.0000033779709,0.00006819031,0.0000038855446,0.0030647647],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.998338,0.00044350605,0.00040290336,0.00046751284,0.00018206095,0.00016601048],"domain_scores_gemma":[0.99872494,0.00020955787,0.00015265029,0.0004538236,0.00040177713,0.000057238587],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00142549,0.00013275574,0.00020053262,0.00019635742,0.0001727985,0.00044019578,0.00034599996,0.00009250362,0.00012376324],"category_scores_gemma":[0.000923541,0.00012477691,0.000024004245,0.0007854671,0.000026543392,0.0007713123,0.00026703702,0.00017038343,0.000015906775],"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":[0.000022021437,0.0001883844,0.24844365,0.0002896249,0.00006827747,0.0000010320441,0.00071285444,0.00042112998,0.015415659,0.09560733,0.01814617,0.62068385],"study_design_scores_gemma":[0.00015897838,0.000034989567,0.33731455,0.000034843568,0.000008218887,5.975539e-7,0.0000070834544,0.66146,0.00054159615,0.000030322226,0.0003346233,0.00007423835],"about_ca_topic_score_codex":0.0007183519,"about_ca_topic_score_gemma":0.00054481975,"teacher_disagreement_score":0.9190754,"about_ca_system_score_codex":0.000012807262,"about_ca_system_score_gemma":0.00021136242,"threshold_uncertainty_score":0.5088254},"labels":[],"label_agreement":null},{"id":"W4415532898","doi":"10.1093/icc/dtaf044","title":"How small is big enough? Open labeled datasets and the development of deep learning","year":2025,"lang":"en","type":"article","venue":"Industrial and Corporate Change","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Canadian Institute for Advanced Research","funders":"Canadian Institute for Advanced Research","keywords":"Deep learning; Function (biology); Citation; Object (grammar); Key (lock); Development (topology)","score_opus":0.2451403693709484,"score_gpt":0.28796669688520776,"score_spread":0.042826327514259355,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415532898","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":[0.7303148,0.0055867466,0.1390483,0.113692,0.001961848,0.0045925863,0.0002177307,0.00030637463,0.0042796438],"genre_scores_gemma":[0.9936946,0.00019160208,0.0037501596,0.00057977316,0.0001580481,0.0000997162,0.00024846802,0.0000066136367,0.0012710028],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991724,0.00017335727,0.00017197823,0.00027175885,0.000091801274,0.00011871503],"domain_scores_gemma":[0.99928355,0.0001091377,0.00026286198,0.00026315963,0.00004062785,0.00004063203],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007521618,0.00009875265,0.00017608915,0.00006484471,0.00024337714,0.0004206763,0.0005689501,0.00007339683,0.0000024542026],"category_scores_gemma":[0.00010998558,0.00006627385,0.000010230099,0.00032848862,0.00007842986,0.00017388654,0.0008213602,0.00020856327,0.0000014295454],"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":[0.000059731603,0.000017006525,0.00256932,0.000013942576,0.000021529922,0.0000010193615,0.0015055614,2.9923228e-7,0.00011023886,0.012129436,0.00033237532,0.98323953],"study_design_scores_gemma":[0.013168966,0.00025042883,0.023011327,0.00030878192,0.00008717967,0.000010868966,0.0015848981,0.024043916,0.0048967786,0.0047445907,0.9272273,0.00066493906],"about_ca_topic_score_codex":0.00020829195,"about_ca_topic_score_gemma":0.00016985396,"teacher_disagreement_score":0.9825746,"about_ca_system_score_codex":0.000009056748,"about_ca_system_score_gemma":0.0000709184,"threshold_uncertainty_score":0.40565914},"labels":[],"label_agreement":null},{"id":"W4415708303","doi":"10.1109/icesc65114.2025.11212623","title":"Green Deep Learning: Sustainable Model Design through Data-Centric Optimization Techniques","year":2025,"lang":"","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Sustainability; Quality (philosophy); Efficient energy use; Scale (ratio); Sustainable design; Overhead (engineering); Sustainable development; Energy (signal processing)","score_opus":0.04450315390018168,"score_gpt":0.30891582659898265,"score_spread":0.264412672698801,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415708303","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":[0.0000016277197,0.0010826095,0.947219,0.0056133894,0.00013712175,0.0009248636,0.0000050050835,0.000977534,0.044038862],"genre_scores_gemma":[0.024079798,0.0017313304,0.8817654,0.00077867025,0.00007888471,0.000052014788,0.00044729817,0.000032900563,0.09103365],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99509776,0.0008885643,0.0007925947,0.0017739425,0.0005426435,0.00090452645],"domain_scores_gemma":[0.99541575,0.0003065043,0.0004017406,0.0031284867,0.0006201226,0.00012737096],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0022181717,0.0004611248,0.0004194303,0.00049421954,0.0011174184,0.0012490273,0.0038428977,0.0003359558,0.00012106251],"category_scores_gemma":[0.0009626237,0.00045936598,0.000072987204,0.0028146636,0.00013124186,0.004215114,0.0021839365,0.00081624475,0.000055365494],"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":[0.00003232107,0.00019387709,0.00013554799,0.00015891438,0.00004098785,0.000008211503,0.000439092,0.63200456,0.000019790205,0.20771477,0.005278584,0.15397337],"study_design_scores_gemma":[0.00032589523,0.000116962074,0.000029916346,0.000056127043,0.000087188964,0.0000045174293,0.00025502054,0.95119387,0.0002239074,0.0074640806,0.03981164,0.00043087703],"about_ca_topic_score_codex":0.0010282734,"about_ca_topic_score_gemma":0.0000078384855,"teacher_disagreement_score":0.31918934,"about_ca_system_score_codex":0.0002649072,"about_ca_system_score_gemma":0.0008343215,"threshold_uncertainty_score":0.99978775},"labels":[],"label_agreement":null},{"id":"W4416037156","doi":"10.18653/v1/2025.emnlp-industry.134","title":"Deploying Tiny LVLM Judges for Real-World Evaluation of Chart Models: Lessons Learned and Best Practices","year":2025,"lang":"","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Compute Canada","keywords":"Best practice; Chart; Natural language; Natural (archaeology); Column (typography)","score_opus":0.38625366395013944,"score_gpt":0.4808505296975183,"score_spread":0.09459686574737886,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416037156","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":[0.023270512,0.0020743532,0.79845273,0.06954528,0.00060012745,0.001731148,0.000036129735,0.00017816715,0.10411156],"genre_scores_gemma":[0.96203583,0.0016236518,0.02619517,0.00017884391,0.000074695425,0.00013217816,0.00005224524,0.000017065462,0.009690321],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.996776,0.0006370196,0.00066000066,0.00096104393,0.00063726725,0.00032870888],"domain_scores_gemma":[0.9957721,0.0011272723,0.0011538652,0.00093129184,0.0009254137,0.00009003006],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0054749413,0.00024400416,0.00035537936,0.00044869914,0.000478382,0.00045787753,0.00058076106,0.00012211225,0.000043724558],"category_scores_gemma":[0.0022964058,0.00023775351,0.00007697101,0.00080679887,0.00011127581,0.0016117701,0.0003420398,0.00026498857,0.000010090967],"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":[0.000055734785,0.00024236162,0.0021854718,0.0003053628,0.00007498335,1.3500186e-7,0.00083136646,0.0036830604,0.0007951786,0.30463168,0.0010477208,0.686147],"study_design_scores_gemma":[0.00093028176,0.00014363608,0.0036593922,0.00021472084,0.00038483867,0.0000010471958,0.00058101653,0.969632,0.0006639574,0.017042266,0.0065347273,0.00021210522],"about_ca_topic_score_codex":0.001799779,"about_ca_topic_score_gemma":0.0016737563,"teacher_disagreement_score":0.96594894,"about_ca_system_score_codex":0.00009101921,"about_ca_system_score_gemma":0.00065499573,"threshold_uncertainty_score":0.96953064},"labels":[],"label_agreement":null},{"id":"W4416046438","doi":"10.48550/arxiv.2505.21813","title":"Optimizing Data Augmentation through Bayesian Model Selection","year":2025,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Robustness (evolution); Model selection; Generalization; Probabilistic logic; Bayesian probability; Bayesian optimization; Marginal likelihood; Selection (genetic algorithm)","score_opus":0.12311203832787017,"score_gpt":0.35653697850816185,"score_spread":0.2334249401802917,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416046438","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":[0.003679507,0.00013924822,0.9876393,0.0025930824,0.0008385283,0.00025393962,0.00006050095,0.00048332266,0.004312542],"genre_scores_gemma":[0.45427,0.00026486858,0.5386168,0.0007014448,0.0002270161,0.000048964335,0.0029683346,0.00002083176,0.0028817807],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99769324,0.00015760802,0.00037249186,0.0012491497,0.00027973545,0.0002477964],"domain_scores_gemma":[0.9970873,0.00006602818,0.00030839266,0.0023864855,0.00009955032,0.000052246094],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00044953276,0.00025316663,0.0002265027,0.00013468374,0.0002308903,0.0002929957,0.0024088423,0.00022108055,0.000012478987],"category_scores_gemma":[0.00012503187,0.0002701159,0.0000549882,0.00033502193,0.00002466851,0.0010930616,0.0029121772,0.0007423622,0.000058974736],"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":[0.000036987065,0.00032804318,0.0917716,0.00064293825,0.00024967286,0.000006518176,0.0045118313,0.77738595,0.0013627688,0.036212206,0.026811637,0.060679864],"study_design_scores_gemma":[0.00015449619,0.000011896393,0.0040769647,0.00010034685,0.00003487644,0.0000017431247,0.000018638766,0.9902374,0.0002219805,0.0020588203,0.0028343718,0.00024842407],"about_ca_topic_score_codex":0.00033464583,"about_ca_topic_score_gemma":0.000048731305,"teacher_disagreement_score":0.4505905,"about_ca_system_score_codex":0.00012805528,"about_ca_system_score_gemma":0.00034060242,"threshold_uncertainty_score":0.9999751},"labels":[],"label_agreement":null},{"id":"W4416251048","doi":"10.1109/ijcnn64981.2025.11228428","title":"Optimizing view generation in classification datasets","year":2025,"lang":"","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"École de Technologie Supérieure","funders":"","keywords":"Decomposition; k-nearest neighbors algorithm; Key (lock); Computational complexity theory; Decomposition method (queueing theory); Divide and conquer algorithms","score_opus":0.0555552130765447,"score_gpt":0.32849967222064774,"score_spread":0.27294445914410304,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416251048","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":[0.0008834803,0.0019516114,0.9582644,0.015391154,0.00090872566,0.00043183335,0.000034058503,0.000114331415,0.02202041],"genre_scores_gemma":[0.92775667,0.0015516339,0.06316937,0.0018029235,0.00015140978,0.00006454464,0.002626768,0.000012324452,0.0028643864],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99696416,0.00050956,0.00081396505,0.0010576878,0.00028782358,0.00036681004],"domain_scores_gemma":[0.9978963,0.000105047904,0.00022389372,0.0016047931,0.00009009469,0.00007985545],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0013726555,0.00025274802,0.00026731647,0.00054425764,0.00027222536,0.0007673103,0.0010404766,0.00017985309,0.00014262054],"category_scores_gemma":[0.00026874768,0.00026193945,0.000052091364,0.0017854068,0.000057644113,0.0012724483,0.00036285678,0.00042358148,0.00024485652],"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":[0.0000069523703,0.00019847362,0.0010965826,0.00008583389,0.000012786022,0.0000028365455,0.0002972323,0.0019311267,0.003447292,0.30434567,0.017235387,0.6713398],"study_design_scores_gemma":[0.000377023,0.000023201033,0.016156886,0.00011063465,0.000014202305,0.0000016211105,0.000049172413,0.87549496,0.00039000815,0.0002468124,0.106921576,0.00021388101],"about_ca_topic_score_codex":0.0002615571,"about_ca_topic_score_gemma":0.00033958137,"teacher_disagreement_score":0.92687315,"about_ca_system_score_codex":0.00019728657,"about_ca_system_score_gemma":0.00031590552,"threshold_uncertainty_score":0.9999833},"labels":[],"label_agreement":null},{"id":"W4416322339","doi":"10.3390/make7040148","title":"Model-Aware Automatic Benchmark Generation with Self-Error Instructions for Data-Driven Models","year":2025,"lang":"en","type":"article","venue":"Machine Learning and Knowledge Extraction","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Ministero dello Sviluppo Economico","keywords":"Benchmark (surveying); Data point; Generative grammar; Regression; Data-driven; Data modeling; Experimental data","score_opus":0.05107415529911185,"score_gpt":0.3329024960587661,"score_spread":0.28182834075965424,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416322339","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":[0.0075857257,0.00033594255,0.986616,0.0008695757,0.00032762863,0.0003201941,0.000016608818,0.0006453958,0.0032829097],"genre_scores_gemma":[0.8378218,0.00006873941,0.15892842,0.000032661435,0.00010842153,0.000086836924,0.00081756985,0.000016956423,0.0021186175],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984859,0.00017154631,0.00028415243,0.0006965277,0.00014397987,0.0002178789],"domain_scores_gemma":[0.9988374,0.00014933156,0.00017984098,0.00059744285,0.00016399183,0.00007198029],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005090389,0.00020603862,0.00019774286,0.00027749606,0.0008348008,0.00030119752,0.00039804837,0.000108540036,0.0000047131093],"category_scores_gemma":[0.00009843458,0.00018217505,0.00003304933,0.0004043256,0.00002953461,0.001333411,0.00018859266,0.00042199437,0.0000061903615],"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":[0.00004205169,0.00043904298,0.0031533497,0.00040127404,0.00016739605,0.0000017615487,0.0017081387,0.25335228,0.0014284778,0.05965323,0.003024453,0.67662853],"study_design_scores_gemma":[0.00055738393,0.000089231755,0.00050447613,0.000047504167,0.00006453277,0.000026848957,0.000038525992,0.98346555,0.000025462436,0.0007219054,0.0142612485,0.00019735716],"about_ca_topic_score_codex":0.00005477871,"about_ca_topic_score_gemma":0.00020920302,"teacher_disagreement_score":0.830236,"about_ca_system_score_codex":0.00007296129,"about_ca_system_score_gemma":0.00018229923,"threshold_uncertainty_score":0.7428883},"labels":[],"label_agreement":null},{"id":"W4416408141","doi":"10.1007/s10994-025-06909-8","title":"MetaML: a multi-label meta-learning approach for pipeline recommendation","year":2025,"lang":"en","type":"article","venue":"Machine Learning","topic":"Machine Learning and Data Classification","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":"École de Technologie Supérieure","funders":"","keywords":"Pipeline (software); Preprocessor; Computational complexity theory; Pipeline transport; Sequence (biology); Code (set theory); Bayesian probability; Source code","score_opus":0.07266868996257791,"score_gpt":0.33080450384217086,"score_spread":0.25813581387959295,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416408141","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":[0.00013100296,0.0008814244,0.986982,0.0041511958,0.00019960833,0.000417564,0.000007138065,0.0007792556,0.006450842],"genre_scores_gemma":[0.1346643,0.00007291636,0.8380377,0.00080186443,0.00009740574,0.0002783648,0.0012839107,0.00004391369,0.02471959],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99730265,0.00067147444,0.00051810313,0.00086655054,0.00021032644,0.00043090124],"domain_scores_gemma":[0.99842787,0.00045716084,0.00033752312,0.0005144343,0.00017194223,0.000091049966],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0022504157,0.00032107576,0.0004903365,0.0004069797,0.0006910565,0.00037248663,0.00080654235,0.00012418175,0.00005783068],"category_scores_gemma":[0.0015423732,0.00028198943,0.00021918361,0.0008396214,0.000031149226,0.0005353925,0.00035512188,0.000827545,0.00002986919],"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":[0.000060626553,0.0004530047,0.0045396816,0.00017015933,0.0007799713,0.000001362609,0.0005243914,0.029864991,0.0017847061,0.031331483,0.0028853086,0.9276043],"study_design_scores_gemma":[0.0010073333,0.000065541244,0.0002846127,0.0000074423137,0.00027221395,0.0000031066338,0.000026651325,0.79227316,0.00015244326,0.00013672681,0.2055537,0.0002170732],"about_ca_topic_score_codex":0.00012863518,"about_ca_topic_score_gemma":0.00001616411,"teacher_disagreement_score":0.92738724,"about_ca_system_score_codex":0.00006277131,"about_ca_system_score_gemma":0.00006251733,"threshold_uncertainty_score":0.9999632},"labels":[],"label_agreement":null},{"id":"W4416797994","doi":"10.1109/tfuzz.2025.3638792","title":"Reinforced Dual-Flow Neural Network for Tabular Data Classification With Dynamical Transformer and Fuzzy Clustering","year":2025,"lang":"","type":"article","venue":"IEEE Transactions on Fuzzy Systems","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"National Research Foundation of Korea","keywords":"Hyperparameter; Cluster analysis; Artificial neural network; Maxima and minima; Radial basis function; Outlier; Radial basis function network; Pattern recognition (psychology); Fuzzy logic; Basis function","score_opus":0.033714762286570915,"score_gpt":0.27854974937092275,"score_spread":0.24483498708435183,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416797994","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":[0.0011729957,0.00058988825,0.9871812,0.0029682436,0.003873617,0.002390911,0.000623862,0.00030111178,0.0008981878],"genre_scores_gemma":[0.98388755,0.00027385482,0.011249867,0.00019711522,0.00030774105,0.0004192206,0.00053527916,0.000063231724,0.0030661097],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9951117,0.00043424676,0.0011891198,0.0018115825,0.0005937944,0.00085958233],"domain_scores_gemma":[0.9957691,0.00057050027,0.00038688182,0.0027340748,0.0002530641,0.00028636897],"candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0013675671,0.00064177706,0.0007245378,0.00040303747,0.0013691762,0.0011498629,0.0012119825,0.00041246644,0.0000057666302],"category_scores_gemma":[0.000024343783,0.00059545,0.00013697396,0.0012133981,0.00023570136,0.0014898881,0.000014833862,0.00085047464,0.000018095587],"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":[0.00081808877,0.00014747446,0.000062736086,0.0011639729,0.00035527165,0.0000060725492,0.00046144912,0.8121191,0.0006272443,0.005871568,0.0010962775,0.17727073],"study_design_scores_gemma":[0.0019892058,0.0005094996,0.00043407077,0.00079302274,0.00034813138,0.000058716156,0.00027343546,0.9875879,0.000043682827,0.000039775186,0.0073337657,0.00058877526],"about_ca_topic_score_codex":0.00033560247,"about_ca_topic_score_gemma":0.00044723504,"teacher_disagreement_score":0.9827146,"about_ca_system_score_codex":0.00019286401,"about_ca_system_score_gemma":0.00031428374,"threshold_uncertainty_score":0.9999309},"labels":[],"label_agreement":null},{"id":"W4416863416","doi":"10.23977/jeis.2025.100217","title":"A Comparative Study on the Training Effects of Different Optimizers for Deep Learning Models","year":2025,"lang":"","type":"article","venue":"Journal of Electronics and Information Science","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Convergence (economics); Artificial neural network; Stochastic gradient descent; Deep learning; Generalization; Selection (genetic algorithm); Overfitting; Moment (physics); Training (meteorology)","score_opus":0.03823319963320846,"score_gpt":0.3136478977489772,"score_spread":0.27541469811576874,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416863416","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":[0.28320184,0.00041227895,0.7136391,0.0010000131,0.00026388018,0.0005446719,6.862396e-7,0.0000051220345,0.0009324267],"genre_scores_gemma":[0.9982758,0.0004231235,0.0010882018,0.00016799859,0.000014530827,0.000011354614,7.019197e-7,0.0000017909548,0.000016464239],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99779165,0.00019298473,0.00085810956,0.00016299798,0.0006806278,0.0003136143],"domain_scores_gemma":[0.9963353,0.0011223938,0.0014072449,0.00024432846,0.00081139285,0.00007929236],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0036405295,0.00016028245,0.0003771918,0.0005862592,0.00075270695,0.0005919585,0.0009072771,0.00003807207,8.9749904e-7],"category_scores_gemma":[0.0009320609,0.00010078396,0.00008590939,0.001013023,0.00022727987,0.0042000534,0.00012777944,0.0005739315,3.7606125e-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":[0.0002898033,0.00033744556,0.0002656958,0.00014700863,0.00012282678,2.76758e-7,0.09385411,0.11532696,0.001318315,0.60761356,0.000055790133,0.18066819],"study_design_scores_gemma":[0.0010562924,0.0031520324,0.0040942538,0.00017527826,0.00004690353,0.000004268198,0.0061250553,0.98165375,0.0010788671,0.002050218,0.0004683723,0.00009468451],"about_ca_topic_score_codex":0.0000020073676,"about_ca_topic_score_gemma":9.087466e-7,"teacher_disagreement_score":0.8663268,"about_ca_system_score_codex":0.00012615051,"about_ca_system_score_gemma":0.0006709266,"threshold_uncertainty_score":0.57892895},"labels":[],"label_agreement":null},{"id":"W4417312491","doi":"10.18280/isi.301002","title":"Hybrid GTO-SA Metaheuristic for Feature Subset Selection in High-Dimensional Medical Datasets","year":2025,"lang":"","type":"article","venue":"Ingénierie des systèmes d information","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Feature selection; Feature (linguistics); Selection (genetic algorithm); Pattern recognition (psychology); Metaheuristic","score_opus":0.01062871343171533,"score_gpt":0.2621798090830336,"score_spread":0.2515510956513183,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417312491","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":[0.02809303,0.0005947873,0.9609972,0.0036865857,0.0022490374,0.0013937119,0.001932634,0.00026836328,0.0007846412],"genre_scores_gemma":[0.96807563,0.00008025777,0.014188253,0.0014544924,0.0001687747,0.00021036579,0.015585381,0.000016475326,0.00022033857],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99592334,0.0004172364,0.0014542122,0.00059509097,0.0009318715,0.0006782342],"domain_scores_gemma":[0.9973839,0.0005444158,0.0007250226,0.0006472659,0.00048897124,0.00021042676],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00281649,0.00044545133,0.0005754282,0.0010729922,0.0007018748,0.0009232946,0.0010462593,0.00039636495,0.00007030516],"category_scores_gemma":[0.004223186,0.0004533951,0.00012895236,0.0015030869,0.00019666122,0.0050475476,0.00036947295,0.0007917701,0.00012300827],"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":[0.00043592154,0.00029717223,0.0037201038,0.002223957,0.00019846809,0.000013984204,0.0013260184,0.005556428,0.00009777904,0.10165059,0.116215765,0.7682638],"study_design_scores_gemma":[0.0018489568,0.00018418714,0.0473498,0.00076004135,0.0000806198,0.00008179616,0.000045577894,0.8950066,0.0004090666,0.006991049,0.046767324,0.0004749855],"about_ca_topic_score_codex":0.0005238348,"about_ca_topic_score_gemma":0.00014852085,"teacher_disagreement_score":0.94680893,"about_ca_system_score_codex":0.0006377801,"about_ca_system_score_gemma":0.0011218971,"threshold_uncertainty_score":0.9997918},"labels":[],"label_agreement":null},{"id":"W4417471048","doi":"10.1109/nss/mic/rtsd57106.2025.11286722","title":"AllMetrics: A Unified Python Library for Standardized Metric Evaluation in Machine Learning","year":2025,"lang":"","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Teck (Canada); University of British Columbia","funders":"","keywords":"Python (programming language); Standardization; Metric (unit); Debugging; Modular design; Modular programming; Product metric; Performance metric","score_opus":0.03454321820544654,"score_gpt":0.32354573281303595,"score_spread":0.2890025146075894,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417471048","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":[0.001642868,0.0066819577,0.9513879,0.007384094,0.0009982955,0.0020044462,0.00005478604,0.0004463442,0.029399348],"genre_scores_gemma":[0.8933452,0.0012362082,0.0843677,0.00065436406,0.00010707569,0.00026741228,0.00088063546,0.000051971143,0.019089436],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9942572,0.0017300076,0.0011199848,0.0013136629,0.0009517089,0.00062745274],"domain_scores_gemma":[0.9960137,0.0020143082,0.00044339916,0.0009997451,0.00038928987,0.00013955613],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.007055,0.00040190853,0.00059645483,0.0041935043,0.0004108326,0.0010724885,0.0012180835,0.0002857818,0.00039837445],"category_scores_gemma":[0.006987881,0.0003969446,0.00019813231,0.012030403,0.000055766806,0.0016436605,0.00056939473,0.00081808853,0.00003516714],"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":[0.0003098869,0.00024738585,0.016360076,0.00021764459,0.00007087654,0.0000021566286,0.00034175685,0.0073844246,0.000102794394,0.06962711,0.002943757,0.90239215],"study_design_scores_gemma":[0.00394302,0.00025103334,0.0117239505,0.00012648897,0.00009231547,0.0000010653878,0.00007794446,0.83676493,0.00036926323,0.0037038617,0.14261791,0.00032818448],"about_ca_topic_score_codex":0.00022652902,"about_ca_topic_score_gemma":0.00005605282,"teacher_disagreement_score":0.90206397,"about_ca_system_score_codex":0.00032159974,"about_ca_system_score_gemma":0.0012446295,"threshold_uncertainty_score":0.9999645},"labels":[],"label_agreement":null},{"id":"W4417473448","doi":"10.36939/ir.202512181252","title":"Dataset Optimization Using Image Processing","year":2025,"lang":"en","type":"dissertation","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Research Manitoba","keywords":"Pruning; Cluster analysis; Pattern recognition (psychology); Range (aeronautics); Generalization; Image (mathematics); Similarity (geometry)","score_opus":0.02389039680665396,"score_gpt":0.3295529037197485,"score_spread":0.30566250691309454,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417473448","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":[0.00003535535,0.00012698252,0.97940844,0.00014317651,0.00033152962,0.00012421879,0.00012749579,0.00017735708,0.019525416],"genre_scores_gemma":[0.0016199552,0.000041684016,0.8635747,0.0001868636,0.00007996245,0.000014603991,0.12301636,0.00001829971,0.011447602],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99881953,0.000055648285,0.00024996925,0.0005061664,0.00021850025,0.0001501933],"domain_scores_gemma":[0.99894077,0.000024711193,0.0002308488,0.0006330845,0.00013270351,0.00003787205],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018061549,0.0001729274,0.00015325361,0.00023649886,0.00020713462,0.0005855071,0.0007521397,0.00014118858,0.000053497693],"category_scores_gemma":[0.000096627635,0.00016622138,0.000028343535,0.0004517004,0.0000064707124,0.0008404278,0.00007910379,0.0002224572,0.000020824626],"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":[0.0000346906,0.00019559158,0.00007168006,0.0018174945,0.000053423402,0.000014763508,0.00077446946,0.051129904,0.0014215674,0.018404378,0.054621696,0.8714603],"study_design_scores_gemma":[0.000073826646,0.0000055254286,0.000079028025,0.00012100568,0.000020297899,0.0000017315768,0.00004744412,0.9905796,0.0001650975,0.00008764315,0.008634845,0.00018395777],"about_ca_topic_score_codex":0.00011294835,"about_ca_topic_score_gemma":0.000034799712,"teacher_disagreement_score":0.93944967,"about_ca_system_score_codex":0.000042828633,"about_ca_system_score_gemma":0.0003237522,"threshold_uncertainty_score":0.6778311},"labels":[],"label_agreement":null},{"id":"W4417509397","doi":"10.1109/icsit65336.2025.11293913","title":"Rewriting Memory: an Efficient Framework for Machine Unlearning in Pretrained Deep Models","year":2025,"lang":"","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Rewriting; Focus (optics); Subject (documents); Rest (music); Noisy data","score_opus":0.028965814282803606,"score_gpt":0.3184475885131965,"score_spread":0.2894817742303929,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417509397","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":[0.0070451302,0.00081739674,0.9719991,0.0051573957,0.0006690261,0.0010147963,0.0000140355105,0.00033725877,0.012945858],"genre_scores_gemma":[0.68995374,0.0000263174,0.30806717,0.0006606644,0.000096325886,0.000081560764,0.00006924228,0.000025068402,0.0010198907],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99531746,0.0006449496,0.0010314526,0.0016453764,0.0004463066,0.0009144354],"domain_scores_gemma":[0.99641955,0.0011883664,0.000353169,0.0015948006,0.00022664233,0.00021746958],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0032951664,0.00044979315,0.0005339756,0.00070135476,0.00066080666,0.00081803446,0.0016413837,0.00039041037,0.000084949505],"category_scores_gemma":[0.0021441604,0.0004649824,0.00015229257,0.0019070192,0.000098172684,0.00072788255,0.0005142486,0.0012169061,0.000015325504],"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":[0.000056670786,0.00021944268,0.00048061353,0.0001409257,0.00001443201,0.0000022257386,0.0017730008,0.3294151,0.000045019595,0.45279565,0.000023400211,0.2150335],"study_design_scores_gemma":[0.0010230236,0.0002045235,0.0016895198,0.000530049,0.000027438376,0.0000027669942,0.0007427395,0.9590786,0.00008585699,0.035734084,0.00043737132,0.00044401776],"about_ca_topic_score_codex":0.00034091604,"about_ca_topic_score_gemma":0.00018125244,"teacher_disagreement_score":0.6829086,"about_ca_system_score_codex":0.00020323879,"about_ca_system_score_gemma":0.0002946352,"threshold_uncertainty_score":0.9997802},"labels":[],"label_agreement":null},{"id":"W4776547","doi":"10.1007/978-3-642-21043-3_46","title":"Extending AdaBoost to Iteratively Vary Its Base Classifiers","year":2011,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Machine Learning and Data Classification","field":"Computer Science","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 Ottawa","funders":"","keywords":"Computer science; AdaBoost; Artificial intelligence; Base (topology); Pattern recognition (psychology); Machine learning; Support vector machine; Mathematics","score_opus":0.04063029010037732,"score_gpt":0.271457159147261,"score_spread":0.23082686904688365,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4776547","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":[0.00003417186,0.0002971996,0.97956955,0.0016053361,0.001659266,0.0004074709,0.000016445756,0.0002604973,0.016150035],"genre_scores_gemma":[0.22932613,0.00009055379,0.7592369,0.00613479,0.0008923512,0.00003927966,0.000044384913,0.00009284713,0.004142819],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99555343,0.0000855836,0.00056145695,0.0021236218,0.000935149,0.0007407328],"domain_scores_gemma":[0.996849,0.00039182082,0.00032757537,0.0017547134,0.0002791985,0.00039768315],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011578829,0.00059942465,0.00049154466,0.0013024891,0.00041259642,0.00075944315,0.0039899847,0.00029541444,0.00008800308],"category_scores_gemma":[0.00028802388,0.0005487622,0.00011443932,0.00085457496,0.00028593547,0.0010663599,0.0016054345,0.0010700679,0.00039161596],"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":[0.0000112674625,0.000032268796,0.000062671,0.000035899422,0.000010082479,0.0000997538,0.0015898508,0.003461746,0.00061129325,0.10202593,0.00017050696,0.89188874],"study_design_scores_gemma":[0.00058575696,0.0007356555,0.0026579765,0.0013712944,0.00002511267,0.00019887756,7.944978e-7,0.83483994,0.003762942,0.09875912,0.054344792,0.0027177301],"about_ca_topic_score_codex":0.00002542437,"about_ca_topic_score_gemma":0.00003708113,"teacher_disagreement_score":0.889171,"about_ca_system_score_codex":0.00030084155,"about_ca_system_score_gemma":0.00050724176,"threshold_uncertainty_score":0.9996964},"labels":[],"label_agreement":null},{"id":"W58495732","doi":"10.1017/cbo9780511921803.010","title":"Conclusion","year":2011,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Machine Learning and Data Classification","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":false,"ca_institutions":"McGill University","funders":"","keywords":"Computer science","score_opus":0.030450745763912043,"score_gpt":0.20341766555977725,"score_spread":0.1729669197958652,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W58495732","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":[0.0000027312772,0.00007321834,0.08140964,0.00003459347,0.00023534628,0.00014421462,0.000040764648,0.00031299324,0.9177465],"genre_scores_gemma":[0.00073848566,0.00008702337,0.0012164586,0.00007715297,0.00006767544,2.4609747e-7,0.00006429231,0.000019114226,0.99772954],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988656,0.000042271986,0.00013232167,0.00055858464,0.00021876555,0.00018242921],"domain_scores_gemma":[0.9984192,0.000040638166,0.00022654812,0.0010696796,0.00010798381,0.000135922],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00011175492,0.00024182629,0.00022167945,0.000150688,0.00021191826,0.00006300554,0.0013761866,0.00026089977,0.0000061283185],"category_scores_gemma":[0.000008610617,0.0002738147,0.00011467457,0.0000073346846,0.000101474216,0.00017230066,0.0011176333,0.00042430355,0.00009749606],"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":[0.000009828749,0.000004176439,0.0000010036895,0.000019007346,0.000021414948,0.0000745073,0.000043576427,2.2616119e-7,0.00002037198,0.9594769,0.025332134,0.014996836],"study_design_scores_gemma":[0.00020227328,0.00003634807,0.00003275974,0.000058650017,0.000034429286,0.000012787037,0.0000018593137,0.0005243654,0.000065282846,0.00006755108,0.99866587,0.00029781664],"about_ca_topic_score_codex":0.0001375384,"about_ca_topic_score_gemma":9.154697e-7,"teacher_disagreement_score":0.9733337,"about_ca_system_score_codex":0.00008915373,"about_ca_system_score_gemma":0.000087141896,"threshold_uncertainty_score":0.9999714},"labels":[],"label_agreement":null},{"id":"W655105626","doi":"10.2307/3315929","title":"Improvement over bayes prediction in small samples in the presence of model uncertainty","year":2004,"lang":"en","type":"article","venue":"Canadian Journal of Statistics","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Bayes' theorem; Bayesian probability; Context (archaeology); Bayes factor; Computer science; Statistics; Naive Bayes classifier; Class (philosophy); Machine learning; Data mining; Artificial intelligence; Econometrics; Mathematics; Geography; Support vector machine","score_opus":0.03664506710128354,"score_gpt":0.24840401322445735,"score_spread":0.2117589461231738,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W655105626","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":[0.08319712,0.000052592128,0.9156078,0.0007279743,0.000086569344,0.00006502623,0.00018554174,0.0000015761149,0.00007578092],"genre_scores_gemma":[0.9418817,0.000018580597,0.057960257,0.000100639314,0.000016920083,0.0000014065996,0.000009353518,0.0000022332704,0.000008917234],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993018,0.00004871325,0.0003057415,0.00008107196,0.00013297118,0.00012969237],"domain_scores_gemma":[0.9993683,0.00011151473,0.00017784625,0.00017245978,0.00008460319,0.00008526086],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00053321273,0.00005072951,0.000084657775,0.00017244155,0.000033827248,0.000046071196,0.00044539996,0.00002353469,0.0000041872354],"category_scores_gemma":[0.00032788722,0.00003891664,0.0000131239885,0.00017850964,0.000039801635,0.0001330616,0.000011231327,0.00018350019,4.171537e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000089667365,0.000046250738,0.02709388,0.000038402097,0.000007503841,0.000052583742,0.0056162956,0.64330554,0.00022753823,0.2819081,0.0010888089,0.040606145],"study_design_scores_gemma":[0.0006336208,0.00022655063,0.22199969,0.00011978413,0.0000065811614,0.000019373243,0.00029727948,0.70334905,0.000039504805,0.07267126,0.00055304135,0.0000842461],"about_ca_topic_score_codex":0.024783857,"about_ca_topic_score_gemma":0.13258246,"teacher_disagreement_score":0.8586846,"about_ca_system_score_codex":0.00013618468,"about_ca_system_score_gemma":0.0008920801,"threshold_uncertainty_score":0.9817102},"labels":[],"label_agreement":null},{"id":"W6901674545","doi":"10.60692/d2ewg-s1y29","title":"Synbols: Probing Learning Algorithms with Synthetic Datasets","year":2020,"lang":"en","type":"article","venue":"Greater South Information System","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Benchmark (surveying); Code (set theory); Synthetic data; Source code; Key (lock); Pattern recognition (psychology)","score_opus":0.03454430125556018,"score_gpt":0.2162257387580032,"score_spread":0.181681437502443,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6901674545","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":[0.007792855,0.0000023009013,0.9882182,0.0007377252,0.000087439854,0.00025138058,0.00005095729,0.00085092627,0.002008244],"genre_scores_gemma":[0.9897789,7.985109e-8,0.009700921,0.00024915184,0.000049633574,0.000035977202,0.00015497577,0.000007720546,0.000022643435],"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99867994,0.00011683482,0.00037319236,0.0002621341,0.00035072136,0.00021718815],"domain_scores_gemma":[0.99897957,0.00001135277,0.00031276685,0.00047832768,0.000077815625,0.00014017426],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00032677525,0.00015874469,0.00016699769,0.000112965274,0.00022357721,0.0005963417,0.00054718653,0.000051182,0.000005893006],"category_scores_gemma":[0.000053059826,0.00011969312,0.000027425893,0.00039447978,0.00001838206,0.0018675607,0.00015311538,0.00020715642,0.0010792881],"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":[0.0002076051,0.00001550501,0.16957188,0.0035025054,0.00025244613,0.00007665086,0.6418285,0.029020438,0.00003553138,0.020692738,0.0017365617,0.13305965],"study_design_scores_gemma":[0.0008289178,0.00019089412,0.009411919,0.00024868007,0.000021697013,0.00013563882,0.0067010433,0.9679465,0.00028365068,6.76921e-7,0.013807972,0.00042239082],"about_ca_topic_score_codex":0.000004172447,"about_ca_topic_score_gemma":3.347383e-8,"teacher_disagreement_score":0.98198605,"about_ca_system_score_codex":0.00004020502,"about_ca_system_score_gemma":0.00004016861,"threshold_uncertainty_score":0.99969846},"labels":[],"label_agreement":null},{"id":"W6901695316","doi":"10.60692/rxvb0-q5858","title":"Synbols: Probing Learning Algorithms with Synthetic Datasets","year":2020,"lang":"en","type":"article","venue":"Greater South Information System","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Benchmark (surveying); Code (set theory); Synthetic data; Source code; Key (lock); Pattern recognition (psychology)","score_opus":0.03454430125556018,"score_gpt":0.2162257387580032,"score_spread":0.181681437502443,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6901695316","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":[0.007792855,0.0000023009013,0.9882182,0.0007377252,0.000087439854,0.00025138058,0.00005095729,0.00085092627,0.002008244],"genre_scores_gemma":[0.9897789,7.985109e-8,0.009700921,0.00024915184,0.000049633574,0.000035977202,0.00015497577,0.000007720546,0.000022643435],"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99867994,0.00011683482,0.00037319236,0.0002621341,0.00035072136,0.00021718815],"domain_scores_gemma":[0.99897957,0.00001135277,0.00031276685,0.00047832768,0.000077815625,0.00014017426],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00032677525,0.00015874469,0.00016699769,0.000112965274,0.00022357721,0.0005963417,0.00054718653,0.000051182,0.000005893006],"category_scores_gemma":[0.000053059826,0.00011969312,0.000027425893,0.00039447978,0.00001838206,0.0018675607,0.00015311538,0.00020715642,0.0010792881],"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":[0.0002076051,0.00001550501,0.16957188,0.0035025054,0.00025244613,0.00007665086,0.6418285,0.029020438,0.00003553138,0.020692738,0.0017365617,0.13305965],"study_design_scores_gemma":[0.0008289178,0.00019089412,0.009411919,0.00024868007,0.000021697013,0.00013563882,0.0067010433,0.9679465,0.00028365068,6.76921e-7,0.013807972,0.00042239082],"about_ca_topic_score_codex":0.000004172447,"about_ca_topic_score_gemma":3.347383e-8,"teacher_disagreement_score":0.98198605,"about_ca_system_score_codex":0.00004020502,"about_ca_system_score_gemma":0.00004016861,"threshold_uncertainty_score":0.99969846},"labels":[],"label_agreement":null},{"id":"W6901786500","doi":"10.60692/ggq9y-pyj57","title":"Task-Informed Meta-Learning data","year":2022,"lang":"en","type":"article","venue":"Greater South Information System","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Data set; Codebase; Data collection; Identification (biology); Work (physics)","score_opus":0.10709365004999226,"score_gpt":0.260133056864539,"score_spread":0.15303940681454675,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6901786500","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":[0.0068983394,0.000014789292,0.9732729,0.0006949794,0.00078237295,0.0003888666,0.00028983413,0.0014173881,0.016240485],"genre_scores_gemma":[0.9943557,1.12173204e-7,0.004164988,0.0002799337,0.00003564091,0.00012066005,0.00059159345,0.000006210994,0.00044518473],"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980894,0.00024602853,0.0005429257,0.0002737608,0.0006089399,0.00023899693],"domain_scores_gemma":[0.99769723,0.000022755752,0.00047424098,0.0016521461,0.00007234431,0.000081274346],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0012719213,0.000151917,0.00021948022,0.00028369998,0.0006815138,0.00050390494,0.0019947516,0.00003380557,0.000082100174],"category_scores_gemma":[0.00008704924,0.00012741565,0.000066285655,0.00051104976,0.000012198669,0.0030015206,0.0015674965,0.00029631908,0.00079495023],"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":[0.00017560321,0.00003372215,0.22521052,0.0016974767,0.0025454469,0.000041295712,0.51397896,0.06015177,0.00000976397,0.080372006,0.036754247,0.07902921],"study_design_scores_gemma":[0.0006953581,0.00008201639,0.018653708,0.0000106223615,0.00013507542,0.00015088863,0.009990929,0.67085135,0.000014813315,0.0000031102422,0.29902944,0.0003826999],"about_ca_topic_score_codex":0.0000140229295,"about_ca_topic_score_gemma":1.2507813e-7,"teacher_disagreement_score":0.98745733,"about_ca_system_score_codex":0.00011665718,"about_ca_system_score_gemma":0.0000979534,"threshold_uncertainty_score":0.9999831},"labels":[],"label_agreement":null},{"id":"W6901811255","doi":"10.60692/pvc15-4bf24","title":"The Bigger Fish: A Comparison of Meta-Learning QSAR Models on Low-Resourced Aquatic Toxicity Regression Tasks","year":2023,"lang":"en","type":"article","venue":"Greater South Information System","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Quantitative structure–activity relationship; Aquatic toxicology; Chemical toxicity; Benchmark (surveying); Toxicity; Random forest","score_opus":0.09654934782186685,"score_gpt":0.27807044034848377,"score_spread":0.1815210925266169,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6901811255","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":[0.5243035,0.00000869848,0.46930116,0.0009989816,0.0003800524,0.00050683785,0.000032564465,0.0010223805,0.0034458265],"genre_scores_gemma":[0.9989431,4.4616425e-7,0.0005361118,0.00008355539,0.000021932829,0.000062730396,0.00004874301,0.000008340716,0.00029502882],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975973,0.00040908236,0.0008137869,0.00022151752,0.00068921276,0.00026912376],"domain_scores_gemma":[0.9979918,0.00013655456,0.0008149214,0.0008655093,0.00011476241,0.00007645676],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014918564,0.00019572898,0.00036498753,0.0003126301,0.00050049863,0.00036703012,0.0007229233,0.00009671843,0.0000031329394],"category_scores_gemma":[0.00016407188,0.00011432626,0.00013946393,0.0007341825,0.000034054396,0.00079436286,0.00019300045,0.00026100624,0.0004991857],"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":[0.0002759128,0.000035185963,0.03422402,0.001339127,0.0007944127,0.0000048680477,0.42975846,0.46789452,0.000073625626,0.026973754,0.0058093388,0.032816786],"study_design_scores_gemma":[0.0002942897,0.00006585562,0.0054090703,0.00012670147,0.000039333954,0.0000023325426,0.0038811404,0.9884494,0.00067714736,0.000011350032,0.00090897473,0.000134402],"about_ca_topic_score_codex":0.000012773263,"about_ca_topic_score_gemma":3.8982608e-7,"teacher_disagreement_score":0.5205549,"about_ca_system_score_codex":0.000052968448,"about_ca_system_score_gemma":0.000029178023,"threshold_uncertainty_score":0.6416189},"labels":[],"label_agreement":null},{"id":"W6906257848","doi":"10.15468/dl.z653b6","title":"Occurrence Download","year":2022,"lang":"en","type":"dataset","venue":"Global Biodiversity Information Facility","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Download; Matching (statistics); Range (aeronautics); Alien; Information system","score_opus":0.015963953544511,"score_gpt":0.2283926934335638,"score_spread":0.2124287398890528,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6906257848","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00001318321,0.000018436109,0.0006535181,0.0005864765,0.0007423369,0.0001918153,0.9974072,0.00022320925,0.0001638152],"genre_scores_gemma":[0.000004438269,0.00005153108,0.000015095724,0.0006443514,9.2691306e-7,0.000007193703,0.9992763,7.723e-9,1.9087774e-7],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981996,0.00016436444,0.00034909093,0.0003443622,0.0006837717,0.0002587994],"domain_scores_gemma":[0.99811596,0.00002937573,0.00039485758,0.0011891469,0.00013557295,0.00013509073],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00046926012,0.00023308398,0.00020392828,0.00012228593,0.00055458257,0.00037259917,0.0020341119,0.0001698549,0.011444161],"category_scores_gemma":[0.00018841306,0.00024983558,0.00011116574,0.0005610709,0.000069947346,0.0018696216,0.0013792459,0.00048195967,0.07811141],"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":[0.000008656377,0.000030761854,0.00032607687,0.00005609813,0.000011489086,0.0000016420192,0.000039188442,0.00002436875,1.3484593e-8,0.0000034234865,0.9916001,0.007898211],"study_design_scores_gemma":[0.00017713773,0.000037217043,0.00014532484,6.188974e-7,0.000013517228,0.000007294295,0.00003675219,0.000005612557,2.8776338e-7,0.0000019477095,0.9993223,0.00025199467],"about_ca_topic_score_codex":0.00052231725,"about_ca_topic_score_gemma":0.0000060922407,"teacher_disagreement_score":0.06666725,"about_ca_system_score_codex":0.0003358572,"about_ca_system_score_gemma":0.00019832127,"threshold_uncertainty_score":0.9999954},"labels":[],"label_agreement":null},{"id":"W6920767952","doi":"10.6084/m9.figshare.16869879","title":"Additional file 1 of Improve hot region prediction by analyzing different machine learning algorithms","year":2021,"lang":"en","type":"article","venue":"Figshare","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Support vector machine; Computational learning theory; Feature (linguistics); Feature selection; Statistical classification","score_opus":0.020983552765622093,"score_gpt":0.22730554925314944,"score_spread":0.20632199648752736,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6920767952","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000044687304,0.00008889519,0.004439156,0.00011236709,0.000030360778,0.000044681252,0.9945248,0.00012624255,0.000629028],"genre_scores_gemma":[0.002323081,0.0000046099394,0.002656663,0.000035558875,0.000082897044,0.00015763832,0.9919327,0.000008465279,0.0027984108],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.999027,0.000079682206,0.00018745725,0.00034361854,0.00022466246,0.00013757247],"domain_scores_gemma":[0.9984464,0.0008204879,0.00020927262,0.0003149183,0.00014794889,0.000060982256],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000022946952,0.00010401098,0.00011778538,0.000053893742,0.0001196341,0.00008203879,0.0002645923,0.00006148943,0.81379044],"category_scores_gemma":[0.0033010473,0.00009991893,0.00006343747,0.00024754144,0.000004585559,0.00025388444,0.00018256647,0.00025033255,0.00024494863],"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":[0.0000010174537,0.00004754067,0.00002575822,0.000029671532,0.0000074560226,0.0000039091983,0.000021741811,0.000014920118,0.00025294098,0.000008093711,0.9640364,0.035550542],"study_design_scores_gemma":[0.0000881057,0.000051194875,0.0037868829,0.00040930134,0.0000025327163,0.000012155654,0.00000559367,0.22972155,0.0006578295,0.000014241888,0.76516175,0.00008886821],"about_ca_topic_score_codex":0.000004628899,"about_ca_topic_score_gemma":0.0000023430512,"teacher_disagreement_score":0.81354547,"about_ca_system_score_codex":0.00003210957,"about_ca_system_score_gemma":0.000054480533,"threshold_uncertainty_score":0.40745756},"labels":[],"label_agreement":null},{"id":"W6920891803","doi":"10.60692/pncx8-syp73","title":"Task-Informed Meta-Learning data","year":2022,"lang":"en","type":"article","venue":"Greater South Information System","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Data set; Codebase; Data collection; Identification (biology); Work (physics)","score_opus":0.10709365004999226,"score_gpt":0.260133056864539,"score_spread":0.15303940681454675,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6920891803","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":[0.0068983394,0.000014789292,0.9732729,0.0006949794,0.00078237295,0.0003888666,0.00028983413,0.0014173881,0.016240485],"genre_scores_gemma":[0.9943557,1.12173204e-7,0.004164988,0.0002799337,0.00003564091,0.00012066005,0.00059159345,0.000006210994,0.00044518473],"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980894,0.00024602853,0.0005429257,0.0002737608,0.0006089399,0.00023899693],"domain_scores_gemma":[0.99769723,0.000022755752,0.00047424098,0.0016521461,0.00007234431,0.000081274346],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0012719213,0.000151917,0.00021948022,0.00028369998,0.0006815138,0.00050390494,0.0019947516,0.00003380557,0.000082100174],"category_scores_gemma":[0.00008704924,0.00012741565,0.000066285655,0.00051104976,0.000012198669,0.0030015206,0.0015674965,0.00029631908,0.00079495023],"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":[0.00017560321,0.00003372215,0.22521052,0.0016974767,0.0025454469,0.000041295712,0.51397896,0.06015177,0.00000976397,0.080372006,0.036754247,0.07902921],"study_design_scores_gemma":[0.0006953581,0.00008201639,0.018653708,0.0000106223615,0.00013507542,0.00015088863,0.009990929,0.67085135,0.000014813315,0.0000031102422,0.29902944,0.0003826999],"about_ca_topic_score_codex":0.0000140229295,"about_ca_topic_score_gemma":1.2507813e-7,"teacher_disagreement_score":0.98745733,"about_ca_system_score_codex":0.00011665718,"about_ca_system_score_gemma":0.0000979534,"threshold_uncertainty_score":0.9999831},"labels":[],"label_agreement":null},{"id":"W6920948796","doi":"10.6084/m9.figshare.16869879.v1","title":"Additional file 1 of Improve hot region prediction by analyzing different machine learning algorithms","year":2021,"lang":"en","type":"article","venue":"Figshare","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Support vector machine; Computational learning theory; Feature (linguistics); Feature selection; Statistical classification","score_opus":0.020983552765622093,"score_gpt":0.22730554925314944,"score_spread":0.20632199648752736,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6920948796","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000044687304,0.00008889519,0.004439156,0.00011236709,0.000030360778,0.000044681252,0.9945248,0.00012624255,0.000629028],"genre_scores_gemma":[0.002323081,0.0000046099394,0.002656663,0.000035558875,0.000082897044,0.00015763832,0.9919327,0.000008465279,0.0027984108],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.999027,0.000079682206,0.00018745725,0.00034361854,0.00022466246,0.00013757247],"domain_scores_gemma":[0.9984464,0.0008204879,0.00020927262,0.0003149183,0.00014794889,0.000060982256],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000022946952,0.00010401098,0.00011778538,0.000053893742,0.0001196341,0.00008203879,0.0002645923,0.00006148943,0.81379044],"category_scores_gemma":[0.0033010473,0.00009991893,0.00006343747,0.00024754144,0.000004585559,0.00025388444,0.00018256647,0.00025033255,0.00024494863],"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":[0.0000010174537,0.00004754067,0.00002575822,0.000029671532,0.0000074560226,0.0000039091983,0.000021741811,0.000014920118,0.00025294098,0.000008093711,0.9640364,0.035550542],"study_design_scores_gemma":[0.0000881057,0.000051194875,0.0037868829,0.00040930134,0.0000025327163,0.000012155654,0.00000559367,0.22972155,0.0006578295,0.000014241888,0.76516175,0.00008886821],"about_ca_topic_score_codex":0.000004628899,"about_ca_topic_score_gemma":0.0000023430512,"teacher_disagreement_score":0.81354547,"about_ca_system_score_codex":0.00003210957,"about_ca_system_score_gemma":0.000054480533,"threshold_uncertainty_score":0.40745756},"labels":[],"label_agreement":null},{"id":"W6924792641","doi":"10.1594/pangaea.972609","title":"Seawater carbonate chemistry and nearshore microbial communities of the Pacific Northwest coasts of Canada and the U.S","year":2024,"lang":"en","type":"dataset","venue":"Open MIND","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Carbonate; Pelagic zone; Seawater; Ocean chemistry; Ocean acidification; Latitude; Spring (device); Benthos","score_opus":0.010787110123702388,"score_gpt":0.23019108960968715,"score_spread":0.21940397948598475,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6924792641","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.032829937,0.00021211871,0.0000023883554,0.0013952137,0.00023562241,0.00024516118,0.96434647,9.331629e-7,0.00073217385],"genre_scores_gemma":[0.25815344,0.00021641099,0.00037973188,0.000071994764,0.00006459795,0.000018397692,0.7394641,0.000015400472,0.0016158874],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99920243,0.00014128789,0.00020612344,0.00018633879,0.00016229076,0.000101552614],"domain_scores_gemma":[0.99866295,0.00016118879,0.00018019411,0.0009259569,0.000041257685,0.000028466082],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003800929,0.00012875702,0.00021711807,0.000011953849,0.00012124036,0.0002587337,0.0015776887,0.00006550846,0.000035419405],"category_scores_gemma":[0.000023939063,0.00007160079,0.000021945181,0.00009265158,0.00034894692,0.000060758506,0.0017501606,0.00035454665,0.0000018786533],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028451106,0.00001984479,0.0007553009,0.0003458705,0.0000797035,0.0000056736108,0.0016780554,0.0000115644125,0.0001704803,0.000017083192,0.9907495,0.0061385105],"study_design_scores_gemma":[0.00024477256,0.000007301975,0.0008053556,0.0001572078,0.000043446293,0.000028985187,0.00031011188,0.0009788749,0.00033034664,0.0000126208315,0.99697304,0.00010791441],"about_ca_topic_score_codex":0.47736296,"about_ca_topic_score_gemma":0.7178525,"teacher_disagreement_score":0.24048948,"about_ca_system_score_codex":0.0000141024175,"about_ca_system_score_gemma":0.00041395755,"threshold_uncertainty_score":0.5261173},"labels":[],"label_agreement":null},{"id":"W6930309412","doi":"10.5281/zenodo.12059182","title":"obsessive-compulsive inventory pdf","year":2024,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Measure (data warehouse); Diafiltration; Scale (ratio); Nucleofection; Frame (networking); Filter (signal processing)","score_opus":0.029467942980760976,"score_gpt":0.25760888044597324,"score_spread":0.22814093746521227,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6930309412","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":[0.0000025944578,0.0006572628,0.047891945,0.00088333956,0.00045005782,0.00027692024,0.00011867324,0.0028250304,0.94689417],"genre_scores_gemma":[0.0011652183,0.00025263455,0.0021806513,0.00023437159,0.00061168463,9.269609e-8,0.0038285488,0.0065268516,0.9851999],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9978569,0.00037661413,0.00022045746,0.0007912001,0.00043438675,0.00032042764],"domain_scores_gemma":[0.99837255,0.000013243417,0.0001988238,0.0010696427,0.00017254146,0.00017317245],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.000420684,0.00022576831,0.00019512083,0.00055039435,0.0005871989,0.0016282146,0.0025786604,0.00015038521,0.032909576],"category_scores_gemma":[0.00031083194,0.00023053879,0.00007329455,0.00063962844,0.00011423493,0.00019422913,0.0021391888,0.0005493389,0.24858744],"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":[0.0000023201892,0.000036317717,3.3021172e-7,0.00012277668,0.00003892218,0.00002100715,0.00026884262,0.0000027627502,0.000053750962,0.023513112,0.9075977,0.06834214],"study_design_scores_gemma":[0.00014803086,0.00006905867,0.000025359897,0.00015710302,0.000013909911,0.000056551195,0.000034849752,0.0017455842,0.000008730489,0.00052570476,0.99697316,0.00024194784],"about_ca_topic_score_codex":0.000034632245,"about_ca_topic_score_gemma":4.92716e-7,"teacher_disagreement_score":0.21567787,"about_ca_system_score_codex":0.00011892536,"about_ca_system_score_gemma":0.0000075797675,"threshold_uncertainty_score":0.9994082},"labels":[],"label_agreement":null},{"id":"W6931072031","doi":"10.5281/zenodo.2614079","title":"cbedetti/Dcm2Bids 2.1.0","year":2019,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; McGill University","funders":"","keywords":"Debugging; Software; Code (set theory); Table (database); Key (lock)","score_opus":0.027779223425335675,"score_gpt":0.24962721370642568,"score_spread":0.22184799028109,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6931072031","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":[0.0000021267924,0.00017580623,0.10209134,0.00096992933,0.0002685765,0.0003171977,0.00013337335,0.002767191,0.8932745],"genre_scores_gemma":[0.0020449099,0.0002732978,0.0043794303,0.00034119497,0.0005115086,5.17645e-8,0.0050800405,0.008593268,0.9787763],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9979607,0.00036305928,0.0001991727,0.0007023662,0.0004399698,0.00033474067],"domain_scores_gemma":[0.9979558,0.000020097074,0.00021311156,0.0015128613,0.00015871812,0.0001394404],"candidate_categories":["scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00050201267,0.00020704635,0.00019469563,0.0004363146,0.0006920722,0.001263273,0.0031092062,0.00016706977,0.013998116],"category_scores_gemma":[0.00029779912,0.00021381042,0.0000589943,0.00051243603,0.000073822805,0.00019741771,0.0018669066,0.00042791784,0.08888381],"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":[0.0000026489972,0.00003562531,4.7538123e-7,0.000055706805,0.000019756342,0.0000036613212,0.000113951966,0.0000042154256,0.00009775377,0.024999086,0.82922596,0.14544116],"study_design_scores_gemma":[0.00021653001,0.00008543383,0.000055586777,0.00006056751,0.000006820537,0.000038464277,0.000017058208,0.0015036851,0.000014211564,0.00007795966,0.9976845,0.00023920005],"about_ca_topic_score_codex":0.00003835506,"about_ca_topic_score_gemma":3.2369272e-7,"teacher_disagreement_score":0.16845852,"about_ca_system_score_codex":0.000081236074,"about_ca_system_score_gemma":0.000006265188,"threshold_uncertainty_score":0.9997735},"labels":[],"label_agreement":null},{"id":"W6931135697","doi":"10.5281/zenodo.5622906","title":"Glypthelmins californiensis (Cort, 1919) Miller 1930","year":2008,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Sucker; Pharynx; Dorsum; Taxonomy (biology); Integumentary system","score_opus":0.049723189935892365,"score_gpt":0.24323010480957957,"score_spread":0.1935069148736872,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6931135697","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":[0.046444636,0.00022873627,0.6049591,0.006559197,0.00047542455,0.00067474396,0.0002637641,0.0050266385,0.33536777],"genre_scores_gemma":[0.98765796,0.0002075488,0.005853405,0.00051957567,0.0002005156,6.652531e-8,0.0013971975,0.0007279399,0.0034358052],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99815255,0.0003016657,0.00023907023,0.00053020363,0.0004194715,0.00035703654],"domain_scores_gemma":[0.99838936,0.000029697574,0.00011036502,0.00092200085,0.00034998893,0.00019858856],"candidate_categories":["sts","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0004891379,0.00013944478,0.00013014265,0.00021772066,0.0026306002,0.0004820579,0.0017367363,0.00005802957,0.0022317441],"category_scores_gemma":[0.0005123918,0.00013825476,0.000055178498,0.0006872131,0.00013818486,0.00043268496,0.0011951393,0.00027542244,0.0139975455],"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":[0.000037836755,0.00029381324,0.00010504158,0.000042633368,0.000049741342,0.00008031575,0.003616489,0.0001956384,0.0036332896,0.032770477,0.56165195,0.39752275],"study_design_scores_gemma":[0.00027219247,0.000101834055,0.003951764,0.000008721429,0.0000038679864,0.00030873527,0.000043152482,0.008494614,0.00017949606,0.00011657598,0.9863471,0.00017197586],"about_ca_topic_score_codex":0.000041943047,"about_ca_topic_score_gemma":3.892471e-7,"teacher_disagreement_score":0.9412133,"about_ca_system_score_codex":0.00007932917,"about_ca_system_score_gemma":0.000006247382,"threshold_uncertainty_score":0.99868035},"labels":[],"label_agreement":null},{"id":"W6931227442","doi":"10.5281/zenodo.4790996","title":"DE LA COMPÉTENCE PRAGMATIQUE EN LANGUE SECONDE: UNE ÉTUDE DES RÉPONSES AUX COMPLIMENTS EN FRANÇAIS L1 ET L2 EN CONTEXTE CANADIEN","year":2021,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Expansive; Realization (probability); Competence (human resources); Pragmatics; French","score_opus":0.022072256102537668,"score_gpt":0.28223409481235107,"score_spread":0.2601618387098134,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6931227442","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":[0.23497157,0.0002907209,0.6066271,0.01077147,0.00014975188,0.0005664374,0.0004057806,0.0019046782,0.14431247],"genre_scores_gemma":[0.99106926,0.000070126865,0.0066586593,0.0005334676,0.00003942795,1.6100807e-7,0.0007935729,0.00025857775,0.0005767445],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.996239,0.0025216746,0.0002132368,0.0004299948,0.00027711736,0.00031894364],"domain_scores_gemma":[0.9984672,0.00031665168,0.000089620225,0.0005869608,0.00035034452,0.00018924531],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0015405158,0.00013758871,0.00014618087,0.000120509925,0.0011487153,0.001028645,0.0013718647,0.000075560194,0.0012787753],"category_scores_gemma":[0.0015800861,0.0001468208,0.000034832963,0.0005258605,0.00014112491,0.00041939504,0.0011796505,0.00040961092,0.001298306],"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":[0.00008078525,0.00072306854,0.0020352807,0.00037026106,0.0002690141,0.00045981305,0.08670729,0.002201145,0.048703186,0.40818536,0.09537986,0.35488492],"study_design_scores_gemma":[0.00065748283,0.00014536342,0.20074175,0.000089221525,0.000013528013,0.0006106082,0.0008275115,0.02253685,0.0011261979,0.0010164031,0.7719267,0.00030840753],"about_ca_topic_score_codex":0.0013842133,"about_ca_topic_score_gemma":0.00010014933,"teacher_disagreement_score":0.7560977,"about_ca_system_score_codex":0.00017584539,"about_ca_system_score_gemma":0.00003815015,"threshold_uncertainty_score":0.9996342},"labels":[],"label_agreement":null},{"id":"W6931605367","doi":"10.5683/sp3/q4ulsx","title":"Impact of Adverse Childhood Experiences and Resilience on Adult Emergency Room","year":2022,"lang":"en","type":"dataset","venue":"Borealis","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University; Western University","funders":"","keywords":"Adverse Childhood Experiences; Resilience (materials science); Psychological resilience; Population; Emergency department; Health care; Adverse effect; Vulnerability (computing)","score_opus":0.009992132657145813,"score_gpt":0.2859608876552374,"score_spread":0.2759687549980916,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6931605367","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0020928688,0.000108371394,0.00020261884,0.0000997618,0.00018074852,0.00014970811,0.99682397,0.00004765721,0.0002942693],"genre_scores_gemma":[0.003912409,0.00052929827,0.00022413727,0.00004576811,0.000054982265,0.00007410259,0.9951241,0.000007755579,0.000027435539],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9981458,0.00016931072,0.0003434009,0.0006207196,0.00050548074,0.00021526979],"domain_scores_gemma":[0.9979378,0.00006453118,0.0004058169,0.0014183503,0.000063410065,0.00011009762],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002170243,0.00023427604,0.00025443404,0.00020742849,0.00018084825,0.00002585656,0.0014153164,0.00009294963,0.001192937],"category_scores_gemma":[0.00035146024,0.00019188483,0.000107709,0.00034108132,0.000041985884,0.00023106867,0.00039741848,0.00032782456,0.0000037302511],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009818756,0.00011780154,0.0003771428,0.000019235635,0.000016275264,0.0000075849844,0.0008931802,0.000047568163,0.0000017083313,0.00034290573,0.99512726,0.0030395184],"study_design_scores_gemma":[0.00024783192,0.00094631943,0.17769009,0.000045243836,0.000022857286,0.000017181685,0.0003254379,0.0007037855,0.0000058760547,0.00012378846,0.8194502,0.00042137102],"about_ca_topic_score_codex":0.029293885,"about_ca_topic_score_gemma":0.00097248366,"teacher_disagreement_score":0.17731294,"about_ca_system_score_codex":0.00004228198,"about_ca_system_score_gemma":0.00014170895,"threshold_uncertainty_score":0.9997201},"labels":[],"label_agreement":null},{"id":"W6931668650","doi":"10.5683/sp3/nv0du8","title":"Triage: Mr Sea and Mr Dee","year":2025,"lang":"en","type":"dataset","venue":"Borealis","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Interpretation (philosophy); Table (database); Object (grammar); Feature (linguistics)","score_opus":0.015688381868091846,"score_gpt":0.2824364879139928,"score_spread":0.26674810604590093,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6931668650","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0000010726782,0.00024546342,0.007856696,0.0017447942,0.00021890437,0.0001302286,0.9885046,0.0001093274,0.0011889342],"genre_scores_gemma":[0.0000057067455,0.00045201048,0.0018512342,0.0005562491,0.0001371358,0.000023936644,0.996434,0.0000038345347,0.00053592754],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986178,0.00015599719,0.00022898806,0.00055849954,0.0002424796,0.00019620515],"domain_scores_gemma":[0.9979161,0.0001823588,0.00014951648,0.0016078181,0.000050650448,0.00009357742],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003661938,0.00020089158,0.0002445095,0.0001888884,0.00013217215,0.00033317506,0.0011495324,0.00017488301,0.00001051462],"category_scores_gemma":[0.0003758409,0.00018058572,0.000045978206,0.0002450177,0.000037555445,0.00017113518,0.00047378332,0.00037099846,0.0000073499987],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000034076527,0.0000180403,0.000021606615,0.00007202593,0.000013763293,0.000010401918,0.000011668559,9.2500693e-7,6.12761e-7,0.001755471,0.9765064,0.021585666],"study_design_scores_gemma":[0.00019398102,0.00002616375,0.0012622568,0.000043415203,0.00002790915,0.0000075357266,0.0000017627052,0.0011956947,0.000003729507,0.00022629678,0.9968312,0.00018010376],"about_ca_topic_score_codex":0.017199988,"about_ca_topic_score_gemma":0.0026511138,"teacher_disagreement_score":0.02140556,"about_ca_system_score_codex":0.000027446797,"about_ca_system_score_gemma":0.0001506705,"threshold_uncertainty_score":0.98934454},"labels":[],"label_agreement":null},{"id":"W6931703398","doi":"10.5281/zenodo.7003390","title":"Copelatus tenebrosus Regimbart 1880","year":2022,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Laurentian University","funders":"","keywords":"Instar; Head (geology); Margin (machine learning); Dorsum; Head and neck; Table (database)","score_opus":0.02960653311971357,"score_gpt":0.23939160179231264,"score_spread":0.20978506867259908,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6931703398","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":[0.008731235,0.00045061423,0.29470384,0.014363307,0.00085199694,0.00093207567,0.00032880908,0.006436008,0.6732021],"genre_scores_gemma":[0.98675,0.00003950482,0.0034364052,0.0006286458,0.0001350987,1.7818229e-7,0.0022123621,0.0007748369,0.00602295],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9979708,0.0005570828,0.00019020379,0.00048853044,0.00048861763,0.00030473198],"domain_scores_gemma":[0.9986484,0.000024429604,0.00011038404,0.0008863853,0.00019546582,0.00013495529],"candidate_categories":["sts","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0008345318,0.0001026156,0.000096429845,0.0002032147,0.0042208284,0.00090308697,0.0023807404,0.000025685891,0.005958881],"category_scores_gemma":[0.00034489093,0.00011381721,0.0000397216,0.0008250788,0.000062923355,0.00035175483,0.0032619394,0.000405221,0.004988822],"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":[0.000030713105,0.00017485993,0.00001433962,0.0000207476,0.000020855841,0.000025242003,0.0013707691,0.00059912534,0.0025717732,0.15539938,0.52494913,0.31482306],"study_design_scores_gemma":[0.00027680778,0.00019124114,0.00088729465,0.0000032793268,0.000003211538,0.0001867054,0.00015397751,0.009444636,0.00005735364,0.0003839001,0.9882745,0.0001370975],"about_ca_topic_score_codex":0.000016187125,"about_ca_topic_score_gemma":8.4910425e-8,"teacher_disagreement_score":0.97801876,"about_ca_system_score_codex":0.00015252619,"about_ca_system_score_gemma":0.0000060460666,"threshold_uncertainty_score":0.99707556},"labels":[],"label_agreement":null},{"id":"W6939173559","doi":"10.60692/90yxk-5w685","title":"Synbols: Probing Learning Algorithms with Synthetic Datasets","year":2020,"lang":"en","type":"article","venue":"Greater South Information System","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Benchmark (surveying); Code (set theory); Synthetic data; Source code; Key (lock); Pattern recognition (psychology)","score_opus":0.03454430125556018,"score_gpt":0.2162257387580032,"score_spread":0.181681437502443,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6939173559","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":[0.007792855,0.0000023009013,0.9882182,0.0007377252,0.000087439854,0.00025138058,0.00005095729,0.00085092627,0.002008244],"genre_scores_gemma":[0.9897789,7.985109e-8,0.009700921,0.00024915184,0.000049633574,0.000035977202,0.00015497577,0.000007720546,0.000022643435],"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99867994,0.00011683482,0.00037319236,0.0002621341,0.00035072136,0.00021718815],"domain_scores_gemma":[0.99897957,0.00001135277,0.00031276685,0.00047832768,0.000077815625,0.00014017426],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00032677525,0.00015874469,0.00016699769,0.000112965274,0.00022357721,0.0005963417,0.00054718653,0.000051182,0.000005893006],"category_scores_gemma":[0.000053059826,0.00011969312,0.000027425893,0.00039447978,0.00001838206,0.0018675607,0.00015311538,0.00020715642,0.0010792881],"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":[0.0002076051,0.00001550501,0.16957188,0.0035025054,0.00025244613,0.00007665086,0.6418285,0.029020438,0.00003553138,0.020692738,0.0017365617,0.13305965],"study_design_scores_gemma":[0.0008289178,0.00019089412,0.009411919,0.00024868007,0.000021697013,0.00013563882,0.0067010433,0.9679465,0.00028365068,6.76921e-7,0.013807972,0.00042239082],"about_ca_topic_score_codex":0.000004172447,"about_ca_topic_score_gemma":3.347383e-8,"teacher_disagreement_score":0.98198605,"about_ca_system_score_codex":0.00004020502,"about_ca_system_score_gemma":0.00004016861,"threshold_uncertainty_score":0.99969846},"labels":[],"label_agreement":null},{"id":"W6939354856","doi":"10.60692/fvd00-km275","title":"Task-Informed Meta-Learning data","year":2022,"lang":"en","type":"article","venue":"Greater South Information System","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Data set; Codebase; Data collection; Identification (biology); Work (physics)","score_opus":0.10709365004999226,"score_gpt":0.260133056864539,"score_spread":0.15303940681454675,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6939354856","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":[0.0068983394,0.000014789292,0.9732729,0.0006949794,0.00078237295,0.0003888666,0.00028983413,0.0014173881,0.016240485],"genre_scores_gemma":[0.9943557,1.12173204e-7,0.004164988,0.0002799337,0.00003564091,0.00012066005,0.00059159345,0.000006210994,0.00044518473],"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980894,0.00024602853,0.0005429257,0.0002737608,0.0006089399,0.00023899693],"domain_scores_gemma":[0.99769723,0.000022755752,0.00047424098,0.0016521461,0.00007234431,0.000081274346],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0012719213,0.000151917,0.00021948022,0.00028369998,0.0006815138,0.00050390494,0.0019947516,0.00003380557,0.000082100174],"category_scores_gemma":[0.00008704924,0.00012741565,0.000066285655,0.00051104976,0.000012198669,0.0030015206,0.0015674965,0.00029631908,0.00079495023],"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":[0.00017560321,0.00003372215,0.22521052,0.0016974767,0.0025454469,0.000041295712,0.51397896,0.06015177,0.00000976397,0.080372006,0.036754247,0.07902921],"study_design_scores_gemma":[0.0006953581,0.00008201639,0.018653708,0.0000106223615,0.00013507542,0.00015088863,0.009990929,0.67085135,0.000014813315,0.0000031102422,0.29902944,0.0003826999],"about_ca_topic_score_codex":0.0000140229295,"about_ca_topic_score_gemma":1.2507813e-7,"teacher_disagreement_score":0.98745733,"about_ca_system_score_codex":0.00011665718,"about_ca_system_score_gemma":0.0000979534,"threshold_uncertainty_score":0.9999831},"labels":[],"label_agreement":null},{"id":"W6957859046","doi":"10.60692/hqq8r-82y34","title":"The Bigger Fish: A Comparison of Meta-Learning QSAR Models on Low-Resourced Aquatic Toxicity Regression Tasks","year":2023,"lang":"en","type":"article","venue":"Greater South Information System","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Quantitative structure–activity relationship; Aquatic toxicology; Chemical toxicity; Benchmark (surveying); Toxicity; Random forest","score_opus":0.09654934782186685,"score_gpt":0.27807044034848377,"score_spread":0.1815210925266169,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6957859046","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":[0.5243035,0.00000869848,0.46930116,0.0009989816,0.0003800524,0.00050683785,0.000032564465,0.0010223805,0.0034458265],"genre_scores_gemma":[0.9989431,4.4616425e-7,0.0005361118,0.00008355539,0.000021932829,0.000062730396,0.00004874301,0.000008340716,0.00029502882],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975973,0.00040908236,0.0008137869,0.00022151752,0.00068921276,0.00026912376],"domain_scores_gemma":[0.9979918,0.00013655456,0.0008149214,0.0008655093,0.00011476241,0.00007645676],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014918564,0.00019572898,0.00036498753,0.0003126301,0.00050049863,0.00036703012,0.0007229233,0.00009671843,0.0000031329394],"category_scores_gemma":[0.00016407188,0.00011432626,0.00013946393,0.0007341825,0.000034054396,0.00079436286,0.00019300045,0.00026100624,0.0004991857],"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":[0.0002759128,0.000035185963,0.03422402,0.001339127,0.0007944127,0.0000048680477,0.42975846,0.46789452,0.000073625626,0.026973754,0.0058093388,0.032816786],"study_design_scores_gemma":[0.0002942897,0.00006585562,0.0054090703,0.00012670147,0.000039333954,0.0000023325426,0.0038811404,0.9884494,0.00067714736,0.000011350032,0.00090897473,0.000134402],"about_ca_topic_score_codex":0.000012773263,"about_ca_topic_score_gemma":3.8982608e-7,"teacher_disagreement_score":0.5205549,"about_ca_system_score_codex":0.000052968448,"about_ca_system_score_gemma":0.000029178023,"threshold_uncertainty_score":0.6416189},"labels":[],"label_agreement":null},{"id":"W6958243593","doi":"10.60692/ypbt8-va881","title":"Association between IL-10 gene polymorphisms (− 1082 A/G, -819 T/C, -592 A/C) and hepatocellular carcinoma: a meta-analysis and trial sequential analysis","year":2023,"lang":"en","type":"article","venue":"Greater South Information System","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Hepatocellular carcinoma; Odds ratio; Confidence interval; Genetic model; Allele; Meta-analysis; Carcinoma; Carcinogenesis","score_opus":0.0815005826719488,"score_gpt":0.2495516832228122,"score_spread":0.16805110055086342,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6958243593","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":[0.6700572,0.000014152268,0.32827356,0.00037977647,0.00009921597,0.00033621234,0.00034784386,0.0003575351,0.00013451552],"genre_scores_gemma":[0.99751157,6.01899e-7,0.0008887472,0.000039704715,0.00008809016,0.000078850026,0.00067687035,0.000007025086,0.00070854975],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9973305,0.0003815939,0.00088144577,0.00042184297,0.00068211765,0.0003025119],"domain_scores_gemma":[0.9980443,0.000057618483,0.0008417865,0.0007172563,0.00018607677,0.00015293136],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020232955,0.00024043163,0.00083592697,0.0016352031,0.00030336305,0.0008657595,0.00033870974,0.00016910478,0.000028902223],"category_scores_gemma":[0.000063809224,0.00020051489,0.0004906677,0.0032040183,0.00002113302,0.0011685143,0.00022607662,0.00013038305,0.00024987123],"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":[0.00008124324,0.0000022010709,0.95114386,0.00005238796,0.037283458,0.0000037153263,0.010622795,0.00025170256,0.0000047438048,0.00017686393,0.00008274192,0.00029426452],"study_design_scores_gemma":[0.003553131,0.00006899856,0.54913336,0.000002281754,0.08328893,0.000004267671,0.00038935203,0.36265543,0.00019966869,0.000004843061,0.00032614448,0.0003736223],"about_ca_topic_score_codex":0.00017028127,"about_ca_topic_score_gemma":0.0000023049552,"teacher_disagreement_score":0.40201053,"about_ca_system_score_codex":0.00011299602,"about_ca_system_score_gemma":0.000035634654,"threshold_uncertainty_score":0.8348539},"labels":[],"label_agreement":null},{"id":"W6958252374","doi":"10.60692/qmhhj-hc007","title":"Synbols: Probing Learning Algorithms with Synthetic Datasets","year":2020,"lang":"en","type":"article","venue":"Greater South Information System","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Benchmark (surveying); Code (set theory); Synthetic data; Source code; Key (lock); Pattern recognition (psychology)","score_opus":0.03454430125556018,"score_gpt":0.2162257387580032,"score_spread":0.181681437502443,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6958252374","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":[0.007792855,0.0000023009013,0.9882182,0.0007377252,0.000087439854,0.00025138058,0.00005095729,0.00085092627,0.002008244],"genre_scores_gemma":[0.9897789,7.985109e-8,0.009700921,0.00024915184,0.000049633574,0.000035977202,0.00015497577,0.000007720546,0.000022643435],"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99867994,0.00011683482,0.00037319236,0.0002621341,0.00035072136,0.00021718815],"domain_scores_gemma":[0.99897957,0.00001135277,0.00031276685,0.00047832768,0.000077815625,0.00014017426],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00032677525,0.00015874469,0.00016699769,0.000112965274,0.00022357721,0.0005963417,0.00054718653,0.000051182,0.000005893006],"category_scores_gemma":[0.000053059826,0.00011969312,0.000027425893,0.00039447978,0.00001838206,0.0018675607,0.00015311538,0.00020715642,0.0010792881],"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":[0.0002076051,0.00001550501,0.16957188,0.0035025054,0.00025244613,0.00007665086,0.6418285,0.029020438,0.00003553138,0.020692738,0.0017365617,0.13305965],"study_design_scores_gemma":[0.0008289178,0.00019089412,0.009411919,0.00024868007,0.000021697013,0.00013563882,0.0067010433,0.9679465,0.00028365068,6.76921e-7,0.013807972,0.00042239082],"about_ca_topic_score_codex":0.000004172447,"about_ca_topic_score_gemma":3.347383e-8,"teacher_disagreement_score":0.98198605,"about_ca_system_score_codex":0.00004020502,"about_ca_system_score_gemma":0.00004016861,"threshold_uncertainty_score":0.99969846},"labels":[],"label_agreement":null},{"id":"W6958589152","doi":"10.6084/m9.figshare.25623756","title":"Poster of Jebel Khalid Volume 7: The Metals","year":2024,"lang":"en","type":"other","venue":"Figshare","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Ornaments; Quarter (Canadian coin); Period (music); Narrative; Horizon; Indian ocean","score_opus":0.0370132875390638,"score_gpt":0.2805457675612982,"score_spread":0.24353248002223438,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6958589152","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":[4.897227e-8,0.0040338994,0.0002355314,0.001378317,0.00023877235,0.00020354168,0.16459733,0.00036420362,0.8289484],"genre_scores_gemma":[0.00022855318,0.000005572875,0.00036784165,0.00021043215,0.00021260144,0.000060034236,0.04219213,0.00012275716,0.95660007],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99916595,0.00006524938,0.00013628049,0.00030572087,0.00021393764,0.0001128424],"domain_scores_gemma":[0.9987549,0.000040916115,0.00017812953,0.00096824346,0.000029875797,0.000027931432],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00007152372,0.0001343072,0.00015129392,0.00010176152,0.000018794628,0.0001372401,0.0011819812,0.00011618301,0.15560327],"category_scores_gemma":[0.00021116852,0.00008557843,0.00008449381,0.00019336991,0.000006378387,0.000058799247,0.0004023162,0.00021472134,0.026995292],"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":[1.6059582e-7,0.0000047356675,0.0000011047528,0.00019691548,0.000022059858,0.0000025815016,0.00004662272,3.0922837e-7,0.0000029192722,0.00043188644,0.9956595,0.0036312267],"study_design_scores_gemma":[0.000022844073,0.000010442842,0.00008605659,0.0010082917,0.000009816642,0.0000049417786,0.0000017833454,0.0009112243,0.000016429347,0.00006610815,0.99776256,0.000099515026],"about_ca_topic_score_codex":0.000037481015,"about_ca_topic_score_gemma":0.000012114747,"teacher_disagreement_score":0.12860799,"about_ca_system_score_codex":0.00000775129,"about_ca_system_score_gemma":0.000041742347,"threshold_uncertainty_score":0.97376233},"labels":[],"label_agreement":null},{"id":"W6958765529","doi":"10.6084/m9.figshare.c.6694825.v1","title":"System dynamics models of depression at the population level: a scoping review","year":2024,"lang":"en","type":"other","venue":"Figshare","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Ottawa; Université de Montréal; University of Toronto; Public Health Agency of Canada","funders":"","keywords":"Depression (economics); Psychological intervention; Population; System dynamics; Meta-analysis; Disease; Incidence (geometry); Recall","score_opus":0.09418895925993197,"score_gpt":0.33340099754412716,"score_spread":0.23921203828419518,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6958765529","genre_codex":"other","genre_gemma":"dataset","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":[1.0883069e-7,0.30885494,0.025175884,0.00053412357,0.00051678845,0.0024717806,0.21335265,0.0014611904,0.44763255],"genre_scores_gemma":[0.0015636533,0.0010874436,0.0021919175,0.0002224192,0.00030180046,0.0005158086,0.59795576,0.0004594663,0.39570174],"study_design_codex":"not_applicable","study_design_gemma":"systematic_review","domain_scores_codex":[0.998981,0.000092432165,0.00022490461,0.00034516398,0.0002613062,0.0000951725],"domain_scores_gemma":[0.9986617,0.000036982692,0.00036826663,0.00087597506,0.00003226315,0.000024839906],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00010542441,0.00013573832,0.00021164281,0.000075210046,0.00003957397,0.00006440551,0.00063684967,0.000114461705,0.0053242804],"category_scores_gemma":[0.00011948154,0.00009041058,0.00006792959,0.00020139165,0.0000024037447,0.000094409,0.0004551955,0.00015074208,0.0014082631],"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":[2.628237e-7,0.000002370969,0.0000023304074,0.037306134,0.000007528221,0.0000013845249,0.000010203528,0.00007076957,1.7263997e-7,0.0010501659,0.9512702,0.010278433],"study_design_scores_gemma":[0.000024681147,0.000003667336,0.000024473165,0.74610066,0.000015989319,0.000009354948,0.0000012443799,0.21892232,0.0000011258968,0.000029167952,0.034745585,0.000121727935],"about_ca_topic_score_codex":0.00010362221,"about_ca_topic_score_gemma":0.00019418803,"teacher_disagreement_score":0.91652465,"about_ca_system_score_codex":0.00008302792,"about_ca_system_score_gemma":0.000038645954,"threshold_uncertainty_score":0.99936926},"labels":[],"label_agreement":null},{"id":"W6966966793","doi":"10.48448/n4d3-w687","title":"Towards Reproducible Machine Learning Research in Natural Language Processing Part 2","year":2022,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Natural language; Support vector machine; Feature (linguistics); Natural (archaeology); Training set","score_opus":0.05891084852940384,"score_gpt":0.3753735924228179,"score_spread":0.3164627438934141,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6966966793","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":[0.00040194075,0.024058087,0.013196135,0.009696236,0.002216256,0.0011366295,0.00003510771,0.0022885834,0.946971],"genre_scores_gemma":[0.26501876,0.00042122416,0.06175568,0.00043963132,0.0011414039,0.00016028801,0.00071934925,0.0003816646,0.669962],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.994713,0.00049248914,0.00034882105,0.0018209753,0.0018326388,0.00079204666],"domain_scores_gemma":[0.9978074,0.00008566359,0.0002651607,0.0015923873,0.000120450015,0.00012898221],"candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0077136573,0.00025045185,0.00027992058,0.0021533794,0.0006995328,0.0006138487,0.0032376081,0.000105772255,0.00068698917],"category_scores_gemma":[0.0010483172,0.0002274527,0.000035347624,0.004931925,0.0004743501,0.0005460338,0.0017995534,0.0023412267,0.000120301025],"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":[0.00000596845,0.0001771922,0.0023063978,0.00016107495,0.0000069920075,0.00008588901,0.001974108,0.00038540087,0.00048517153,0.00795372,0.03139094,0.95506716],"study_design_scores_gemma":[0.0002026728,0.000074576295,0.0004440468,0.00012633257,0.0000024452047,0.000022337339,0.00037394947,0.32472557,0.000039324597,0.00018668668,0.6735206,0.0002814572],"about_ca_topic_score_codex":0.002359679,"about_ca_topic_score_gemma":0.0007453887,"teacher_disagreement_score":0.9547857,"about_ca_system_score_codex":0.00036655462,"about_ca_system_score_gemma":0.0011256518,"threshold_uncertainty_score":0.9999604},"labels":[],"label_agreement":null},{"id":"W6968573593","doi":"10.5281/zenodo.3858650","title":"Stenus (Nestus) brivioi Puthz 1972","year":2012,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Fish <Actinopterygii>; White (mutation); Bottle neck","score_opus":0.04149566955746612,"score_gpt":0.25742483310400194,"score_spread":0.21592916354653582,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6968573593","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":[0.024081446,0.00043789632,0.6565252,0.0050531873,0.00072181114,0.00060712633,0.00009597375,0.0045393864,0.307938],"genre_scores_gemma":[0.9936836,0.00003917131,0.0033668177,0.00023130923,0.0002654534,3.9233587e-8,0.00067737146,0.00047533266,0.0012609122],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99826425,0.00037038422,0.00019641935,0.0003599038,0.00036870767,0.0004403073],"domain_scores_gemma":[0.9985617,0.00002923771,0.000101739606,0.0008252815,0.00023636027,0.0002456742],"candidate_categories":["sts","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00097532547,0.000119910546,0.00010436081,0.0001761453,0.0015244015,0.00095341733,0.0017212366,0.000050891285,0.0017447376],"category_scores_gemma":[0.0005314582,0.00012140448,0.00003886906,0.00059683487,0.00006997713,0.00090855395,0.0013970381,0.00025797603,0.016094327],"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":[0.000011558252,0.0002547501,0.00017728924,0.000041258387,0.000024958737,0.000005785353,0.002546195,0.000037189104,0.0026950014,0.10167736,0.15358904,0.7389396],"study_design_scores_gemma":[0.00020347764,0.0000629638,0.012129641,0.000010183453,0.0000047235053,0.00011043825,0.00006659459,0.002753472,0.00015375284,0.00012053266,0.9842335,0.00015073025],"about_ca_topic_score_codex":0.000020767497,"about_ca_topic_score_gemma":1.2472398e-7,"teacher_disagreement_score":0.96960217,"about_ca_system_score_codex":0.0000803426,"about_ca_system_score_gemma":0.000003077701,"threshold_uncertainty_score":0.99977547},"labels":[],"label_agreement":null},{"id":"W6979357642","doi":"","title":"Darwin Godel Machine: Open-Ended Evolution of Self-Improving Agents","year":2025,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; Government of Canada; Canadian Institute for Advanced Research","keywords":"Darwin (ADL); Coding (social sciences); Code (set theory); Polyglot; Reinforcement learning; Source code; Tree (set theory); Artificial life","score_opus":0.040464422981267165,"score_gpt":0.20776375856981819,"score_spread":0.16729933558855103,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6979357642","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":[0.051041126,0.00003525268,0.92252517,0.00017885142,0.00016791858,0.0001585691,0.0000062977874,0.00017419196,0.025712602],"genre_scores_gemma":[0.9929024,0.000013690918,0.004618979,0.00006284531,0.0000074375425,4.2710488e-7,0.000011114224,0.0000040010195,0.0023791052],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99899584,0.00013450734,0.00014956112,0.0004935528,0.000060431208,0.00016608497],"domain_scores_gemma":[0.99887246,0.00005683905,0.0001521174,0.00077781896,0.00008560159,0.0000551829],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029770666,0.00010688156,0.00013648238,0.00020885507,0.00016736664,0.00007960597,0.0016341613,0.00006158192,0.000016100255],"category_scores_gemma":[0.00006430532,0.00011885575,0.000048331218,0.0009596407,0.00003214062,0.0007598648,0.0008222776,0.00014867012,0.000030680145],"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":[0.000023137727,0.00016692124,0.019109944,0.000047589954,0.000036066715,0.00001069819,0.000099232784,0.007397399,0.0007473749,0.96625835,0.0008544049,0.0052488926],"study_design_scores_gemma":[0.0006198232,0.000032602424,0.032824587,0.000022244016,0.000025932955,9.225229e-7,0.00004317811,0.958645,0.00017420083,0.0057119797,0.0017769798,0.00012257986],"about_ca_topic_score_codex":0.00056695397,"about_ca_topic_score_gemma":0.000038745577,"teacher_disagreement_score":0.9605464,"about_ca_system_score_codex":0.0001635789,"about_ca_system_score_gemma":0.00016638782,"threshold_uncertainty_score":0.48467967},"labels":[],"label_agreement":null},{"id":"W6986081557","doi":"","title":"Offical avg tech Support number 1-(855)990-5999 avg antivirus tech support phone number avg Symantec phone number","year":2016,"lang":"en","type":"other","venue":"OSF Preprints (OSF Preprints)","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Phone; Toll; Telephone number; Phone call; Service (business)","score_opus":0.013832750261402675,"score_gpt":0.28266377752430094,"score_spread":0.26883102726289826,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6986081557","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":[0.00036588282,0.000002365861,0.09524071,0.0009987644,0.0015690199,0.0013229507,0.0002223474,0.0020440447,0.8982339],"genre_scores_gemma":[0.010486819,0.00042192132,0.013769757,0.00040786745,0.0006611251,0.00046686054,0.00041063983,0.00066592,0.9727091],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9870612,0.0012774367,0.0018029392,0.006073537,0.002024133,0.0017607611],"domain_scores_gemma":[0.98588693,0.0006854244,0.0016718323,0.010601862,0.00036162883,0.00079229614],"candidate_categories":["metaepi_narrow","open_science","research_integrity","insufficient_payload"],"consensus_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"category_scores_codex":[0.0054031275,0.0015515751,0.0016433066,0.0005280915,0.00044381208,0.0007058439,0.00651142,0.0016842695,0.9098062],"category_scores_gemma":[0.0016447814,0.0015086338,0.00068322883,0.0011911228,0.00058869686,0.0008714787,0.0053553316,0.0023367733,0.993801],"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":[0.000082671126,0.0010289045,0.01895936,0.00025614697,0.0003600828,0.00024715837,0.00037184198,0.0000061481683,0.0013839279,0.0040735705,0.94596076,0.027269399],"study_design_scores_gemma":[0.0013266692,0.0000013964831,0.002850749,0.00031452687,0.00014193407,0.00078983605,0.000027374557,0.00048107858,0.0019542982,0.0011926733,0.989139,0.0017804296],"about_ca_topic_score_codex":0.0011269499,"about_ca_topic_score_gemma":0.00013184927,"teacher_disagreement_score":0.08399481,"about_ca_system_score_codex":0.00056573405,"about_ca_system_score_gemma":0.00088108145,"threshold_uncertainty_score":0.9999649},"labels":[],"label_agreement":null},{"id":"W6987841809","doi":"","title":"The use of unlabelled data for supervised learning","year":2001,"lang":"en","type":"dissertation","venue":"The Atrium (University of Guelph)","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Benchmark (surveying); Task (project management); Labeled data; Class (philosophy); Semi-supervised learning; Supervised learning; Novelty; Novelty detection","score_opus":0.0663893700932026,"score_gpt":0.26811545107722906,"score_spread":0.20172608098402645,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6987841809","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":[0.21308577,0.0029059665,0.7537241,0.017255796,0.0023462877,0.0030723023,0.0006710287,0.0005404617,0.0063982843],"genre_scores_gemma":[0.8303391,0.0032813463,0.03171849,0.000051852185,0.00016648306,0.0000017591078,0.01119772,0.000051028244,0.12319225],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988308,0.00021654085,0.0001721573,0.00034112923,0.00027112273,0.00016823267],"domain_scores_gemma":[0.99648416,0.00090866216,0.0005234264,0.0018017192,0.00024836778,0.00003365093],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00072228897,0.0001288404,0.00022096882,0.000090018024,0.00067797955,0.00006696735,0.0036895566,0.00011292115,0.000014506134],"category_scores_gemma":[0.0003733847,0.00010043741,0.000103751176,0.00035832883,0.000082612576,0.00045768055,0.00041347856,0.00029322502,0.00001037926],"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":[0.0025426946,0.0003968091,0.0018129672,0.0012052656,0.001109815,0.000014477834,0.021307774,0.0042507364,0.047700226,0.08402176,0.104029566,0.7316079],"study_design_scores_gemma":[0.0009143871,0.00016335893,0.02951493,0.0000919604,0.00025364556,0.0000026565542,0.004695634,0.39810845,0.00006218341,0.000520183,0.56538695,0.00028567255],"about_ca_topic_score_codex":0.00082083227,"about_ca_topic_score_gemma":0.0005035653,"teacher_disagreement_score":0.7313222,"about_ca_system_score_codex":0.000017527134,"about_ca_system_score_gemma":0.00012989691,"threshold_uncertainty_score":0.68561757},"labels":[],"label_agreement":null},{"id":"W6989289054","doi":"","title":"Artificial intelligence for human computing ICMI 2006 and IJCAI 2007 International Workshops, Banff, Canada, November 3, 2006 and Hyderabad, India, January 6, 2007 ; revised selected and invited papers","year":2007,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","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":"Applications of artificial intelligence; Human intelligence; Expert system; Intelligent decision support system","score_opus":0.014452182499678789,"score_gpt":0.2694197421913581,"score_spread":0.25496755969167934,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6989289054","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":[0.15003738,0.0006413362,0.8377282,0.0045228675,0.00063517096,0.0007040988,0.00006250671,0.00020940242,0.005459031],"genre_scores_gemma":[0.9690712,0.00004656654,0.026773686,0.0028159278,0.00030493716,0.000007924441,0.00028525273,0.000020925007,0.0006735633],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9978924,0.00006947074,0.000564388,0.0006981849,0.00032768698,0.00044789576],"domain_scores_gemma":[0.99850214,0.00054818275,0.00021880896,0.0002907995,0.00021249831,0.00022759788],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010344884,0.0002488328,0.00023349287,0.00022062908,0.00042060684,0.00036328007,0.00036270896,0.00012763217,0.000035303758],"category_scores_gemma":[0.00029633087,0.00024429988,0.000023219756,0.00043871783,0.00011056627,0.0003237557,0.00021840488,0.00031945787,0.0000020480327],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001410585,0.0001907508,0.11593353,0.00012604278,0.00013772692,0.000036121033,0.001057257,0.00024421787,0.0038433103,0.025644137,0.061520636,0.79112524],"study_design_scores_gemma":[0.00085957645,0.00018757905,0.5804881,0.00018089474,0.000045224486,0.00011472161,0.00039352194,0.32602954,0.0014092462,0.0014658045,0.08761253,0.0012132969],"about_ca_topic_score_codex":0.032564964,"about_ca_topic_score_gemma":0.09377185,"teacher_disagreement_score":0.81903386,"about_ca_system_score_codex":0.00008307876,"about_ca_system_score_gemma":0.000103386155,"threshold_uncertainty_score":0.99622595},"labels":[],"label_agreement":null},{"id":"W7021239391","doi":"","title":"Newsbrief - updating the Model National Energy Code for Buildings (MNECB)","year":2008,"lang":"en","type":"article","venue":"NPARC","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Code (set theory); Field (mathematics); Energy (signal processing); Building code; Mode (computer interface)","score_opus":0.04043278952880204,"score_gpt":0.276060558649026,"score_spread":0.23562776912022398,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7021239391","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":[0.0013055978,0.0000108620925,0.9717721,0.008526508,0.000063669686,0.000051479514,0.000014292146,0.00010255681,0.01815293],"genre_scores_gemma":[0.77531356,0.000013388554,0.22126637,0.0018921178,0.000121827354,0.000043631706,0.00003993802,0.000007448166,0.001301718],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991855,0.00003079282,0.00013557519,0.0002360545,0.0002643521,0.00014770599],"domain_scores_gemma":[0.9993251,0.00016363135,0.00008337942,0.00028248795,0.000108923814,0.000036456677],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030499685,0.00006919684,0.00006194745,0.000037171496,0.00041527615,0.00006936264,0.0006208594,0.000029792256,0.000010289075],"category_scores_gemma":[0.0001968634,0.00005199401,0.00003732308,0.00013987553,0.000037236692,0.00025506588,0.0001002033,0.00007927399,0.000008372805],"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":[0.0000024247518,0.000013781351,0.000055962442,0.000001978462,0.000003855142,2.3379093e-7,0.00019021869,0.0040634777,0.0030296918,0.9278692,0.04790309,0.016866097],"study_design_scores_gemma":[0.00012369514,0.0000111921645,0.00015277279,0.00000199585,0.0000013346996,0.000010911304,0.0000053681347,0.84160596,0.00025778232,0.044183202,0.11358317,0.00006262528],"about_ca_topic_score_codex":0.000011184662,"about_ca_topic_score_gemma":0.000007293072,"teacher_disagreement_score":0.883686,"about_ca_system_score_codex":0.000025703916,"about_ca_system_score_gemma":0.00010840689,"threshold_uncertainty_score":0.31940106},"labels":[],"label_agreement":null},{"id":"W7026617208","doi":"","title":"Accounting for variance and hyperparameter optimization in machine learning benchmarks","year":2022,"lang":"fr","type":"dissertation","venue":"Papyrus : Institutional Repository (Université de Montréal)","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Agence Nationale de la Recherche; Compute Canada; Canadian Institute for Advanced Research","keywords":"Test (biology); Decision tree","score_opus":0.00776089845587945,"score_gpt":0.19382905189640265,"score_spread":0.1860681534405232,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7026617208","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":[0.43222916,0.07381179,0.44914317,0.004097394,0.005360833,0.0027452372,0.00030557482,0.0004220096,0.031884838],"genre_scores_gemma":[0.8761537,0.001936462,0.07137461,0.00020808111,0.00021989801,0.00021113225,0.007691497,0.00006639838,0.04213821],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974022,0.00032302632,0.000460624,0.0009317394,0.00046107933,0.00042131575],"domain_scores_gemma":[0.998339,0.00039374054,0.00057428796,0.0003501388,0.00019266664,0.00015016427],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.00064081256,0.0003688349,0.0003623097,0.0004231536,0.007142526,0.00025050138,0.0005417002,0.00029864686,0.00009553338],"category_scores_gemma":[0.00035768273,0.00047244361,0.00013312873,0.0005349322,0.00010639908,0.000988139,0.00033544764,0.00083029305,0.0000042521037],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006089865,0.00023538622,0.07524635,0.0004171344,0.00012746065,0.0003019987,0.03929918,0.7796968,0.0019320499,0.06738724,0.000096671945,0.034650754],"study_design_scores_gemma":[0.00096157315,0.00012643724,0.03431343,0.00014925191,0.00009450763,0.00025385045,0.0049090832,0.90361387,0.000104858176,0.00014533686,0.054867696,0.00046010676],"about_ca_topic_score_codex":0.031779405,"about_ca_topic_score_gemma":0.0038788887,"teacher_disagreement_score":0.44392458,"about_ca_system_score_codex":0.002410073,"about_ca_system_score_gemma":0.00083300564,"threshold_uncertainty_score":0.9997727},"labels":[],"label_agreement":null},{"id":"W7030455091","doi":"","title":"New Socialist - QUEBEC: \"Reasonable Accommodation\", A Feminist Response","year":2007,"lang":"fr","type":"other","venue":"OpenEdition (OpenEdition)","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Commission; Power (physics); Government (linguistics); Context (archaeology); Politics","score_opus":0.027568970711661308,"score_gpt":0.28811543039341797,"score_spread":0.26054645968175666,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7030455091","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":[0.00004414377,0.0007961948,0.3479339,0.1535475,0.005397329,0.0011979266,0.00078295043,0.0005544247,0.48974565],"genre_scores_gemma":[0.0033364575,0.00017257089,0.037999883,0.033084866,0.0047354945,0.00024173663,0.008061964,0.00029283855,0.9120742],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99205726,0.0015698061,0.0014639806,0.0020553072,0.0016628281,0.0011908233],"domain_scores_gemma":[0.9933292,0.001179938,0.0016674882,0.002290604,0.00058951665,0.0009431994],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.003266623,0.0011089585,0.0009964411,0.0010103113,0.001504121,0.0032148643,0.0027454952,0.0012016476,0.08048723],"category_scores_gemma":[0.0014058565,0.0012645114,0.00040464837,0.0018084657,0.00044087935,0.0134320315,0.00076567463,0.0012964961,0.030171325],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029234833,0.00024269878,0.00008959979,0.00007704318,0.000079977566,0.00006774133,0.00024462448,0.000051797015,0.00009098336,0.54796195,0.36079437,0.090006866],"study_design_scores_gemma":[0.0015278839,0.00023277113,0.03527518,0.0006760098,0.0001377816,0.0001314761,0.00014271059,0.0018523835,0.00015997149,0.002311799,0.95623285,0.0013192047],"about_ca_topic_score_codex":0.010152433,"about_ca_topic_score_gemma":0.03209396,"teacher_disagreement_score":0.5954385,"about_ca_system_score_codex":0.0011460222,"about_ca_system_score_gemma":0.0030568012,"threshold_uncertainty_score":0.9997958},"labels":[],"label_agreement":null},{"id":"W7036107355","doi":"","title":"Annual report for the town of Hollis, New Hampshire for the year two thousand eighteen. Annual reports of the officers and committees of the town of Hollis, New Hampshire for the year ending December 31, 2018 with reports of the Hollis school district and the Hollis/Brookline cooperative school district.","year":2019,"lang":"en","type":"article","venue":"University of New Hampshire Scholars Repository (University of New Hampshire at Manchester)","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Annual report; Year-ending; Quarter (Canadian coin); Period (music); Work (physics)","score_opus":0.00968199126840471,"score_gpt":0.2100769099380401,"score_spread":0.20039491866963538,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7036107355","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":[0.9541593,0.0029154422,0.02474817,0.00933896,0.0009465748,0.006012749,0.0008927589,0.000065971915,0.0009200335],"genre_scores_gemma":[0.97372293,0.00043719198,0.0046398123,0.0000911231,0.00016584362,0.0000033890433,0.00006689998,0.000047666937,0.020825133],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9955719,0.00046134726,0.0011422052,0.0010678624,0.0012582844,0.00049838016],"domain_scores_gemma":[0.9883116,0.002158968,0.004576632,0.0036221736,0.0010316967,0.00029892105],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0019719847,0.00058145524,0.0011472815,0.00016366653,0.0016849356,0.00013904701,0.0029693726,0.00031934248,0.000031414602],"category_scores_gemma":[0.0010672569,0.00032711137,0.0007941856,0.0011572314,0.0019340775,0.0014223921,0.001680746,0.0007684089,4.6888388e-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":[0.0126087135,0.00090085936,0.59141403,0.0015374891,0.005082813,0.00011620707,0.06143608,0.0089125,0.010209647,0.007075181,0.28656158,0.014144869],"study_design_scores_gemma":[0.013072235,0.0011851972,0.7532941,0.0016871403,0.002834714,0.00073934125,0.038412504,0.0034833795,0.0059892274,0.00043702868,0.17774345,0.0011216691],"about_ca_topic_score_codex":0.0052065714,"about_ca_topic_score_gemma":0.0014308135,"teacher_disagreement_score":0.16188006,"about_ca_system_score_codex":0.0001919823,"about_ca_system_score_gemma":0.0019159041,"threshold_uncertainty_score":0.9999181},"labels":[],"label_agreement":null},{"id":"W7036418816","doi":"","title":"Canada's economic apartheid the social exclusion of racialized groups in the new century","year":2006,"lang":"en","type":"other","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":21,"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":"Social exclusion; Ethnic group; Race (biology); Inequality; Social inequality; Context (archaeology)","score_opus":0.00890109055571035,"score_gpt":0.24292135387025562,"score_spread":0.23402026331454528,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7036418816","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":[0.00006307311,0.00047939524,0.018500518,0.020177675,0.00075928133,0.00042625886,0.000046951835,0.00008917512,0.9594577],"genre_scores_gemma":[0.08247861,0.00041732972,0.0043776687,0.0051762704,0.0038370977,0.00005089202,0.00070083974,0.00026598087,0.9026953],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989916,0.00021818506,0.00020993895,0.00023287168,0.0002035001,0.00014387036],"domain_scores_gemma":[0.9991058,0.00008371354,0.00025623632,0.0005310486,0.0000054331213,0.000017785218],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00031856544,0.00012908026,0.00017173933,0.00006442758,0.000089152425,0.000061012222,0.0013130822,0.000092530216,0.00017974066],"category_scores_gemma":[0.000011975416,0.00007115419,0.000045140383,0.00011480473,0.00003142593,0.00003586678,0.00013984197,0.0001843292,0.000014109081],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000017730891,0.0000090479625,0.00004005396,0.0000055656774,0.000004240826,6.3172234e-7,0.00020540823,0.00000860207,0.0000029175012,0.06004501,0.9251813,0.01449542],"study_design_scores_gemma":[0.00017924557,0.000004662882,0.0023084176,0.000010506089,0.0000040724176,0.0000011125979,0.000034929046,0.0011941922,0.000002580195,0.00029494296,0.9958751,0.00009022719],"about_ca_topic_score_codex":0.86839575,"about_ca_topic_score_gemma":0.9360777,"teacher_disagreement_score":0.082415536,"about_ca_system_score_codex":0.000066874534,"about_ca_system_score_gemma":0.0006542134,"threshold_uncertainty_score":0.29015833},"labels":[],"label_agreement":null},{"id":"W7036863513","doi":"","title":"The Cross-National Determinants of Legislative Party Switching","year":2017,"lang":"en","type":"article","venue":"Civil War Book Review","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Legislature; Legislator; Extant taxon; Incentive; Representation (politics); Order (exchange); Single non-transferable vote; Electoral system","score_opus":0.0438668216032894,"score_gpt":0.3715457766262585,"score_spread":0.32767895502296907,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7036863513","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":[0.0009352997,0.73010665,0.08735258,0.017769817,0.0011743515,0.0011980061,0.000026607673,0.00019606046,0.16124062],"genre_scores_gemma":[0.6282952,0.3429089,0.005541586,0.0062226537,0.0004221644,0.00016295936,0.00002405203,0.0000395534,0.016382948],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989564,0.00010482824,0.00029465693,0.00021950967,0.00029213552,0.00013246461],"domain_scores_gemma":[0.99804175,0.0001672407,0.0005602722,0.0010353499,0.00015769353,0.000037712703],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013102235,0.00008575049,0.00017261783,0.000013998589,0.00074723316,0.00017375339,0.0013824495,0.000023010845,0.00001749639],"category_scores_gemma":[0.0012250271,0.000054202574,0.00007181414,0.000042011317,0.000093978255,0.00070049905,0.00026455754,0.00012224047,0.00007365357],"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":[0.0000038202807,0.000043699336,0.030102678,0.0009535172,0.000025567013,0.0000040666314,0.00034945263,0.000005335338,0.00006166599,0.04674095,0.05180489,0.86990434],"study_design_scores_gemma":[0.00009653948,0.000016080281,0.060391713,0.0010809784,0.000007710975,0.0000070103347,7.568174e-7,0.0072693606,0.00005967242,0.0014516575,0.92952174,0.000096765594],"about_ca_topic_score_codex":0.000012820722,"about_ca_topic_score_gemma":0.000025437203,"teacher_disagreement_score":0.87771684,"about_ca_system_score_codex":0.000016222752,"about_ca_system_score_gemma":0.00009339543,"threshold_uncertainty_score":0.5747189},"labels":[],"label_agreement":null},{"id":"W7037802289","doi":"","title":"Exploring COVID-19 Morbidity and Mortality During the First Three Epidemic Waves in Ontario, Canada: A One Health Perspective to Assessing Risk","year":2023,"lang":"en","type":"dissertation","venue":"The Atrium (University of Guelph)","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Sustenance; Agriculture; Risk factor; Livestock; Pandemic; Regression analysis; Incidence (geometry); Association (psychology); Epidemiology; Public health","score_opus":0.10248072618290031,"score_gpt":0.29722537998100634,"score_spread":0.19474465379810602,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7037802289","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":[0.98203546,0.00013496715,0.00419001,0.012775313,0.00025189656,0.00036451142,0.000030536794,0.00006957691,0.00014773152],"genre_scores_gemma":[0.99869835,0.00023591927,0.00048476056,0.00009328305,0.000032655364,0.0000023908767,0.000058003723,0.000010771348,0.00038383543],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9982945,0.00028734055,0.00021226266,0.0005313017,0.00039898156,0.00027566872],"domain_scores_gemma":[0.99806494,0.0004399735,0.0005006241,0.0007557246,0.000087323584,0.00015140619],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014516286,0.00017866278,0.00034268555,0.00018744111,0.0011482267,0.00006624768,0.0010661681,0.00006402232,0.000009055347],"category_scores_gemma":[0.00039707552,0.0001633769,0.00006317269,0.0005814097,0.000060269445,0.00042485012,0.00033864722,0.00075652427,0.0000033477115],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033884638,0.00016179086,0.64542854,0.0014449767,0.0005298577,0.00011676274,0.31808642,0.011115047,0.000631691,0.012305722,0.0022733558,0.0075669587],"study_design_scores_gemma":[0.00019052465,0.000020899335,0.9734522,0.000092854,0.000033564007,0.0000017487394,0.022546912,0.0026560938,0.0000023538732,0.00055911357,0.00029222207,0.00015149072],"about_ca_topic_score_codex":0.99797285,"about_ca_topic_score_gemma":0.9996759,"teacher_disagreement_score":0.32802364,"about_ca_system_score_codex":0.0019262765,"about_ca_system_score_gemma":0.0020328201,"threshold_uncertainty_score":0.8831347},"labels":[],"label_agreement":null},{"id":"W7037988867","doi":"","title":"Fourier spectral methods for solving the Korteweg-de Vries equation","year":2000,"lang":"en","type":"other","venue":"Library and Archives Canada (Government of Canada)","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Fourier transform; Fourier analysis; Korteweg–de Vries equation; Spectral method; Fourier series; Spectral analysis; Stability (learning theory); Spectrum (functional analysis); Dispersionless equation; Noise (video)","score_opus":0.00792324431021326,"score_gpt":0.20646570740011455,"score_spread":0.19854246308990128,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7037988867","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":[0.000012790388,0.00054930797,0.30320445,0.007715679,0.0002059732,0.00021412091,0.00011289275,0.000035326924,0.6879495],"genre_scores_gemma":[0.007443054,0.0004323389,0.3715526,0.0019682322,0.00036393508,0.000042132306,0.000062652296,0.00012391986,0.6180111],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985677,0.00011993363,0.00018326672,0.00027088914,0.00061711814,0.00024107835],"domain_scores_gemma":[0.9988307,0.0004557613,0.00021400121,0.00039753772,2.3612392e-7,0.00010180373],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00003836654,0.00016642564,0.00018345958,0.000027730743,0.00017321772,0.00007477562,0.0005566109,0.00003880509,0.000059401347],"category_scores_gemma":[0.000009274075,0.0001309128,0.000030943633,0.00006295807,0.000051895473,0.00019065267,0.00009976679,0.00014777295,2.961281e-9],"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":[0.000068827365,0.000016035874,0.0007444516,0.00020181757,0.00010830562,0.0000064754427,0.00020350597,0.000072986295,0.0012553664,0.52331126,0.10971481,0.36429614],"study_design_scores_gemma":[0.000129007,0.000030167335,0.002420279,0.00007622084,0.00001835195,0.0000033770914,0.00012084814,0.0750711,0.0022170164,0.00398734,0.91572976,0.00019650703],"about_ca_topic_score_codex":0.0033257834,"about_ca_topic_score_gemma":0.012881266,"teacher_disagreement_score":0.80601496,"about_ca_system_score_codex":0.000005028649,"about_ca_system_score_gemma":0.0011445828,"threshold_uncertainty_score":0.7188049},"labels":[],"label_agreement":null},{"id":"W7038995052","doi":"","title":"Learning from past stories of success: values, skills, and attitudes as key determinants of first year postsecondary education completion among Nunavimmiut in Montreal","year":2020,"lang":"en","type":"dissertation","venue":"eScholarship@McGill (McGill)","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Cognitive reframing; Graduation (instrument); Indigenous; Feeling; Ethnic group; Educational attainment; Higher education; Study skills; Career Pathways","score_opus":0.00988842510249315,"score_gpt":0.2532488279476179,"score_spread":0.24336040284512472,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7038995052","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":[0.99480003,0.00028204272,0.000005562505,0.00002477903,0.00051627425,0.00035574415,0.00025791195,0.00009458954,0.003663043],"genre_scores_gemma":[0.9945787,0.00033114056,0.0018700082,0.000019963947,0.00004153791,0.00004183312,0.0024815884,0.00005411415,0.00058109127],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99665946,0.00046997404,0.00096004514,0.0009923797,0.0006208246,0.00029729336],"domain_scores_gemma":[0.99725807,0.0003541859,0.0012464745,0.00062318385,0.0003457077,0.00017236579],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005369615,0.00044413796,0.0007603567,0.000388657,0.00039956145,0.00012389547,0.0008794774,0.00039860012,0.000042654287],"category_scores_gemma":[0.0008621533,0.0004961987,0.000118877666,0.00051495223,0.000093874114,0.0012563745,0.00022799993,0.0010316047,0.000026440935],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020382185,0.00086643145,0.7034366,0.0014065064,0.00011967976,0.000020902384,0.0011453907,0.00010234516,0.003564978,0.01564,0.000010848931,0.2734825],"study_design_scores_gemma":[0.00057871785,0.00025846975,0.9878454,0.0011803617,0.00006167778,0.000004413388,0.00071503624,0.0009558139,0.0037335611,0.002773944,0.0013933319,0.0004992778],"about_ca_topic_score_codex":0.013374494,"about_ca_topic_score_gemma":0.02037661,"teacher_disagreement_score":0.28440878,"about_ca_system_score_codex":0.000193582,"about_ca_system_score_gemma":0.00011067737,"threshold_uncertainty_score":0.99974895},"labels":[],"label_agreement":null},{"id":"W7042705905","doi":"","title":"Precision-Based Selection Criteria for Classification with Ensembles of Learners","year":2016,"lang":"en","type":"dissertation","venue":"oURspace (University of Regina)","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"University of Regina","keywords":"Nucleofection; Gestational period; TSG101; Dysgeusia; Diafiltration; Liquation; Durvalumab; Emperipolesis; Triacetin","score_opus":0.018206027131129846,"score_gpt":0.2603312155872899,"score_spread":0.24212518845616005,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7042705905","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":[0.022469757,0.000042042488,0.852244,0.12380567,0.00016395544,0.00035764257,0.000029065131,0.00009623592,0.0007916145],"genre_scores_gemma":[0.49935088,0.00024279258,0.28658023,0.00002488433,0.00011604747,0.0000107786755,0.0017811223,0.00007913455,0.21181414],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99895316,0.00010418991,0.000029982559,0.0004530504,0.00030445532,0.00015514993],"domain_scores_gemma":[0.99798805,0.00019344257,0.0007629556,0.0004924454,0.0005065867,0.000056528675],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028790848,0.00016340624,0.00027578848,0.00035682606,0.00017805769,0.000028261311,0.00059960975,0.000200482,0.0000042480565],"category_scores_gemma":[0.00008461264,0.00015919183,0.00009990761,0.00033708467,0.0000639089,0.00034763897,0.000018596442,0.00012388013,0.0000055750497],"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":[0.0033652498,0.00028005434,0.0034316264,0.002559319,0.00031370885,0.0000056810786,0.0031531898,0.00044733382,0.15289876,0.07151346,0.35142633,0.41060528],"study_design_scores_gemma":[0.0026198681,0.0013811201,0.020048354,0.001539444,0.00024814316,0.000003859081,0.0051059388,0.11331522,0.006249268,0.00013922215,0.84858066,0.00076890603],"about_ca_topic_score_codex":0.000019783934,"about_ca_topic_score_gemma":0.00026217467,"teacher_disagreement_score":0.56566375,"about_ca_system_score_codex":0.000072539864,"about_ca_system_score_gemma":0.00033482828,"threshold_uncertainty_score":0.64916545},"labels":[],"label_agreement":null},{"id":"W7045507979","doi":"","title":"An analysis of semi-supervised learning with the Guelph Cluster Class algorithm","year":2002,"lang":"en","type":"dissertation","venue":"The Atrium (University of Guelph)","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Cluster analysis; Classifier (UML); Remainder; Class (philosophy); Cluster (spacecraft); Statistical classification; Fuzzy clustering; Selection (genetic algorithm)","score_opus":0.011802964667715913,"score_gpt":0.22604844544042724,"score_spread":0.21424548077271133,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7045507979","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":[0.41644827,0.0005406052,0.5679099,0.0056002582,0.00028167077,0.0006752864,0.000093097704,0.0002972987,0.008153589],"genre_scores_gemma":[0.98696464,0.000115910145,0.004680738,0.000045120745,0.000039054252,5.7064494e-7,0.00093637174,0.000015854333,0.007201735],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99802834,0.0005095662,0.00019674613,0.0004689403,0.0005801761,0.00021623778],"domain_scores_gemma":[0.9973172,0.0002358283,0.00071158627,0.0013459016,0.00032185615,0.0000676139],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00066885387,0.00022633134,0.00044965645,0.00042693404,0.00049772137,0.000069467496,0.002487275,0.0001782314,0.0001087878],"category_scores_gemma":[0.000024350487,0.00016175682,0.00025263062,0.0017104544,0.00014077521,0.0004186673,0.0001393079,0.00058516045,0.000019238738],"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":[0.0011263678,0.0010646139,0.011004544,0.00077882246,0.009914106,0.00006427674,0.17696615,0.14129138,0.03957457,0.0100824395,0.009138767,0.59899396],"study_design_scores_gemma":[0.0003549383,0.00017878645,0.17525129,0.000031197917,0.0013965303,0.0000021466794,0.011215302,0.80756545,0.00002945476,0.000018105693,0.00373253,0.00022425468],"about_ca_topic_score_codex":0.0014007519,"about_ca_topic_score_gemma":0.0010386897,"teacher_disagreement_score":0.6662741,"about_ca_system_score_codex":0.00004234838,"about_ca_system_score_gemma":0.000074747615,"threshold_uncertainty_score":0.6596252},"labels":[],"label_agreement":null},{"id":"W7065586234","doi":"","title":"“Es kommt nur naturally”: Language use of sixth grade students in an English-German bilingual program","year":2010,"lang":"en","type":"dissertation","venue":"UWSpace (University of Waterloo)","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Nasalization; Nucleofection; Hyporeflexia; Oscillograph; Dysgeusia; Pretext","score_opus":0.013538409166449128,"score_gpt":0.2829928072456343,"score_spread":0.2694543980791852,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7065586234","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":[0.9988904,0.000035531717,0.000024338491,0.000116378375,0.0003564507,0.00035237704,0.00002885301,0.00016363712,0.000032007058],"genre_scores_gemma":[0.95838726,0.000030628787,0.01491659,0.000009867668,0.000044892666,9.949615e-7,0.0017976499,0.000020180873,0.024791932],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.998387,0.00016804994,0.00018844107,0.00052040396,0.00049324566,0.00024287084],"domain_scores_gemma":[0.9984066,0.000057832858,0.00039666015,0.00080014125,0.0002397774,0.00009901937],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00021643081,0.00022468704,0.0003555493,0.00045222242,0.00009511349,0.00012043186,0.0016259264,0.00030120296,0.000017485923],"category_scores_gemma":[0.00006216251,0.00024195694,0.000097975564,0.00033429026,0.0000696002,0.00096807926,0.00017561646,0.0006892217,0.000007197733],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017088783,0.0014722205,0.026441539,0.0004976861,0.00008284133,0.00009904809,0.88566273,0.000088110624,0.01860422,0.0017189288,0.00017066354,0.064991124],"study_design_scores_gemma":[0.0025239484,0.0012350027,0.7980512,0.0006304574,0.00016291601,0.0000049318446,0.17087512,0.016868627,0.00564249,0.00011341429,0.0025327487,0.0013591386],"about_ca_topic_score_codex":0.0181287,"about_ca_topic_score_gemma":0.0960789,"teacher_disagreement_score":0.77160966,"about_ca_system_score_codex":0.000035896705,"about_ca_system_score_gemma":0.00009981068,"threshold_uncertainty_score":0.98840964},"labels":[],"label_agreement":null},{"id":"W7083549","doi":"10.1007/978-0-387-88843-9_19","title":"Tailoring Classifier Hyperplanes to General Metrics","year":2009,"lang":"en","type":"book-chapter","venue":"","topic":"Machine Learning and Data Classification","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":"Carleton University","funders":"","keywords":"Hyperplane; Mathematical optimization; Integer programming; Mathematics; Linear programming; Classifier (UML); Heuristic; Set (abstract data type); Computer science; Population; Algorithm; Data mining; Artificial intelligence; Combinatorics","score_opus":0.041062740165231794,"score_gpt":0.2660707104686858,"score_spread":0.225007970303454,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7083549","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":[0.000007179407,0.000120060504,0.19153894,0.0020738589,0.0003725928,0.00012345312,0.0000067263477,0.0003436215,0.80541354],"genre_scores_gemma":[0.0005536824,0.0000790811,0.08930285,0.0015190671,0.00041832513,0.000004637065,0.00008447055,0.000023964225,0.90801394],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99826807,0.00001808032,0.0003024811,0.00070086116,0.0004504889,0.0002600263],"domain_scores_gemma":[0.9984276,0.00006928248,0.00013340167,0.0010859558,0.00008853912,0.00019521598],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00023997316,0.00029612574,0.0002826516,0.00052332075,0.000110360794,0.00029061476,0.0011245413,0.0002293199,0.00016734943],"category_scores_gemma":[0.000057844183,0.0002613226,0.00009017328,0.00015176037,0.000014221147,0.00021350148,0.00026275846,0.00039705262,0.0015642877],"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":[0.000001538911,0.0000053423137,0.000018824381,0.000005097773,0.000009007932,0.000009633065,0.000018374269,0.00003521093,0.000029519315,0.626315,0.015773851,0.3577786],"study_design_scores_gemma":[0.000067982655,0.00007460732,0.00043591275,0.000022564667,0.00001077464,0.000017803319,8.237699e-7,0.0066393195,0.000024992118,0.0049402704,0.98739415,0.00037079005],"about_ca_topic_score_codex":0.000025864107,"about_ca_topic_score_gemma":0.000011182547,"teacher_disagreement_score":0.9716203,"about_ca_system_score_codex":0.000077815464,"about_ca_system_score_gemma":0.00006435161,"threshold_uncertainty_score":0.9999839},"labels":[],"label_agreement":null},{"id":"W7097947209","doi":"","title":"LSAC RESEARCH REPORT SERIES � Application of Robust Optimization to Automated Test Assembly","year":2012,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Process (computing); Test (biology); Corporation; Work (physics); Series (stratigraphy); Robustness (evolution)","score_opus":0.057629995531939995,"score_gpt":0.36512645629281537,"score_spread":0.3074964607608754,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7097947209","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":[0.0018406679,0.000012355802,0.9832233,0.0020895707,0.00007113904,0.0002195953,0.0000015359205,0.00056907843,0.011972757],"genre_scores_gemma":[0.65066856,0.0000031305408,0.34813118,0.00003331907,0.000046355766,0.000041622152,0.000064677675,0.0000062590893,0.0010049201],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99872434,0.0001102593,0.0002764326,0.00026260276,0.00039086668,0.00023551389],"domain_scores_gemma":[0.998426,0.00015765756,0.00011810336,0.0008144704,0.0003713925,0.00011233948],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001820103,0.00006911076,0.000093159615,0.00019001993,0.00012290089,0.00008123922,0.000436318,0.000053643682,0.00001790973],"category_scores_gemma":[0.00087112887,0.000061813626,0.000015755004,0.0010367822,0.00002662912,0.00084931427,0.00019017754,0.00010164279,0.00009553387],"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":[0.000031323532,0.0013856995,0.15778878,0.00015825927,0.00003155915,0.0000069932908,0.0021463498,0.34004068,0.060871202,0.30704167,0.051381234,0.07911622],"study_design_scores_gemma":[0.000055524975,0.000064243264,0.056426853,0.000007453642,0.0000020259265,0.000035246016,0.000041952677,0.9297136,0.0039701886,0.000036837355,0.009552026,0.00009406467],"about_ca_topic_score_codex":0.00015880092,"about_ca_topic_score_gemma":0.000011633012,"teacher_disagreement_score":0.64882785,"about_ca_system_score_codex":0.000038836162,"about_ca_system_score_gemma":0.00005112452,"threshold_uncertainty_score":0.25206864},"labels":[],"label_agreement":null},{"id":"W7105742640","doi":"10.6084/m9.figshare.30616401.v1","title":"Additional file 2 of A stomata imaging and segmentation pipeline incorporating generative AI to reduce dependency on manual groundtruthing","year":2025,"lang":"","type":"article","venue":"Figshare","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Agriculture and Agri-Food Canada; University of Saskatchewan; National Research Council Canada","funders":"","keywords":"Pipeline (software); Segmentation; Dependency (UML); Pattern recognition (psychology); Image segmentation","score_opus":0.023447134901508834,"score_gpt":0.3082258847119648,"score_spread":0.284778749810456,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7105742640","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000028123406,0.00008545018,0.007097357,0.00163147,0.0001008137,0.00035261537,0.9881468,0.000067316716,0.0024900746],"genre_scores_gemma":[0.022481324,0.0000011196493,0.028107138,0.0016526852,0.00019646589,0.0005192851,0.9453999,0.000014867329,0.001627229],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997784,0.00024058078,0.00052689004,0.0007827183,0.00042577687,0.00024003646],"domain_scores_gemma":[0.9970767,0.0014803255,0.00048357112,0.0004730949,0.00037203688,0.00011427456],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00013857601,0.00025495014,0.00022821399,0.0003450778,0.0004327868,0.0004918598,0.0005056068,0.0000773984,0.6533554],"category_scores_gemma":[0.0054655443,0.00028269782,0.00004903625,0.0006919454,0.000017869048,0.0009595826,0.000610197,0.00038666514,0.0004832723],"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":[0.000014276508,0.0000479528,0.000005664797,0.00014369084,0.000010714227,0.000005518421,0.00039637726,0.00023681029,0.00016453453,0.00036836235,0.8252908,0.17331532],"study_design_scores_gemma":[0.00047517233,0.00017764598,0.0054689134,0.014474614,0.00001895787,0.00002380832,0.00051692163,0.79567844,0.001207828,0.00079743756,0.18063816,0.0005221274],"about_ca_topic_score_codex":0.000025757105,"about_ca_topic_score_gemma":0.000024656605,"teacher_disagreement_score":0.7954416,"about_ca_system_score_codex":0.00011677882,"about_ca_system_score_gemma":0.0003905039,"threshold_uncertainty_score":0.9999625},"labels":[],"label_agreement":null},{"id":"W7105764655","doi":"10.6084/m9.figshare.30616401","title":"Additional file 2 of A stomata imaging and segmentation pipeline incorporating generative AI to reduce dependency on manual groundtruthing","year":2025,"lang":"","type":"article","venue":"Figshare","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Agriculture and Agri-Food Canada; University of Saskatchewan; National Research Council Canada","funders":"","keywords":"Pipeline (software); Segmentation; Dependency (UML); Pattern recognition (psychology); Image segmentation","score_opus":0.023447134901508834,"score_gpt":0.3082258847119648,"score_spread":0.284778749810456,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7105764655","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000028123406,0.00008545018,0.007097357,0.00163147,0.0001008137,0.00035261537,0.9881468,0.000067316716,0.0024900746],"genre_scores_gemma":[0.022481324,0.0000011196493,0.028107138,0.0016526852,0.00019646589,0.0005192851,0.9453999,0.000014867329,0.001627229],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.997784,0.00024058078,0.00052689004,0.0007827183,0.00042577687,0.00024003646],"domain_scores_gemma":[0.9970767,0.0014803255,0.00048357112,0.0004730949,0.00037203688,0.00011427456],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00013857601,0.00025495014,0.00022821399,0.0003450778,0.0004327868,0.0004918598,0.0005056068,0.0000773984,0.6533554],"category_scores_gemma":[0.0054655443,0.00028269782,0.00004903625,0.0006919454,0.000017869048,0.0009595826,0.000610197,0.00038666514,0.0004832723],"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":[0.000014276508,0.0000479528,0.000005664797,0.00014369084,0.000010714227,0.000005518421,0.00039637726,0.00023681029,0.00016453453,0.00036836235,0.8252908,0.17331532],"study_design_scores_gemma":[0.00047517233,0.00017764598,0.0054689134,0.014474614,0.00001895787,0.00002380832,0.00051692163,0.79567844,0.001207828,0.00079743756,0.18063816,0.0005221274],"about_ca_topic_score_codex":0.000025757105,"about_ca_topic_score_gemma":0.000024656605,"teacher_disagreement_score":0.7954416,"about_ca_system_score_codex":0.00011677882,"about_ca_system_score_gemma":0.0003905039,"threshold_uncertainty_score":0.9999625},"labels":[],"label_agreement":null},{"id":"W7117109126","doi":"10.1109/tpami.2025.3647921","title":"Robust Semi-Supervised Feature Selection With Multi-Granularity Zentropy Modeling","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Pattern Analysis and Machine Intelligence","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Regina","funders":"National Natural Science Foundation of China","keywords":"Robustness (evolution); Feature selection; Granularity; Pattern recognition (psychology); Data modeling; Feature learning; Feature (linguistics); Fuzzy logic","score_opus":0.027491252161963645,"score_gpt":0.26695073047756707,"score_spread":0.23945947831560344,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7117109126","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":[0.0020816117,0.000104403,0.9960403,0.0012784088,0.000096287535,0.0001420486,0.000021987207,0.0001810172,0.000053964966],"genre_scores_gemma":[0.97848004,0.00019691023,0.020303924,0.0003843595,0.0000116841575,0.00002452317,0.000028389795,0.000009048137,0.0005611283],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984134,0.00013682587,0.00026959772,0.000707375,0.00024153903,0.00023129454],"domain_scores_gemma":[0.9990941,0.0000661095,0.000078292265,0.0005352786,0.0001309836,0.000095203344],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00024981104,0.00024451307,0.000290615,0.000629538,0.00041971146,0.00026045457,0.0004107147,0.00009928145,0.000028317714],"category_scores_gemma":[0.0000061360342,0.0001972287,0.00015108939,0.0018775075,0.000037867634,0.0002996551,0.000006678715,0.0005303764,0.000008713142],"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":[0.000028582836,0.00016311792,0.004208182,0.000028702196,0.0004099094,0.0000026217563,0.0001496329,0.6252553,0.0005363183,0.00020842823,0.000008311764,0.3690009],"study_design_scores_gemma":[0.00017689155,0.00006336941,0.0010231878,0.000030864197,0.00037977815,0.0000059428767,0.000030911066,0.9858141,0.012170707,0.00003944262,0.000063371284,0.00020141914],"about_ca_topic_score_codex":0.001843043,"about_ca_topic_score_gemma":0.0026712373,"teacher_disagreement_score":0.9763984,"about_ca_system_score_codex":0.000044128476,"about_ca_system_score_gemma":0.00003670377,"threshold_uncertainty_score":0.80427533},"labels":[],"label_agreement":null},{"id":"W7117851814","doi":"","title":"Galaxy Zoo Evo: 1 million human-annotated images of galaxies","year":2025,"lang":"","type":"article","venue":"ArXiv.org","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Alliance de recherche numérique du Canada; University of Toronto; Alfred P. Sloan Foundation; National Science Foundation","keywords":"Galaxy; Space (punctuation); Benchmark (surveying); Image (mathematics); Domain (mathematical analysis); Spiral galaxy","score_opus":0.03054621689064294,"score_gpt":0.30790744481617527,"score_spread":0.2773612279255323,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7117851814","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":[0.9353198,0.0028273652,0.04350795,0.0056001246,0.0014935943,0.00044171946,0.00003363305,0.0003098033,0.010466002],"genre_scores_gemma":[0.98238605,0.00041138698,0.001433451,0.00012647742,0.00011166733,0.000020346472,0.000097176824,0.000022330269,0.015391101],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9964343,0.00045412066,0.0010159825,0.001064563,0.00046866818,0.000562423],"domain_scores_gemma":[0.9966696,0.00024456315,0.00060561416,0.0018576097,0.00049379043,0.00012880427],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008649856,0.00042007433,0.0005503956,0.0005252574,0.0005489536,0.00022634889,0.0015707696,0.00022360162,0.00022564524],"category_scores_gemma":[0.0005372527,0.0004219829,0.00020452707,0.0017764254,0.00038264136,0.00075532764,0.0006710716,0.0005986797,0.00034649434],"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":[0.000030316374,0.00023461271,0.93639517,0.00026452955,0.000098126955,0.0000075327234,0.00064696564,0.00007087152,0.032753795,0.007268164,0.00636449,0.015865434],"study_design_scores_gemma":[0.0006304445,0.00019107752,0.96139085,0.00035542497,0.00007597114,0.0000036195333,0.000086241904,0.009359885,0.019405965,0.00052382646,0.0076222927,0.00035438724],"about_ca_topic_score_codex":0.000524641,"about_ca_topic_score_gemma":0.000027358969,"teacher_disagreement_score":0.047066256,"about_ca_system_score_codex":0.00008593637,"about_ca_system_score_gemma":0.00024456167,"threshold_uncertainty_score":0.9998232},"labels":[],"label_agreement":null},{"id":"W7118317836","doi":"10.15680/ijirset.2025.1412113","title":"The Symbiotic Evolution: Modern AI Algorithms and the Paradigm Shift to DataCentric Technologies","year":2025,"lang":"","type":"article","venue":"International Journal of Innovative Research in Science Engineering and Technology","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Paradigm shift; Synthetic data; Trustworthiness; Architecture; Artificial neural network; Transformer; Data modeling; Data management","score_opus":0.022967014014019356,"score_gpt":0.368340244275527,"score_spread":0.3453732302615076,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7118317836","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":[0.024750764,0.0070462683,0.57272,0.39400306,0.0010555934,0.00029325686,0.0000048800603,0.000049573086,0.00007663567],"genre_scores_gemma":[0.99602723,0.0014823077,0.0023327004,0.000058626058,0.000047323127,0.00001873138,3.693876e-7,0.000004513913,0.000028189132],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.996926,0.0001575002,0.0006952561,0.00047416412,0.0011733111,0.00057375594],"domain_scores_gemma":[0.99604523,0.0012687151,0.00022362384,0.00055911165,0.0018456262,0.000057687557],"candidate_categories":["metaresearch","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.010780199,0.00016432679,0.00024953563,0.005186501,0.00061528344,0.0010810795,0.0044109197,0.00013254528,4.0894366e-7],"category_scores_gemma":[0.008999988,0.000101297635,0.000020728472,0.01367825,0.0038503304,0.00074570626,0.0024571402,0.0021168126,0.0000017996138],"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":[0.000042605392,0.000026387897,0.002851782,0.000007711579,0.000036378762,0.000018449113,0.0002420022,0.0006535127,0.00038448712,0.7663586,0.000053831936,0.22932425],"study_design_scores_gemma":[0.0016457968,0.00029791787,0.023049485,0.00083477754,0.0000047327385,0.00029400323,0.0012097276,0.68148524,0.0011115754,0.28095016,0.0088982,0.00021837211],"about_ca_topic_score_codex":0.00003714378,"about_ca_topic_score_gemma":0.0000065963886,"teacher_disagreement_score":0.97127646,"about_ca_system_score_codex":0.00043277946,"about_ca_system_score_gemma":0.0008862563,"threshold_uncertainty_score":0.9999559},"labels":[],"label_agreement":null},{"id":"W7125000707","doi":"10.26615/978-954-452-098-4-142","title":"Demographic Features for Annotation-Aware Classification","year":2025,"lang":"","type":"article","venue":"International conference Recent advances in natural language processing","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Population; Identification (biology); Feature (linguistics); Set (abstract data type); Field (mathematics)","score_opus":0.02015870596706755,"score_gpt":0.362967026904323,"score_spread":0.34280832093725544,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7125000707","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":[0.001242715,0.2178216,0.74530536,0.01856895,0.00519574,0.0009934198,0.00009521692,0.00022507309,0.010551945],"genre_scores_gemma":[0.9670709,0.01670237,0.012839922,0.0004965354,0.00022165109,0.00016324525,0.0007180144,0.000016991793,0.0017704084],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99690324,0.0001689391,0.00080155145,0.0010844449,0.0005643107,0.0004775199],"domain_scores_gemma":[0.9972307,0.0003114445,0.0006290558,0.00042710267,0.0013297535,0.000071925366],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0006015815,0.00038728802,0.0003399871,0.0009143434,0.0003426043,0.001055487,0.0016399166,0.00021041349,0.000052537966],"category_scores_gemma":[0.0010871798,0.00038005516,0.00011046989,0.0014991731,0.00016181952,0.0028563053,0.00019989179,0.00079635164,0.0000066256125],"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":[0.00014346368,0.00010646809,0.0026706755,0.0003090787,0.000023829654,0.0000034842976,0.0010577159,0.00014359833,0.00069750234,0.04634678,0.00009749264,0.9483999],"study_design_scores_gemma":[0.001133085,0.00004298421,0.01690664,0.0016240292,0.000029178182,0.000008660609,0.0018602526,0.91264653,0.00035897893,0.0056307768,0.05926438,0.00049448665],"about_ca_topic_score_codex":0.00002430387,"about_ca_topic_score_gemma":0.00035658124,"teacher_disagreement_score":0.9658281,"about_ca_system_score_codex":0.00030229465,"about_ca_system_score_gemma":0.0004644072,"threshold_uncertainty_score":0.9999815},"labels":[],"label_agreement":null},{"id":"W7125644085","doi":"10.1109/cascon66301.2025.00039","title":"Adaptive Fine-Tuning for Multiclass Classification Over Software Requirement Data","year":2025,"lang":"","type":"article","venue":"","topic":"Machine Learning and Data Classification","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":"Toronto Metropolitan University","funders":"","keywords":"Software; Class (philosophy); Feature (linguistics); Key (lock); Software requirements","score_opus":0.13471098321509112,"score_gpt":0.3685924803664949,"score_spread":0.23388149715140377,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7125644085","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":[0.00014980392,0.0005184748,0.9818582,0.009804266,0.0015464607,0.0012533099,0.0002985183,0.00035922157,0.004211759],"genre_scores_gemma":[0.52348554,0.000111048445,0.4540913,0.0012372212,0.0002946135,0.0001897392,0.0020089657,0.00003917475,0.018542407],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9952853,0.00032107922,0.0009963113,0.0021733346,0.00054966967,0.0006743277],"domain_scores_gemma":[0.99295795,0.0010464224,0.00053775957,0.0048120324,0.00047534317,0.00017051678],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0019537006,0.0004479167,0.00041522802,0.00035377283,0.0008162756,0.0008086838,0.0037216507,0.0002544692,0.000075542135],"category_scores_gemma":[0.0021456114,0.00044392707,0.00012007577,0.0010030108,0.00015483773,0.0019538566,0.002081802,0.00043456056,0.0000731588],"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":[0.00012235677,0.00032552815,0.0027544575,0.00019853898,0.00014755374,0.0000012554576,0.0003155042,0.0002511899,0.0013018061,0.20831144,0.05351372,0.7327566],"study_design_scores_gemma":[0.0011970561,0.00014039208,0.017436478,0.00023177084,0.00010964025,9.119299e-7,0.00017547056,0.85390604,0.00011551581,0.0012369575,0.1250583,0.00039146087],"about_ca_topic_score_codex":0.00023952014,"about_ca_topic_score_gemma":0.00025730216,"teacher_disagreement_score":0.85365486,"about_ca_system_score_codex":0.0002900792,"about_ca_system_score_gemma":0.0006975477,"threshold_uncertainty_score":0.9998013},"labels":[],"label_agreement":null},{"id":"W7131097258","doi":"10.1109/iccvw69036.2025.00708","title":"Task-Specific Generative Dataset Distillation with Difficulty-Guided Sampling","year":2025,"lang":"","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Preprocessor; Task (project management); Distillation; Matching (statistics); Sampling (signal processing); Transformation (genetics); Downstream (manufacturing); Focus (optics)","score_opus":0.048029801339141635,"score_gpt":0.319385498422392,"score_spread":0.27135569708325036,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7131097258","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":[0.0021505256,0.0004240073,0.98307115,0.005651094,0.0005780986,0.00044459602,0.00087981805,0.00018858588,0.00661212],"genre_scores_gemma":[0.8100345,0.00035631994,0.16512042,0.0012140488,0.00032779845,0.00004664216,0.017312376,0.00002701474,0.005560845],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9966908,0.00031487594,0.00065883016,0.001391804,0.00048072144,0.00046293178],"domain_scores_gemma":[0.9972634,0.00022433697,0.00032197058,0.0017823554,0.00025668452,0.00015129846],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00050909526,0.0004176003,0.00035400238,0.0002648402,0.0008148275,0.0012941301,0.0010014297,0.00013740316,0.00017423987],"category_scores_gemma":[0.000121974015,0.00032425637,0.000055470515,0.001352641,0.00016901537,0.0008296205,0.00044280925,0.0004268094,0.00021046106],"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":[0.00011052163,0.0003756535,0.0039287303,0.00011553141,0.00016782945,0.000011559166,0.0010835748,0.014052778,0.0038721766,0.5302452,0.2366083,0.20942819],"study_design_scores_gemma":[0.0008473718,0.000110955305,0.03665388,0.00013844871,0.000045245684,0.0000119544575,0.00011036284,0.4859015,0.00041724058,0.00033488657,0.47493997,0.00048818826],"about_ca_topic_score_codex":0.00016940663,"about_ca_topic_score_gemma":0.000096638454,"teacher_disagreement_score":0.8179507,"about_ca_system_score_codex":0.00015221968,"about_ca_system_score_gemma":0.00023472596,"threshold_uncertainty_score":0.99992096},"labels":[],"label_agreement":null},{"id":"W7132070262","doi":"","title":"Sıralama ve arama algoritmalarının geliştirilmesi","year":2017,"lang":"en","type":"dissertation","venue":"AYBU AVESIS","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Institute of Steel Construction","keywords":"Headline; Context (archaeology); Sorting","score_opus":0.014238357527646541,"score_gpt":0.289551204436753,"score_spread":0.27531284690910646,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7132070262","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":[0.041065507,0.0045191892,0.047909465,0.008068572,0.014327833,0.0016066612,0.00015752813,0.0024794785,0.87986577],"genre_scores_gemma":[0.40213037,0.0015205329,0.061420955,0.00082278997,0.0020690379,0.00030605495,0.010559771,0.00023448898,0.520936],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99768186,0.00011137067,0.00038969287,0.0008926794,0.0005161144,0.00040827246],"domain_scores_gemma":[0.9964748,0.00010362235,0.0006558393,0.0024312048,0.00018077962,0.00015373166],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00038365356,0.00038572645,0.0004024726,0.00024532992,0.00054127484,0.000915479,0.0025374147,0.00042333786,0.00011072078],"category_scores_gemma":[0.00026707634,0.00037793024,0.0001925406,0.00017206259,0.000033867913,0.0006990607,0.000104581195,0.000555428,0.001279655],"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":[0.000017499302,0.00007336405,0.00033358444,0.00015540182,0.00007823075,0.00003491906,0.0011887839,0.000004195267,0.0005350471,0.017593306,0.023806479,0.9561792],"study_design_scores_gemma":[0.00077827106,0.00017669304,0.26512885,0.00048174686,0.0001671546,0.00003248442,0.00029437238,0.015377022,0.0050048027,0.004219482,0.706521,0.001818166],"about_ca_topic_score_codex":0.0001914551,"about_ca_topic_score_gemma":0.00007019691,"teacher_disagreement_score":0.954361,"about_ca_system_score_codex":0.00005975809,"about_ca_system_score_gemma":0.00022008498,"threshold_uncertainty_score":0.99986726},"labels":[],"label_agreement":null},{"id":"W7132904433","doi":"","title":"Reconciling with Noise in Machine Learning for Healthcare","year":2025,"lang":"","type":"dissertation","venue":"TSpace","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Institutes of Health Research; Hospital for Sick Children","keywords":"Noise (video); SAFER; Reliability (semiconductor); Harm; Health care; Key (lock)","score_opus":0.03895756000869239,"score_gpt":0.3589666005046334,"score_spread":0.32000904049594103,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7132904433","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":[0.1376659,0.011898023,0.79598564,0.031929135,0.0031732416,0.0053396057,0.00007508592,0.00079614157,0.013137205],"genre_scores_gemma":[0.8590362,0.0011208972,0.03810753,0.0004231143,0.00023761374,0.0005237267,0.0058087017,0.000101191654,0.09464099],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9962694,0.00044358143,0.0007002122,0.0014721623,0.00043009073,0.00068453857],"domain_scores_gemma":[0.99707144,0.0006534031,0.0007600038,0.00089410204,0.00045128935,0.00016972871],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0012599721,0.0005573047,0.00069819164,0.00063999626,0.00056510355,0.00035156135,0.0009272604,0.00040516647,0.000032309978],"category_scores_gemma":[0.00083554396,0.00055418874,0.00012498134,0.0012260115,0.000029673534,0.00032074627,0.00010011509,0.0016777414,0.000024856734],"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":[0.0021794662,0.00035479845,0.04979617,0.007970163,0.00014283648,0.00003674711,0.06682322,0.035517715,0.00087169674,0.019582544,0.00029979742,0.81642485],"study_design_scores_gemma":[0.0018873992,0.00077482424,0.012496965,0.0028136596,0.00006474144,0.0000079258725,0.004886821,0.9399183,0.00032639582,0.00017502996,0.035768904,0.00087908236],"about_ca_topic_score_codex":0.0057622776,"about_ca_topic_score_gemma":0.012216495,"teacher_disagreement_score":0.9044005,"about_ca_system_score_codex":0.00027548175,"about_ca_system_score_gemma":0.0012192272,"threshold_uncertainty_score":0.99969095},"labels":[],"label_agreement":null},{"id":"W7134163353","doi":"10.1109/bigdata66926.2025.11400965","title":"Enhancing Interpretability in Self-Training with Tsetlin Machines for Mitigating Noisy Pseudo-Labels","year":2025,"lang":"","type":"article","venue":"","topic":"Machine Learning and Data Classification","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 Toronto","funders":"","keywords":"Interpretability; Noisy data; Feature (linguistics); Noise (video); Pattern recognition (psychology)","score_opus":0.0142521620139618,"score_gpt":0.2914397057257438,"score_spread":0.277187543711782,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7134163353","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":[0.14636256,0.00019404224,0.8405792,0.0042439452,0.0005483213,0.0009925548,0.000017234775,0.00034827323,0.006713861],"genre_scores_gemma":[0.71079266,0.000009158415,0.28776944,0.00055710936,0.00006809081,0.00013008871,0.000025904425,0.000019611041,0.0006279438],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9955492,0.0004682396,0.0012236416,0.0015823602,0.00034110365,0.00083544315],"domain_scores_gemma":[0.9962745,0.0016527876,0.0004008104,0.0012501635,0.00027346352,0.00014830068],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0032274693,0.0004964468,0.0006524607,0.00043314396,0.00046878643,0.0006986479,0.0012217104,0.00020464888,0.00004518554],"category_scores_gemma":[0.0014315981,0.00043673036,0.00013122702,0.0014973612,0.0001249492,0.0009787189,0.00047684027,0.000747725,0.000013019145],"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":[0.00025628533,0.0007481748,0.12760326,0.0022058045,0.00021643967,0.000009374025,0.031158544,0.0013962622,0.011253326,0.1135732,0.0001660656,0.71141326],"study_design_scores_gemma":[0.001434714,0.00027411888,0.015524091,0.0012211383,0.000052308253,0.000008317062,0.00095455424,0.9732911,0.0028917126,0.0030932121,0.00074219896,0.0005125193],"about_ca_topic_score_codex":0.00054735085,"about_ca_topic_score_gemma":0.0024271822,"teacher_disagreement_score":0.97189486,"about_ca_system_score_codex":0.00023465087,"about_ca_system_score_gemma":0.0007635626,"threshold_uncertainty_score":0.99980843},"labels":[],"label_agreement":null},{"id":"W7155029760","doi":"10.1109/synasc69064.2025.00066","title":"Applied Metaheuristic Hyperparameter Tuning: Machine Learning in Internet of Things Cybersecurity","year":2025,"lang":"","type":"article","venue":"","topic":"Machine Learning and Data Classification","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":"Artificial Intelligence in Medicine (Canada)","funders":"European Commission","keywords":"Hyperparameter; Internet of Things; Key (lock); Metaheuristic; The Internet","score_opus":0.015831369355332865,"score_gpt":0.2568685905176738,"score_spread":0.24103722116234094,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7155029760","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":[0.021727707,0.0009651883,0.8550506,0.0018358513,0.0005611474,0.0004220811,0.0000027665412,0.00021427435,0.11922035],"genre_scores_gemma":[0.96248704,0.00010226109,0.028093992,0.0005846032,0.00001594585,0.000019075345,0.00004713284,0.000017353275,0.008632581],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9961258,0.00058149354,0.0012112007,0.0011093805,0.00045045157,0.0005216762],"domain_scores_gemma":[0.99743414,0.0007397545,0.0005228217,0.0010617978,0.00012636735,0.000115133735],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0021008085,0.00041832586,0.00076054886,0.00086559705,0.00012047162,0.00029139343,0.001605451,0.00023541371,0.00027337435],"category_scores_gemma":[0.0010322989,0.00040329475,0.00015723711,0.0016838183,0.00021092182,0.00055404624,0.0011032085,0.0015230719,0.00008958304],"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":[0.00018315951,0.00070062355,0.04359143,0.00054451573,0.0001901018,0.000015417787,0.008669352,0.00091146864,0.0025856595,0.5671094,0.0006140324,0.37488484],"study_design_scores_gemma":[0.00091021054,0.000112769114,0.0101616485,0.00022327708,0.00006991597,0.0000043865152,0.00014068828,0.9716647,0.0010546534,0.0027059028,0.012594006,0.0003578102],"about_ca_topic_score_codex":0.0031242743,"about_ca_topic_score_gemma":0.00007841633,"teacher_disagreement_score":0.97075325,"about_ca_system_score_codex":0.00010966938,"about_ca_system_score_gemma":0.00021687386,"threshold_uncertainty_score":0.99984187},"labels":[],"label_agreement":null},{"id":"W7160063519","doi":"10.1109/iccv51701.2025.01881","title":"S <sup>4</sup> M: Boosting Semi-Supervised Instance Segmentation with SAM","year":2025,"lang":"","type":"article","venue":"","topic":"Machine Learning and Data Classification","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":"Kootenay Association for Science & Technology","funders":"Korea Creative Content Agency; National Research Foundation of Korea; Ministry of Culture, Sports and Tourism","keywords":"Boosting (machine learning); Segmentation; Pattern recognition (psychology); Image segmentation; Classifier (UML)","score_opus":0.015367091025701737,"score_gpt":0.26414223677004467,"score_spread":0.24877514574434292,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7160063519","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":[0.026275514,0.00043091684,0.898474,0.0062078144,0.00024501965,0.00051385903,0.00001096679,0.00036483185,0.06747713],"genre_scores_gemma":[0.8911974,0.00014161064,0.09109824,0.002192745,0.00010146144,0.000046553057,0.00010508671,0.000021598513,0.015095337],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9966803,0.00032969404,0.0006551711,0.0011916698,0.00058052567,0.00056261045],"domain_scores_gemma":[0.997708,0.000311566,0.00025986598,0.0012849888,0.00028040752,0.00015512716],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00073377084,0.0004010354,0.00033427172,0.00030242407,0.00070903136,0.00094113045,0.0010656547,0.00014834407,0.00021277969],"category_scores_gemma":[0.0002369645,0.0003537343,0.00006927647,0.0018979405,0.00012822762,0.0014607778,0.00035331547,0.0005225126,0.00016902432],"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":[0.00011958062,0.00026102367,0.03343783,0.0003440907,0.00011636387,0.000013563279,0.004022247,0.024295848,0.001333703,0.06927687,0.004478948,0.8622999],"study_design_scores_gemma":[0.0012809527,0.00017619533,0.009066089,0.00045682405,0.00005485422,0.000009467336,0.0010316685,0.97404426,0.0010794033,0.00028565578,0.0120975245,0.00041711354],"about_ca_topic_score_codex":0.00026981797,"about_ca_topic_score_gemma":0.000059192265,"teacher_disagreement_score":0.9497484,"about_ca_system_score_codex":0.00018599881,"about_ca_system_score_gemma":0.0005096649,"threshold_uncertainty_score":0.99989146},"labels":[],"label_agreement":null},{"id":"W7160169153","doi":"10.1109/iccv51701.2025.00048","title":"Multimodal Large Language Model-Guided ISP Hyperparameter Optimization with Dynamic Preference Learning","year":2025,"lang":"","type":"article","venue":"","topic":"Machine Learning and Data Classification","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":"Artificial Intelligence in Medicine (Canada)","funders":"Natural Science Foundation of Beijing Municipality; National Natural Science Foundation of China","keywords":"Preference; Hyperparameter; Preference learning; Statistical learning; Deep learning","score_opus":0.017465603211785988,"score_gpt":0.28407591647502756,"score_spread":0.2666103132632416,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7160169153","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":[0.016251372,0.00020352138,0.963892,0.0016143708,0.00018392528,0.0004484674,0.000015063849,0.00044453357,0.016946774],"genre_scores_gemma":[0.7113038,0.00006958688,0.26464716,0.00038278277,0.000014111642,0.000030386725,0.00016655635,0.000020779768,0.023364868],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99667543,0.00039656876,0.00055838726,0.0012459955,0.000467061,0.00065656606],"domain_scores_gemma":[0.997887,0.0001663017,0.00028966495,0.0012419692,0.00027296456,0.00014209635],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006781747,0.00043085116,0.00037854392,0.0003650806,0.0005689593,0.00073638605,0.0010641172,0.00022797115,0.00022100972],"category_scores_gemma":[0.0003181749,0.0003664521,0.00008378408,0.0010647186,0.00008950047,0.0010184698,0.00052501116,0.0008426483,0.00009352996],"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":[0.00004706566,0.0001888712,0.0022482278,0.00008000154,0.000048524005,0.0000043213026,0.001413362,0.94767034,0.00027712886,0.010087644,0.00015286752,0.037781626],"study_design_scores_gemma":[0.0012128263,0.00013673547,0.0017645757,0.00017185697,0.00006162264,0.0000075785397,0.00024164113,0.99538094,0.00011268372,0.00006526583,0.0004093671,0.00043490287],"about_ca_topic_score_codex":0.00019802856,"about_ca_topic_score_gemma":0.000094866766,"teacher_disagreement_score":0.6992448,"about_ca_system_score_codex":0.00014072996,"about_ca_system_score_gemma":0.00038617392,"threshold_uncertainty_score":0.99987876},"labels":[],"label_agreement":null},{"id":"W97673500","doi":"","title":"CISpace: tools for learning computational intelligence","year":2001,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Artificial intelligence","score_opus":0.05222639351257195,"score_gpt":0.31919620570829704,"score_spread":0.2669698121957251,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W97673500","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":[0.0007762358,0.000019684278,0.98553133,0.003481576,0.00008794435,0.000095308074,5.981909e-7,0.00024670357,0.009760619],"genre_scores_gemma":[0.6667299,0.0000130727685,0.32919717,0.0003161551,0.000052296302,0.000018632436,0.000047337675,0.000004508546,0.003620864],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993274,0.0000353707,0.0001261052,0.00023810253,0.00013239968,0.00014059825],"domain_scores_gemma":[0.99919873,0.00043140384,0.000052608793,0.00018918948,0.00008232032,0.000045715093],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00028078735,0.00006292624,0.000062477804,0.000053838397,0.00015454594,0.00028677244,0.00037233453,0.00002670315,0.00005117247],"category_scores_gemma":[0.00033541318,0.00005669705,0.000031122298,0.0002032153,0.000014599671,0.0005494339,0.00006750197,0.000096038064,0.00012876044],"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":[0.0000035783467,0.0000122345755,0.0013775611,0.0000036949368,0.000003174877,7.4087717e-7,0.00010695401,0.0312433,0.000034284814,0.43716633,0.0009023155,0.52914584],"study_design_scores_gemma":[0.00006670326,0.00004857263,0.0032107122,0.00000353233,0.0000010780816,0.000011477489,0.00004162477,0.8564102,0.000055899884,0.009801943,0.13026272,0.000085513544],"about_ca_topic_score_codex":0.000010475524,"about_ca_topic_score_gemma":0.0000031490601,"teacher_disagreement_score":0.82516694,"about_ca_system_score_codex":0.000014645651,"about_ca_system_score_gemma":0.000028548893,"threshold_uncertainty_score":0.27653533},"labels":[],"label_agreement":null}]}