{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":374,"total_is_capped":false,"direct_labels_cover":2,"predictions_cover":374,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"query_hash":"3de55248b53f","filters":{"topic":"Text and Document Classification Technologies"}},"results":[{"id":"W2170505850","doi":"10.1016/j.ipm.2009.03.002","title":"A systematic analysis of performance measures for classification tasks","year":2009,"lang":"en","type":"article","venue":"Information Processing & Management","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":6477,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Computer Research Institute of Montréal; Université de Montréal; Children's Hospital of Eastern Ontario","funders":"McGill University","keywords":"Confusion matrix; Confusion; Computer science; Artificial intelligence; Classifier (UML); Measure (data warehouse); Binary classification; Machine learning; Binary number; Natural language processing; Set (abstract data type); Class (philosophy); Data mining; Pattern recognition (psychology); Mathematics; Support vector machine; Arithmetic","retraction":null,"screen_n_in":null,"score":{"opus":0.02272805573408605,"gpt":0.2683619694755179,"spread":0.2456339137414319,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005199111,0.0001059729,0.0002267584,0.00090179,0.0001382695,0.000278447,0.0006544032,0.0000446479,0.000001574917],"category_scores_gemma":[0.00005272912,0.00009086225,0.00008432471,0.001556263,0.00002355796,0.002518761,0.00004344318,0.00003703653,0.000009626126],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006142181,"about_ca_system_score_gemma":0.00002069184,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":4.345231e-7,"about_ca_topic_score_gemma":2.244121e-7,"domain_scores_codex":[0.9986649,0.00001372859,0.0006673835,0.0001404787,0.0003664799,0.0001470203],"domain_scores_gemma":[0.9986134,0.00002567492,0.0006158617,0.0004597011,0.0002630583,0.00002225739],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000007650897,0.00004420116,0.00005411914,0.003947658,0.0001726364,4.809408e-8,0.0008975135,0.000870404,0.00006555935,0.2056251,0.0001892062,0.7881259],"study_design_scores_gemma":[0.0004045221,0.00009616658,0.02155467,0.0007110161,0.0005237047,6.181966e-7,0.0008964241,0.966887,0.001240324,0.003864699,0.003575963,0.0002449008],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001074945,0.00007709054,0.9930567,0.0007474971,0.0000471955,0.0006256838,0.000001587601,0.0003392645,0.004030053],"genre_scores_gemma":[0.9708304,0.00003119811,0.02864741,0.0001895291,0.000003095157,0.0001674918,0.00002337171,0.000001756143,0.0001057534],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9697555,"threshold_uncertainty_score":0.3705255,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2148972377","doi":"10.1145/1571941.1572114","title":"Reciprocal rank fusion outperforms condorcet and individual rank learning methods","year":2009,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":568,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Reciprocal; Condorcet method; Rank (graph theory); Computer science; Simple (philosophy); Mean reciprocal rank; Fusion; Fuse (electrical); Artificial intelligence; Learning to rank; Machine learning; Mathematics; Ranking (information retrieval); Combinatorics; Engineering; Voting","retraction":null,"screen_n_in":null,"score":{"opus":0.04029236246797672,"gpt":0.3261430280054581,"spread":0.2858506655374814,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007501042,0.0001244288,0.0001601067,0.0001474123,0.0002060639,0.00026078,0.0005565053,0.000111847,0.00003670608],"category_scores_gemma":[0.0001629367,0.00009088519,0.00003352474,0.0002948893,0.00006488518,0.0005816484,0.0002359593,0.0002409107,0.00003097756],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001452276,"about_ca_system_score_gemma":0.00002014796,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003976441,"about_ca_topic_score_gemma":5.527925e-7,"domain_scores_codex":[0.9989361,0.00008060106,0.0002097054,0.0003460079,0.0002042915,0.0002232618],"domain_scores_gemma":[0.9993972,0.0001181975,0.00007602625,0.0003118026,0.00003660022,0.00006024426],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000005739527,0.00001702684,0.0007480193,0.000002022571,0.000004699802,0.000001004627,0.0003668522,0.000004846911,0.00296929,0.07665597,0.0006408013,0.9185838],"study_design_scores_gemma":[0.00714894,0.002926986,0.1681686,0.00008221654,0.00006198471,0.0001422785,0.003148523,0.1444578,0.2467341,0.1920366,0.2329379,0.002154037],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04832601,0.0002566224,0.9379131,0.005465303,0.0001164271,0.0001640124,2.252233e-7,0.001773828,0.005984518],"genre_scores_gemma":[0.7153832,0.00008497421,0.2828057,0.0004910077,0.00001685561,0.000006820275,0.000002210812,0.000004317411,0.001204839],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9164297,"threshold_uncertainty_score":0.3706191,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4211256381","doi":"10.1109/access.2022.3151048","title":"MLCM: Multi-Label Confusion Matrix","year":2022,"lang":"en","type":"article","venue":"IEEE Access","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":409,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Toronto Metropolitan University; Vector Institute; McMaster University","funders":"Ministère de la Défense Nationale","keywords":"Computer science; Confusion; Confusion matrix; Artificial intelligence; Classifier (UML); Class (philosophy); Ambiguity; Machine learning; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.08270770067299012,"gpt":0.3675705466220109,"spread":0.2848628459490208,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001567223,0.00008557954,0.00009010234,0.0001439854,0.0003451537,0.0002836933,0.002573919,0.00003113496,0.0002112564],"category_scores_gemma":[0.00001759905,0.00008223268,0.00002815927,0.0005314158,0.00003398956,0.0007091648,0.001087602,0.0001613538,0.00008706904],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005396647,"about_ca_system_score_gemma":0.00003945224,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003165556,"about_ca_topic_score_gemma":0.000002688922,"domain_scores_codex":[0.9990472,0.00004016093,0.000157127,0.0003000307,0.0002721448,0.0001833503],"domain_scores_gemma":[0.9992073,0.00003875991,0.0001002456,0.0005852787,0.00003546053,0.00003293775],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001919852,0.0007608294,0.005156224,0.00002733722,0.0000301497,0.00005734683,0.0007485126,0.0004089011,0.03853337,0.1986778,0.09197998,0.6636003],"study_design_scores_gemma":[0.004623064,0.0004084426,0.01512519,0.00001838567,0.0000217825,0.00006948417,0.000573425,0.5143856,0.1283557,0.03427044,0.3006743,0.001474107],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1276147,0.0003526577,0.8579744,0.007166324,0.002315782,0.0003859779,0.00001010048,0.002117572,0.002062554],"genre_scores_gemma":[0.9831483,0.00002232774,0.01372844,0.0004697015,0.00002237285,0.0001143476,0.000002983719,0.000007082645,0.002484443],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8555337,"threshold_uncertainty_score":0.4783024,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2142742813","doi":"","title":"Learning from multiple partially observed views - an application to multilingual text categorization","year":2009,"lang":"en","type":"preprint","venue":"NPARC","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":274,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Computer science; Artificial intelligence; Leverage (statistics); Categorization; Machine learning; Natural language processing; Generalization; Text categorization; Set (abstract data type); Training set; Supervised learning; Artificial neural network; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.0694166084151494,"gpt":0.2987423463949583,"spread":0.2293257379798089,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003265804,0.0003073078,0.0003240968,0.0001850471,0.0001879634,0.0004922353,0.001949464,0.0003764007,0.00002914979],"category_scores_gemma":[0.0002953745,0.0003176553,0.0000863537,0.0003365961,0.00003193115,0.0003943325,0.0008508241,0.0005563978,0.0002040651],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001222126,"about_ca_system_score_gemma":0.0001280237,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001576676,"about_ca_topic_score_gemma":0.0001917961,"domain_scores_codex":[0.9975087,0.0001609916,0.0005191137,0.001130961,0.0003735243,0.0003067017],"domain_scores_gemma":[0.9976572,0.00009008375,0.0003894017,0.001542292,0.0001801285,0.0001408943],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001269075,0.0001457746,0.001918054,0.00001359689,0.00001370613,0.000001643771,0.001874234,0.01383519,0.08372882,0.008698211,0.0003018146,0.8894563],"study_design_scores_gemma":[0.0004410162,0.000199671,0.02534932,0.0000572219,0.00002232638,5.945522e-7,0.0001954516,0.7903901,0.06278173,0.09704278,0.02270797,0.000811869],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1029808,0.00004770913,0.8917206,0.001857023,0.0002992431,0.0007943869,0.000006441059,0.001723491,0.0005703304],"genre_scores_gemma":[0.8345945,0.00003468487,0.1642394,0.0001881927,0.000142693,0.0002584111,0.000352822,0.00001834134,0.000170923],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8886444,"threshold_uncertainty_score":0.9999276,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W167522204","doi":"","title":"Beyond TFIDF weighting for text categorization in the vector space model","year":2005,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":232,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université Laval","funders":"","keywords":"Weighting; tf–idf; Vector space model; Computer science; Artificial intelligence; Categorization; Leverage (statistics); Vocabulary; Feature selection; Support vector machine; Text categorization; Word (group theory); Feature vector; Natural language processing; Machine learning; Information retrieval; Pattern recognition (psychology); Mathematics; Term (time)","retraction":null,"screen_n_in":null,"score":{"opus":0.02088681033409115,"gpt":0.2605201725384578,"spread":0.2396333622043666,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002106247,0.00006599649,0.00005621601,0.00008115535,0.00008920509,0.0001416229,0.0006710455,0.00004463021,0.000006933611],"category_scores_gemma":[0.0000449408,0.00004333883,0.00002352552,0.0003019319,0.00001850894,0.0004982087,0.00006211383,0.00005728816,0.00002748181],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003424355,"about_ca_system_score_gemma":0.00002650696,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006283191,"about_ca_topic_score_gemma":0.00003636875,"domain_scores_codex":[0.9993961,0.00001243511,0.0001325906,0.0001889467,0.0001184198,0.000151468],"domain_scores_gemma":[0.9994859,0.00008719326,0.00004969614,0.0003340742,0.00003152157,0.0000116317],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[7.459707e-7,0.00002172111,0.00007295346,0.000001860438,8.531248e-7,6.24086e-8,0.0005590461,0.001026591,0.0007926935,0.9607506,0.002867666,0.03390522],"study_design_scores_gemma":[0.0001683387,0.00001756063,0.0003313762,0.000001615209,0.000001216206,7.247457e-7,0.0001856786,0.9080166,0.008270115,0.07531867,0.007604068,0.00008408588],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003784743,0.00003793399,0.9500412,0.03656249,0.00004376234,0.0002222862,4.619872e-7,0.000250612,0.00905655],"genre_scores_gemma":[0.8762227,0.000007246621,0.1216634,0.0004539123,0.00003058514,0.00006506559,0.000002120652,0.000003244042,0.001551685],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9069899,"threshold_uncertainty_score":0.1767306,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2099126842","doi":"10.1109/icdm.2001.989592","title":"A simple KNN algorithm for text categorization","year":2002,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":225,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université Laval","funders":"","keywords":"Computer science; Interpretability; Artificial intelligence; Text categorization; Feature (linguistics); Context (archaeology); Vocabulary; Feature selection; Word (group theory); Categorization; Simple (philosophy); Class (philosophy); k-nearest neighbors algorithm; Process (computing); Machine learning; Natural language processing; Pattern recognition (psychology); Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.03016497877693925,"gpt":0.2537802900861292,"spread":0.22361531130919,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00005089884,0.00006147106,0.00005853032,0.00007360875,0.00009079086,0.0001246442,0.000437138,0.00004453016,0.0001445838],"category_scores_gemma":[0.00002573412,0.00005180555,0.00002965318,0.0002641226,0.00001873607,0.0003942382,0.00006833048,0.00002767173,0.0001760096],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001887051,"about_ca_system_score_gemma":0.000005316641,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005505789,"about_ca_topic_score_gemma":0.000001469667,"domain_scores_codex":[0.9994497,0.000005638633,0.0001127411,0.0002000874,0.00008970848,0.0001421273],"domain_scores_gemma":[0.9995209,0.00004045247,0.00004043352,0.0003235185,0.00005028878,0.00002441642],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[7.980512e-8,0.00002095014,0.00002854779,0.000001155663,0.000001979119,1.347503e-7,0.00004584582,0.000001362672,0.0001356888,0.3066415,0.01653753,0.6765852],"study_design_scores_gemma":[0.0002315967,0.0000584793,0.0001912395,7.566895e-7,0.000001771454,0.000001494343,0.00004645347,0.8083091,0.00974343,0.04754684,0.1337463,0.0001225462],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.00007800005,0.00003147982,0.9915096,0.002448056,0.00009333993,0.00016533,0.000001304503,0.0008307786,0.004842147],"genre_scores_gemma":[0.6075973,0.00003884285,0.3773731,0.0004594227,0.00005140491,0.0001427332,0.00001033092,0.000008625558,0.01431825],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8083078,"threshold_uncertainty_score":0.2262306,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2089870669","doi":"10.1016/j.eswa.2011.09.160","title":"Comparison of term frequency and document frequency based feature selection metrics in text categorization","year":2011,"lang":"en","type":"article","venue":"Expert Systems with Applications","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":152,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Regina","funders":"Faculty of Graduate Studies and Research, University of Alberta; Natural Sciences and Engineering Research Council of Canada; University of Regina","keywords":"Feature selection; Discriminative model; Computer science; Term (time); Text categorization; Categorization; Word lists by frequency; Feature (linguistics); Frequency; Artificial intelligence; Selection (genetic algorithm); Pattern recognition (psychology); tf–idf; Data mining; Mathematics; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.03104747594243825,"gpt":0.2863871260576094,"spread":0.2553396501151711,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001451599,0.0001449336,0.0002187988,0.0004319269,0.0001083949,0.00007278683,0.0004383797,0.0001207827,0.000006395428],"category_scores_gemma":[0.00001616889,0.0001201902,0.00001915196,0.001553678,0.00006929315,0.0004054891,0.00003889412,0.0001189491,0.00000599574],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001103373,"about_ca_system_score_gemma":0.00007483242,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003874626,"about_ca_topic_score_gemma":0.00004635248,"domain_scores_codex":[0.998818,0.00004818357,0.0003624511,0.0003779054,0.0002285486,0.0001649525],"domain_scores_gemma":[0.9989477,0.00004931776,0.0003041427,0.0004997521,0.0001482781,0.00005084547],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.00000663657,0.000301439,0.3544643,0.00008507377,0.00002143912,6.614484e-7,0.002562189,0.00003322574,0.009819295,0.6222152,0.000515205,0.009975277],"study_design_scores_gemma":[0.005529375,0.001854689,0.6391277,0.0006298409,0.0001000628,0.00007703797,0.007982855,0.09260122,0.1881626,0.04686606,0.01386802,0.003200532],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004883914,0.001507407,0.9900603,0.0004039295,0.00005503541,0.0009927601,0.000002316281,0.0003044728,0.001789862],"genre_scores_gemma":[0.9390606,0.00003145553,0.0596256,0.00001939772,0.00001459754,0.001170222,0.00001352673,0.000009036117,0.00005551413],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9341767,"threshold_uncertainty_score":0.4901213,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2151849342","doi":"10.1109/hicss.2003.1174243","title":"Support vector machines for text categorization","year":2003,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":146,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Categorization; Text categorization; Sorting; Set (abstract data type); Support vector machine; Artificial intelligence; Vocabulary; Feature (linguistics); Natural language processing; Information retrieval; Process (computing); Feature vector","retraction":null,"screen_n_in":null,"score":{"opus":0.01982714791796406,"gpt":0.2626373654355585,"spread":0.2428102175175944,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009643464,0.00005992852,0.00005580956,0.00006231396,0.00007105281,0.00009500469,0.0003143681,0.00003760693,0.0001124533],"category_scores_gemma":[0.00009176708,0.00004760844,0.00002700431,0.0001986557,0.00001572319,0.0003072124,0.00002669201,0.00002336691,0.00008012522],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001448722,"about_ca_system_score_gemma":0.00003266957,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002815788,"about_ca_topic_score_gemma":0.000002627773,"domain_scores_codex":[0.9995108,0.000009061888,0.0001071723,0.0001784536,0.0000745645,0.0001199395],"domain_scores_gemma":[0.9995708,0.00003705822,0.00003853439,0.0002851201,0.00004685183,0.00002157213],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[3.972883e-7,0.00001450326,0.0003895808,0.000002566749,0.000001888897,1.082012e-7,0.00003048733,0.000001531942,0.001172717,0.9752176,0.004960276,0.01820836],"study_design_scores_gemma":[0.0006186058,0.0001979388,0.003471085,0.00000196946,0.000005867747,0.000008139508,0.00008002784,0.01421932,0.2052138,0.3157833,0.4600383,0.0003616383],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0006294516,0.00001264966,0.9766536,0.002131676,0.0002308965,0.0001541201,7.083727e-7,0.0005892997,0.01959759],"genre_scores_gemma":[0.9184598,0.00000444505,0.07218964,0.0001987578,0.00001122563,0.00005850771,0.000005572235,0.000004346626,0.009067714],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9178303,"threshold_uncertainty_score":0.1941416,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1528447234","doi":"10.1145/563932.563930","title":"Classifying text documents by associating terms with text categories","year":2002,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":111,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Categorization; Computer science; Text categorization; Association rule learning; Classifier (UML); Artificial intelligence; Text mining; Natural language processing; Information retrieval; Machine learning; Data mining","retraction":null,"screen_n_in":null,"score":{"opus":0.01833621184447505,"gpt":0.2287015926834513,"spread":0.2103653808389762,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000131775,0.0001929363,0.0001727572,0.0001067186,0.0002444365,0.0006152834,0.0009792477,0.00009982859,0.0002400485],"category_scores_gemma":[0.00005295697,0.000140893,0.00003904826,0.0005289527,0.00009531646,0.001316491,0.0002434354,0.0001770273,0.000354701],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001448338,"about_ca_system_score_gemma":0.00001624254,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003723051,"about_ca_topic_score_gemma":0.00001104226,"domain_scores_codex":[0.9984573,0.00002947259,0.0002568989,0.0004520022,0.0003994227,0.0004049177],"domain_scores_gemma":[0.999007,0.00009326028,0.0001914114,0.0005897605,0.00005150447,0.00006704285],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000003457177,0.0002366253,0.03897792,0.00002037519,0.0000882823,0.00001653791,0.001826358,0.000006552154,0.002996015,0.2185813,0.2739843,0.4632623],"study_design_scores_gemma":[0.005978078,0.001372954,0.01780608,0.0001943555,0.00008123826,0.0001287415,0.005976298,0.09496666,0.07479599,0.05697798,0.7370024,0.004719259],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01829816,0.0007491024,0.5361313,0.02432651,0.0005643612,0.0005728456,0.000005525602,0.005546388,0.4138058],"genre_scores_gemma":[0.9279951,0.00004348593,0.01778522,0.0003907546,0.00001834653,0.00004331938,0.000003046653,0.00001254867,0.05370818],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9096969,"threshold_uncertainty_score":0.5933192,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2012971775","doi":"10.1080/0952813x.2012.721010","title":"Naive Bayes text classifiers: a locally weighted learning approach","year":2012,"lang":"en","type":"article","venue":"Journal of Experimental & Theoretical Artificial Intelligence","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":107,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of New Brunswick","funders":"","keywords":"Naive Bayes classifier; Computer science; Artificial intelligence; Machine learning; Conditional independence; Bayes error rate; Bayesian programming; Bayes' theorem; Benchmark (surveying); Complement (music); Bayes classifier; Bayesian probability; Support vector machine; Bayes factor","retraction":null,"screen_n_in":null,"score":{"opus":0.03611338585351168,"gpt":0.3060859303784622,"spread":0.2699725445249506,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009144688,0.0002396505,0.0003270722,0.0002373482,0.0002104802,0.0002729346,0.00129126,0.0001748619,0.000334693],"category_scores_gemma":[0.0002728032,0.0001832922,0.0002104095,0.0005143788,0.0008898595,0.001155233,0.0003285641,0.0006530599,0.0001733914],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001372996,"about_ca_system_score_gemma":0.00006618175,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001892644,"about_ca_topic_score_gemma":6.110972e-8,"domain_scores_codex":[0.9974698,0.0002028163,0.0008520248,0.0002797174,0.0006692237,0.0005264455],"domain_scores_gemma":[0.998501,0.0002479359,0.0004200476,0.0003423505,0.0002055335,0.0002831216],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00008547059,0.0006060054,0.00008845663,0.000003448251,0.0000280587,0.000006149906,0.001583429,0.00002433447,0.02626935,0.9285442,0.00009306895,0.04266809],"study_design_scores_gemma":[0.00008786885,0.0007957029,0.00003389224,0.00003979126,0.00001526116,0.0001254545,0.007202719,0.02843588,0.781793,0.1800135,0.001139314,0.0003176664],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0531248,0.001223829,0.9367777,0.0009313916,0.0006039502,0.0001450908,4.246142e-7,0.0001577846,0.007035095],"genre_scores_gemma":[0.9550135,0.00004376105,0.04449932,0.0001358083,0.0002338697,0.0000109438,8.113285e-7,0.00001443847,0.00004756886],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9018887,"threshold_uncertainty_score":0.7474439,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2135420268","doi":"10.1109/grc.2007.40","title":"Naïve Bayes Text Classifier","year":2007,"lang":"en","type":"article","venue":"2007 IEEE International Conference on Granular Computing (GRC 2007)","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":98,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Acadia University","funders":"","keywords":"Naive Bayes classifier; Computer science; Bayes' theorem; Support vector machine; Artificial intelligence; Machine learning; Detector; Classifier (UML); Bayesian probability; Information retrieval; Data mining","retraction":null,"screen_n_in":null,"score":{"opus":0.07050096873332103,"gpt":0.3294173998244482,"spread":0.2589164310911272,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001325139,0.0004319678,0.0003389218,0.0006879121,0.0003219351,0.0006082693,0.002751708,0.0002769299,0.0006369083],"category_scores_gemma":[0.0002309544,0.000418536,0.00019955,0.000538956,0.0002415108,0.0005357633,0.0003288498,0.0006263896,0.002019621],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002422164,"about_ca_system_score_gemma":0.0001315882,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003160731,"about_ca_topic_score_gemma":0.00001691479,"domain_scores_codex":[0.9962035,0.00008026652,0.0008558437,0.0009529921,0.001161585,0.0007458274],"domain_scores_gemma":[0.9974197,0.0003340518,0.0004587866,0.0009820425,0.0006064997,0.0001989207],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00006561218,0.0003633664,0.003795926,0.00001606645,0.00009815882,0.00006853428,0.0004676294,0.0001837841,0.006740526,0.7801839,0.03503496,0.1729816],"study_design_scores_gemma":[0.004017391,0.0006914929,0.03033517,0.0007216603,0.00005294131,0.0002600985,0.000932888,0.2473689,0.03607211,0.08312909,0.5928733,0.003544944],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02107755,0.00007610444,0.8960201,0.002423766,0.005307004,0.0002562521,0.000009928619,0.0009023241,0.07392693],"genre_scores_gemma":[0.9498128,0.00004760843,0.04350821,0.001220557,0.0005639984,0.000008724181,0.00002831158,0.0000293757,0.004780462],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9287352,"threshold_uncertainty_score":0.9998267,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2013023084","doi":"10.1007/s10994-013-5371-6","title":"Beam search algorithms for multilabel learning","year":2013,"lang":"en","type":"article","venue":"Machine Learning","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":90,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Inference; Beam search; Computer science; Machine learning; Artificial intelligence; Probabilistic logic; Classifier (UML); Task (project management); Range (aeronautics); Algorithm; Search algorithm","retraction":null,"screen_n_in":null,"score":{"opus":0.03105901679861803,"gpt":0.289212411422877,"spread":0.2581533946242589,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000366159,0.0001450635,0.0001494282,0.000172967,0.0004402222,0.0003714832,0.0007656517,0.00008366771,0.000101856],"category_scores_gemma":[0.0003196758,0.0001295721,0.00006835938,0.0003135354,0.00004708021,0.0005696135,0.000339421,0.0004485688,0.0003290929],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003675995,"about_ca_system_score_gemma":0.00002162396,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001353082,"about_ca_topic_score_gemma":0.000002085887,"domain_scores_codex":[0.9987253,0.00006050496,0.0002020486,0.0003978094,0.000222309,0.0003920475],"domain_scores_gemma":[0.9991853,0.0002253539,0.00008975557,0.0003150235,0.0001173943,0.00006713851],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000002900017,0.00005173376,0.01683797,0.00002470373,0.00002036728,0.000001388122,0.0007406826,0.004272901,0.008324143,0.01192018,0.0009114185,0.9568916],"study_design_scores_gemma":[0.0004873811,0.0001861828,0.005119447,0.00001028928,0.000003086764,0.000003964265,0.0002214035,0.9297019,0.006100121,0.001395461,0.05653935,0.0002314131],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03946071,0.0002638565,0.9522077,0.003916801,0.0001526392,0.0004657455,7.060763e-7,0.001924199,0.001607612],"genre_scores_gemma":[0.8799031,0.00002405072,0.1091819,0.0001099333,0.00005100281,0.0001632862,0.00001476697,0.0000203198,0.01053171],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9566602,"threshold_uncertainty_score":0.5283796,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2997205428","doi":"10.1609/aaai.v34i04.5822","title":"Nonlinear Mixup: Out-Of-Manifold Data Augmentation for Text Classification","year":2020,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":81,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"National Research Council Canada","funders":"","keywords":"Nonlinear system; Mixing (physics); Manifold (fluid mechanics); Computer science; Regularization (linguistics); Scalar (mathematics); Interpolation (computer graphics); Benchmark (surveying); Mathematics; Artificial intelligence; Pattern recognition (psychology); Algorithm; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.2956569575793979,"gpt":0.3630008410034393,"spread":0.06734388342404135,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033477,0.0001570563,0.0002090433,0.00008331267,0.0001169446,0.0001623826,0.003697287,0.00008678984,0.00002187277],"category_scores_gemma":[0.0008069013,0.0001239708,0.00007277098,0.0004992922,0.0001657963,0.0007066545,0.0005505591,0.0001441218,0.00004941087],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002335237,"about_ca_system_score_gemma":0.00008345805,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000058039,"about_ca_topic_score_gemma":0.000003233139,"domain_scores_codex":[0.998278,0.000009456557,0.0006008007,0.0005517531,0.0003696916,0.0001902612],"domain_scores_gemma":[0.9981022,0.0001092795,0.0006415391,0.0005480581,0.0005443922,0.00005457232],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00004621621,0.00009114343,0.00008101243,0.00005556144,0.00001119579,2.598225e-8,0.0008275225,0.000003800869,0.1346215,0.7711114,0.0008869607,0.09226366],"study_design_scores_gemma":[0.0000439981,0.0002286492,0.0001153977,0.00005721511,0.00001544882,2.086081e-7,0.001185045,0.2604725,0.6817673,0.05461723,0.001352474,0.0001445388],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03135372,0.00004934012,0.8838167,0.07606008,0.0008698027,0.001868023,0.0001063144,0.0004923767,0.005383696],"genre_scores_gemma":[0.9726282,0.00003836573,0.0268971,0.0002347761,0.00005787928,0.00003773192,0.000009349051,0.000009065433,0.00008748028],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9412745,"threshold_uncertainty_score":0.6870541,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3121217868","doi":"10.1016/j.is.2021.101718","title":"Multi-label legal document classification: A deep learning-based approach with label-attention and domain-specific pre-training","year":2021,"lang":"en","type":"article","venue":"Information Systems","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":73,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Thomson Reuters (Canada)","funders":"","keywords":"Computer science; Artificial intelligence; Multi-label classification; Domain (mathematical analysis); Training (meteorology); Machine learning; Training set","retraction":null,"screen_n_in":null,"score":{"opus":0.03582749930198761,"gpt":0.2545681606306928,"spread":0.2187406613287052,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0004799287,0.000196509,0.0002139572,0.0002374666,0.0003335836,0.00156437,0.0003775302,0.0001274306,0.000004134928],"category_scores_gemma":[0.00002346437,0.0001694723,0.0000292433,0.0006576794,0.00008871951,0.003115146,0.00009989538,0.0002179944,0.00005584566],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001204263,"about_ca_system_score_gemma":0.0001132541,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008880105,"about_ca_topic_score_gemma":0.000002981439,"domain_scores_codex":[0.9981939,0.0001204331,0.00057619,0.0003307719,0.0005142342,0.0002645055],"domain_scores_gemma":[0.9985068,0.00005603382,0.0004582877,0.0005418338,0.0003545514,0.00008245977],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005427674,0.000295074,0.003239909,0.0004453867,0.0001070932,0.0000107401,0.009492532,0.004399923,0.003346255,0.7562264,0.0005176134,0.2218647],"study_design_scores_gemma":[0.003862281,0.00019336,0.01247016,0.0001405036,0.00001300107,0.0001597312,0.01561235,0.7643647,0.0003320122,0.000116964,0.2021708,0.0005641083],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01468044,0.0003703678,0.9808335,0.0008071798,0.0002119854,0.0004559892,0.000002154409,0.0007042507,0.001934143],"genre_scores_gemma":[0.843629,0.00003499851,0.1554356,0.00008078929,0.00002634424,0.0002681687,0.00009810821,0.000008532191,0.0004184518],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8289486,"threshold_uncertainty_score":0.9994721,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2000918452","doi":"10.1145/1281192.1281260","title":"A concept-based model for enhancing text categorization","year":2007,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":65,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Natural language processing; Categorization; Sentence; Artificial intelligence; Phrase; Term (time); Weighting; Graph; Information retrieval; Theoretical computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.02597749126124376,"gpt":0.281605414501903,"spread":0.2556279232406592,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002070395,0.00006303743,0.00005970197,0.00009536494,0.0000832271,0.0000735563,0.0003719279,0.00005345253,0.000007813404],"category_scores_gemma":[0.00005328581,0.00005477833,0.00002995145,0.0002182904,0.00002530069,0.0002816493,0.00003669229,0.00003166722,0.00001370216],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000362874,"about_ca_system_score_gemma":0.00005388312,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000425365,"about_ca_topic_score_gemma":0.00005880543,"domain_scores_codex":[0.9993671,0.000003286548,0.0001583843,0.0001970765,0.00010167,0.0001725454],"domain_scores_gemma":[0.9994721,0.00008748129,0.00005703214,0.0002800289,0.00007532422,0.00002807202],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000002687566,0.0000221483,0.00003808089,0.000004072253,0.000001770857,1.662817e-7,0.0001793996,0.002350407,0.009137586,0.9396791,0.0008059966,0.0477786],"study_design_scores_gemma":[0.0001828135,0.0000218578,0.00005017675,0.000001644141,0.000001046072,1.620168e-7,0.00005096713,0.7843188,0.1988266,0.01566663,0.0008055213,0.00007376039],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0005468536,0.00001366491,0.9955518,0.001387699,0.00007908075,0.0001765791,5.409963e-7,0.0007395489,0.001504216],"genre_scores_gemma":[0.8124476,5.452409e-7,0.1857898,0.0003336122,0.00001038607,0.00001896411,0.00000393899,0.000003338093,0.001391774],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9240125,"threshold_uncertainty_score":0.2233796,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4386266758","doi":"10.1109/access.2023.3309697","title":"MCNN-LSTM: Combining CNN and LSTM to Classify Multi-Class Text in Imbalanced News Data","year":2023,"lang":"en","type":"article","venue":"IEEE Access","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":64,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Calgary","funders":"","keywords":"Computer science; Artificial intelligence; Convolutional neural network; Machine learning; Margin (machine learning); Deep learning; Class (philosophy); Feature (linguistics); Sentence; Document classification; Categorization; Natural language processing","retraction":null,"screen_n_in":null,"score":{"opus":0.1552556872135712,"gpt":0.3857469680310411,"spread":0.2304912808174699,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003370133,0.0001827046,0.0002427622,0.0004462007,0.0001251985,0.0007097174,0.004120491,0.0001197357,0.000008184219],"category_scores_gemma":[0.0001844186,0.0001727936,0.00002087893,0.001796335,0.00007503873,0.00182333,0.002349402,0.000225453,0.0002354718],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004581357,"about_ca_system_score_gemma":0.0000550068,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000132686,"about_ca_topic_score_gemma":0.0003113922,"domain_scores_codex":[0.9981015,0.00004881342,0.0003401162,0.0008190055,0.0002602905,0.0004302508],"domain_scores_gemma":[0.9979042,0.0001686605,0.0001152844,0.001666744,0.000041793,0.0001033223],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004031753,0.0003398743,0.1703411,0.0001076167,0.00005336578,0.0001308385,0.001947741,0.0005907568,0.0183096,0.0210444,0.1524752,0.6346192],"study_design_scores_gemma":[0.003494161,0.0001582469,0.3949886,0.0002005687,0.00001363328,0.00001151684,0.0008979039,0.4931268,0.01349057,0.008055352,0.08426645,0.001296193],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7069339,0.0002162544,0.2434696,0.03965316,0.002461603,0.001141395,0.00004387033,0.003963279,0.002116932],"genre_scores_gemma":[0.9927286,0.0001250742,0.005332245,0.0009082628,0.00003768362,0.00007046541,0.00002035441,0.00001560926,0.0007617046],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.633323,"threshold_uncertainty_score":0.7656966,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2018764947","doi":"10.1016/j.ipm.2011.11.001","title":"A three-phase method for patent classification","year":2012,"lang":"en","type":"article","venue":"Information Processing & Management","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":60,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"McGill University","keywords":"Phase (matter); Computer science; Information retrieval; Chemistry","retraction":null,"screen_n_in":null,"score":{"opus":0.07881797612441159,"gpt":0.3411085603720877,"spread":0.2622905842476761,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006607394,0.000125291,0.0000981699,0.000283908,0.0002375818,0.0004575102,0.0005704798,0.00005651815,0.000007982271],"category_scores_gemma":[0.00002949054,0.0001115491,0.00004664606,0.0004198579,0.00002121835,0.005439035,0.0001525608,0.00005836493,0.0001109711],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009195747,"about_ca_system_score_gemma":0.00001985712,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001833911,"about_ca_topic_score_gemma":3.245976e-7,"domain_scores_codex":[0.9988663,0.00001109594,0.0004052084,0.0001449719,0.0002738065,0.0002986437],"domain_scores_gemma":[0.9990601,0.00002497742,0.0003226257,0.0004011143,0.0001328752,0.00005832159],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000004738677,0.00005595036,0.00003859719,0.00008757296,0.000007898981,3.106219e-8,0.000384733,0.000008977382,0.00002460234,0.290449,0.002106506,0.7068314],"study_design_scores_gemma":[0.001484247,0.00006670636,0.00509353,0.0000439508,0.00003367876,0.000003388899,0.000947761,0.5157804,0.001637315,0.03178029,0.4427781,0.0003505454],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001550226,0.00008875235,0.991313,0.002328967,0.000228209,0.0006231918,0.000002218361,0.0007531848,0.004507479],"genre_scores_gemma":[0.3796265,0.00001218211,0.6189886,0.0005502132,0.00003052516,0.0006151486,0.0000390169,0.000005489467,0.0001322767],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7064809,"threshold_uncertainty_score":0.4548838,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4394987794","doi":"10.1016/j.datak.2024.102306","title":"Effective text classification using BERT, MTM LSTM, and DT","year":2024,"lang":"en","type":"article","venue":"Data & Knowledge Engineering","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":56,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Artificial Intelligence in Medicine (Canada); University of Calgary","funders":"","keywords":"Security token; Computer science; Artificial intelligence; Encoder; Binary classification; Transformer; Recall; Deep learning; Long short term memory; Natural language processing; Artificial neural network; Machine learning; Recurrent neural network; Support vector machine","retraction":null,"screen_n_in":null,"score":{"opus":0.04931219236959951,"gpt":0.3094819476933262,"spread":0.2601697553237267,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002519094,0.0001472722,0.0001180398,0.0002472433,0.00007370016,0.0004071466,0.0008940719,0.00007670767,0.000004944014],"category_scores_gemma":[0.0001231538,0.0001400477,0.00001987578,0.0005601778,0.00003425457,0.001286346,0.0007719047,0.0001800129,0.00009020637],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007620501,"about_ca_system_score_gemma":0.00003418062,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005098803,"about_ca_topic_score_gemma":0.000002220187,"domain_scores_codex":[0.9989894,0.00001694631,0.0001609418,0.0005411881,0.00009655448,0.0001949833],"domain_scores_gemma":[0.9988191,0.0001900226,0.00002473445,0.0008875146,0.00002819763,0.00005040084],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[8.676244e-7,0.00002347563,0.00009825209,0.0001527444,0.00003624986,0.000005839518,0.0004128938,0.00001672452,0.02223007,0.1486993,0.002350505,0.825973],"study_design_scores_gemma":[0.00006077505,0.00001190403,0.001815586,0.00008393756,0.0000108021,0.00001295044,0.00002606875,0.9251232,0.001904855,0.0002897153,0.0705009,0.0001593432],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008288466,0.006318005,0.9817908,0.0003773586,0.0007573832,0.0002188747,0.00002400855,0.001592662,0.0006323743],"genre_scores_gemma":[0.9438424,0.0001292412,0.05555006,0.000009459266,0.0001516366,0.00004043996,0.0000644263,0.00002555523,0.0001867975],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9355539,"threshold_uncertainty_score":0.5710978,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2108345839","doi":"10.1177/0165551508092257","title":"A hidden Markov model-based text classification of medical documents","year":2008,"lang":"en","type":"article","venue":"Journal of Information Science","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":55,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"","keywords":"Hidden Markov model; Computer science; Categorization; Artificial intelligence; Markov model; Subject (documents); Natural language processing; Machine learning; Markov chain; World Wide Web","retraction":null,"screen_n_in":null,"score":{"opus":0.02964063379902278,"gpt":0.2983874154971723,"spread":0.2687467816981495,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001973821,0.00008070636,0.0001516449,0.0008803965,0.0001757875,0.000139693,0.00260537,0.00007644366,0.00002679518],"category_scores_gemma":[0.0008385261,0.00006173714,0.00006665951,0.001406317,0.000503784,0.008477471,0.0001578012,0.0001743848,0.00002637882],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001109317,"about_ca_system_score_gemma":0.001463366,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002425456,"about_ca_topic_score_gemma":2.220605e-7,"domain_scores_codex":[0.9963148,0.00002148631,0.000882838,0.00009451181,0.002518119,0.000168255],"domain_scores_gemma":[0.9973648,0.00006694795,0.001158411,0.0003889369,0.0008880211,0.0001328862],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005646573,0.0002634931,0.006424019,0.00005883891,0.00001831873,0.000007609636,0.004034898,0.001454269,0.007235628,0.250389,0.01043854,0.7196189],"study_design_scores_gemma":[0.0009463889,0.0001637839,0.03148461,0.00007038117,0.000004289027,0.0001324859,0.0003167702,0.944443,0.01732289,0.002605049,0.002349431,0.0001609241],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09866388,0.0000210134,0.8929573,0.005431447,0.000211327,0.00007655611,8.048054e-7,0.00005021742,0.002587415],"genre_scores_gemma":[0.9134364,0.00007101661,0.08619491,0.0002584907,0.00001001175,0.000002624027,5.000563e-7,0.000001296882,0.00002478187],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9429888,"threshold_uncertainty_score":0.6145962,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2756654724","doi":"10.18653/v1/d17-1202","title":"Shortest-Path Graph Kernels for Document Similarity","year":2017,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":54,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Computer science; Graph; Similarity measure; Shortest path problem; Kernel (algebra); Similarity (geometry); Macro; Data mining; Artificial intelligence; Pattern recognition (psychology); Theoretical computer science; Mathematics; Combinatorics","retraction":null,"screen_n_in":null,"score":{"opus":0.04094903064209897,"gpt":0.3136976083326138,"spread":0.2727485776905149,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002238975,0.0001036372,0.0001110135,0.00005803631,0.0004940039,0.0007744386,0.002076445,0.00006679186,0.00002947793],"category_scores_gemma":[0.0001327217,0.00008333742,0.00007942157,0.00005100374,0.00009181792,0.000915802,0.0004165021,0.00006124202,0.000034901],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002140419,"about_ca_system_score_gemma":0.00002758143,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002816525,"about_ca_topic_score_gemma":0.00001274392,"domain_scores_codex":[0.9991156,0.000007190845,0.0001552489,0.0003415322,0.0001575201,0.0002229247],"domain_scores_gemma":[0.9981591,0.00005249089,0.000124061,0.00154578,0.00006826867,0.0000503162],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000001846973,0.0000342465,0.003814014,0.000003478748,0.000009293375,0.000001038372,0.0000364016,0.000002112572,0.0003291697,0.9292241,0.01117301,0.05537129],"study_design_scores_gemma":[0.0006619311,0.0001654583,0.05026225,0.00001153613,0.000009831933,0.000002831657,0.00006159761,0.007502892,0.03850405,0.8436001,0.05881664,0.0004008877],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005608544,0.00003536202,0.9712582,0.01189723,0.0003429043,0.0003420626,0.000002663062,0.0007905407,0.009722557],"genre_scores_gemma":[0.9089508,0.0000350353,0.0879635,0.0002577048,0.00002412913,0.00009648561,0.000001591227,0.000004399402,0.002666323],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9033423,"threshold_uncertainty_score":0.7467929,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2263083451","doi":"","title":"Bi-parameter space partition for cost-sensitive SVM","year":2015,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":54,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University","funders":"","keywords":"Support vector machine; Partition (number theory); Hyperparameter optimization; Regularization (linguistics); Algorithm; Invariant (physics); Parameter space; Piecewise; Grid; Model selection; Computer science; Mathematical optimization; Mathematics; Generalization; Artificial intelligence; Statistics; Combinatorics; Mathematical analysis; Geometry","retraction":null,"screen_n_in":null,"score":{"opus":0.08266643554195872,"gpt":0.3065639875173696,"spread":0.2238975519754109,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001583385,0.00007188682,0.00007824598,0.0000690258,0.00004328803,0.0001261717,0.0002666891,0.0000512351,0.000006142912],"category_scores_gemma":[0.0001841557,0.00005608768,0.00003492089,0.0001729723,0.00004180436,0.0004388866,0.00008938937,0.0000382914,0.0001765406],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003859799,"about_ca_system_score_gemma":0.00003313333,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007673701,"about_ca_topic_score_gemma":0.000005534651,"domain_scores_codex":[0.9993893,0.00001513837,0.0001007296,0.0002172033,0.0001193534,0.0001583057],"domain_scores_gemma":[0.9993189,0.0001054604,0.0000485204,0.0003360243,0.0001328588,0.0000582272],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000008620787,0.00003686606,0.000168832,0.000002549214,0.0000071103,0.000001061611,0.0002236506,0.0000119351,0.0006979142,0.8617041,0.0744489,0.06268849],"study_design_scores_gemma":[0.001223264,0.000407315,0.00141846,0.00001074823,0.00001058638,0.00001027041,0.000932639,0.08660285,0.289278,0.2618388,0.3578247,0.0004423905],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003285284,0.00001446263,0.9757215,0.01353297,0.0002144562,0.0003217071,0.000001902985,0.0006819335,0.006225833],"genre_scores_gemma":[0.8335084,0.000003977585,0.1625821,0.0004617009,0.00002604806,0.0001144955,0.000004930825,0.000004224083,0.003294217],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8302231,"threshold_uncertainty_score":0.2287189,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2740468505","doi":"10.24963/ijcai.2017/443","title":"Incomplete Label Distribution Learning","year":2017,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":52,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Novelis (Canada)","funders":"National Natural Science Foundation of China","keywords":"Computer science; Artificial intelligence; Relevance (law); Minification; Exploit; Annotation; Machine learning; Algorithm","retraction":null,"screen_n_in":null,"score":{"opus":0.04191246432389344,"gpt":0.2960959009144437,"spread":0.2541834365905503,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009665194,0.00004452644,0.00004639206,0.00001745361,0.0005516133,0.000491238,0.001052194,0.00002995808,0.00002266438],"category_scores_gemma":[0.0001439404,0.00003698999,0.00001456696,0.00003787813,0.00005356854,0.000623773,0.0004028178,0.00007483886,0.0002023579],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001693195,"about_ca_system_score_gemma":0.000008992407,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001809791,"about_ca_topic_score_gemma":0.000003327479,"domain_scores_codex":[0.9995782,0.000008817367,0.00006971793,0.0001474875,0.00008932334,0.0001064692],"domain_scores_gemma":[0.9992263,0.00001582965,0.00008436483,0.0006248737,0.00002870504,0.00001986856],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[3.388351e-7,0.000007548413,0.004629956,9.11646e-7,0.000001753437,7.327843e-7,0.00001142013,9.234342e-7,0.000650638,0.8168336,0.00198439,0.1758778],"study_design_scores_gemma":[0.0007287926,0.0001218222,0.2494325,0.00001267234,0.000003486343,0.000006195456,0.00006305896,0.08876295,0.01908336,0.09539095,0.5460006,0.0003936526],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01252084,0.00001168322,0.9617971,0.007993007,0.0001272961,0.00004197793,6.375146e-7,0.0008817604,0.01662569],"genre_scores_gemma":[0.9856563,0.000008538889,0.01101197,0.00003436556,0.00001118146,0.000005651345,0.000003680651,0.000001421083,0.0032669],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9731355,"threshold_uncertainty_score":0.473702,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1507852567","doi":"10.1007/11425274_17","title":"Evaluation of Two Systems on Multi-class Multi-label Document Classification","year":2005,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":52,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Document classification; Classifier (UML); Search engine indexing; Artificial intelligence; Class (philosophy); Multi-label classification; Pattern recognition (psychology); Data mining; Information retrieval; Natural language processing; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.09346704776640828,"gpt":0.3400993522796007,"spread":0.2466323045131924,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.003457853,0.0005449155,0.0005509044,0.001342658,0.00020382,0.0004811847,0.003393979,0.0003896084,0.00001648297],"category_scores_gemma":[0.0002657605,0.0004875409,0.0001094996,0.0007052555,0.0006469667,0.0007795533,0.0006772522,0.0006381827,0.0001030171],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001262763,"about_ca_system_score_gemma":0.0007390997,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002589193,"about_ca_topic_score_gemma":0.0000599653,"domain_scores_codex":[0.9938892,0.0001382852,0.0009520543,0.001640897,0.002866146,0.0005134528],"domain_scores_gemma":[0.9952969,0.0003308638,0.0009371681,0.002211664,0.001113584,0.0001098451],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000003172589,0.0001346596,0.00002115951,0.0000231644,0.00001690703,0.000002019043,0.0002239848,0.04238051,0.0007964142,0.1074263,0.0000177798,0.848954],"study_design_scores_gemma":[0.001321732,0.0001614823,0.0002118961,0.0003278494,0.00003022328,0.000007399385,0.000001083358,0.9738369,0.002964642,0.02009273,0.0005623599,0.0004816847],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.000230999,0.0008572523,0.9931389,0.001029381,0.001636281,0.001177751,0.000006194378,0.0003432932,0.001579909],"genre_scores_gemma":[0.6168596,0.0001067871,0.3817362,0.0002489346,0.0002086772,0.0001068753,0.00001195442,0.00003677127,0.0006842397],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9314564,"threshold_uncertainty_score":0.9997576,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2998605053","doi":"10.1609/aaai.v34i04.6132","title":"Partial Label Learning with Batch Label Correction","year":2020,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":50,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Carleton University","funders":"China Scholarship Council; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Computer science; Consistency (knowledge bases); Artificial intelligence; Machine learning; Set (abstract data type); Multi-label classification; Stability (learning theory)","retraction":null,"screen_n_in":null,"score":{"opus":0.1001122140207756,"gpt":0.2912905940668809,"spread":0.1911783800461053,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001967079,0.0001806597,0.0001926601,0.00006815733,0.0002292888,0.0002881696,0.001512589,0.00008289384,0.00004232773],"category_scores_gemma":[0.0004644689,0.0001260655,0.00004190083,0.0008986824,0.0002317863,0.0005034364,0.00030398,0.0004124158,0.000125786],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002807046,"about_ca_system_score_gemma":0.00007189978,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001495319,"about_ca_topic_score_gemma":0.000002389584,"domain_scores_codex":[0.9984927,0.00001458753,0.0003436798,0.0004638071,0.0004247311,0.0002605612],"domain_scores_gemma":[0.9989077,0.00006181883,0.0003499828,0.0001938216,0.0004085041,0.00007814398],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00009180381,0.0001120243,0.0008126945,0.00001962565,0.00001346318,4.006121e-7,0.001503343,0.00007222029,0.05162746,0.7457023,0.0005376262,0.199507],"study_design_scores_gemma":[0.00005558478,0.0006459429,0.0001130759,0.00008106067,0.000009863948,0.000002589798,0.001163047,0.2351196,0.7455462,0.01630289,0.0007524656,0.0002076963],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3756599,0.00005440888,0.4983231,0.0965308,0.001373588,0.00124282,0.000003545216,0.002239224,0.02457266],"genre_scores_gemma":[0.9956477,0.00002566028,0.003589393,0.0002927013,0.00004813163,0.00002812951,3.401067e-7,0.000009615615,0.0003583429],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7293994,"threshold_uncertainty_score":0.5140801,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1714192071","doi":"","title":"Categorical proportional difference: a feature selection method for text categorization","year":2008,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":47,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Regina","funders":"","keywords":"Artificial intelligence; Computer science; Feature selection; Categorical variable; Word (group theory); Task (project management); Naive Bayes classifier; Mutual information; Natural language processing; Feature (linguistics); Selection (genetic algorithm); Categorization; Measure (data warehouse); Support vector machine; Pattern recognition (psychology); Machine learning; Data mining; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.02953612645523518,"gpt":0.2917414232733742,"spread":0.262205296818139,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001151066,0.0001095135,0.0001112201,0.0001295436,0.0002818085,0.00006946789,0.0003755028,0.0001291801,0.00002358722],"category_scores_gemma":[0.00008052043,0.00008428883,0.00005294949,0.00054741,0.00003550346,0.0003255774,0.00005929843,0.0001052272,0.00001996268],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006985648,"about_ca_system_score_gemma":0.000118856,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001455251,"about_ca_topic_score_gemma":0.000004597076,"domain_scores_codex":[0.9990567,0.00002543867,0.0001604449,0.0003514502,0.0002191942,0.0001867736],"domain_scores_gemma":[0.9994017,0.00006741799,0.00009067329,0.0002153513,0.000182845,0.00004195414],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000006520164,0.00007506644,0.001745282,0.000006419067,0.000008574119,7.503305e-7,0.0001225459,0.00002156465,0.004967832,0.9365674,0.01275043,0.04372763],"study_design_scores_gemma":[0.00116468,0.0004855444,0.08880085,0.000004240161,0.0000181231,0.0002948736,0.0001066156,0.4773076,0.1018567,0.2797098,0.04952803,0.000722897],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001269227,0.00001887073,0.9902875,0.006389541,0.0001435145,0.0003148815,8.113222e-7,0.0008499384,0.0007256875],"genre_scores_gemma":[0.5981073,0.0000144186,0.3902147,0.0001425556,0.00005386302,0.0001786432,0.00002058512,0.000005777752,0.01126218],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6568576,"threshold_uncertainty_score":0.3437199,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2137320444","doi":"","title":"Linear Text Segmentation Using Affinity Propagation","year":2011,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":44,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa","funders":"","keywords":"Affinity propagation; Segmentation; Computer science; Cluster analysis; Pairwise comparison; Graph; Image segmentation; Set (abstract data type); Algorithm; Artificial intelligence; Pattern recognition (psychology); Theoretical computer science; Correlation clustering; Canopy clustering algorithm","retraction":null,"screen_n_in":null,"score":{"opus":0.103551508256095,"gpt":0.2887300140038151,"spread":0.1851785057477202,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009515174,0.00005567117,0.0000444803,0.00007989236,0.00007759623,0.00004461091,0.0003166631,0.00003753374,0.00009112891],"category_scores_gemma":[0.00002086662,0.0000462342,0.00001764593,0.0002455595,0.00002672329,0.0007149649,0.000091211,0.00004202568,0.0001216353],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002802045,"about_ca_system_score_gemma":0.00002393839,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000278093,"about_ca_topic_score_gemma":0.000002855225,"domain_scores_codex":[0.9994957,0.00001687274,0.0001214284,0.0001634444,0.0001083615,0.00009415724],"domain_scores_gemma":[0.999583,0.000009738606,0.00006806014,0.0002717006,0.00004761794,0.00001989906],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000006326068,0.0002257091,0.005663724,0.00001218467,0.00001255373,0.000002326819,0.001702646,0.00002265469,0.05536156,0.7291049,0.0005512977,0.2073341],"study_design_scores_gemma":[0.0002983905,0.0001247139,0.01165032,0.000007772502,0.000006250672,0.000006293556,0.0004488159,0.1310301,0.8291741,0.02640037,0.0005927319,0.0002601528],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07769594,0.000006488826,0.9139084,0.0002097106,0.00009738796,0.0001168889,1.628949e-7,0.0006371516,0.007327894],"genre_scores_gemma":[0.6749741,0.000002560792,0.3247308,0.00004625539,0.000007621531,0.000006301851,8.603411e-7,0.00000200021,0.0002294604],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7738125,"threshold_uncertainty_score":0.1885376,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2131912994","doi":"10.1109/icdew.2007.4401066","title":"Document Representation and Dimension Reduction for Text Clustering","year":2007,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":44,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Dalhousie University","funders":"","keywords":"Cluster analysis; Dimensionality reduction; Computer science; Document clustering; Artificial intelligence; Pattern recognition (psychology); Representation (politics); Context (archaeology); Benchmark (surveying); Word (group theory); Dimension (graph theory); Natural language processing; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.02785592813353458,"gpt":0.3078267137122061,"spread":0.2799707855786715,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002519525,0.00005118533,0.00004886976,0.00009647326,0.00009538406,0.00009624547,0.0001276294,0.0000355154,0.000004375647],"category_scores_gemma":[0.00002651994,0.00004410408,0.00001660649,0.0001410746,0.00002276869,0.0004909618,0.0001091903,0.00002629172,0.000005947546],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002766852,"about_ca_system_score_gemma":0.000004532207,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000107598,"about_ca_topic_score_gemma":0.000004462546,"domain_scores_codex":[0.999424,0.000005443623,0.0001390108,0.0002271151,0.00008821722,0.0001161542],"domain_scores_gemma":[0.9996092,0.00004577156,0.00005218328,0.0002315743,0.00003605157,0.00002517798],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001482485,0.00001657826,0.0002019335,0.000008723651,0.000005199556,5.376764e-7,0.0003344176,0.00001773625,0.04210392,0.2377426,0.001683357,0.7178702],"study_design_scores_gemma":[0.001466735,0.0003680457,0.02085935,0.00002855552,0.00001283034,0.00007821995,0.002283142,0.0428228,0.7828527,0.1269625,0.02177699,0.0004881259],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03816921,0.00004274033,0.9575168,0.002445099,0.0002432149,0.0002159633,7.239156e-8,0.0003627986,0.001004096],"genre_scores_gemma":[0.8472134,0.00002110011,0.1516455,0.00004352581,0.00002076745,0.00001560046,0.000001408148,0.00000251112,0.001036171],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8090442,"threshold_uncertainty_score":0.1798512,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1586413166","doi":"10.3115/1118935.1118941","title":"Text classification in Asian languages without word segmentation","year":2003,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":43,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Text segmentation; Artificial intelligence; Natural language processing; Language model; n-gram; Word (group theory); Segmentation; Feature (linguistics); Character (mathematics); Key (lock); Word lists by frequency; Simple (philosophy); Linguistics; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.02359207191929053,"gpt":0.2946768134136925,"spread":0.2710847414944019,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001789973,0.0000799988,0.00007437186,0.0001903877,0.0000439871,0.0001002619,0.0003096564,0.00005697926,0.00006977552],"category_scores_gemma":[0.00006194756,0.00006986336,0.00001850996,0.0004990756,0.00002871162,0.0005248912,0.00003050026,0.00007548933,0.0001494182],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005958532,"about_ca_system_score_gemma":0.00002831297,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009172792,"about_ca_topic_score_gemma":0.00005453698,"domain_scores_codex":[0.9992299,0.00005088991,0.000175282,0.0002535092,0.0001422209,0.0001482037],"domain_scores_gemma":[0.9994693,0.00002325827,0.00006629037,0.0003926246,0.00002311897,0.00002545138],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[9.394474e-7,0.00004495458,0.02574952,0.000002846835,0.000002122676,0.000001019747,0.0003141345,0.000002514498,0.006358578,0.7895874,0.0005354322,0.1774006],"study_design_scores_gemma":[0.001967231,0.0001244973,0.6795692,0.00004046395,0.00000805998,0.00002004324,0.01662115,0.01026478,0.1942832,0.05119971,0.0449721,0.0009296359],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05588375,0.00009830817,0.7880285,0.005827494,0.0001460504,0.0003321739,3.821639e-7,0.0009798049,0.1487035],"genre_scores_gemma":[0.9187962,0.00001549902,0.07888921,0.0001281774,0.000004569163,0.00004320383,0.000002542957,0.000003892818,0.002116675],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8629125,"threshold_uncertainty_score":0.2848945,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2079238049","doi":"10.1007/s13042-013-0152-x","title":"Bayesian Citation-KNN with distance weighting","year":2013,"lang":"en","type":"article","venue":"International Journal of Machine Learning and Cybernetics","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":41,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of New Brunswick","funders":"National Natural Science Foundation of China","keywords":"Computer science; Artificial intelligence; Bayesian probability; Machine learning; Benchmark (surveying); k-nearest neighbors algorithm; Weighting; Computational intelligence; Field (mathematics); Naive Bayes classifier; Pattern recognition (psychology); Overhead (engineering); Supervised learning; Data mining; Mathematics; Support vector machine; Artificial neural network","retraction":null,"screen_n_in":null,"score":{"opus":0.005946413716180115,"gpt":0.2347103549350663,"spread":0.2287639412188862,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001470449,0.00007826913,0.00009079086,0.0001412213,0.00005942664,0.0003116402,0.0004798704,0.00002925264,0.00003689598],"category_scores_gemma":[0.0001247932,0.00005677878,0.00002637951,0.0001042623,0.0000503248,0.0004147599,0.00007437656,0.0002479344,0.000008882545],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000232482,"about_ca_system_score_gemma":0.00002268322,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001845127,"about_ca_topic_score_gemma":0.000003906746,"domain_scores_codex":[0.999181,0.00003262362,0.0002372678,0.0001053314,0.0003528137,0.00009099802],"domain_scores_gemma":[0.99908,0.0001147423,0.0003335927,0.00007510348,0.0003491192,0.00004744765],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002818348,0.00009628705,0.2188467,0.00001001005,0.0001633769,0.00004747451,0.00142597,0.00080637,0.001047134,0.1824971,0.0007534542,0.5942779],"study_design_scores_gemma":[0.004111325,0.001617369,0.1738011,0.0005041474,0.00005481759,0.001327507,0.001726433,0.5607941,0.003933151,0.103081,0.1480307,0.00101834],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09322374,0.0005244949,0.8923337,0.01125753,0.0002370852,0.00005060288,5.964334e-7,0.00008435667,0.002287913],"genre_scores_gemma":[0.9564636,0.0001662064,0.04249305,0.00008496861,0.00005558087,0.000001823951,0.000001189805,0.000005171444,0.0007284054],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8632399,"threshold_uncertainty_score":0.3005153,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3008638314","doi":"10.1016/j.ijar.2020.02.003","title":"Label distribution learning: A local collaborative mechanism","year":2020,"lang":"en","type":"article","venue":"International Journal of Approximate Reasoning","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":41,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"National Natural Science Foundation of China","keywords":"Robustness (evolution); Ambiguity; Computer science; Artificial intelligence; Machine learning; Feature learning; Representation (politics); Pattern recognition (psychology)","retraction":null,"screen_n_in":null,"score":{"opus":0.0166668925147492,"gpt":0.2669003154745818,"spread":0.2502334229598325,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002589125,0.0001033755,0.0001542499,0.00007968155,0.00006897705,0.0002676037,0.001056982,0.00005863148,0.00001638981],"category_scores_gemma":[0.0004348961,0.00008991195,0.0000597752,0.0003299525,0.0000495066,0.0007825179,0.0002153074,0.0002862126,0.0000176642],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001190011,"about_ca_system_score_gemma":0.0001128019,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001443337,"about_ca_topic_score_gemma":1.305253e-7,"domain_scores_codex":[0.9987615,0.00005165229,0.0003484946,0.0001636791,0.0005411404,0.0001335242],"domain_scores_gemma":[0.9985489,0.00005894844,0.0005253839,0.00008756086,0.0006901376,0.00008902478],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006606374,0.00006092784,0.0002182746,0.000005740266,0.0001142323,0.00008520655,0.0009736781,0.0003666189,0.004263502,0.9099582,0.000950666,0.08293691],"study_design_scores_gemma":[0.003207968,0.001036204,0.0004256582,0.0002456272,0.00003489318,0.0003927986,0.003486695,0.7388716,0.1385707,0.05729422,0.0558857,0.0005478908],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0103459,0.000124048,0.9770364,0.01156121,0.0002919213,0.00005468719,0.000005163762,0.0001488855,0.0004318228],"genre_scores_gemma":[0.9514133,0.0001056167,0.04814651,0.0001814225,0.0001067644,0.000003425551,0.000008482189,0.000006160969,0.00002832346],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9410674,"threshold_uncertainty_score":0.3666503,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2237248385","doi":"10.1007/978-3-642-33460-3_48","title":"Learning and Inference in Probabilistic Classifier Chains with Beam Search","year":2012,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":38,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Inference; Classifier (UML); Probabilistic logic; Artificial intelligence; Machine learning; Beam search; Binary classification; Flexibility (engineering); sort; Algorithm; Search algorithm; Mathematics; Support vector machine; Information retrieval","retraction":null,"screen_n_in":null,"score":{"opus":0.02746902263249762,"gpt":0.2691181450713802,"spread":0.2416491224388826,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008231634,0.0003994194,0.0003956683,0.0009957973,0.0001958015,0.0005018114,0.001745192,0.0003020753,0.00001379223],"category_scores_gemma":[0.0001983296,0.0003209851,0.00003225163,0.000770321,0.001220802,0.0007454033,0.001263227,0.001272833,0.000018738],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000251047,"about_ca_system_score_gemma":0.0003919171,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001879586,"about_ca_topic_score_gemma":0.0001065292,"domain_scores_codex":[0.9970107,0.00003565717,0.0003592398,0.001189529,0.0007192636,0.0006855874],"domain_scores_gemma":[0.9980863,0.0006691149,0.0001747783,0.0007924796,0.0001464579,0.0001308086],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000006108444,0.00003454268,0.005158886,0.00005493297,0.000004933711,0.00002431496,0.001426106,0.007122978,0.0001146909,0.09906332,0.000001374551,0.8869878],"study_design_scores_gemma":[0.001266978,0.001369829,0.01336094,0.001594661,0.00001817358,0.0001187246,0.00001065174,0.7664655,0.002609963,0.2066363,0.003929618,0.002618712],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001992576,0.0005043189,0.9941248,0.0009589508,0.0001981367,0.0004297076,8.666984e-7,0.000269304,0.001521289],"genre_scores_gemma":[0.9145082,0.0001477898,0.08450511,0.0001439227,0.00007223192,0.00002319809,0.000002275284,0.00002044786,0.000576795],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9125156,"threshold_uncertainty_score":0.9999242,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1983349993","doi":"10.1016/j.neunet.2006.12.005","title":"The learning vector quantization algorithm applied to automatic text classification tasks","year":2007,"lang":"en","type":"article","venue":"Neural Networks","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":38,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Vedecká Grantová Agentúra MŠVVaŠ SR a SAV; McGill University","keywords":"Learning vector quantization; Computer science; Artificial intelligence; Classifier (UML); Artificial neural network; Word-sense disambiguation; Categorization; Linde–Buzo–Gray algorithm; Text categorization; Machine learning; Word (group theory); Natural language processing; Pattern recognition (psychology); Vector quantization; Mathematics; WordNet","retraction":null,"screen_n_in":null,"score":{"opus":0.02001477650850889,"gpt":0.2704345014242594,"spread":0.2504197249157505,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005551036,0.0001402388,0.0001105118,0.0001014721,0.0005413569,0.0003880635,0.0008611446,0.0001115257,0.000005617153],"category_scores_gemma":[0.0000868006,0.0001044656,0.00003950821,0.0009203138,0.00005897208,0.0002307173,0.0001653563,0.0002916762,0.00007531566],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006255889,"about_ca_system_score_gemma":0.00001291914,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000338565,"about_ca_topic_score_gemma":0.000007770441,"domain_scores_codex":[0.9986175,0.00004700579,0.0003265078,0.0003435238,0.0002752314,0.0003902242],"domain_scores_gemma":[0.9988171,0.0003310842,0.0001759734,0.000532995,0.00006606085,0.0000767419],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000002928054,0.00001133546,0.0001470745,0.000001369852,0.000004007058,7.436959e-7,0.00008567754,0.005170246,0.0005248782,0.0534569,0.0009567189,0.9396381],"study_design_scores_gemma":[0.0001011706,0.00004974673,0.02280371,0.000004909449,0.000003140761,0.000002553447,0.0001356107,0.9671338,0.000354089,0.0008592818,0.008413307,0.0001387199],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005900348,0.00009799671,0.9880517,0.003230608,0.0005197202,0.0003272012,1.452718e-7,0.001194903,0.0006773683],"genre_scores_gemma":[0.9830504,0.00002428841,0.016226,0.000288734,0.0001246222,0.00004581608,0.000007025697,0.00001221142,0.0002209172],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.97715,"threshold_uncertainty_score":0.4259982,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2214660060","doi":"10.1609/aaai.v25i1.7895","title":"Adaptive Large Margin Training for Multilabel Classification","year":2011,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":37,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Margin (machine learning); Computer science; Exploit; Scalability; Categorization; Machine learning; Generalization; Classifier (UML); Artificial intelligence; Training set; Data mining; Pattern recognition (psychology); Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.3253993417235344,"gpt":0.3314708791762336,"spread":0.006071537452699172,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004898446,0.0001849468,0.0002007543,0.0001438875,0.0002277559,0.0001211881,0.00209165,0.0001139605,0.00004923626],"category_scores_gemma":[0.0003987687,0.0001411194,0.0001114196,0.0004510126,0.0002194031,0.0005372854,0.0002386677,0.0001892954,0.00005679658],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004086635,"about_ca_system_score_gemma":0.0000748836,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008440476,"about_ca_topic_score_gemma":0.000004538885,"domain_scores_codex":[0.9984238,0.000009967471,0.0004598325,0.0004780089,0.0002809375,0.0003475109],"domain_scores_gemma":[0.9984998,0.00008468141,0.0004522441,0.0003468827,0.0005634374,0.00005301669],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00004673809,0.0001195903,0.00006458697,0.0000104784,0.000008516949,4.443264e-8,0.002829134,4.79537e-7,0.01267836,0.8625808,0.0001301402,0.1215312],"study_design_scores_gemma":[0.00005450313,0.0002375066,0.0009234312,0.00007830931,0.00001014865,9.724092e-7,0.004929273,0.0960876,0.4343747,0.4627402,0.0003529842,0.0002103964],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03163686,0.00003070376,0.9170049,0.005141978,0.0006630771,0.001632588,0.00002282687,0.0006484163,0.04321861],"genre_scores_gemma":[0.9638386,0.00001559179,0.03549369,0.0001052603,0.00002372664,0.0001592603,5.912457e-7,0.00001017191,0.0003531343],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9322017,"threshold_uncertainty_score":0.5754681,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2609579487","doi":"10.1007/s11280-017-0460-2","title":"Collaborative text categorization via exploiting sparse coefficients","year":2017,"lang":"en","type":"article","venue":"World Wide Web","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":35,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Computer science; Sparse approximation; Pattern recognition (psychology); Categorization; Artificial intelligence; Classifier (UML); Sparse matrix; Representation (politics); Information retrieval; Data mining","retraction":null,"screen_n_in":null,"score":{"opus":0.01904446666712901,"gpt":0.2666869600097453,"spread":0.2476424933426163,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000180381,0.0001310135,0.0001331556,0.0001945851,0.0007185917,0.0007188632,0.001409987,0.00004425931,0.00003299072],"category_scores_gemma":[0.0002713512,0.0001241996,0.00003082716,0.0004714935,0.0001313225,0.001019404,0.0003947787,0.0001075505,0.0003174217],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006153612,"about_ca_system_score_gemma":0.0000763657,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001744491,"about_ca_topic_score_gemma":0.0001076875,"domain_scores_codex":[0.998906,0.00003104236,0.0002125517,0.0003666638,0.0002404985,0.0002432525],"domain_scores_gemma":[0.9983078,0.00007460759,0.0003229534,0.001093861,0.0001461854,0.00005460116],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001251943,0.0001837013,0.04214465,0.00001737512,0.00003314676,0.00002358771,0.001110046,0.0002077654,0.01168314,0.651364,0.02749866,0.2657214],"study_design_scores_gemma":[0.002493059,0.0001740699,0.09498329,0.0001616374,0.00003188891,0.000007934374,0.0009252041,0.1570261,0.134213,0.05507298,0.5532948,0.001616104],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02720687,0.0001291291,0.9164581,0.01326913,0.001245641,0.0004592788,0.000005538569,0.001342671,0.03988361],"genre_scores_gemma":[0.987865,0.00001582687,0.007503513,0.0001875354,0.00003861269,0.00003819998,0.000005017593,0.000009036043,0.004337231],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9606581,"threshold_uncertainty_score":0.6932015,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1960913922","doi":"10.1007/3-540-44886-1_41","title":"Feature Selection Strategies for Text Categorization","year":2003,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université Laval","funders":"","keywords":"Feature selection; Categorization; Computer science; Selection (genetic algorithm); Text categorization; Feature (linguistics); Rank (graph theory); Artificial intelligence; Set (abstract data type); Filter (signal processing); Function (biology); Representation (politics); Machine learning; Data mining; Pattern recognition (psychology); Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.01843416811592578,"gpt":0.2540111248480112,"spread":0.2355769567320854,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0004275457,0.0004167155,0.0003342142,0.000810865,0.000338848,0.001079387,0.0019822,0.0004907637,0.000009686974],"category_scores_gemma":[0.00008289864,0.0003809681,0.0001022517,0.0007891048,0.0003640897,0.001165555,0.0002784313,0.0005086085,0.00001730028],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003122049,"about_ca_system_score_gemma":0.0005656017,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004119874,"about_ca_topic_score_gemma":0.00003847121,"domain_scores_codex":[0.997418,0.00001787801,0.0002953478,0.001247624,0.0005337835,0.0004873807],"domain_scores_gemma":[0.9982501,0.0002074944,0.0003019304,0.0008295058,0.0003416091,0.00006934546],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000003438444,0.000016466,0.00002315113,0.00003387323,0.000006850931,0.000002293169,0.000207915,0.00684462,0.0004442736,0.6106219,0.0007038043,0.3810914],"study_design_scores_gemma":[0.0002589671,0.0002108866,0.00005062897,0.0000778157,0.000008246497,0.00002646305,0.000001099159,0.1731184,0.00481138,0.7912964,0.02952479,0.0006149675],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00001022032,0.0002910671,0.9914142,0.003683981,0.001215873,0.0005955395,0.000003350098,0.000498282,0.002287447],"genre_scores_gemma":[0.09378729,0.0001003339,0.9001791,0.001651051,0.0003712694,0.00009519058,0.00002717819,0.00005656149,0.003732013],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3804765,"threshold_uncertainty_score":0.9999576,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2077512673","doi":"10.1214/07-ba209","title":"Improving classification when a class hierarchy is available using a hierarchy-based prior","year":2007,"lang":"en","type":"article","venue":"Bayesian Analysis","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Hierarchy; Multinomial logistic regression; Class hierarchy; Computer science; Class (philosophy); Machine learning; Artificial intelligence; Multinomial distribution; Bayesian probability; Tree (set theory); Data mining; Mathematics; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.03222386111863169,"gpt":0.2757000272695841,"spread":0.2434761661509524,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001020241,0.0002750694,0.0003880284,0.001881816,0.0003955406,0.0005062144,0.00138614,0.0002082427,0.0003978417],"category_scores_gemma":[0.000108897,0.0002687766,0.0003562243,0.004043818,0.0001507999,0.0007715565,0.0002030478,0.0002551402,0.0001862748],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004566361,"about_ca_system_score_gemma":0.0002404266,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002604588,"about_ca_topic_score_gemma":0.00007222577,"domain_scores_codex":[0.997104,0.00008442237,0.000655738,0.0009307492,0.0006031868,0.0006218944],"domain_scores_gemma":[0.9973353,0.0001476378,0.0004509182,0.001688691,0.0001953619,0.0001821662],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001142314,0.0008372234,0.06725814,0.0001566827,0.001720859,0.0001053697,0.002341725,0.0002581308,0.09966429,0.2137783,0.01151895,0.602246],"study_design_scores_gemma":[0.0004261737,0.00004897438,0.003992012,0.00001304357,0.0003362149,0.000003115822,0.0002111167,0.9663775,0.01684521,0.002210925,0.00907199,0.0004637044],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005505625,0.0001401087,0.9868657,0.002653972,0.00007227575,0.0002356449,0.000005182279,0.0007410078,0.003780468],"genre_scores_gemma":[0.696539,0.000006364703,0.3011951,0.0005787318,0.00003598466,0.00001730749,0.00001422289,0.00001642582,0.001596859],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9661194,"threshold_uncertainty_score":0.9999765,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W160585330","doi":"10.1007/978-3-642-33486-3_23","title":"Semi-supervised Multi-label Classification","year":2012,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":33,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Artificial intelligence; Semi-supervised learning; Machine learning; Subspace topology; Margin (machine learning); Supervised learning; Classifier (UML); Exploit; Pattern recognition (psychology); Labeled data; Unsupervised learning; Artificial neural network","retraction":null,"screen_n_in":null,"score":{"opus":0.0571843465909377,"gpt":0.2826659220794802,"spread":0.2254815754885425,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007503417,0.0005427862,0.0004487654,0.001005178,0.0002964155,0.0005976837,0.004617332,0.0005427954,0.00004498823],"category_scores_gemma":[0.0001160075,0.0004943804,0.0001055686,0.0007745311,0.0007952281,0.001276826,0.001360226,0.0008287122,0.0003111232],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004009773,"about_ca_system_score_gemma":0.0003430645,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007483461,"about_ca_topic_score_gemma":0.00001663482,"domain_scores_codex":[0.9962173,0.00003080668,0.0005937408,0.001492857,0.0009106702,0.0007546007],"domain_scores_gemma":[0.9966778,0.0002691968,0.0003791672,0.002241803,0.0002529122,0.0001790924],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000001665067,0.00005835531,0.0001313699,0.00001780061,0.000006270981,0.000005417397,0.0002953351,0.0001234575,0.001219541,0.08054773,0.00004445955,0.9175486],"study_design_scores_gemma":[0.0005906204,0.0001003398,0.0009454819,0.000180606,0.00001205827,0.00002914229,7.741262e-7,0.902124,0.004002756,0.08481736,0.006180732,0.001016113],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0000532722,0.001205289,0.991672,0.002160062,0.001377007,0.0004404295,0.000004103037,0.0008058753,0.0022819],"genre_scores_gemma":[0.1757311,0.0002655489,0.821204,0.0009873203,0.0003162793,0.00003985183,0.00001423105,0.00004601895,0.00139566],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9165325,"threshold_uncertainty_score":0.9997508,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3194282644","doi":"10.1186/s10033-021-00598-9","title":"ML-ANet: A Transfer Learning Approach Using Adaptation Network for Multi-label Image Classification in Autonomous Driving","year":2021,"lang":"en","type":"article","venue":"Chinese Journal of Mechanical Engineering","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":31,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"Shenzhen Fundamental Research and Discipline Layout project; National Natural Science Foundation of China","keywords":"Reproducing kernel Hilbert space; Artificial intelligence; Computer science; Pattern recognition (psychology); Transfer of learning; Kernel (algebra); Embedding; Image (mathematics); Domain adaptation; Feature (linguistics); Adaptation (eye); Matching (statistics); Mathematics; Hilbert space; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.04901093335217047,"gpt":0.2809918205667821,"spread":0.2319808872146116,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008213824,0.0001629168,0.000301385,0.0001938143,0.00007364069,0.0001399399,0.0004100465,0.0001227111,0.000002170147],"category_scores_gemma":[0.0006802034,0.0001428912,0.0001139283,0.0006505845,0.000009771564,0.0006837826,0.00006253903,0.0004297253,6.268866e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001333867,"about_ca_system_score_gemma":0.00009779524,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001420699,"about_ca_topic_score_gemma":0.000002541036,"domain_scores_codex":[0.9986568,0.00005708219,0.0005886953,0.0002380976,0.0002036824,0.000255624],"domain_scores_gemma":[0.9992186,0.0001838866,0.000158716,0.0001935252,0.0001770292,0.00006827673],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001363302,0.000193952,0.0002277168,0.00007284222,0.00004148192,0.00001974484,0.000494451,0.6813008,0.2494347,0.03212643,0.000006641615,0.03606763],"study_design_scores_gemma":[0.0008378755,0.00004674399,0.0009509714,0.00007317433,0.00001119606,0.00006526412,0.0001050734,0.9950806,0.001909843,0.0007086266,0.00006249658,0.0001480692],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08756585,0.0002688186,0.9114491,0.0002137872,0.0002697309,0.0001155729,3.524793e-7,0.0001095683,0.000007271689],"genre_scores_gemma":[0.5091503,0.00002160036,0.4907269,0.000008173273,0.00006471974,0.000006997091,0.000001866288,0.00001143286,0.000008017878],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.4215844,"threshold_uncertainty_score":0.5826935,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2340990333","doi":"10.1177/0165551515625030","title":"The impact of indexing approaches on Arabic text classification","year":2016,"lang":"en","type":"article","venue":"Journal of Information Science","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of New Brunswick","funders":"","keywords":"Computer science; Classifier (UML); Search engine indexing; Arabic; Artificial intelligence; Naive Bayes classifier; Natural language processing; Pattern recognition (psychology); Word (group theory); Mathematics; Support vector machine","retraction":null,"screen_n_in":null,"score":{"opus":0.06173573844272501,"gpt":0.3028807703285067,"spread":0.2411450318857817,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001925785,0.0000642427,0.00008728581,0.00047141,0.0002182553,0.0002808968,0.001647536,0.00003108321,0.000002960765],"category_scores_gemma":[0.0009535845,0.00002670527,0.00007534585,0.0009720784,0.0003892191,0.007358836,0.0000861912,0.00008971629,0.00002589624],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001706905,"about_ca_system_score_gemma":0.0003520497,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000001058237,"about_ca_topic_score_gemma":9.833091e-8,"domain_scores_codex":[0.9985344,0.00002216669,0.0005558532,0.00006602269,0.0006744868,0.000147108],"domain_scores_gemma":[0.9976785,0.0002250174,0.001181632,0.0003840883,0.0004817612,0.00004904726],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00001484388,0.00001988695,0.001503164,0.000001954023,0.000005814164,7.022848e-8,0.0005077799,0.0001607187,0.007371659,0.3357193,0.0004556811,0.6542391],"study_design_scores_gemma":[0.001428404,0.00144186,0.7550424,0.0002279804,0.000006886482,0.00009764985,0.002360692,0.05217132,0.1330754,0.04635817,0.007416472,0.0003727837],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2316907,0.00002968422,0.7531817,0.006925679,0.0002985455,0.0001329954,0.000001117662,0.00005438854,0.007685232],"genre_scores_gemma":[0.9970692,0.0000518655,0.002817614,0.00001998854,0.00001152843,0.000002011898,5.274321e-8,9.050483e-7,0.00002679051],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7653786,"threshold_uncertainty_score":0.5334978,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4390873538","doi":"10.1109/iccv51070.2023.00166","title":"Parametric Information Maximization for Generalized Category Discovery","year":2023,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Institut National de la Recherche Scientifique; Thales (Canada)","funders":"","keywords":"Parameterized complexity; Maximization; Computer science; Parametric statistics; Mutual information; Class (philosophy); Code (set theory); Data mining; Nonparametric statistics; Artificial intelligence; Theoretical computer science; Machine learning; Algorithm; Mathematics; Mathematical optimization; Statistics; Set (abstract data type); Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.02811367513141904,"gpt":0.2630281952364658,"spread":0.2349145201050468,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001433308,0.00005834184,0.00006118869,0.0004245253,0.00008417819,0.0003547833,0.000384684,0.00004715532,0.000005934819],"category_scores_gemma":[0.0001376961,0.00004819731,0.00003492632,0.001346285,0.00001448916,0.002843036,0.00009932434,0.00002496323,0.0001969352],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002426299,"about_ca_system_score_gemma":0.00002628481,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000934626,"about_ca_topic_score_gemma":8.891717e-7,"domain_scores_codex":[0.9994488,0.000008360731,0.000167612,0.0001153472,0.0001220693,0.0001378133],"domain_scores_gemma":[0.9994981,0.00006801845,0.00007022222,0.0002906657,0.00005617487,0.00001679356],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000002084478,0.000005972801,0.0001220411,0.000009502709,0.000003376825,7.38619e-8,0.0000532007,0.0005313189,0.00009074639,0.9067972,0.02110966,0.07127482],"study_design_scores_gemma":[0.0008362008,0.00007470295,0.007636096,0.000003059465,0.000006563677,0.000001258029,0.0002167103,0.6684316,0.01266004,0.239006,0.07084309,0.0002846067],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.004697946,0.0000100352,0.9889295,0.002798849,0.0002194229,0.0002345701,0.000002305891,0.00163326,0.001474118],"genre_scores_gemma":[0.916238,0.00009073549,0.07762641,0.0005010086,0.00002225492,0.0002848356,0.0001637218,0.00000573037,0.005067314],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.91154,"threshold_uncertainty_score":0.3421184,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1997305228","doi":"10.1109/nlpke.2010.5587767","title":"Automatic classification of documents by formality","year":2010,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":29,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa","funders":"","keywords":"Formality; Computer science; Naive Bayes classifier; Artificial intelligence; Feature selection; Classifier (UML); Support vector machine; Machine learning; Decision tree; Task (project management); Style (visual arts); Data mining; Natural language processing; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.01347406047579485,"gpt":0.2704840205753174,"spread":0.2570099600995225,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001966331,0.00006472514,0.00008244859,0.0000653203,0.00004533733,0.00006487712,0.000809258,0.00006734557,0.0001627271],"category_scores_gemma":[0.0000509823,0.00005233012,0.00002959484,0.0002314934,0.0000678534,0.0007026963,0.0001180665,0.00009331443,0.00006398232],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009688242,"about_ca_system_score_gemma":0.00002105556,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001435847,"about_ca_topic_score_gemma":0.000005142414,"domain_scores_codex":[0.9992801,0.00001189214,0.0002368409,0.0001674904,0.0001862287,0.0001174461],"domain_scores_gemma":[0.9990735,0.00003582803,0.0001405111,0.0006668997,0.00005240953,0.00003085379],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[3.388631e-7,0.00005873408,0.00234162,0.00000768875,0.000003952166,4.678316e-8,0.00004432114,4.087409e-8,0.1432511,0.6935045,0.008083038,0.1527046],"study_design_scores_gemma":[0.0005884039,0.00009949904,0.1620238,0.000008327847,0.000007644092,0.00000461413,0.0001565116,0.08397029,0.6330305,0.0816893,0.03806393,0.0003571843],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5423102,0.00001550898,0.4282617,0.004654074,0.000331241,0.0002125033,0.000002427867,0.001136617,0.02307563],"genre_scores_gemma":[0.9631925,0.000003484185,0.03603388,0.0000486146,0.000003667971,0.00001814414,0.000003362859,0.000002168184,0.0006941524],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6118152,"threshold_uncertainty_score":0.213396,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3086863200","doi":"10.1002/ett.3977","title":"Digital Hadith authentication: Recent advances, open challenges, and future directions","year":2020,"lang":"en","type":"article","venue":"Transactions on Emerging Telecommunications Technologies","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Northern British Columbia","funders":"Deanship of Scientific Research, King Saud University","keywords":"Authentication (law); Islam; Computer science; Field (mathematics); Legislation; Task (project management); Computer security; Political science; Law; History; Engineering; Systems engineering; Mathematics; Archaeology","retraction":null,"screen_n_in":null,"score":{"opus":0.04322460988914023,"gpt":0.2839163424881219,"spread":0.2406917325989817,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001240388,0.0002451139,0.0002377658,0.0003071878,0.0008265331,0.000377937,0.00368624,0.0001732517,0.00003436268],"category_scores_gemma":[0.00008974242,0.0002380493,0.00005824344,0.001245411,0.000271652,0.00200325,0.0003110984,0.0005428162,0.00006700899],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007230751,"about_ca_system_score_gemma":0.0000529771,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002131314,"about_ca_topic_score_gemma":0.00001303242,"domain_scores_codex":[0.9985072,0.00004879073,0.0003676384,0.0006089652,0.0001914986,0.0002759127],"domain_scores_gemma":[0.9974856,0.0001342196,0.0001709482,0.002014266,0.0001208577,0.00007408549],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000004672271,0.000130386,0.000004944821,0.000008809824,0.00002795175,3.582745e-7,0.0005641218,0.00001162019,0.00002884965,0.08633071,0.0002732982,0.9126143],"study_design_scores_gemma":[0.0002509614,0.0001287189,0.0002053918,0.00001753221,0.00001415898,0.000008652756,0.003829202,0.001673904,0.0008890777,0.01053072,0.982165,0.000286618],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"review","genre_scores_codex":[0.0000664896,0.04576434,0.3035754,0.6325813,0.0001770041,0.0006909604,0.00003294115,0.008055569,0.00905601],"genre_scores_gemma":[0.2332804,0.6377399,0.1273368,0.0004415229,0.00002966432,0.0007777677,0.00002289764,0.00003589755,0.0003350913],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.9818918,"threshold_uncertainty_score":0.9707369,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2943818116","doi":"10.5539/mas.v13n5p88","title":"Arabic Text Classification: A Review","year":2019,"lang":"en","type":"review","venue":"Modern Applied Science","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Computer science; Arabic; Weighting; Artificial intelligence; Classifier (UML); Decision tree; Natural language processing; Naive Bayes classifier; Support vector machine; Set (abstract data type); Data mining; Information retrieval; Machine learning; Linguistics","retraction":null,"screen_n_in":null,"score":{"opus":0.126081744370099,"gpt":0.3611282266457068,"spread":0.2350464822756078,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001259743,0.0005413587,0.001443191,0.0005965381,0.0003527761,0.0006251535,0.009007856,0.0002532192,0.00003727962],"category_scores_gemma":[0.0001117071,0.0004152638,0.0002965436,0.003893566,0.0006560829,0.0007572682,0.001295435,0.0005560976,0.003685707],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003545083,"about_ca_system_score_gemma":0.00148235,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":7.160332e-7,"about_ca_topic_score_gemma":2.243566e-7,"domain_scores_codex":[0.9952954,0.00004940388,0.0008738509,0.001936239,0.001167787,0.0006772854],"domain_scores_gemma":[0.9947302,0.0001401127,0.0008177595,0.004012514,0.0001440819,0.0001553113],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[1.193034e-7,0.0000204663,7.418936e-8,0.005872312,0.000005479724,6.149835e-7,0.0000155487,1.091536e-7,0.00002830046,0.1398639,0.001461939,0.8527312],"study_design_scores_gemma":[0.00005144958,0.00001249527,0.000002098273,0.006011493,0.00007633518,0.00001760396,0.000003625637,0.002596942,0.000006325237,0.0032284,0.9874792,0.0005140384],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[1.035126e-8,0.7031172,0.2794556,0.0004388326,0.0002496741,0.001243543,0.000002915918,0.0006487193,0.01484354],"genre_scores_gemma":[0.00004719185,0.9900385,0.006960151,0.0004230099,0.00003492555,0.0006795048,0.00001141839,0.00002633916,0.001778949],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9860172,"threshold_uncertainty_score":0.9998299,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2143765837","doi":"10.1109/icmla.2005.47","title":"Multi-label Associative Classification of Medical Documents from MEDLINE","year":2006,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Associative property; Information retrieval; Document classification; Point (geometry); Multi-label classification; Data mining; Artificial intelligence; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.03854488586979353,"gpt":0.3163884499854844,"spread":0.2778435641156908,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003008053,0.0001061466,0.000165792,0.0001029578,0.00005316602,0.00006655899,0.001216455,0.0001795121,0.0001774125],"category_scores_gemma":[0.0001763441,0.00008704019,0.00003995423,0.000361833,0.00009182923,0.0004218582,0.0002398385,0.0001196547,0.00008544898],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006502577,"about_ca_system_score_gemma":0.00006503225,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006328996,"about_ca_topic_score_gemma":0.0001301447,"domain_scores_codex":[0.9982793,0.00004921057,0.0003993041,0.0003135621,0.0007954694,0.0001631024],"domain_scores_gemma":[0.9989641,0.000164985,0.0002609776,0.0004532489,0.0001124406,0.0000442638],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000004604371,0.000942214,0.02920754,0.000006074058,0.00005217219,0.000003090062,0.0002174181,9.237917e-7,0.02528161,0.7357659,0.01852513,0.1899933],"study_design_scores_gemma":[0.002729057,0.00007521427,0.3235673,0.00003427048,0.00001565621,8.686605e-7,0.0003309346,0.5488092,0.05867723,0.06091833,0.004463778,0.0003782382],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06091245,0.00014201,0.9194327,0.01448188,0.0002197576,0.0001630069,0.00001300775,0.0006617251,0.003973442],"genre_scores_gemma":[0.7865039,0.00003622807,0.2117833,0.0001247179,0.00003347116,0.00002230916,0.0000404316,0.000005177011,0.001450491],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7255914,"threshold_uncertainty_score":0.3549396,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2979091142","doi":"10.5539/mas.v13n11p31","title":"Application of Naïve Bayes, Decision Tree, and K-Nearest Neighbors for Automated Text Classification","year":2019,"lang":"en","type":"article","venue":"Modern Applied Science","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":27,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Computer science; Naive Bayes classifier; Decision tree; k-nearest neighbors algorithm; Artificial intelligence; Precision and recall; Data mining; Tree (set theory); Process (computing); Arabic; Bayes' theorem; Machine learning; The Internet; Translation (biology); Pattern recognition (psychology); Bayesian probability; Mathematics; Support vector machine; World Wide Web","retraction":null,"screen_n_in":null,"score":{"opus":0.01284137028378582,"gpt":0.2646484026858366,"spread":0.2518070324020507,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005419906,0.0001328574,0.0001715104,0.000295156,0.000190348,0.0001790237,0.001296561,0.00008836005,0.000002321419],"category_scores_gemma":[0.000064383,0.0001178667,0.00002829928,0.0009856054,0.0003441936,0.000582686,0.0002640872,0.00006951325,0.00003476748],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006805326,"about_ca_system_score_gemma":0.0001075627,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006212731,"about_ca_topic_score_gemma":0.000003428471,"domain_scores_codex":[0.9982244,0.000007275223,0.000310213,0.0007410896,0.0004542385,0.0002627903],"domain_scores_gemma":[0.9984378,0.0001721786,0.0002469464,0.0009196653,0.0001549341,0.00006846969],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001030517,0.00003017421,0.0006972809,0.00001180993,0.000001461611,2.044876e-8,0.0001370287,0.00008415223,0.4028614,0.2612362,0.00006481834,0.3348653],"study_design_scores_gemma":[0.0003357846,0.00004514137,0.0346214,0.000007568352,0.000002664366,9.252128e-7,0.0000663898,0.9058512,0.02380971,0.03456743,0.0005575649,0.0001342222],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06252325,0.00004027276,0.9336798,0.0003640086,0.00007790313,0.0007823789,0.000003433037,0.0006392277,0.001889721],"genre_scores_gemma":[0.9126067,0.00001068475,0.08712852,0.00004641093,0.000005802751,0.0001380513,0.000004135278,0.000007137273,0.00005259382],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.905767,"threshold_uncertainty_score":0.4806464,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3009458272","doi":"10.7717/peerj-cs.261","title":"An evolutionary decomposition-based multi-objective feature selection for multi-label classification","year":2020,"lang":"en","type":"article","venue":"PeerJ Computer Science","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Ontario Tech University","funders":"","keywords":"Computer science; Feature selection; Multi-label classification; Artificial intelligence; Feature (linguistics); Data mining; Selection (genetic algorithm); Field (mathematics); Machine learning; Evolutionary algorithm; Genetic algorithm; Pattern recognition (psychology); Optimization problem; Mathematics; Algorithm","retraction":null,"screen_n_in":null,"score":{"opus":0.0639818680707189,"gpt":0.3394460651024501,"spread":0.2754641970317312,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003752646,0.0002262307,0.0001836983,0.0003060418,0.0008421026,0.0005839603,0.002138096,0.0001177598,0.000003105057],"category_scores_gemma":[0.0001114997,0.0002207839,0.00007169111,0.001922263,0.000323073,0.002167139,0.000189955,0.0002073007,0.00003361106],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002374463,"about_ca_system_score_gemma":0.0004140735,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008670199,"about_ca_topic_score_gemma":0.000004649314,"domain_scores_codex":[0.9975435,0.00006344998,0.0002605851,0.001185334,0.0005177491,0.0004293905],"domain_scores_gemma":[0.9981498,0.00009847568,0.0002055604,0.0005769397,0.0007371023,0.0002321798],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001122891,0.002148129,0.0129816,0.00009700658,0.00004045316,0.000003773885,0.002778848,0.01115243,0.3210153,0.1287898,0.008124213,0.5127561],"study_design_scores_gemma":[0.0009078244,0.0003928248,0.03554131,0.000009347048,0.000005629405,0.000004388469,0.00003245917,0.9475176,0.0144527,0.0004104572,0.0004528293,0.0002725922],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005797497,0.0000424049,0.9820167,0.009660914,0.0004218147,0.0006151589,0.000009452894,0.001423598,0.00001245969],"genre_scores_gemma":[0.4275707,0.000001299969,0.57139,0.0008397424,0.00007439216,0.00008560067,0.00001506099,0.000007122189,0.00001604827],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9363652,"threshold_uncertainty_score":0.9003305,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W49807964","doi":"","title":"A simple feature selection method for text classification","year":2001,"lang":"en","type":"article","venue":"International Joint Conference on Artificial Intelligence","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université Laval","funders":"","keywords":"Feature selection; Computer science; Information gain; Feature (linguistics); Simple (philosophy); Set (abstract data type); Artificial intelligence; Selection (genetic algorithm); Pattern recognition (psychology); Data mining; Feature extraction; Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.1510900227271396,"gpt":0.3835078255874474,"spread":0.2324178028603078,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004294358,0.0002243549,0.0001898155,0.0003890519,0.0002160705,0.0005579018,0.001211665,0.0001662892,0.0002508794],"category_scores_gemma":[0.0004357975,0.0002130757,0.0001310681,0.0005185675,0.00007544675,0.000615337,0.0001189899,0.0002535256,0.0003496277],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001763135,"about_ca_system_score_gemma":0.0001081762,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003000382,"about_ca_topic_score_gemma":0.00005887542,"domain_scores_codex":[0.9980019,0.00006280678,0.0004736558,0.0006989729,0.0004494225,0.0003132412],"domain_scores_gemma":[0.9982961,0.0002062664,0.0002849587,0.0004565737,0.0006754443,0.00008068897],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000318615,0.00008534625,0.00005186684,0.000002036264,0.00001337399,0.000001070502,0.00007666352,0.0001168624,0.0157699,0.6268655,0.001189392,0.3557961],"study_design_scores_gemma":[0.00004645118,0.0001492551,0.0007683095,0.00001948851,0.000004662375,0.00001413243,0.0002564202,0.546196,0.06476967,0.3614761,0.02607468,0.0002247993],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0009265626,0.000008568831,0.9591491,0.0315516,0.0006988092,0.0004118876,0.00001064887,0.00055733,0.006685445],"genre_scores_gemma":[0.8898557,0.00006470622,0.1076037,0.0006159761,0.0001813968,0.0002411114,0.00003488724,0.00001362386,0.001388859],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8889292,"threshold_uncertainty_score":0.8688976,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2808417254","doi":"10.24963/ijcai.2018/395","title":"Does Tail Label Help for Large-Scale Multi-Label Learning","year":2018,"lang":"en","type":"article","venue":"","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Novelis (Canada)","funders":"Fundamental Research Funds for the Central Universities; National Natural Science Foundation of China","keywords":"Trimming; Computer science; Multi-label classification; Artificial intelligence; Scale (ratio); Machine learning; Learning to rank; Fraction (chemistry); Pattern recognition (psychology); Ranking (information retrieval)","retraction":null,"screen_n_in":null,"score":{"opus":0.03686393115797922,"gpt":0.3014385748661733,"spread":0.2645746437081941,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001995015,0.0001093429,0.0001098073,0.0000878964,0.0003070493,0.0001838454,0.000775633,0.00008667797,0.0000703437],"category_scores_gemma":[0.0001179525,0.00006657001,0.00003218123,0.0002496367,0.00007124947,0.0004548083,0.0002939961,0.00009391988,0.000277458],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002149905,"about_ca_system_score_gemma":0.00002316359,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007718696,"about_ca_topic_score_gemma":0.00005918437,"domain_scores_codex":[0.9989955,0.00001785746,0.0001662195,0.0003683501,0.0001333784,0.0003187121],"domain_scores_gemma":[0.9992258,0.00006933646,0.00007654189,0.0004393662,0.0001443102,0.00004464067],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001547891,0.0005925569,0.01624694,0.00003283026,0.00003258704,0.000001169179,0.00154642,0.000001095371,0.01747069,0.4229915,0.02688005,0.5141887],"study_design_scores_gemma":[0.002348738,0.0004263899,0.001329055,0.0000153078,0.000007242951,0.000001384235,0.001880986,0.6014906,0.07006983,0.009781491,0.3122219,0.0004271182],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.008930873,0.00003337544,0.9833918,0.004310662,0.0003916256,0.0002038987,0.0000021806,0.001507186,0.00122845],"genre_scores_gemma":[0.3193729,0.00001461144,0.6401939,0.0003892918,0.0000793107,0.00007640252,0.000003367237,0.0000101663,0.03986007],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6014895,"threshold_uncertainty_score":0.3566255,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4327499178","doi":"10.1007/978-3-031-28241-6","title":"Advances in Information Retrieval","year":2023,"lang":"en","type":"book","venue":"Lecture notes in computer science","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Leibniz-Gemeinschaft; University of Massachusetts Amherst; City, University of London; National Institute of Standards and Technology; La Rochelle Université; National Institute of Informatics; Indian Institute of Science Education and Research Mohali; University of Chinese Academy of Sciences; National Institute of Technology Hamirpur; Université de Lyon; Masarykova Univerzita; Ural Federal University; Université de Nantes; Stockholms Universitet; Institut National des Sciences Appliquées de Lyon; Universität Duisburg-Essen; Università di Pisa; Technische Universität Berlin; Bauhaus-Universität Weimar; Universidad de Granada; Università di Bologna; Universität Regensburg; Universitetet i Bergen; University of Windsor; Technische Universität Wien; Radboud Universiteit; University of Waterloo; Commonwealth Scientific and Industrial Research Organisation; Orta Doğu Teknik Üniversitesi; Instituto Superior Técnico; Université de Bretagne Occidentale; Tsinghua University; Chinese Academy of Sciences; Birkbeck, University of London; Universidade de Lisboa; Renmin University of China; Universität Innsbruck; Technische Universiteit Delft; Région Normandie; University of Minnesota; TU Graz, Internationale Beziehungen und Mobilitätsprogramme; Universiteit Utrecht; RMIT University; Haute école Spécialisée de Suisse Occidentale; University of Southampton; Universidade da Coruña; Istituto di Scienza e Tecnologie dell'Informazione; Universidad Nacional de Educación a Distancia; Universiteit Leiden; York University; University of Glasgow; Universität Passau; Universidade do Porto; Dublin City University; Politecnico di Torino; Friedrich-Schiller-Universität Jena; Universitetet i Stavanger; University of Regina; Université Grenoble Alpes; University of Southern Maine; Centre National de la Recherche Scientifique; University of Roehampton; Norges Teknisk-Naturvitenskapelige Universitet; Sun Yat-sen University; Universiteit van Amsterdam; Universidade de Santiago de Compostela; Università degli Studi di Cagliari; Aix-Marseille Université; University of Wolverhampton; Universidade Federal de Minas Gerais; Chinese University of Hong Kong; Aalborg Universitet; Kaiser Permanente; Indian Institute of Technology Kharagpur; Indian Institute of Science; Qatar University; Universidad Autónoma de Madrid; University of Tsukuba; Georgetown University; Universitatea din București; Università degli Studi di Padova; Zürcher Hochschule für Angewandte Wissenschaften; Johns Hopkins University; Indian National Science Academy","keywords":"Computer science; Information retrieval; State (computer science); Artificial intelligence; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.01286416010257471,"gpt":0.2606042818289115,"spread":0.2477401217263368,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008405329,0.0002899569,0.0003169416,0.001928779,0.0001170708,0.0006179182,0.00362444,0.0003012306,0.000004170675],"category_scores_gemma":[0.0003792703,0.0002671153,0.0000567943,0.003257431,0.0004240106,0.0038951,0.001193172,0.0006715202,0.000205523],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005548968,"about_ca_system_score_gemma":0.0007918752,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004471214,"about_ca_topic_score_gemma":0.00004366994,"domain_scores_codex":[0.9973144,0.00002771435,0.0005445898,0.0007289505,0.0008652672,0.0005191119],"domain_scores_gemma":[0.9980711,0.0003943428,0.0002843942,0.001059126,0.0001329404,0.00005803732],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00000333091,0.0000103197,0.00009167994,0.0000377178,9.225093e-7,0.00001165506,0.0004535663,0.00712844,0.00001097535,0.01443888,0.0001625133,0.97765],"study_design_scores_gemma":[0.0003915283,0.0001386987,0.0009093247,0.0003928367,0.000001892329,0.00001236045,0.000001322107,0.3398017,0.001287002,0.6325015,0.02386153,0.0007003275],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00002860165,0.0003865315,0.9923408,0.001335664,0.00170102,0.0003046065,0.00000244005,0.0007023911,0.003197934],"genre_scores_gemma":[0.1609375,0.004221642,0.8224877,0.004659752,0.001015355,0.0001399069,0.0001206056,0.0001083941,0.006309245],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9769497,"threshold_uncertainty_score":0.9999781,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3108841339","doi":"10.1109/tcyb.2020.3032707","title":"Semisupervised Learning via Axiomatic Fuzzy Set Theory and SVM","year":2020,"lang":"en","type":"article","venue":"IEEE Transactions on Cybernetics","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"National Key Research and Development Program of China; National Natural Science Foundation of China","keywords":"Interpretability; Artificial intelligence; Computer science; Support vector machine; Machine learning; Fuzzy logic; Exploit; Classifier (UML); Schema (genetic algorithms); Set (abstract data type); Frame (networking); Natural language processing; Data mining","retraction":null,"screen_n_in":null,"score":{"opus":0.02293823256316044,"gpt":0.2413329743429583,"spread":0.2183947417797979,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001427309,0.0001435073,0.0001341973,0.00008448449,0.0001741368,0.0001335103,0.0004151625,0.00009183195,0.00004718242],"category_scores_gemma":[0.00001984167,0.0001372734,0.00004934832,0.0003506058,0.00008893931,0.0002068661,0.000007016463,0.0002824827,0.0001325174],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001941039,"about_ca_system_score_gemma":0.00001962049,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003347034,"about_ca_topic_score_gemma":0.000001544505,"domain_scores_codex":[0.9990218,0.0000982978,0.0001927418,0.0003162754,0.0001905038,0.0001803519],"domain_scores_gemma":[0.9992989,0.0002131478,0.00005527507,0.0002969925,0.00003153354,0.0001041389],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00007097363,0.0002259532,0.000140792,0.0001679169,0.0001362705,0.00002129558,0.01284129,0.007657104,0.03441811,0.07390473,0.0007178151,0.8696977],"study_design_scores_gemma":[0.002748051,0.001686371,0.001342907,0.0001275276,0.0001601113,0.00007195514,0.002995345,0.5963575,0.3041343,0.07650633,0.01219431,0.001675257],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02101179,0.00008165748,0.9741805,0.002981866,0.0001178152,0.0001302255,0.000002414471,0.0007974752,0.0006963057],"genre_scores_gemma":[0.9905785,0.0001144426,0.008356292,0.0004699154,0.00001341948,0.00001973454,8.885416e-7,0.00001246789,0.0004343121],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9695668,"threshold_uncertainty_score":0.5597845,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}