{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":70,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":70,"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":"d932170372cf","filters":{"venue":"Text REtrieval Conference"}},"results":[{"id":"W2294145134","doi":"","title":"Overview of the TREC 2009 Web Track","year":2009,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":94,"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; Information retrieval; Relevance (law); Task (project management); World Wide Web; Clef; Session (web analytics); Web page; Set (abstract data type); Search engine indexing; Query expansion","retraction":null,"screen_n_in":null,"score":{"opus":0.07088538982854531,"gpt":0.3088896404462865,"spread":0.2380042506177412,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004543763,0.0001514952,0.0002217576,0.00008019483,0.0001259549,0.0001380988,0.001585726,0.00008695435,0.0002486268],"category_scores_gemma":[0.0001498203,0.00009915593,0.0001428233,0.00104194,0.00009826345,0.0005909562,0.000149827,0.0002629655,0.0001366591],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003761409,"about_ca_system_score_gemma":0.000427779,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000103657,"about_ca_topic_score_gemma":0.00000314765,"domain_scores_codex":[0.9982626,0.00009596199,0.0004066919,0.0002232816,0.0007059554,0.000305472],"domain_scores_gemma":[0.9985422,0.00006436472,0.0001878406,0.0007459125,0.0003539263,0.0001057654],"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":[0.0001049974,0.0002818466,0.001012261,0.00007809139,0.00001730235,0.000009825684,0.002425437,0.00001132835,0.02657913,0.5875516,0.003571629,0.3783565],"study_design_scores_gemma":[0.003571992,0.002038413,0.5455216,0.0006108407,0.00007687527,0.000125097,0.0002037698,0.06355919,0.268313,0.0316722,0.08269104,0.001616001],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8756815,0.001441493,0.03274683,0.01211961,0.00114509,0.001409233,0.00007430393,0.0005071023,0.07487483],"genre_scores_gemma":[0.9966022,0.0001219281,0.0007620483,0.0007134377,0.00002337445,0.000001053247,0.000001526343,0.000003018302,0.00177136],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5558794,"threshold_uncertainty_score":0.4043461,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W305879088","doi":"","title":"Domain-specific synonym expansion and validation for biomedical information retrieval (multitext experiments for trec 2004)","year":2004,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":45,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Synonym (taxonomy); Information retrieval; Domain (mathematical analysis); Natural language processing; Artificial intelligence; Biology; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.03568668182173386,"gpt":0.3012554734088946,"spread":0.2655687915871607,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003877986,0.0002138572,0.000227439,0.00009061299,0.0001860242,0.00009080678,0.0001916634,0.0003938933,0.00002975397],"category_scores_gemma":[0.0003031413,0.0001889045,0.00008709596,0.0001407843,0.0003003449,0.00002646281,0.00007785072,0.00009768,0.00001172986],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005549481,"about_ca_system_score_gemma":0.0001980731,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000651369,"about_ca_topic_score_gemma":0.000001260751,"domain_scores_codex":[0.9986063,0.00003161269,0.0003865346,0.0003805999,0.0002554094,0.0003395817],"domain_scores_gemma":[0.999116,0.0000680079,0.0001505822,0.0002555595,0.0002447446,0.0001650754],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.003331059,0.0001688226,0.00006358968,0.0001406675,0.00006605392,0.000001435446,0.001094367,0.000005080454,0.8786006,0.002981175,0.003422321,0.1101248],"study_design_scores_gemma":[0.004860142,0.001845624,0.0003802074,0.00008061715,0.00002093356,0.00001697799,0.0007533231,0.00007638294,0.4529843,0.001350476,0.5372643,0.0003666911],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6554379,0.0008336888,0.3417757,0.0005839707,0.0003610666,0.0007006956,0.000120827,0.00004859894,0.0001374641],"genre_scores_gemma":[0.9701712,0.0003077131,0.02780039,0.0001737072,0.0002437514,0.00004742343,0.001016441,0.00001907193,0.0002203409],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.533842,"threshold_uncertainty_score":0.7703301,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2604321711","doi":"","title":"TREC 2016 Total Recall Track Overview.","year":2016,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Public Relations and Crisis Communication","field":"Social Sciences","cited_by":29,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Track (disk drive); Recall; Information retrieval; Psychology","retraction":null,"screen_n_in":null,"score":{"opus":0.07651398741119439,"gpt":0.3523979570630005,"spread":0.2758839696518061,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.000921414,0.0001017371,0.0001441095,0.00006500313,0.0003701606,0.0001321895,0.0005054775,0.0001488498,0.003725546],"category_scores_gemma":[0.0007656122,0.00007118943,0.00007515045,0.0003639326,0.0002828871,0.0005635699,0.00007296406,0.0001232417,0.0008301816],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001299434,"about_ca_system_score_gemma":0.0004589527,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004383838,"about_ca_topic_score_gemma":0.0002559007,"domain_scores_codex":[0.9985151,0.0003293333,0.0002474802,0.000227417,0.0003870925,0.0002935367],"domain_scores_gemma":[0.9986402,0.0003271835,0.0001197961,0.0004820105,0.0002784295,0.0001523731],"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":[0.00004634085,0.00007946353,0.001534657,0.00000383947,0.0000181144,0.000001087794,0.002784292,1.954252e-7,0.002321145,0.5974774,0.009072029,0.3866614],"study_design_scores_gemma":[0.0007640338,0.0001106148,0.04266663,0.000153298,0.00002532173,0.000002834708,0.001283115,0.00007870929,0.0006582298,0.03195355,0.9218692,0.0004345],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.2871326,0.001307607,0.004331506,0.03069486,0.0004735155,0.0004247489,0.00002665162,0.0003050701,0.6753035],"genre_scores_gemma":[0.9572566,0.002515935,0.000205808,0.00009209392,0.0001112158,0.00000579529,0.000003898775,0.000007548535,0.03980115],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9127972,"threshold_uncertainty_score":0.9999478,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3013164143","doi":"","title":"TREC 2015 Total Recall Track Overview.","year":2015,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Library Science and Information Systems","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Track (disk drive); Computer science; Recall; Information retrieval; Artificial intelligence; Cognitive psychology; Psychology; Operating system","retraction":null,"screen_n_in":null,"score":{"opus":0.1064969915600995,"gpt":0.3029353534591744,"spread":0.1964383618990748,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0008901235,0.0001807535,0.0002434259,0.0001231509,0.00008958948,0.0007537273,0.00153371,0.0001019133,0.0001669421],"category_scores_gemma":[0.0001620461,0.000147338,0.00007203789,0.000918738,0.00008775269,0.006476577,0.0003096456,0.0001775021,0.002601524],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005624232,"about_ca_system_score_gemma":0.0006222773,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003359531,"about_ca_topic_score_gemma":0.00000185406,"domain_scores_codex":[0.9978684,0.0001083117,0.0004563747,0.0003754765,0.0008102393,0.0003811877],"domain_scores_gemma":[0.998292,0.00005820989,0.0001809458,0.0007320019,0.0003261488,0.0004106989],"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":[0.0001813501,0.0002367144,0.004240414,0.0001015333,0.00005072679,0.00006785192,0.03913847,0.0001689645,0.001966005,0.4799345,0.3113755,0.162538],"study_design_scores_gemma":[0.003424549,0.001776043,0.01799095,0.0002231475,0.000009628997,0.0004861388,0.002663173,0.271892,0.01637867,0.02237816,0.6606503,0.002127214],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.2947018,0.001629474,0.2655891,0.01160732,0.005748078,0.001113358,0.00003177564,0.001625876,0.4179532],"genre_scores_gemma":[0.9881002,0.00002836597,0.002378362,0.0008566907,0.0001232142,0.000003633411,0.000006938536,0.000006044354,0.00849661],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6933984,"threshold_uncertainty_score":0.9981751,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3013426078","doi":"","title":"Overview of the TREC 2010 Legal Track.","year":2010,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Law, logistics, and international trade","field":"Business, Management and Accounting","cited_by":22,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Track (disk drive); Information retrieval; Data science","retraction":null,"screen_n_in":null,"score":{"opus":0.07474354518727247,"gpt":0.2791428321533284,"spread":0.2043992869660559,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002450216,0.0001225254,0.0001643643,0.00005257642,0.00008834343,0.0001709287,0.00059089,0.00008153382,0.002331439],"category_scores_gemma":[0.0005288169,0.00008526239,0.0001049359,0.0002196841,0.0003070326,0.0004690673,0.000127682,0.0002983787,0.0002032595],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008366252,"about_ca_system_score_gemma":0.00006208769,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005212506,"about_ca_topic_score_gemma":0.0003373127,"domain_scores_codex":[0.999038,0.00000797709,0.0002566363,0.0001867073,0.0003435114,0.0001671685],"domain_scores_gemma":[0.9991072,0.00005741299,0.0002123593,0.0003067937,0.0003048352,0.00001140416],"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":[0.00003811616,0.00006413259,0.005336978,0.0000858937,0.00001522079,0.000001767484,0.00002263197,0.000001084282,0.008414043,0.9791592,0.004092108,0.002768775],"study_design_scores_gemma":[0.001002328,0.00003126108,0.2872454,0.0001563047,0.0001134338,0.00000899733,0.00007923501,0.003341666,0.00910164,0.04621165,0.652216,0.0004920565],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.726491,0.0001237276,0.0003805806,0.004545001,0.004704469,0.0003017165,0.00002439133,0.00009977585,0.2633294],"genre_scores_gemma":[0.9934708,0.00002222509,0.00005255751,0.0008672493,0.0007643485,0.000001481106,0.000007200632,0.00001086706,0.004803222],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9329476,"threshold_uncertainty_score":0.9985806,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1878790362","doi":"10.3390/ijms232113127","title":"Overview of the TREC 2012 Contextual Suggestion Track.","year":2012,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":22,"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":"Track (disk drive); Computer science; Context (archaeology); Information retrieval; Task (project management); Set (abstract data type); World Wide Web; Data science; Geography; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.09325439221598353,"gpt":0.3162031300342015,"spread":0.2229487378182179,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008496901,0.0001584328,0.0002205653,0.00007530746,0.0001436815,0.00009304033,0.00107559,0.0001061003,0.0004394313],"category_scores_gemma":[0.0002364491,0.0001049862,0.0001307778,0.0007089788,0.0001600851,0.001656835,0.0002763462,0.0002743919,0.0002358077],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005099293,"about_ca_system_score_gemma":0.000207249,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003097792,"about_ca_topic_score_gemma":0.000004949593,"domain_scores_codex":[0.9981331,0.0001673619,0.0004129577,0.0001679261,0.0006983352,0.0004203673],"domain_scores_gemma":[0.9984732,0.0001449121,0.0002271437,0.0006198778,0.0003701922,0.0001646502],"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":[0.00009807901,0.0002913011,0.01010189,0.0001210394,0.00002570758,0.000001346664,0.004801118,0.000003194539,0.008761893,0.8103043,0.002039656,0.1634505],"study_design_scores_gemma":[0.002001241,0.0004963327,0.7684234,0.0003238497,0.0000746888,0.00009798446,0.0003728706,0.006715406,0.1514352,0.00255875,0.06652452,0.0009757322],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8817296,0.002590402,0.09075242,0.002444373,0.002278713,0.001134048,0.00005518946,0.0003018745,0.01871339],"genre_scores_gemma":[0.9973133,0.00007584964,0.0005211904,0.0002153694,0.0000570156,0.000003890842,0.000003552525,0.00000542315,0.001804393],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8077456,"threshold_uncertainty_score":0.4811465,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2887055502","doi":"","title":"Overview of the TREC 2016 Real-Time Summarization Track.","year":2016,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Topic Modeling","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Automatic summarization; Computer science; Track (disk drive); Information retrieval; Multi-document summarization; Natural language processing; Operating system","retraction":null,"screen_n_in":null,"score":{"opus":0.0542293694693188,"gpt":0.2754098846886667,"spread":0.2211805152193479,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003716943,0.0001214229,0.0001853143,0.00004374917,0.00006275121,0.00004949738,0.001168522,0.0000769495,0.0002518416],"category_scores_gemma":[0.0002184528,0.00006597726,0.00007610533,0.0003502814,0.00008368021,0.0003633572,0.00027328,0.00007072802,0.0001295279],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004504829,"about_ca_system_score_gemma":0.0002779569,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000574873,"about_ca_topic_score_gemma":0.000006734777,"domain_scores_codex":[0.998648,0.0001289262,0.000309345,0.0003327839,0.0003708017,0.0002101841],"domain_scores_gemma":[0.9984456,0.0001808102,0.0001894391,0.0009199085,0.0002058256,0.0000583742],"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":[0.00003689671,0.00006656813,0.002128045,0.00006361952,0.00002450569,0.000002606212,0.0006912926,0.000009570589,0.2311245,0.3916854,0.001011776,0.3731553],"study_design_scores_gemma":[0.0049918,0.0006899877,0.1320094,0.004082508,0.0001281312,0.00005330035,0.00005327373,0.1711225,0.5054467,0.1523388,0.02681001,0.002273593],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1708127,0.0003633895,0.7969151,0.005248847,0.0007137062,0.0005178058,0.00002082121,0.0002923294,0.02511529],"genre_scores_gemma":[0.9904671,0.0003474902,0.002437786,0.00007317196,0.00004164103,0.000001855058,6.127306e-7,0.000007304539,0.006623003],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8196544,"threshold_uncertainty_score":0.2757489,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2395887233","doi":"","title":"University of Waterloo at TREC 2015 Microblog Track","year":2015,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":17,"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; Microblogging; Exploit; Social media; Information retrieval; Relevance (law); Word (group theory); Query expansion; World Wide Web; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.0386870167005127,"gpt":0.2642413455623248,"spread":0.2255543288618121,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003810784,0.0001730339,0.0003282477,0.0001337738,0.00007255063,0.00003913387,0.00138159,0.0001126875,0.0001165625],"category_scores_gemma":[0.00007798227,0.0001700386,0.0001015181,0.0005596566,0.0002059084,0.0005204067,0.0005719574,0.000153227,0.0002233744],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001696803,"about_ca_system_score_gemma":0.000200163,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001849097,"about_ca_topic_score_gemma":0.0001326423,"domain_scores_codex":[0.9985613,0.0001008582,0.0002323469,0.0004542591,0.0003647506,0.0002864895],"domain_scores_gemma":[0.9982482,0.00006069702,0.0002011319,0.0007948011,0.0004918354,0.0002033644],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001392805,0.001046793,0.01406388,0.0001775583,0.0004157548,0.0005078957,0.03177594,0.0002283667,0.5589889,0.1631197,0.06698333,0.1612991],"study_design_scores_gemma":[0.003168806,0.001276995,0.005170565,0.000153102,0.0001480595,0.0001067961,0.0008560008,0.02874123,0.8334761,0.04456826,0.0806324,0.001701717],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3298946,0.000337672,0.6574223,0.001091771,0.0001520088,0.0002822654,0.00001466798,0.0006629161,0.01014173],"genre_scores_gemma":[0.9489643,0.00004845374,0.04131206,0.00004073548,0.00001348946,2.181969e-7,0.000006472258,0.00000784057,0.009606437],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6190696,"threshold_uncertainty_score":0.6933972,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2402510845","doi":"","title":"Overview of the TREC 2011 Legal Track.","year":2011,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Topic Modeling","field":"Computer Science","cited_by":15,"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":"Task (project management); Computer science; Track (disk drive); Rank (graph theory); Information retrieval; Natural language processing; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.1480039556696987,"gpt":0.2856423647114191,"spread":0.1376384090417204,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003269789,0.0001286346,0.0001931643,0.00004006183,0.00006405603,0.00004592891,0.001752679,0.00007045639,0.0005231067],"category_scores_gemma":[0.0000713617,0.0000894498,0.0001019204,0.0002487886,0.00009578756,0.0003545131,0.0003533612,0.0001955842,0.0001001972],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002036086,"about_ca_system_score_gemma":0.0002226482,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000293418,"about_ca_topic_score_gemma":0.00002858648,"domain_scores_codex":[0.9987166,0.00009161724,0.0002955726,0.0003230716,0.0003435539,0.0002296006],"domain_scores_gemma":[0.998558,0.00004693034,0.0001527396,0.001021459,0.0001542814,0.00006656743],"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":[0.00002643569,0.00008603968,0.001838077,0.00005481904,0.00001977236,0.000007296303,0.002630332,0.000003032516,0.002464341,0.9285529,0.0002966841,0.06402031],"study_design_scores_gemma":[0.002917664,0.0009398698,0.2977532,0.0008338299,0.0001452456,0.0001983489,0.0003388269,0.1319644,0.3745921,0.1534304,0.03466652,0.00221967],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4119511,0.001723096,0.4672304,0.001359925,0.001792273,0.0005974689,0.000010272,0.0003043697,0.115031],"genre_scores_gemma":[0.9921593,0.00004813143,0.006078776,0.0001627481,0.00002737248,0.000001596786,1.971367e-7,0.000005651247,0.001516194],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7751225,"threshold_uncertainty_score":0.5727652,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2121587139","doi":"","title":"York University at TREC 2009: Relevance Feedback Track","year":2009,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"York University","funders":"","keywords":"Relevance feedback; Relevance (law); Computer science; Weighting; Task (project management); Track (disk drive); Domain (mathematical analysis); Information retrieval; Series (stratigraphy); Artificial intelligence; Mathematics; Engineering; Image retrieval","retraction":null,"screen_n_in":null,"score":{"opus":0.03342038611951475,"gpt":0.2467342868726649,"spread":0.2133139007531501,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003645467,0.0002359631,0.0002610778,0.0001543747,0.0003659309,0.0002221213,0.001454242,0.0001531299,0.000438339],"category_scores_gemma":[0.0001272535,0.0002272232,0.000119453,0.001138984,0.0001227053,0.001102475,0.0002087115,0.0003500649,0.001500879],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002622612,"about_ca_system_score_gemma":0.0002965573,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002246,"about_ca_topic_score_gemma":0.000009981302,"domain_scores_codex":[0.9978891,0.00009830341,0.0003120005,0.0004669753,0.0006828408,0.000550768],"domain_scores_gemma":[0.9983705,0.0001206508,0.0001637355,0.000708518,0.0003382688,0.0002983088],"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":[0.001402385,0.0005125119,0.001347448,0.00006764413,0.00004213284,0.0003204768,0.00705452,0.00007450154,0.02303275,0.4402848,0.02543207,0.5004287],"study_design_scores_gemma":[0.006594076,0.003220695,0.2226959,0.00029251,0.00008119406,0.0002855656,0.0006660166,0.06114883,0.09923125,0.009851556,0.5924993,0.003433095],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7222897,0.0003700492,0.1459977,0.00651852,0.0008379177,0.001001005,0.00007858378,0.001433696,0.1214729],"genre_scores_gemma":[0.9717585,0.0001129442,0.003817918,0.0005121716,0.00004187401,3.331509e-7,0.00001094529,0.000005638175,0.02373964],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5670673,"threshold_uncertainty_score":0.9992766,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3013805123","doi":"","title":"Query and Answer Expansion from Conversation History.","year":2019,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Topic Modeling","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Conversation; Computer science; Query expansion; Information retrieval; Linguistics; Philosophy","retraction":null,"screen_n_in":null,"score":{"opus":0.02976830130571452,"gpt":0.2219263047048665,"spread":0.192158003399152,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00016825,0.0001117472,0.0001485463,0.00005498488,0.00002695401,0.00007165025,0.0003594314,0.00008504043,0.0004101348],"category_scores_gemma":[0.00004675702,0.0001088991,0.00002388708,0.00007701765,0.00003785643,0.0005160287,0.0001636445,0.0001392809,0.0002232758],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001120329,"about_ca_system_score_gemma":0.0001638641,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002356461,"about_ca_topic_score_gemma":0.000007291622,"domain_scores_codex":[0.9989229,0.00005027606,0.000166186,0.0004413393,0.0002586614,0.0001605664],"domain_scores_gemma":[0.9991381,0.00009539872,0.00007749221,0.0005118193,0.0001003058,0.00007689723],"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":[0.0002193712,0.0001104984,0.04544045,0.0001205473,0.00006441742,0.00003368938,0.02459138,0.00007304914,0.2721299,0.4620789,0.001584159,0.1935536],"study_design_scores_gemma":[0.002082069,0.0002977305,0.0551051,0.0001948403,0.00002384526,0.00001404888,0.0004302928,0.8672867,0.01283268,0.02406419,0.03664524,0.001023206],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6820397,0.0003226096,0.3145282,0.0003853255,0.0007380269,0.0001252839,0.000001232436,0.0001067894,0.001752859],"genre_scores_gemma":[0.9914427,0.00003289763,0.007346278,0.0003245036,0.00004385422,0.000001032484,0.000003818671,0.000005436986,0.0007994672],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8672137,"threshold_uncertainty_score":0.4490688,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W94318738","doi":"","title":"Synonym-Based Expansion and Boosting-Based Re-Ranking: A Two-phase Approach for Genomic Information Retrieval.","year":2005,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Boosting (machine learning); WordNet; Information retrieval; Artificial intelligence; Ranking (information retrieval); Machine learning","retraction":null,"screen_n_in":null,"score":{"opus":0.02894459750801155,"gpt":0.2989211651388505,"spread":0.269976567630839,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001099385,0.0003419531,0.0003511124,0.0003384868,0.0003164553,0.0006914739,0.001004195,0.0002055532,0.00002336548],"category_scores_gemma":[0.0007680997,0.0003159393,0.00009078829,0.0006357682,0.0001364913,0.001552623,0.0001945211,0.0003682292,0.0000110406],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001725159,"about_ca_system_score_gemma":0.0005397989,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001754065,"about_ca_topic_score_gemma":0.000002907834,"domain_scores_codex":[0.9977347,0.00009130008,0.0005655849,0.0005871018,0.0005281339,0.0004932305],"domain_scores_gemma":[0.9978603,0.0003097311,0.0003958569,0.0007007085,0.0005558196,0.0001775594],"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":[0.004068195,0.0007030289,0.0002076937,0.001441995,0.00005778627,0.00001930451,0.003756149,0.001416461,0.1782361,0.04957505,0.001484358,0.7590339],"study_design_scores_gemma":[0.00309316,0.0004492438,0.00003813726,0.0001328624,0.00002047184,0.00001188159,0.00002523135,0.85144,0.1405836,0.001637217,0.002081584,0.0004866441],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03078459,0.0007144722,0.9651731,0.0009766364,0.00007379136,0.0009345165,0.00002144642,0.0008787909,0.0004426609],"genre_scores_gemma":[0.6012512,0.000004227714,0.3976868,0.0008909154,0.00005283218,0.0000162153,0.00005247098,0.00001293896,0.0000324424],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8500235,"threshold_uncertainty_score":0.9999292,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3173838993","doi":"","title":"Overview of the TREC 2020 Health Misinformation Track.","year":2020,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Misinformation and Its Impacts","field":"Social Sciences","cited_by":11,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Misinformation; Track (disk drive); Computer science; Information retrieval; Data science; Computer security","retraction":null,"screen_n_in":null,"score":{"opus":0.1556287675719629,"gpt":0.3753961097522171,"spread":0.2197673421802542,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0006229705,0.00008044404,0.0001715927,0.00001897445,0.0002614271,0.0000810202,0.0003581003,0.0000604432,0.001587859],"category_scores_gemma":[0.001018906,0.00005856384,0.00007213197,0.0006569742,0.0001499686,0.0004923598,0.00003780413,0.0001422476,0.0001365239],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000587908,"about_ca_system_score_gemma":0.0009839912,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002975235,"about_ca_topic_score_gemma":0.0001131108,"domain_scores_codex":[0.998596,0.0001592406,0.0003781203,0.00008489728,0.0005736178,0.0002081886],"domain_scores_gemma":[0.9990787,0.00005979076,0.0003239256,0.0001503897,0.0001670006,0.0002202263],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001570852,0.00005111005,0.0005081973,0.0004206678,0.00002427607,4.031693e-7,0.5410255,0.00001770913,0.0003150445,0.2048535,0.05372569,0.1989008],"study_design_scores_gemma":[0.00177916,0.0005312022,0.06617425,0.0004594567,0.00003352535,0.000003530822,0.05818657,0.004275978,0.004513449,0.002161806,0.8612672,0.0006138706],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.3747842,0.001349313,0.002153311,0.1984375,0.0007869132,0.001752026,0.0001071088,0.0002886859,0.420341],"genre_scores_gemma":[0.9935406,0.000696509,0.0000565255,0.005042004,0.00006655259,2.323153e-7,0.000004826011,0.000003239728,0.0005895245],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8075415,"threshold_uncertainty_score":0.9993248,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2132630274","doi":"","title":"York University at TREC 2012: Medical Records Track","year":2012,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Algorithms and Data Compression","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"York University","funders":"","keywords":"Track (disk drive); Computer science; Information retrieval; Medical record; Work (physics); Artificial intelligence; Medicine; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.03818721144490055,"gpt":0.2545070467609054,"spread":0.2163198353160048,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0005675179,0.0001728172,0.0002107226,0.00007451197,0.0002407925,0.0000756497,0.001471363,0.0001871031,0.002555422],"category_scores_gemma":[0.0001206515,0.0001517618,0.00006879496,0.0004300588,0.0001169749,0.001169322,0.0009346745,0.0002944692,0.0008982558],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001140544,"about_ca_system_score_gemma":0.0002200975,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009658392,"about_ca_topic_score_gemma":0.00002935853,"domain_scores_codex":[0.9980978,0.0001431028,0.0001885755,0.0003912385,0.0006884951,0.0004908069],"domain_scores_gemma":[0.9983845,0.0001797057,0.0001028688,0.000697599,0.0000923513,0.0005429208],"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":[0.0004171855,0.0006599082,0.01348452,0.00005762402,0.00007016335,0.0001683086,0.003008606,0.000002160494,0.001427619,0.2013428,0.1341659,0.6451952],"study_design_scores_gemma":[0.001351103,0.0002502587,0.0447296,0.0001405697,0.00002634837,0.0001501494,0.0001240716,0.03517094,0.002965439,0.0008965302,0.9133415,0.0008534578],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1553592,0.001417774,0.7821051,0.002186703,0.003109222,0.0003378747,0.00005639029,0.000736777,0.05469096],"genre_scores_gemma":[0.9782911,0.0001763317,0.00979845,0.0002113923,0.0002578208,4.539504e-7,0.00001880591,0.000009243607,0.0112364],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8229319,"threshold_uncertainty_score":0.9998797,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2885586573","doi":"","title":"MRG_UWaterloo and WaterlooCormack Participation in the TREC 2017 Common Core Track.","year":2017,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Advanced Bandit Algorithms Research","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Track (disk drive); Core (optical fiber); Telecommunications; Operating system","retraction":null,"screen_n_in":null,"score":{"opus":0.354013297376704,"gpt":0.5097599940313238,"spread":0.1557466966546198,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.003914333,0.0001983542,0.0003588877,0.0001672272,0.0007377155,0.001575882,0.002192511,0.0001182195,0.000331995],"category_scores_gemma":[0.002699625,0.0001137524,0.0000551833,0.0002520839,0.0007304106,0.001050975,0.0003311655,0.0004694424,0.0003751333],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003785266,"about_ca_system_score_gemma":0.00008853283,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000293035,"about_ca_topic_score_gemma":0.0009712568,"domain_scores_codex":[0.9964394,0.0003281837,0.0005856534,0.0005757079,0.00155892,0.000512142],"domain_scores_gemma":[0.9964777,0.001140841,0.0003286458,0.001558596,0.0003508464,0.0001434234],"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":[0.001292942,0.0003686488,0.2007646,0.00003432153,0.00002712362,0.0003570848,0.02004927,0.00009467639,0.004368275,0.005300851,0.002603775,0.7647385],"study_design_scores_gemma":[0.001325116,0.0003204818,0.9216443,0.00004473372,0.0000117708,0.00003339603,0.001143737,0.01812915,0.00537481,0.04567178,0.005984386,0.0003163752],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9924815,0.00007485587,0.001005279,0.002230848,0.0001799338,0.0005004735,0.00002225597,0.00002308595,0.003481803],"genre_scores_gemma":[0.9970298,0.00007816932,0.0001054423,0.00008975925,0.00008057982,0.00001958053,0.00000677194,0.00000952735,0.002580306],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7644221,"threshold_uncertainty_score":0.9994606,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W161736330","doi":"","title":"Approaches to High Accuracy Retrieval: Phrase-Based Search Experiments in the HARD Track.","year":2004,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":8,"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; Focus (optics); Phrase; Selection (genetic algorithm); Natural language processing; Word (group theory); Artificial intelligence; Noun phrase; Noun; Information retrieval; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.1651441880432227,"gpt":0.3311107469396994,"spread":0.1659665588964767,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001380695,0.0003373413,0.0003258022,0.0003040098,0.0001919882,0.000778665,0.003581743,0.0001809997,0.000040816],"category_scores_gemma":[0.0007256838,0.0002478734,0.00008389514,0.002056107,0.0001413219,0.000745538,0.0003788706,0.0007241949,0.0001078556],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002588208,"about_ca_system_score_gemma":0.0006165315,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002230892,"about_ca_topic_score_gemma":0.00001382214,"domain_scores_codex":[0.9966598,0.0002633739,0.0004258848,0.0008571842,0.001128584,0.000665174],"domain_scores_gemma":[0.9979746,0.0002900496,0.000122129,0.001255855,0.0001811242,0.0001762353],"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":[0.001488601,0.001632142,0.0006945869,0.0003080695,0.00005624104,0.0006718631,0.03475406,0.000609999,0.1537034,0.7007619,0.0008070495,0.104512],"study_design_scores_gemma":[0.001585772,0.0005805323,0.00238777,0.0003128822,0.00001083761,0.00003105509,0.0003561387,0.003219717,0.9441438,0.04615677,0.0004157064,0.0007990714],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4219636,0.001013082,0.5574816,0.01632828,0.0002081543,0.001456115,0.00001211003,0.000897758,0.0006393063],"genre_scores_gemma":[0.8511466,0.000008469591,0.1472663,0.00140839,0.00005190403,0.00002382485,0.000008491839,0.00001897679,0.00006704013],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7904403,"threshold_uncertainty_score":0.9999974,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2885556514","doi":"","title":"UWaterlooMDS at the TREC 2017 Common Core Track.","year":2017,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Track (disk drive); Computer science; Core (optical fiber); Telecommunications; Operating system","retraction":null,"screen_n_in":null,"score":{"opus":0.06543898827919384,"gpt":0.3335348181136187,"spread":0.2680958298344248,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0005903672,0.0002457944,0.0002685511,0.00005110316,0.001338433,0.001388386,0.005323424,0.0001571776,0.0001332455],"category_scores_gemma":[0.000258854,0.0001571,0.00009141899,0.0001243115,0.000455833,0.0008772811,0.00145612,0.0004555659,0.000217671],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008688765,"about_ca_system_score_gemma":0.0001204913,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002323124,"about_ca_topic_score_gemma":0.0002206129,"domain_scores_codex":[0.9982294,0.00007024825,0.0002594907,0.0005394059,0.0004819487,0.0004194716],"domain_scores_gemma":[0.996568,0.0001384764,0.0003492613,0.002609297,0.0002183985,0.0001166299],"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":[0.0002755586,0.0001457527,0.008218133,0.0001098347,0.0000693737,0.0004169658,0.004599126,0.000001048316,0.05758341,0.3003816,0.02749817,0.600701],"study_design_scores_gemma":[0.00152927,0.0006630735,0.03532819,0.0004856684,0.00007417305,0.0005342589,0.00008174439,0.01262911,0.7038386,0.2062743,0.03663706,0.00192459],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7607842,0.007746073,0.1203478,0.02858178,0.002662297,0.001770226,0.00006915955,0.003781726,0.07425673],"genre_scores_gemma":[0.9812773,0.00005644591,0.009503745,0.0003639218,0.00008121693,0.000007230039,0.000005392133,0.00001328669,0.008691492],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6462552,"threshold_uncertainty_score":0.9999617,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2145841197","doi":"","title":"Selecting versus Describing: A Preliminary Analysis of the Efficacy of Categories in Exploring the Web","year":2001,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Task (project management); Session (web analytics); Directory; Computer science; Information retrieval; Point (geometry); Rating scale; Certainty; Scale (ratio); Process (computing); Psychology; World Wide Web; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.1460100374333013,"gpt":0.3010006766775535,"spread":0.1549906392442522,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007831022,0.0001255717,0.0002625348,0.0002967358,0.0001517797,0.00008362657,0.001277703,0.00004512896,0.00003122759],"category_scores_gemma":[0.0007437264,0.00007695201,0.000149701,0.005389473,0.000167457,0.000519418,0.0003752337,0.0002834499,0.000004045882],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005894046,"about_ca_system_score_gemma":0.0003111313,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001760152,"about_ca_topic_score_gemma":0.00008005533,"domain_scores_codex":[0.9982901,0.0001501907,0.0004835811,0.000198868,0.000594007,0.0002832037],"domain_scores_gemma":[0.9980803,0.0006779461,0.0002419192,0.000594897,0.000360373,0.00004456873],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00647865,0.0009503284,0.3636985,0.0002103661,0.001178718,0.00004808719,0.1253768,0.009309434,0.03685044,0.2358058,0.00009687967,0.2199959],"study_design_scores_gemma":[0.001772783,0.0005745453,0.7468692,0.0001274041,0.0002969937,0.000008982433,0.002369771,0.1961692,0.05100362,0.0002021729,0.0002622785,0.0003430591],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9931577,0.00004273044,0.005011163,0.0002879031,0.0002104203,0.0002199629,0.000002505009,0.00003182958,0.001035758],"genre_scores_gemma":[0.9996216,0.00004552488,0.0002066029,0.00001662062,0.0000110083,0.000006195253,0.000001506814,0.000003649508,0.00008734552],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3831707,"threshold_uncertainty_score":0.3138012,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W413120383","doi":"","title":"Frequent Itemset Mining for Query Expansion in Microblog Ad-hoc Search","year":2012,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Data Mining Algorithms and Applications","field":"Computer Science","cited_by":7,"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":"Microblogging; Computer science; Social media; Data mining; Information retrieval; Process (computing); Volume (thermodynamics); World Wide Web","retraction":null,"screen_n_in":null,"score":{"opus":0.07056403817857194,"gpt":0.3173098186451487,"spread":0.2467457804665768,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008557502,0.000158241,0.0001985342,0.0001407698,0.000130935,0.0001765712,0.0008644817,0.00009644601,0.00003261559],"category_scores_gemma":[0.000116335,0.0001519063,0.00004824858,0.0005081991,0.00006321388,0.0006446952,0.0002926381,0.0001840393,0.00008816061],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007534306,"about_ca_system_score_gemma":0.0001855932,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004435785,"about_ca_topic_score_gemma":0.00001589107,"domain_scores_codex":[0.9984061,0.0000588222,0.0003053965,0.0004232639,0.0002426919,0.0005637589],"domain_scores_gemma":[0.9987223,0.0002696771,0.00007781356,0.0006186032,0.0001431344,0.0001684392],"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":[0.00009661803,0.0005929152,0.006121839,0.000143398,0.00003030168,0.000009866859,0.01212328,0.00001669147,0.0938437,0.09269581,0.006333132,0.7879925],"study_design_scores_gemma":[0.006385418,0.001661064,0.1111039,0.001331088,0.00006699095,0.0001875559,0.003934585,0.4283859,0.160346,0.007051369,0.2755311,0.004014991],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4567871,0.00110652,0.5389504,0.001141535,0.0003774989,0.000604018,0.00009665192,0.0001727336,0.0007635816],"genre_scores_gemma":[0.8635902,0.00007868039,0.1355896,0.0001744244,0.00007638692,0.00004368496,0.00005150244,0.00001256754,0.0003829076],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7839774,"threshold_uncertainty_score":0.6194559,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3013646476","doi":"","title":"WaterlooClarke at the TREC 2019 Conversational Assistant Track.","year":2019,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Track (disk drive); Artificial intelligence; Natural language processing; World Wide Web; Multimedia; Operating system","retraction":null,"screen_n_in":null,"score":{"opus":0.01528003651922833,"gpt":0.2526781807060182,"spread":0.2373981441867898,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0005942879,0.0002038469,0.0002045284,0.00007034636,0.0001705446,0.0003480388,0.001588475,0.0001269182,0.001066134],"category_scores_gemma":[0.000105695,0.0001292948,0.00008369771,0.0003747712,0.0001329897,0.0005487673,0.0004663368,0.000340288,0.001012359],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001566166,"about_ca_system_score_gemma":0.0002361978,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005056483,"about_ca_topic_score_gemma":0.0000159351,"domain_scores_codex":[0.9981271,0.0001159956,0.0002640739,0.0005277212,0.0006180558,0.0003470314],"domain_scores_gemma":[0.9984084,0.0002396548,0.0001603895,0.0008455554,0.0002632367,0.00008279458],"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":[0.000542384,0.0001768826,0.00607563,0.0001639561,0.0001325073,0.00009404372,0.005848021,0.000009616446,0.2294655,0.6223268,0.03023195,0.1049328],"study_design_scores_gemma":[0.002677105,0.0008625705,0.01867818,0.0003647645,0.00006950647,0.0003344819,0.0002235381,0.03827024,0.7318508,0.1070977,0.09723498,0.002336183],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6724924,0.006636634,0.2653591,0.02354282,0.002543878,0.002168749,0.00009349308,0.002989321,0.0241736],"genre_scores_gemma":[0.9658635,0.00002359162,0.0134878,0.0006280161,0.00004147689,0.000004732053,0.00001722283,0.00001169704,0.01992199],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5152291,"threshold_uncertainty_score":0.9998471,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W165780999","doi":"","title":"DalTREC 2005 Spam Track: Spam Filtering using N-gram-based Techniques","year":2005,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Spam and Phishing Detection","field":"Computer Science","cited_by":6,"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; n-gram; Track (disk drive); Spambot; Computer network; Spamming; World Wide Web; Artificial intelligence; Operating system; The Internet","retraction":null,"screen_n_in":null,"score":{"opus":0.04681525418723725,"gpt":0.2834078574464462,"spread":0.2365926032592089,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005912915,0.0002840902,0.0002733838,0.0002296324,0.0002485843,0.0005460157,0.001013947,0.0001852547,0.0002518075],"category_scores_gemma":[0.0001297518,0.0002866797,0.0001086306,0.0005888816,0.00009035695,0.000933097,0.0001654753,0.0003947852,0.0001181454],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001983785,"about_ca_system_score_gemma":0.0002909363,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001460092,"about_ca_topic_score_gemma":0.0000629077,"domain_scores_codex":[0.9978703,0.0001007278,0.0003714808,0.0006254285,0.000475641,0.0005563873],"domain_scores_gemma":[0.9985543,0.0001171954,0.0001826348,0.0007722505,0.0001801114,0.0001935285],"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":[0.0002400621,0.0003616707,0.001546158,0.0001399758,0.00005243057,0.00005795732,0.00119278,0.001892501,0.3957789,0.01183359,0.001733604,0.5851704],"study_design_scores_gemma":[0.0003317361,0.0001850637,0.0007188177,0.0001539825,0.00001572205,0.00003836331,0.0000132077,0.4902335,0.4755551,0.0006991171,0.03152976,0.0005255989],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1474845,0.0001784617,0.8454019,0.001117323,0.0005137334,0.0003192827,0.000006841769,0.001203881,0.003774113],"genre_scores_gemma":[0.9057441,0.00002249701,0.0931314,0.0003807597,0.0003442271,0.000005061671,0.000003771944,0.00002067748,0.000347554],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7582596,"threshold_uncertainty_score":0.9999585,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2573384236","doi":"","title":"Waterloo (Cormack) Participation in the TREC 2015 Total Recall Track.","year":2015,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Library Science and Information Systems","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Recall; Track (disk drive); Computer science; Information retrieval; Artificial intelligence; Cognitive psychology; Psychology","retraction":null,"screen_n_in":null,"score":{"opus":0.08988319202190065,"gpt":0.3078099765277643,"spread":0.2179267845058637,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001852876,0.0001335275,0.000159016,0.0001104247,0.00009050675,0.0006916233,0.001343261,0.00007106613,0.00004758321],"category_scores_gemma":[0.0001697518,0.00008462206,0.00003965146,0.0008802832,0.00007417764,0.005145048,0.0001280262,0.0002163497,0.0007564578],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004139659,"about_ca_system_score_gemma":0.0002901509,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008922254,"about_ca_topic_score_gemma":0.000014633,"domain_scores_codex":[0.997982,0.000283745,0.0004515352,0.0002593609,0.0006785815,0.0003448139],"domain_scores_gemma":[0.9988872,0.0001041651,0.0001339718,0.0005485825,0.0001701571,0.0001559353],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000390201,0.0007777305,0.02555946,0.00009180238,0.00003322681,0.0001023511,0.5528194,0.001136382,0.00215505,0.1885588,0.0777517,0.1506239],"study_design_scores_gemma":[0.004263183,0.002454811,0.1233593,0.0001747721,0.00001131119,0.0002683585,0.01389796,0.7137433,0.01495326,0.01625942,0.1089168,0.001697553],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9434649,0.00006489739,0.02013088,0.005078149,0.001077455,0.0004441031,0.000003949654,0.0001652864,0.02957034],"genre_scores_gemma":[0.997087,0.000005742459,0.0003255256,0.0006538889,0.00006741061,0.00001120098,0.000007156991,0.000003049258,0.001839052],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7126068,"threshold_uncertainty_score":0.9722987,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3175902990","doi":"","title":"H2oloo at TREC 2020: When all you got is a hammer... Deep Learning, Health Misinformation, and Precision Medicine.","year":2020,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Topic Modeling","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Misinformation; Hammer; Computer science; Artificial intelligence; Deep learning; Data science; Engineering; Computer security; Mechanical engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.05694637064717668,"gpt":0.2868362349313853,"spread":0.2298898642842086,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006319039,0.0002389876,0.0003788315,0.0000699812,0.0002342832,0.0001718861,0.0007891954,0.0001114909,0.0006057622],"category_scores_gemma":[0.0005409115,0.0002071604,0.00004489314,0.0003151171,0.00009984105,0.0005652618,0.0005577766,0.0003717801,0.000194512],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001020728,"about_ca_system_score_gemma":0.0001796909,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001697681,"about_ca_topic_score_gemma":0.00002625291,"domain_scores_codex":[0.9975805,0.0001451875,0.0005921987,0.0006357064,0.0006332751,0.0004130797],"domain_scores_gemma":[0.9984088,0.0001566281,0.0003094547,0.0004645536,0.0002044512,0.0004561273],"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":[0.0002298518,0.00003675749,0.002519054,0.0002807409,0.00006180203,0.00002196357,0.1673732,0.0002050579,0.001037271,0.01267351,0.0334364,0.7821245],"study_design_scores_gemma":[0.001213626,0.0008684453,0.001934793,0.0001440489,0.00001466028,0.00004595765,0.0003867362,0.8611636,0.0005122804,0.00237281,0.1309355,0.0004075581],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04166699,0.002195487,0.8680221,0.08236996,0.0003023971,0.0004827006,0.000004354772,0.0003574382,0.004598543],"genre_scores_gemma":[0.9720333,0.000884134,0.014446,0.01021141,0.0001701182,0.000003808174,0.00001852001,0.00001628291,0.002216382],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9303663,"threshold_uncertainty_score":0.8447754,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2115057477","doi":"","title":"York University at TREC 2006: Enterprise Email Discussion Search","year":2006,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"York University","funders":"","keywords":"Computer science; Information retrieval; Thread (computing); Ranking (information retrieval); Search engine; Word (group theory); Document retrieval; Rank (graph theory); Query expansion; World Wide Web","retraction":null,"screen_n_in":null,"score":{"opus":0.02514964510748901,"gpt":0.2407946580660498,"spread":0.2156450129585608,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000432185,0.00021106,0.0002177874,0.0002141406,0.0004510059,0.0002652244,0.001218968,0.0001301932,0.0006314731],"category_scores_gemma":[0.00003196665,0.0001538929,0.0001191499,0.0009412284,0.000160035,0.0008333632,0.0006988372,0.0003027328,0.001143377],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002869298,"about_ca_system_score_gemma":0.0002685514,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003299088,"about_ca_topic_score_gemma":0.00007876952,"domain_scores_codex":[0.9977244,0.0001550893,0.0002980384,0.0004320045,0.000848763,0.0005417592],"domain_scores_gemma":[0.9987053,0.00007796547,0.0001053686,0.0006089096,0.0002811576,0.000221303],"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":[0.003032052,0.001657532,0.1010874,0.0003390454,0.00009660204,0.0009077431,0.01285575,0.0002724037,0.06691819,0.5236142,0.05709398,0.2321251],"study_design_scores_gemma":[0.00804271,0.00172555,0.3893001,0.0004269054,0.00009470054,0.000223243,0.001715499,0.1236938,0.1141828,0.003281603,0.3536436,0.00366947],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7569639,0.00008334635,0.1853918,0.002952099,0.0005551567,0.0006971783,0.00009130452,0.0006859336,0.05257926],"genre_scores_gemma":[0.9515941,0.00001917986,0.001499327,0.00007111076,0.00004823256,7.029503e-7,0.00003055646,0.000007498299,0.04672931],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5203326,"threshold_uncertainty_score":0.9996343,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2166281503","doi":"","title":"DalTREC 2004: Question Answering using Regular Expression Rewriting","year":2004,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"Dalhousie University","funders":"","keywords":"Rewriting; Regular expression; Computer science; Expression (computer science); Question answering; Search engine; Information retrieval; Track (disk drive); Programming language; Natural language processing; World Wide Web; Artificial intelligence; Operating system","retraction":null,"screen_n_in":null,"score":{"opus":0.02825001249352575,"gpt":0.2986974757111274,"spread":0.2704474632176017,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005870951,0.0002382437,0.0002310738,0.0001733229,0.000274776,0.0004193625,0.001038615,0.0001751234,0.00001571429],"category_scores_gemma":[0.0004004231,0.0002255891,0.0000586047,0.0006641574,0.00008455727,0.001338826,0.0003850908,0.0004045802,0.00001652799],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002462956,"about_ca_system_score_gemma":0.0002672039,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001368804,"about_ca_topic_score_gemma":0.000005166013,"domain_scores_codex":[0.998033,0.00009065986,0.0003406508,0.0006099014,0.000497938,0.0004277749],"domain_scores_gemma":[0.9986324,0.00005046784,0.0002134069,0.0006679422,0.0003064162,0.0001293865],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00002931313,0.00003945495,0.0001192252,0.00007390835,0.000005217531,0.00008567797,0.000701083,0.0001543359,0.8876539,0.08617448,0.00002493309,0.02493841],"study_design_scores_gemma":[0.0003468691,0.00008439561,0.0000891903,0.001167945,0.000007407546,0.0001099089,0.00004479996,0.009985743,0.90548,0.08211081,0.0001519263,0.0004209684],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09903895,0.001751156,0.897034,0.0003984281,0.0001703141,0.0001752213,0.000001461692,0.001084114,0.0003463882],"genre_scores_gemma":[0.6032013,0.00001441293,0.3965726,0.00007710383,0.00006186849,0.000001747659,0.000002296186,0.0000120352,0.00005662906],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5041624,"threshold_uncertainty_score":0.9199258,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2947689917","doi":"","title":"KlickLabs at TREC 2018 Precision Medicine track.","year":2018,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":5,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Track (disk drive); Precision medicine; Information retrieval; Artificial intelligence; Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.04302524158150629,"gpt":0.3146855815370476,"spread":0.2716603399555413,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003899843,0.0002101245,0.0002472667,0.00004839081,0.0001620823,0.00001941343,0.0003976635,0.0003340114,0.001396891],"category_scores_gemma":[0.00094206,0.0001563378,0.00005765753,0.0001843366,0.00110415,0.000003471679,0.0002335012,0.0001339317,0.0003641895],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002824224,"about_ca_system_score_gemma":0.00009629839,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003117627,"about_ca_topic_score_gemma":0.00007406814,"domain_scores_codex":[0.9984437,0.00008183625,0.0002910791,0.000528914,0.0003017106,0.0003527443],"domain_scores_gemma":[0.9989142,0.00006055315,0.0001085431,0.0005251367,0.0002163527,0.0001751696],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001049243,0.00006164181,0.00135852,0.00002160658,0.00005201858,0.000008524553,0.0004011469,1.213394e-7,0.7493186,0.0002526328,0.09598885,0.1514871],"study_design_scores_gemma":[0.001302617,0.003580634,0.01065941,0.00009904224,0.00003584804,0.00005494713,0.0001531246,0.0001083822,0.3600321,0.0005778201,0.6229948,0.000401278],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9674541,0.001355243,0.003526289,0.001532356,0.0007376607,0.0001760509,0.0000199683,0.00008702403,0.02511132],"genre_scores_gemma":[0.9821305,0.0003029467,0.0007399212,0.0004500852,0.0008527071,0.00000355632,0.00006434168,0.00001728988,0.01543862],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5270059,"threshold_uncertainty_score":0.999516,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2578945560","doi":"","title":"Real Time Filtering of Tweets Using Wikipedia Concepts and Google Tri-gram Semantic Relatedness","year":2015,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Topic Modeling","field":"Computer Science","cited_by":5,"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; Information retrieval; n-gram; Semantic similarity; Word (group theory); Social media; World Wide Web; Natural language processing; Language model","retraction":null,"screen_n_in":null,"score":{"opus":0.07837344284233229,"gpt":0.3094833050650553,"spread":0.231109862222723,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005453297,0.0001911611,0.0003620736,0.0001042444,0.00006559748,0.0001313883,0.0005991042,0.000135013,0.00002243183],"category_scores_gemma":[0.0002200808,0.0001879911,0.00004075182,0.000363859,0.0001439212,0.0005037197,0.0004351654,0.0001953489,0.00002770786],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006176149,"about_ca_system_score_gemma":0.0003370727,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002436907,"about_ca_topic_score_gemma":0.000003385014,"domain_scores_codex":[0.9982616,0.0001085987,0.0004108146,0.0004727895,0.0004173889,0.0003287893],"domain_scores_gemma":[0.9986024,0.0001246829,0.0002068594,0.0005581833,0.0002881838,0.0002196835],"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":[0.0007375663,0.0004747024,0.02176086,0.0008686349,0.000312977,0.0004948259,0.05148742,0.004263583,0.7154399,0.09467457,0.0008466554,0.1086383],"study_design_scores_gemma":[0.001376262,0.0002795748,0.00191283,0.0002868171,0.00003945873,0.00009211886,0.000159065,0.9754195,0.01525745,0.00441224,0.0002488773,0.0005157844],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8783889,0.0001398393,0.1179811,0.00008330756,0.0003374529,0.000172115,0.000003338348,0.000142972,0.002750959],"genre_scores_gemma":[0.9834204,0.00002565896,0.01601733,0.00001726885,0.00006705023,9.483891e-7,0.000001901023,0.00001230214,0.0004371857],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9711559,"threshold_uncertainty_score":0.7666056,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2604217576","doi":"","title":"Word embeddings and Global Preference for Contextual Suggestion.","year":2016,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Language, Metaphor, and Cognition","field":"Psychology","cited_by":4,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Lakehead University; Université Laval","funders":"","keywords":"Preference; Computer science; Word (group theory); Natural language processing; Artificial intelligence; Speech recognition; Linguistics; Mathematics; Statistics; Philosophy","retraction":null,"screen_n_in":null,"score":{"opus":0.05459598172282607,"gpt":0.3217472922575974,"spread":0.2671513105347713,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003093258,0.00021635,0.0002649842,0.00004774327,0.0001097247,0.00007541234,0.0002190122,0.0001938349,0.002324746],"category_scores_gemma":[0.0005047155,0.0001512473,0.00006701773,0.0001688256,0.0002424762,0.0001776775,0.00005632173,0.0001013775,0.0003352393],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005092417,"about_ca_system_score_gemma":0.00008036113,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006508469,"about_ca_topic_score_gemma":0.00004339057,"domain_scores_codex":[0.9984852,0.00009605531,0.0002764657,0.0005316982,0.0001993748,0.0004112278],"domain_scores_gemma":[0.9987375,0.0003631854,0.0001301012,0.0002895107,0.0003181139,0.0001616464],"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":[0.002500213,0.0001394369,0.005852122,0.00004674853,0.0001249059,0.00001655016,0.002090433,2.333604e-8,0.006983558,0.4334794,0.004113077,0.5446535],"study_design_scores_gemma":[0.02696589,0.00436931,0.5387735,0.0012061,0.0007624545,0.0004720427,0.00692087,0.0001484565,0.0148911,0.3118832,0.0900588,0.003548281],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9289656,0.0006872459,0.04450893,0.0007136737,0.0006486309,0.0006547449,0.0003379215,0.0001949841,0.02328831],"genre_scores_gemma":[0.9915773,0.00005426123,0.0003083648,0.000262411,0.0001533283,0.0000481589,0.00001869085,0.00001490729,0.007562633],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5411053,"threshold_uncertainty_score":0.9985873,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3176967269","doi":"","title":"TREC 2020 Podcasts Track Overview.","year":2020,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Advanced Text Analysis Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"","keywords":"Track (disk drive); Computer science; Information retrieval; Operating system","retraction":null,"screen_n_in":null,"score":{"opus":0.06050055887350622,"gpt":0.310150801677166,"spread":0.2496502428036598,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002263201,0.0003033684,0.0004469625,0.0000754072,0.0001102624,0.0002642488,0.001953899,0.0001237471,0.0004097967],"category_scores_gemma":[0.0003479741,0.0002881573,0.0001778715,0.001535562,0.00009898301,0.0009223288,0.0005146723,0.0003919293,0.0006564579],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000614885,"about_ca_system_score_gemma":0.0001693409,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001235844,"about_ca_topic_score_gemma":0.000006683763,"domain_scores_codex":[0.9975493,0.0001142606,0.0004415426,0.0008632253,0.0005900356,0.0004416466],"domain_scores_gemma":[0.9982361,0.0001163383,0.0002059748,0.0008277104,0.0002572138,0.0003567105],"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":[0.0001976266,0.0002392163,0.001648578,0.0001471896,0.0001538454,0.0004039199,0.004179454,0.0000545767,0.06832547,0.4019478,0.0175546,0.5051477],"study_design_scores_gemma":[0.002590619,0.002232165,0.01391922,0.000259084,0.0001714183,0.000135353,0.0002294702,0.33514,0.3077622,0.09944484,0.2342013,0.00391429],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01293691,0.0007891304,0.9662435,0.008811666,0.0001310277,0.0003138929,0.000009229618,0.001522874,0.009241764],"genre_scores_gemma":[0.9545207,0.0002751022,0.04237547,0.002239589,0.000132541,0.000005416113,0.000006167622,0.00001957402,0.0004254409],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9415838,"threshold_uncertainty_score":0.9999571,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2135220386","doi":"","title":"Query-Structure Based Web Page Indexing","year":2012,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":4,"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":"Search engine indexing; Computer science; Information retrieval; Web page; Index (typography); World Wide Web; Web search query; Set (abstract data type); Static web page; Search engine; Web navigation","retraction":null,"screen_n_in":null,"score":{"opus":0.02983501488973424,"gpt":0.2575284238493121,"spread":0.2276934089595779,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004726445,0.0002054578,0.0002463058,0.0001632148,0.0001636105,0.0003000938,0.001156086,0.0001252419,0.000427636],"category_scores_gemma":[0.0002417491,0.0001775423,0.00008542009,0.0008196693,0.00007201338,0.0008473704,0.0002687557,0.0003166785,0.000189031],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004241884,"about_ca_system_score_gemma":0.0002476768,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002980379,"about_ca_topic_score_gemma":0.000008939095,"domain_scores_codex":[0.998266,0.000118607,0.0002433065,0.0003938723,0.0004474339,0.0005308116],"domain_scores_gemma":[0.9984823,0.0001412371,0.0001277958,0.0008802031,0.0001245509,0.0002438996],"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":[0.0001409591,0.000494983,0.177526,0.0002380095,0.0003101039,0.0001095767,0.005466498,0.000126895,0.3367502,0.3039359,0.01233679,0.1625641],"study_design_scores_gemma":[0.002503948,0.0003342171,0.04930981,0.0003575695,0.0001947028,0.00008734409,0.0003563091,0.744475,0.1085477,0.003665393,0.08726138,0.002906698],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5254001,0.0004394546,0.4615646,0.001347802,0.0008526247,0.000171803,0.00008746827,0.0006591912,0.009476984],"genre_scores_gemma":[0.9867616,0.000006626713,0.01211499,0.0004585396,0.0001498758,0.000001249444,0.00002341359,0.00001002348,0.0004737015],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7443481,"threshold_uncertainty_score":0.7239964,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W26866788","doi":"10.1088/0957-4484/27/10/105204","title":"Experiments for HARD and Enterprise Tracks.","year":2005,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":4,"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":"Fundamental Research Funds for the Central Universities; National Natural Science Foundation of China","keywords":"Cohesion (chemistry); Computer science; Natural language processing; Lexical database; Social connectedness; Artificial intelligence; Information retrieval; Selection (genetic algorithm); Lexical item; Schema (genetic algorithms); Linguistics; Psychology; WordNet","retraction":null,"screen_n_in":null,"score":{"opus":0.0348368139127696,"gpt":0.3130115114656667,"spread":0.2781746975528971,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002044794,0.0001453706,0.0001561687,0.00006992207,0.00009552151,0.0002843874,0.0006746163,0.0000783932,0.0000298672],"category_scores_gemma":[0.0001092946,0.0001280401,0.00003801786,0.0001140151,0.00006167245,0.0006271467,0.0001966631,0.0001253736,0.00001596504],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003916321,"about_ca_system_score_gemma":0.00006143623,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005169138,"about_ca_topic_score_gemma":0.00000147931,"domain_scores_codex":[0.9989548,0.00002257234,0.0001792081,0.0003980689,0.0001951187,0.0002502509],"domain_scores_gemma":[0.99929,0.00007056762,0.00007761231,0.0003437531,0.0001203155,0.00009778582],"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":[0.0001525241,0.0001209586,0.0002300535,0.00006788073,0.00002337916,0.00001299492,0.003811158,3.981193e-7,0.106847,0.120048,0.002689801,0.7659959],"study_design_scores_gemma":[0.001044356,0.0003617904,0.0003921321,0.0001340187,0.00001074932,0.00005307751,0.0000589463,0.02390052,0.9153553,0.03516745,0.02290309,0.0006186206],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04658149,0.004038824,0.9460503,0.001544581,0.000116779,0.0003759512,0.000006291024,0.0005982102,0.0006875945],"genre_scores_gemma":[0.6664059,0.00003261138,0.3326477,0.0003175313,0.00004382561,0.00001091102,0.000001498993,0.000006329044,0.0005337819],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8085082,"threshold_uncertainty_score":0.5221323,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3175228675","doi":"","title":"Abstract Podcast Summarization using BART with Longformer Attention.","year":2020,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"","keywords":"Automatic summarization; Computer science; Information retrieval; Bartok; Multi-document summarization; Natural language processing; Literature; Art","retraction":null,"screen_n_in":null,"score":{"opus":0.05972704396145603,"gpt":0.2576175202927503,"spread":0.1978904763312942,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001583227,0.0001552599,0.0001893423,0.00007075816,0.0001492811,0.0004069658,0.0006181849,0.00005572169,0.0001843615],"category_scores_gemma":[0.00008730559,0.0001288818,0.00005178137,0.0008689453,0.00006061265,0.000895863,0.0001534042,0.0001681373,0.0001770538],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002486281,"about_ca_system_score_gemma":0.0001891153,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005139678,"about_ca_topic_score_gemma":0.000006690941,"domain_scores_codex":[0.9986485,0.00003005875,0.0002273965,0.0004549873,0.000394933,0.0002441183],"domain_scores_gemma":[0.999072,0.00003620589,0.000137931,0.0003703945,0.0002118299,0.0001717071],"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":[0.0009213933,0.0007147635,0.2407199,0.0007053051,0.001080039,0.0007398482,0.009073413,0.004729349,0.3980481,0.1295876,0.005499098,0.2081812],"study_design_scores_gemma":[0.00126638,0.0004649824,0.1044617,0.0002556262,0.0001450624,0.00004998482,0.0003768435,0.8798329,0.007955703,0.0003335483,0.003705775,0.001151567],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2274397,0.00003014776,0.7692777,0.001100953,0.00005523979,0.0000767385,0.00001299746,0.0001543628,0.001852196],"genre_scores_gemma":[0.9851514,0.000008270454,0.01430097,0.000300373,0.00006721322,6.272683e-7,0.00003560411,0.000009009534,0.000126569],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8751035,"threshold_uncertainty_score":0.5255648,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2546705495","doi":"","title":"WaterlooClarke: TREC 2015 Clinical Decision Support Track","year":2015,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"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; Information retrieval; Mean reciprocal rank; Search engine; Reciprocal; Clinical decision support system; Test (biology); Rank (graph theory); Decision support system; Data mining","retraction":null,"screen_n_in":null,"score":{"opus":0.08993383767107038,"gpt":0.3806690461193441,"spread":0.2907352084482737,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001285501,0.0002098141,0.0003123512,0.00004104728,0.00005293864,0.00005517461,0.0004592543,0.0005073156,0.0002676976],"category_scores_gemma":[0.001893533,0.000163062,0.0001341475,0.0001279255,0.0003928341,0.000005714677,0.0002063209,0.0002692682,0.0003773606],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000171319,"about_ca_system_score_gemma":0.0004847986,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001609878,"about_ca_topic_score_gemma":0.00002821537,"domain_scores_codex":[0.9980555,0.000152638,0.0004936268,0.0005558094,0.0003637694,0.0003787105],"domain_scores_gemma":[0.9985568,0.00007738434,0.0001130688,0.0005293204,0.0002973003,0.0004261573],"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":[0.003061767,0.000361727,0.01412965,0.00002157239,0.0001122864,0.00008343084,0.0003090411,0.000002396432,0.02066123,0.000204441,0.3316276,0.6294249],"study_design_scores_gemma":[0.002968412,0.003527104,0.01213346,0.00004104334,0.00004821349,0.00009177798,0.0003580022,0.0002117025,0.02489262,0.001224892,0.9539291,0.0005736609],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.980431,0.000770298,0.009614192,0.0008402051,0.001075354,0.0001774797,0.00002911112,0.00009718892,0.006965238],"genre_scores_gemma":[0.9880388,0.0002372171,0.004533532,0.000412386,0.0003834918,0.000003487119,0.0001265161,0.00001945439,0.006245146],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6288512,"threshold_uncertainty_score":0.6649475,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3013135062","doi":"","title":"Overview of the TREC 2018 Real-Time Summarization Track.","year":2018,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Topic Modeling","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Automatic summarization; Computer science; Track (disk drive); Multi-document summarization; Information retrieval; World Wide Web; Operating system","retraction":null,"screen_n_in":null,"score":{"opus":0.06766606094889346,"gpt":0.2918718006947948,"spread":0.2242057397459013,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003882969,0.0001229547,0.0001847483,0.00004568876,0.0001085074,0.00008051544,0.001240068,0.00008234408,0.0002779462],"category_scores_gemma":[0.000167879,0.00008991322,0.00006119806,0.0005567477,0.0001599467,0.0002975266,0.0003100834,0.0001060877,0.0001549182],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003767661,"about_ca_system_score_gemma":0.0002345983,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000121933,"about_ca_topic_score_gemma":0.00002184911,"domain_scores_codex":[0.9986296,0.0001196368,0.0003065937,0.0003413227,0.0003896427,0.0002131774],"domain_scores_gemma":[0.9983989,0.0000841157,0.0001868391,0.0009721224,0.0003030272,0.00005500069],"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":[0.00008708482,0.0001713533,0.003687434,0.0001636279,0.00005681825,0.000004081327,0.004783378,0.00003107975,0.1409634,0.6415051,0.00346361,0.2050831],"study_design_scores_gemma":[0.001545118,0.0007604424,0.06757589,0.0007788243,0.00007795088,0.0000321109,0.0000636272,0.6136886,0.2487614,0.05235922,0.01323874,0.001118125],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4211119,0.0002949861,0.5082324,0.002283662,0.001470252,0.0006689873,0.00001515643,0.0003710026,0.06555173],"genre_scores_gemma":[0.9923829,0.00008772193,0.004822834,0.0001253939,0.0001029122,0.000001264985,0.000001398941,0.000007189678,0.002468396],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6136575,"threshold_uncertainty_score":0.3666555,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2946940318","doi":"","title":"UWaterlooMDS at the TREC 2018 Common Core Track.","year":2018,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Track (disk drive); Computer science; Core (optical fiber); Information retrieval; Artificial intelligence; Telecommunications; Operating system","retraction":null,"screen_n_in":null,"score":{"opus":0.03971195414912118,"gpt":0.2932357582956169,"spread":0.2535238041464958,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005938451,0.0002235418,0.0002304105,0.00005512299,0.000570781,0.000324195,0.001695755,0.0001005669,0.0009021085],"category_scores_gemma":[0.0001099502,0.0001441944,0.00007641687,0.000466009,0.0004246698,0.0002354012,0.0005533242,0.0003843199,0.00180226],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005689149,"about_ca_system_score_gemma":0.00009666785,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000246589,"about_ca_topic_score_gemma":0.0001536076,"domain_scores_codex":[0.9981428,0.0001561771,0.0002688945,0.0005216885,0.0004623955,0.0004480839],"domain_scores_gemma":[0.998285,0.0001975922,0.0001339807,0.001063492,0.0001823629,0.0001375516],"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":[0.0002786864,0.0002272373,0.0135329,0.00004910559,0.00009821897,0.00008978786,0.01151575,0.00001973666,0.01136127,0.07513656,0.05503864,0.8326521],"study_design_scores_gemma":[0.002772055,0.003623999,0.08579616,0.0002391982,0.00007995877,0.0005006305,0.0002564129,0.3496934,0.07394654,0.02419903,0.4566807,0.002211927],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8853215,0.0002904475,0.05581202,0.007936896,0.002055544,0.0003950179,0.00001671989,0.0007625931,0.04740925],"genre_scores_gemma":[0.9746631,0.00001703901,0.001379508,0.000665968,0.0003391767,0.000003344047,0.000006892076,0.00001318015,0.02291172],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8304402,"threshold_uncertainty_score":0.998975,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2572043595","doi":"","title":"WaterlooClarke: TREC 2015 Total Recall Track","year":2015,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Topic Modeling","field":"Computer Science","cited_by":3,"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; Recall; Track (disk drive); Cluster analysis; Selection (genetic algorithm); Process (computing); Precision and recall; Information retrieval; Data mining; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.0752741043559129,"gpt":0.2872297986682088,"spread":0.2119556943122959,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007651807,0.0002284876,0.0002770282,0.0000942977,0.00007102723,0.0003283994,0.001228822,0.0001541906,0.0001128198],"category_scores_gemma":[0.0002594177,0.0002009253,0.00007348024,0.0003532619,0.0000723877,0.0007167425,0.0003654327,0.0003249949,0.0006678387],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000106038,"about_ca_system_score_gemma":0.0004538975,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000102121,"about_ca_topic_score_gemma":0.00001360834,"domain_scores_codex":[0.9977333,0.0001307326,0.0003685235,0.0006455101,0.0006306506,0.0004912965],"domain_scores_gemma":[0.9980915,0.00007080256,0.000101371,0.0009588466,0.0003768598,0.0004006734],"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":[0.0006162816,0.0005992707,0.002987974,0.000131459,0.0001545581,0.0005397448,0.02451095,0.001059075,0.01636729,0.3235488,0.03753409,0.5919505],"study_design_scores_gemma":[0.004584339,0.001332085,0.004254844,0.0001973623,0.00005218302,0.000511394,0.0005375033,0.8448822,0.02997568,0.05370995,0.05754199,0.002420388],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3226627,0.0004062275,0.6412211,0.00429307,0.001602608,0.0003518386,0.000006192607,0.0007148474,0.0287415],"genre_scores_gemma":[0.9722361,0.00001103652,0.01923305,0.000215449,0.000154993,0.00000390001,0.000004108494,0.00001334709,0.008128],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8438232,"threshold_uncertainty_score":0.8583938,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1503829033","doi":"","title":"Experiments with the Negotiated Boolean Queries of the TREC 2008 Legal Track","year":2008,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Topic Modeling","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Open Text (Canada)","funders":"","keywords":"Relevance (law); Task (project management); Computer science; Relevance feedback; Information retrieval; Recall; Standard Boolean model; Rank (graph theory); Boolean expression; Learning to rank; Boolean network; And-inverter graph; Theoretical computer science; Boolean function; Data mining; Artificial intelligence; Algorithm; Mathematics; Ranking (information retrieval); Combinatorics; Psychology; Cognitive psychology","retraction":null,"screen_n_in":null,"score":{"opus":0.04573418768938414,"gpt":0.2495933093840824,"spread":0.2038591216946983,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001666855,0.0001715063,0.0001976701,0.00003203595,0.0002752872,0.00008105252,0.001504658,0.00005734408,0.0000586813],"category_scores_gemma":[0.00005652732,0.00009000124,0.00006457244,0.0004413139,0.0003898885,0.0003649032,0.0002417333,0.000240538,0.00001525335],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002937974,"about_ca_system_score_gemma":0.000369703,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002516737,"about_ca_topic_score_gemma":0.00004891858,"domain_scores_codex":[0.9984827,0.0001213202,0.0002472118,0.0003379031,0.0005385536,0.000272303],"domain_scores_gemma":[0.998547,0.00007792337,0.0001667672,0.0009638192,0.0001845359,0.00005992593],"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":[0.001455832,0.001126009,0.03629505,0.0001745481,0.0005630305,0.0003786283,0.1296809,0.002577599,0.09982333,0.6560469,0.01403489,0.05784323],"study_design_scores_gemma":[0.004446808,0.001420549,0.1155278,0.0004221655,0.00008454494,0.0008854013,0.002713538,0.1353521,0.7044419,0.001985454,0.03082487,0.001894898],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8947985,0.0002322767,0.09706339,0.001986193,0.0002237454,0.0002940428,0.000002964742,0.0001092226,0.005289692],"genre_scores_gemma":[0.9958075,0.0000174663,0.001660442,0.0002308659,0.00003240892,0.000004147845,5.429334e-7,0.000008649295,0.002237967],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6540615,"threshold_uncertainty_score":0.3670144,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2182378606","doi":"","title":"Universite de Montreal at TREC 2013: Experiments with Quantum Language Models in the Web Track.","year":2013,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"Université de Montréal","funders":"","keywords":"Robustness (evolution); Computer science; Language model; Artificial intelligence; Focus (optics); Information retrieval; Data mining","retraction":null,"screen_n_in":null,"score":{"opus":0.03172284299808632,"gpt":0.2476529462624022,"spread":0.2159301032643159,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002295495,0.0001623019,0.0001605109,0.00008109822,0.00009287658,0.0001734627,0.001134401,0.00007144875,0.0001319897],"category_scores_gemma":[0.0000110834,0.0001124363,0.00003435449,0.0002852616,0.00005887452,0.0007029246,0.0001859921,0.0001987869,0.0001079886],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001292426,"about_ca_system_score_gemma":0.0001533815,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003511953,"about_ca_topic_score_gemma":0.0006090933,"domain_scores_codex":[0.9985873,0.0001320793,0.0001632646,0.0003800364,0.0003552803,0.0003820401],"domain_scores_gemma":[0.9990407,0.00009126947,0.0000704307,0.0006330835,0.00007009361,0.00009438732],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0007749993,0.001024949,0.01245157,0.0001282803,0.0001756867,0.001244432,0.3941232,0.01424425,0.07769018,0.3898643,0.007547061,0.100731],"study_design_scores_gemma":[0.0007276428,0.0001060831,0.003639833,0.00003651092,0.000005657828,0.00002522508,0.001751025,0.9895027,0.001373787,0.002511741,0.00009968645,0.0002201433],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8959514,0.0001823165,0.09435176,0.000891378,0.00004271046,0.0002821711,0.000002123303,0.00008332227,0.008212755],"genre_scores_gemma":[0.995407,0.00003595839,0.002962142,0.0002242598,0.00001987817,0.000008177424,0.000002041397,0.000007449372,0.00133303],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9752584,"threshold_uncertainty_score":0.5309047,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2604796591","doi":"","title":"\"When to Stop\" Waterloo (Cormack) Participation in the TREC 2016 Total Recall Track.","year":2016,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Border Security and International Relations","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Recall; Track (disk drive); Computer science; Information retrieval; Natural language processing; Psychology; Operating system; Cognitive psychology","retraction":null,"screen_n_in":null,"score":{"opus":0.06282087771289732,"gpt":0.3540823752187992,"spread":0.2912614975059018,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001048808,0.0000898252,0.000101573,0.00007221542,0.0002512844,0.0001196114,0.0003784261,0.00009590458,0.001830518],"category_scores_gemma":[0.001169648,0.00005430197,0.00004425104,0.0002487774,0.0001564667,0.0004254694,0.00003178442,0.000157976,0.0007206117],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001080985,"about_ca_system_score_gemma":0.0002409405,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001866028,"about_ca_topic_score_gemma":0.005507838,"domain_scores_codex":[0.9984064,0.0003725069,0.000241814,0.0002092187,0.0004806963,0.0002893747],"domain_scores_gemma":[0.9989583,0.0005211832,0.00005870907,0.000167128,0.0001899684,0.0001046689],"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":[0.0003194236,0.0003669703,0.006395913,0.000006648546,0.0000251209,0.000008516703,0.2145505,0.000008807984,0.00252032,0.6368074,0.007258243,0.1317322],"study_design_scores_gemma":[0.001957156,0.0007732437,0.2866347,0.0003895066,0.00005339662,0.000004468933,0.008296279,0.0004223528,0.00264571,0.1113171,0.5866189,0.0008871796],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9069056,0.00003303539,0.001798337,0.03704466,0.0002813134,0.0003769209,0.00002224179,0.00004819014,0.05348973],"genre_scores_gemma":[0.9849629,0.00005855287,0.00007144939,0.0004003464,0.0001349102,0.00001959502,0.000003903677,0.000004874575,0.01434348],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5793607,"threshold_uncertainty_score":0.999082,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W125929235","doi":"","title":"In Enterprise Search: Methods to Identify Argumentative Discussions and to Find Topical Experts.","year":2006,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Expert finding and Q&A systems","field":"Computer Science","cited_by":2,"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":"Argumentative; Computer science; Ranking (information retrieval); Argument (complex analysis); Information retrieval; Rank (graph theory); World Wide Web; Topic model; Data science; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.06126711204444565,"gpt":0.4111753007816831,"spread":0.3499081887372375,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006286922,0.0001818145,0.0002914577,0.0002482892,0.0001187267,0.0003438849,0.0006407358,0.00008122911,0.00005780815],"category_scores_gemma":[0.0001878683,0.0001431261,0.00004306217,0.000642536,0.00005412406,0.0003292015,0.000557769,0.0001745335,0.00008074226],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009838646,"about_ca_system_score_gemma":0.00007016785,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006251857,"about_ca_topic_score_gemma":0.00007551685,"domain_scores_codex":[0.9979064,0.0003791001,0.0003440474,0.0006113935,0.0003469848,0.0004120088],"domain_scores_gemma":[0.9989056,0.0002780277,0.00004134547,0.0004322204,0.00007759659,0.0002651998],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.0003061886,0.0005534168,0.02330312,0.0000867686,0.00004420719,0.0002827744,0.1065883,0.00007149271,0.5290592,0.205779,0.01815437,0.1157711],"study_design_scores_gemma":[0.003425176,0.001890448,0.5932577,0.001265831,0.00002202679,0.0001695713,0.006643512,0.01845456,0.3063856,0.01852496,0.04715074,0.002809882],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4497984,0.00009008712,0.5411358,0.00648426,0.0003680581,0.0003806563,0.000004835824,0.00006307259,0.001674877],"genre_scores_gemma":[0.9454991,0.000005459924,0.04998973,0.0004644994,0.00007246518,0.00002319304,0.000001443493,0.000008013661,0.003936089],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5699545,"threshold_uncertainty_score":0.5836514,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2572785564","doi":"","title":"WaterlooClarke: TREC 2015 Temporal Summarization Track.","year":2015,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Automatic summarization; Computer science; Track (disk drive); Multi-document summarization; Information retrieval","retraction":null,"screen_n_in":null,"score":{"opus":0.04169239849904795,"gpt":0.2977835804427729,"spread":0.256091181943725,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007414333,0.0002299876,0.0002427977,0.0001547655,0.00008914051,0.0004947874,0.001390709,0.0001820321,0.00004577923],"category_scores_gemma":[0.0003940985,0.0001915504,0.00005144108,0.0006960058,0.00009365736,0.001244104,0.0003161504,0.0003208628,0.0001420396],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001155365,"about_ca_system_score_gemma":0.000458778,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001298035,"about_ca_topic_score_gemma":0.00002258141,"domain_scores_codex":[0.9980454,0.0001304313,0.0003215599,0.0005235602,0.0006050779,0.0003739582],"domain_scores_gemma":[0.9982645,0.00004955232,0.0001614744,0.0006579036,0.0006148509,0.0002516983],"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":[0.0006313804,0.000517618,0.008983675,0.0002145832,0.00008960922,0.000441038,0.01255885,0.0000165637,0.04196689,0.4678754,0.06603497,0.4006694],"study_design_scores_gemma":[0.003079669,0.001510708,0.001283875,0.000374547,0.00006047109,0.0002685376,0.0003123309,0.08562172,0.42503,0.4309247,0.04877533,0.002758062],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0151062,0.001798838,0.9724383,0.002984083,0.0005824909,0.0003733395,0.000008000023,0.002114836,0.004593904],"genre_scores_gemma":[0.8630338,0.00001221819,0.1340907,0.0002207348,0.0000769584,0.000004760771,0.00002599769,0.00001460598,0.002520176],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8479276,"threshold_uncertainty_score":0.7811198,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2576853603","doi":"","title":"Laval University and Lakehead University at TREC Dynamic Domain 2015: Combination of Techniques for Subtopics Coverage.","year":2015,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"Lakehead University; Université Laval","funders":"","keywords":"Computer science; Domain (mathematical analysis); Information retrieval; Library science; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.02569653499890819,"gpt":0.2502806054467507,"spread":0.2245840704478425,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003837369,0.0000958835,0.0001893202,0.0001253105,0.0001026864,0.00003529221,0.0004607312,0.00007893367,0.000005073739],"category_scores_gemma":[0.00006705923,0.0001035275,0.00004382084,0.0003379744,0.0001170785,0.0003608103,0.0002881747,0.00007182723,0.000003099698],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001358049,"about_ca_system_score_gemma":0.000183851,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001365846,"about_ca_topic_score_gemma":0.0002831548,"domain_scores_codex":[0.9992026,0.00009073126,0.0001054706,0.0002784425,0.0001849496,0.0001377775],"domain_scores_gemma":[0.9990995,0.0001035597,0.0001213612,0.0002986065,0.0002776688,0.00009932897],"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":[0.001766293,0.000605471,0.04130578,0.0003035004,0.0002850385,0.0001206833,0.007472945,0.00002056568,0.01950956,0.7867478,0.01067297,0.1311894],"study_design_scores_gemma":[0.01954888,0.006773836,0.1038416,0.0005979423,0.0006904013,0.0001134349,0.004990303,0.3284297,0.06077721,0.08623298,0.3842945,0.003709287],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5410211,0.00003653487,0.4565053,0.0006607746,0.00005045918,0.0001369316,0.00009617647,0.00009338166,0.001399316],"genre_scores_gemma":[0.9886207,0.00004767315,0.0085674,0.000009116409,0.000005594367,9.645875e-8,0.00003607968,0.000003057133,0.002710256],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7005148,"threshold_uncertainty_score":0.422173,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3176527752","doi":"","title":"Spotify at the TREC 2020 Podcasts Track: Segment Retrieval.","year":2020,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"","keywords":"Track (disk drive); Computer science; Information retrieval; World Wide Web; Operating system","retraction":null,"screen_n_in":null,"score":{"opus":0.05451127183627481,"gpt":0.2668095807724929,"spread":0.2122983089362181,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005906344,0.0003316788,0.000356995,0.00003991168,0.0003050962,0.0003747578,0.002196471,0.0001494446,0.0008384367],"category_scores_gemma":[0.0004308479,0.0002490807,0.0001531076,0.0008904657,0.000138182,0.0003954852,0.001032372,0.000546566,0.001054488],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001597812,"about_ca_system_score_gemma":0.0003126427,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003370463,"about_ca_topic_score_gemma":0.00001501895,"domain_scores_codex":[0.9967576,0.000196109,0.0005171433,0.001007129,0.0009348269,0.0005871675],"domain_scores_gemma":[0.9977999,0.0002495801,0.0002032516,0.001153755,0.0002173643,0.0003761772],"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":[0.002167956,0.0004458473,0.003990184,0.0004414508,0.0003926161,0.001027969,0.04012174,0.001949848,0.1397465,0.1660319,0.04566588,0.5980181],"study_design_scores_gemma":[0.003279746,0.001207354,0.01268118,0.000195348,0.000111718,0.0002410098,0.0005572198,0.7365292,0.1251231,0.005103718,0.1127146,0.002255786],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4373351,0.001206786,0.4708723,0.07490225,0.001419357,0.001110347,0.00003202316,0.0008980934,0.01222375],"genre_scores_gemma":[0.9904486,0.00009128574,0.003578209,0.003015613,0.000322414,0.000003490895,0.000006069328,0.00002094188,0.002513368],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7345794,"threshold_uncertainty_score":0.9999961,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2296709160","doi":"","title":"GUCAS at TREC 2011 Microblog Track.","year":2011,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"York University","funders":"","keywords":"Computer science; Microblogging; Social media; Context (archaeology); Relevance (law); Track (disk drive); Probabilistic logic; Information retrieval; Baseline (sea); Natural language processing; Query expansion; Artificial intelligence; Language model; World Wide Web","retraction":null,"screen_n_in":null,"score":{"opus":0.09059576231893875,"gpt":0.2552359157374093,"spread":0.1646401534184706,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0003346246,0.0002217256,0.000244887,0.00009796029,0.000140679,0.00009687075,0.001509127,0.0001392478,0.001882605],"category_scores_gemma":[0.00005857723,0.0002062222,0.00009028442,0.0002073922,0.0000959749,0.0004182789,0.0005139979,0.0002358242,0.002017718],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008500463,"about_ca_system_score_gemma":0.0001563489,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001542434,"about_ca_topic_score_gemma":0.00004495036,"domain_scores_codex":[0.9981552,0.00007620593,0.000340454,0.0006622784,0.0002991899,0.000466708],"domain_scores_gemma":[0.9984109,0.00006467562,0.0001279593,0.001045462,0.0001650455,0.0001859598],"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":[0.0003823305,0.0005556839,0.01237687,0.0001335147,0.0001357136,0.0003945332,0.02647697,0.00001474256,0.09554705,0.587179,0.01034182,0.2664618],"study_design_scores_gemma":[0.004793286,0.001603173,0.08554494,0.0003143582,0.0001348468,0.0008875057,0.0003232624,0.1469687,0.5788514,0.1055851,0.07027108,0.004722336],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3655605,0.0004442319,0.5264538,0.0006315414,0.001027064,0.0003351162,0.000007163046,0.0006072242,0.1049334],"genre_scores_gemma":[0.9614867,0.00003326388,0.02923464,0.0002735789,0.00005920544,0.000003465331,0.000001997017,0.00001280057,0.008894358],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5959262,"threshold_uncertainty_score":0.9990298,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3173373527","doi":"","title":"TREC 2020 Notebook: CAsT Track.","year":2020,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Track (disk drive); Computer science; Operating system","retraction":null,"screen_n_in":null,"score":{"opus":0.06551698452288615,"gpt":0.2644454919931136,"spread":0.1989285074702274,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001800533,0.0001995638,0.0002547943,0.00003452062,0.00009815679,0.0002594345,0.001351416,0.00009865699,0.0003479063],"category_scores_gemma":[0.0002338918,0.0001931336,0.00008048396,0.0004295863,0.00005602679,0.0004031365,0.0003415072,0.0003352682,0.0007193108],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003680499,"about_ca_system_score_gemma":0.0002482324,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002946415,"about_ca_topic_score_gemma":0.000006982217,"domain_scores_codex":[0.9981506,0.00006782376,0.0003141206,0.0006714572,0.0004283951,0.0003675485],"domain_scores_gemma":[0.9987811,0.0000889667,0.00009526215,0.0005798022,0.0001434949,0.0003113618],"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":[0.0002395694,0.0001421351,0.001406415,0.0001904962,0.00008450519,0.0006550396,0.01950568,0.0004713381,0.04762368,0.334733,0.007475096,0.587473],"study_design_scores_gemma":[0.001230259,0.0004640191,0.001826558,0.00006820163,0.00002310702,0.00007198882,0.0001559528,0.9271718,0.02473984,0.004991821,0.03827265,0.0009837901],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04697183,0.0001700351,0.923755,0.01141437,0.000359337,0.0002309621,0.000006288466,0.0005051065,0.0165871],"genre_scores_gemma":[0.9829963,0.00002052258,0.01434848,0.00175255,0.0002135488,0.00000233216,0.000001909805,0.00001154884,0.0006527884],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9360245,"threshold_uncertainty_score":0.9245525,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W342589544","doi":"","title":"York University at TREC 2012: CrowdSourcing Track.","year":2012,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Information Retrieval and Search Behavior","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"York University","funders":"","keywords":"Crowdsourcing; Computer science; Quality (philosophy); Work (physics); Crowdsourcing software development; Data science; Control (management); Information retrieval; World Wide Web; Artificial intelligence; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.04766109456374461,"gpt":0.2510287572091137,"spread":0.2033676626453691,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0006179572,0.000189224,0.000201965,0.0001596894,0.0003983033,0.0001651671,0.001004534,0.0001306756,0.0009599446],"category_scores_gemma":[0.0000739869,0.0001783555,0.0001029241,0.0007532671,0.0001111754,0.002084857,0.0004398398,0.0002845997,0.001684688],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002244628,"about_ca_system_score_gemma":0.0001582114,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003806946,"about_ca_topic_score_gemma":0.000007871033,"domain_scores_codex":[0.9981668,0.000113912,0.0002393154,0.0002623849,0.0005579417,0.0006596216],"domain_scores_gemma":[0.9986211,0.0001265841,0.0001302604,0.0005256203,0.0002013741,0.0003950311],"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":[0.0009014531,0.0007410526,0.04982572,0.0001821166,0.0001121748,0.0001033574,0.03441041,0.00003645128,0.02777197,0.658189,0.02264289,0.2050834],"study_design_scores_gemma":[0.003251893,0.000587743,0.266388,0.0001383569,0.00008795928,0.0002364665,0.001345063,0.02074996,0.08391462,0.0006480517,0.6203349,0.002316959],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7711383,0.0003044213,0.1706701,0.0008446156,0.0009436655,0.0004260537,0.0000252081,0.0006400004,0.0550077],"genre_scores_gemma":[0.9802427,0.00002341204,0.002389904,0.0001436409,0.00007623508,5.352064e-7,0.000007601637,0.000007060865,0.01710885],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6575409,"threshold_uncertainty_score":0.9999533,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2403585915","doi":"","title":"University of Ottawa at TREC 2010 Web Track Ranking Web Documents Using Meta-Data","year":2010,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Track (disk drive); Ranking (information retrieval); Information retrieval; World Wide Web","retraction":null,"screen_n_in":null,"score":{"opus":0.0936111074354567,"gpt":0.2862664339247185,"spread":0.1926553264892618,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00103726,0.0002156264,0.0004913894,0.0001770195,0.0002503702,0.0001667136,0.003318174,0.0001330705,0.001246498],"category_scores_gemma":[0.000189546,0.0002024459,0.0001619679,0.0007426015,0.0001984425,0.001202902,0.001464445,0.0003651234,0.0001159452],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003531476,"about_ca_system_score_gemma":0.0003993465,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004805538,"about_ca_topic_score_gemma":0.0009019474,"domain_scores_codex":[0.9979363,0.0001376276,0.0003107443,0.0007515267,0.0005275565,0.0003362331],"domain_scores_gemma":[0.9970679,0.0001733201,0.0003210251,0.00206836,0.0002143569,0.000155074],"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":[0.0003003319,0.0006724467,0.02902361,0.0002141246,0.004390669,0.0003798392,0.003047994,0.00016528,0.839623,0.0314084,0.01832224,0.07245202],"study_design_scores_gemma":[0.001991241,0.0001280397,0.004378405,0.00007712156,0.002111324,0.00007161857,0.0001599544,0.9235734,0.01548957,0.0005045937,0.05050283,0.001011952],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9462008,0.0001843667,0.04754441,0.0005656963,0.000634532,0.0001590795,0.0003378819,0.0001838633,0.00418932],"genre_scores_gemma":[0.9747522,0.00004208126,0.02280725,0.00003007767,0.00003530802,9.788709e-8,0.00004911232,0.000008385542,0.002275428],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9234081,"threshold_uncertainty_score":0.9996665,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2407544020","doi":"","title":"Ranking Web Pages Using Collective Knowledge.","year":2011,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Web Data Mining and Analysis","field":"Computer Science","cited_by":2,"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":"Computer science; Search engine indexing; Information retrieval; Web page; Ranking (information retrieval); World Wide Web; Static web page; Index (typography); Web navigation","retraction":null,"screen_n_in":null,"score":{"opus":0.1401130716483935,"gpt":0.2917074747109926,"spread":0.1515944030625991,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004823178,0.0001923658,0.000279748,0.0002233584,0.0002596869,0.0002271255,0.001177511,0.00008677175,0.0002250778],"category_scores_gemma":[0.0002049166,0.0001765577,0.00009237131,0.001313099,0.0001089224,0.0005508113,0.0004238445,0.0002110374,0.0001869811],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008427646,"about_ca_system_score_gemma":0.0006726187,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005523185,"about_ca_topic_score_gemma":0.00002352523,"domain_scores_codex":[0.9984468,0.0001460301,0.0002546209,0.0005358812,0.0002556291,0.0003610987],"domain_scores_gemma":[0.9986619,0.0001236685,0.0001333753,0.0006550879,0.0003026153,0.0001233346],"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":[0.0005701548,0.001646634,0.03598341,0.0002808342,0.001395381,0.0005598151,0.111237,0.00005265038,0.15822,0.3437563,0.009436063,0.3368618],"study_design_scores_gemma":[0.002078959,0.0005850922,0.01783488,0.0005041577,0.0002704231,0.0001166086,0.001130877,0.8660879,0.0856446,0.0183185,0.005369272,0.002058732],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2377643,0.0006309304,0.6353545,0.0001058457,0.0005587129,0.0002063388,0.0000161117,0.0005124961,0.1248508],"genre_scores_gemma":[0.9780018,0.00003413311,0.02035217,0.0000452331,0.00005301282,0.000001702793,0.000002345832,0.000009852025,0.001499723],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8660352,"threshold_uncertainty_score":0.7199816,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3173187978","doi":"","title":"The CLaC System at the TREC 2020 News Track.","year":2020,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Concordia University","funders":"","keywords":"Track (disk drive); Computer science; Operating system","retraction":null,"screen_n_in":null,"score":{"opus":0.02671213014052321,"gpt":0.2636659143570772,"spread":0.236953784216554,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004789715,0.0002256964,0.0002189113,0.0000179089,0.0006152834,0.0007487366,0.003025706,0.0001109222,0.00004397742],"category_scores_gemma":[0.0004446775,0.0001174064,0.00009879937,0.0007637686,0.0001965276,0.0003210331,0.000606041,0.0004994454,0.0002885403],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001210202,"about_ca_system_score_gemma":0.0002001756,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004585416,"about_ca_topic_score_gemma":0.0000453008,"domain_scores_codex":[0.9979632,0.0002147383,0.0003313335,0.0005398661,0.0005603944,0.0003904118],"domain_scores_gemma":[0.9981389,0.0004150157,0.0002042388,0.0008732941,0.0002063089,0.0001622318],"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":[0.0003778734,0.00003221944,0.0002941018,0.000213763,0.00006851269,0.0001783361,0.006537254,0.000004607917,0.02984732,0.5173872,0.06689504,0.3781638],"study_design_scores_gemma":[0.001846629,0.001367603,0.001007971,0.0005779716,0.000135616,0.0005528159,0.00252195,0.1529555,0.4306833,0.02926428,0.3764661,0.002620209],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02392247,0.02873464,0.7162219,0.1979422,0.001548383,0.002139984,0.00003289929,0.006402558,0.02305499],"genre_scores_gemma":[0.9891424,0.000102673,0.007385585,0.001666267,0.0001867697,0.00001136868,0.000002315914,0.00001507698,0.001487579],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9652199,"threshold_uncertainty_score":0.7220084,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W60608539","doi":"","title":"Passage Retrieval by Shrinkage of Language Models.","year":2006,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Topic Modeling","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Guelph","funders":"","keywords":"Computer science; Information retrieval; Scope (computer science); Search engine; World Wide Web; The Internet; Process (computing); Human–computer information retrieval","retraction":null,"screen_n_in":null,"score":{"opus":0.02283974409388151,"gpt":0.2468398962509053,"spread":0.2240001521570238,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004755507,0.0002407515,0.0003505496,0.0001138335,0.00007850795,0.0001438713,0.001395929,0.000159309,0.0001077034],"category_scores_gemma":[0.00008278672,0.00023387,0.0001028258,0.0005616378,0.0001065294,0.0006011307,0.0003695229,0.0002942084,0.00004337688],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005942486,"about_ca_system_score_gemma":0.0001620002,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003714399,"about_ca_topic_score_gemma":0.00001252481,"domain_scores_codex":[0.9976327,0.00009328676,0.0005193313,0.0006023239,0.0007028182,0.0004495692],"domain_scores_gemma":[0.9983163,0.0001213394,0.0002186599,0.001023307,0.0002102877,0.0001101323],"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":[0.0001280554,0.0002804618,0.0006552702,0.0001367167,0.00003960824,0.00009255898,0.002435619,0.0009868373,0.2201825,0.7536514,0.004261122,0.01714986],"study_design_scores_gemma":[0.001505366,0.0002597771,0.0009269367,0.000129492,0.00002896097,0.00002885939,0.0001814339,0.6853189,0.2453852,0.06352153,0.001752892,0.0009606294],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2460372,0.0006865473,0.7266011,0.0003207804,0.0001842409,0.0001935808,0.00002536091,0.0002527617,0.02569843],"genre_scores_gemma":[0.9866465,0.00002258961,0.01016559,0.00009147651,0.00007027639,0.000001512056,0.00001349234,0.000016012,0.002972546],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7406093,"threshold_uncertainty_score":0.9536942,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}