{"meta":{"query_hash":"2026479010f0","filters":{"venue":"Natural Language Engineering"},"cohort_total":31,"direct_labels_cover":0,"predictions_cover":31,"exported":31,"export_cap":100000,"truncated":false,"label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"permalink":"https://metacan.xera.ac/q/2026479010f0","api":"https://metacan.xera.ac/api/v1/cohort?venue=Natural+Language+Engineering"},"results":[{"id":"W1971541835","doi":"10.1017/s1351324901002650","title":"Real-time automatic insertion of accents in French text","year":2001,"lang":"en","type":"article","venue":"Natural Language Engineering","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Computer Research Institute of Montréal","funders":"","keywords":"Computer science; Stress (linguistics); Character (mathematics); Word (group theory); Natural language processing; Speech recognition; Artificial intelligence; Linguistics","score_opus":0.004005314190147125,"score_gpt":0.23514128188684852,"score_spread":0.2311359676967014,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1971541835","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9684198,0.004058183,0.025747601,0.00007479345,0.00020975276,0.00017726407,0.0000011542434,0.0010772247,0.00023422345],"genre_scores_gemma":[0.78329706,0.000017101764,0.21650468,0.000017066037,0.000029042234,0.0000067695323,0.000004662744,0.0000115243,0.000112087604],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989499,0.00002190411,0.00027151726,0.00023184152,0.00025138346,0.00027349085],"domain_scores_gemma":[0.99942636,0.00006608152,0.00008084717,0.00034067445,0.00004232337,0.000043732205],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00018301864,0.00015463073,0.00020439885,0.00032416047,0.000018256835,0.0000475144,0.0006630679,0.00009467465,0.000024749746],"category_scores_gemma":[0.0001739489,0.00013868242,0.00004722364,0.00080793526,0.000010213063,0.0005769445,0.00015562278,0.00026739543,0.000012692719],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000050909093,0.00006796478,0.0012185612,0.00017262304,0.000016858072,0.00027116912,0.0023534265,0.0003670846,0.73785484,0.001368385,0.00011208882,0.2561919],"study_design_scores_gemma":[0.00040944817,0.000042328935,0.01900652,0.0004177383,0.0000056010545,0.00008093732,0.000023559156,0.90994596,0.06938758,0.00023760548,0.00004565733,0.00039703015],"about_ca_topic_score_codex":0.0002814207,"about_ca_topic_score_gemma":0.000012893881,"teacher_disagreement_score":0.9095789,"about_ca_system_score_codex":0.00011869851,"about_ca_system_score_gemma":0.000023375174,"threshold_uncertainty_score":0.5655305},"labels":[],"label_agreement":null},{"id":"W2029070039","doi":"10.1017/s135132490600444x","title":"A general feature space for automatic verb classification","year":2006,"lang":"en","type":"article","venue":"Natural Language Engineering","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":88,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canada Research Chairs; University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Lexicon; Artificial intelligence; Feature vector; Natural language processing; Feature (linguistics); Redundancy (engineering); Verb; Support vector machine; Variety (cybernetics); Feature selection; Machine learning; Linguistics","score_opus":0.004724068616820104,"score_gpt":0.235974427016896,"score_spread":0.2312503584000759,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2029070039","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.031018611,0.017087331,0.9461088,0.001398089,0.0006770262,0.00044790332,0.0000075201237,0.003108267,0.00014642093],"genre_scores_gemma":[0.48306888,0.0000010640091,0.5158736,0.000054091386,0.00023898753,0.000036351124,0.000024034805,0.000016442718,0.0006865161],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989389,0.000012451275,0.00015701517,0.00033089294,0.00021927213,0.00034145036],"domain_scores_gemma":[0.9993442,0.000082090366,0.00007524875,0.00038130677,0.00007285978,0.00004426298],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014289221,0.00020216356,0.00016679076,0.00015954394,0.000075134,0.00019375936,0.00060982694,0.00013168425,0.000002801844],"category_scores_gemma":[0.000118565375,0.00017612554,0.00009000428,0.00038141958,0.000010775913,0.0004649125,0.00008408884,0.00028819757,0.000005167272],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007945687,0.000043857275,0.00004553142,0.000329842,0.000029519366,0.00006294355,0.0006545996,0.00063830573,0.6270614,0.2547209,0.011247884,0.10515723],"study_design_scores_gemma":[0.00026713187,0.000023159246,0.0006951969,0.00006448664,0.000009813653,0.000044937715,0.000013384752,0.9324474,0.06272795,0.000972021,0.002383108,0.00035143597],"about_ca_topic_score_codex":0.000035723533,"about_ca_topic_score_gemma":0.000006763098,"teacher_disagreement_score":0.93180907,"about_ca_system_score_codex":0.0001410518,"about_ca_system_score_gemma":0.000027821417,"threshold_uncertainty_score":0.7182191},"labels":[],"label_agreement":null},{"id":"W2047851837","doi":"10.1017/s1351324901002716","title":"Scalable generation of texts using causal and temporal expansions of sentences","year":2001,"lang":"en","type":"article","venue":"Natural Language Engineering","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Lethbridge","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Sentence; Artificial intelligence; Natural language processing; Scalability; Kernel (algebra); Process (computing); Theoretical computer science; Information retrieval; Programming language","score_opus":0.015037052180989056,"score_gpt":0.2628490486382299,"score_spread":0.24781199645724084,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2047851837","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.81673723,0.01572579,0.16707109,0.000039332393,0.00016948178,0.00007918,0.0000020896832,0.00016070175,0.000015088976],"genre_scores_gemma":[0.70118076,0.000013428434,0.29871815,0.000009597681,0.000044737444,0.000001158087,0.0000027527537,0.0000057786337,0.000023630248],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99926126,0.00001463244,0.00020023166,0.00017827001,0.00018897951,0.00015661532],"domain_scores_gemma":[0.99957436,0.00003602299,0.0000879374,0.00018755729,0.000075529046,0.000038602608],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00013232815,0.00011080555,0.00016443401,0.00015803252,0.000034939127,0.000031599386,0.00023649064,0.00006181744,0.0000036042395],"category_scores_gemma":[0.000090970665,0.00009352991,0.000030913656,0.00036092673,0.000026176333,0.00044322084,0.00011846809,0.00014183216,1.8968291e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000023732905,0.000011890977,0.00080756267,0.000055865272,0.000009384128,0.000028560395,0.0007230564,0.0004322385,0.98352414,0.00138454,0.000014454177,0.013005933],"study_design_scores_gemma":[0.00013704652,0.000031258438,0.00030991648,0.0001365092,0.000008285559,0.00011121335,0.000072445044,0.5973214,0.4016088,0.00007400581,0.000020834523,0.00016830202],"about_ca_topic_score_codex":0.00022589363,"about_ca_topic_score_gemma":0.000015162739,"teacher_disagreement_score":0.59688914,"about_ca_system_score_codex":0.000023931485,"about_ca_system_score_gemma":0.000024377317,"threshold_uncertainty_score":0.38140392},"labels":[],"label_agreement":null},{"id":"W2052696540","doi":"10.1017/s1351324908005044","title":"A corpus-based analysis of argument realization by preposition structures","year":2009,"lang":"en","type":"article","venue":"Natural Language Engineering","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"FrameNet; Computer science; Realization (probability); Argument (complex analysis); Natural language processing; Artificial intelligence; Semantics (computer science); Semantic role labeling; Linguistics; Frame (networking); Parsing; Programming language; Sentence; Mathematics; Philosophy","score_opus":0.0024766510758832297,"score_gpt":0.231932056132034,"score_spread":0.22945540505615075,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2052696540","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.055814415,0.01118239,0.93200326,0.00010473273,0.00009182387,0.00012342077,0.000008376438,0.0006476469,0.000023940744],"genre_scores_gemma":[0.84012026,0.0000037852972,0.15961799,0.00012388856,0.000016227208,0.0000030702904,0.000091980466,0.000005447584,0.000017342241],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990851,0.000018392107,0.00021033482,0.00023721633,0.00028113884,0.00016778741],"domain_scores_gemma":[0.9994185,0.000035193334,0.00011748501,0.0003163714,0.000072067305,0.00004037255],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010152977,0.00013894598,0.00020142735,0.00037379834,0.00002964183,0.00006680033,0.00038657794,0.000074983574,0.000004698105],"category_scores_gemma":[0.000067850306,0.00012155343,0.00009212058,0.0011812581,0.00000742379,0.0002645266,0.000029885623,0.00014877882,2.34399e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015475041,0.000048576265,0.00012257934,0.000057942565,0.00016653327,0.000027722248,0.00080039515,0.019362198,0.8804362,0.02009866,0.00025483855,0.07860892],"study_design_scores_gemma":[0.00013149141,0.000054553042,0.0012533022,0.00003760364,0.00008871772,0.0000039032716,0.000004923895,0.5381186,0.45977086,0.00030614258,0.00003633788,0.00019360112],"about_ca_topic_score_codex":0.0000325519,"about_ca_topic_score_gemma":0.0000035409723,"teacher_disagreement_score":0.7843059,"about_ca_system_score_codex":0.00008385123,"about_ca_system_score_gemma":0.000014528481,"threshold_uncertainty_score":0.49568048},"labels":[],"label_agreement":null},{"id":"W2058214962","doi":"10.1017/s1351324913000090","title":"On the semantics of noun compounds","year":2013,"lang":"en","type":"article","venue":"Natural Language Engineering","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Automatic summarization; Computer science; Noun; Natural language processing; Cover (algebra); Artificial intelligence; Proper noun; Semantics (computer science); Subject (documents); Machine translation; Linguistics; Noun phrase; Question answering; Sequence (biology); World Wide Web; Programming language; Philosophy; Chemistry","score_opus":0.0038637183364422247,"score_gpt":0.2078067341440626,"score_spread":0.20394301580762036,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2058214962","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5202578,0.014047343,0.4524724,0.005858913,0.0014412277,0.00097301474,0.0000048641364,0.0027812584,0.0021631957],"genre_scores_gemma":[0.8676668,0.0000019664403,0.13191642,0.00024784883,0.000036849382,0.000010399402,0.0000012351084,0.000010909149,0.00010757305],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992133,0.000016153384,0.00014870084,0.00016343698,0.0002526695,0.00020574046],"domain_scores_gemma":[0.9991627,0.00023905326,0.00005944695,0.00044775373,0.000058253456,0.00003281234],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012727646,0.00013653476,0.00012985358,0.0000779223,0.000041097308,0.000093858056,0.0008775565,0.000056299148,0.000037726797],"category_scores_gemma":[0.00020937917,0.0000847855,0.00005549593,0.000338381,0.000021389053,0.0002717786,0.00019933317,0.00035288985,0.000036857313],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000039344554,0.000053025542,0.00005624063,0.00012607986,0.000052230094,0.00004415566,0.0026545578,0.00044769913,0.4865402,0.45634612,0.009554303,0.044121448],"study_design_scores_gemma":[0.0003114835,0.00012198801,0.0009766724,0.00031168142,0.000012850061,0.00007826166,0.00010759491,0.53891194,0.4494552,0.008307411,0.0006771802,0.0007277403],"about_ca_topic_score_codex":0.00005819524,"about_ca_topic_score_gemma":0.0000012612314,"teacher_disagreement_score":0.53846425,"about_ca_system_score_codex":0.000036890608,"about_ca_system_score_gemma":0.000009377606,"threshold_uncertainty_score":0.34574524},"labels":[],"label_agreement":null},{"id":"W2089752704","doi":"10.1017/s1351324910000264","title":"Subjectivity detection in spoken and written conversations","year":2010,"lang":"en","type":"article","venue":"Natural Language Engineering","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Conversation; Set (abstract data type); Subjectivity; Natural language processing; Artificial intelligence; Domain (mathematical analysis); Speech recognition; Linguistics","score_opus":0.0024433274761154348,"score_gpt":0.20363026364576112,"score_spread":0.20118693616964567,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2089752704","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97623724,0.0002286822,0.02288679,0.00007160596,0.00040312385,0.000035985693,2.3106409e-7,0.00007546315,0.000060876988],"genre_scores_gemma":[0.99355125,0.000002145576,0.006334227,0.00001593603,0.000057691566,0.000002272397,0.0000013340444,0.0000031705729,0.00003196582],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9996126,0.0000063559264,0.000069613205,0.000134244,0.000074135634,0.000103039296],"domain_scores_gemma":[0.9997878,0.000045798435,0.000016129226,0.00011333992,0.000010592596,0.000026354732],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012484792,0.00005641611,0.00006553554,0.00014108943,0.000025978568,0.000058558362,0.00010020657,0.000034788332,0.000007631134],"category_scores_gemma":[0.00005080345,0.000053796903,0.000020770583,0.00023683047,0.000005139335,0.00026644522,0.000045352594,0.00022520398,0.0000031902573],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000030267943,0.000021032403,0.01057286,0.000018201985,0.000026815771,0.000035145626,0.004896181,0.0006906486,0.812909,0.0032953206,0.000011066293,0.16752069],"study_design_scores_gemma":[0.0001948622,0.000006141304,0.12514243,0.000006912992,0.000002948382,0.000011672816,0.00008243727,0.84666157,0.02762984,0.000010349554,0.00013100248,0.00011983909],"about_ca_topic_score_codex":0.00009290009,"about_ca_topic_score_gemma":0.00020581497,"teacher_disagreement_score":0.8459709,"about_ca_system_score_codex":0.000012434544,"about_ca_system_score_gemma":0.0000038338617,"threshold_uncertainty_score":0.21937741},"labels":[],"label_agreement":null},{"id":"W2101481293","doi":"10.1017/s1351324905003694","title":"Segmenting documents by stylistic character","year":2005,"lang":"en","type":"article","venue":"Natural Language Engineering","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":104,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"IBM (Canada); University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Character (mathematics); Bigram; Natural language processing; Artificial intelligence; Vocabulary; Baseline (sea); Artificial neural network; Market segmentation; Information retrieval; Linguistics; Trigram","score_opus":0.002330387928883056,"score_gpt":0.22306770749537055,"score_spread":0.2207373195664875,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2101481293","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10098847,0.07203068,0.8167299,0.0013499844,0.0011580455,0.0004962252,0.000016363781,0.0062672175,0.0009631183],"genre_scores_gemma":[0.683963,0.00000617535,0.31469303,0.00031448403,0.00016342981,0.000010485462,0.000015051789,0.000018678536,0.00081569573],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9986805,0.000014675939,0.00021273519,0.00034923747,0.00030997276,0.0004328938],"domain_scores_gemma":[0.9993882,0.00005321521,0.00007094934,0.00036328274,0.00003808533,0.00008626459],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00017233205,0.00021999897,0.00016291608,0.00012957008,0.00006876089,0.00025946795,0.0008081105,0.00008360177,0.000031058287],"category_scores_gemma":[0.000107139895,0.00019586233,0.00005921471,0.00029178982,0.000009428623,0.0011274125,0.0002468994,0.0004385067,0.000048563394],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004510795,0.00004754789,0.000060280665,0.000089393594,0.000046144287,0.000095392694,0.0013882887,0.00010459014,0.5649291,0.007009497,0.0033081223,0.4229171],"study_design_scores_gemma":[0.0009252927,0.000054868928,0.00023107449,0.00031247167,0.00002768702,0.0001825479,0.00005498858,0.4112251,0.5360843,0.00012539193,0.049111586,0.0016646747],"about_ca_topic_score_codex":0.000015724323,"about_ca_topic_score_gemma":0.000001639616,"teacher_disagreement_score":0.5829745,"about_ca_system_score_codex":0.0001497417,"about_ca_system_score_gemma":0.000012921069,"threshold_uncertainty_score":0.79870343},"labels":[],"label_agreement":null},{"id":"W2121929533","doi":"10.1017/s135132491300003x","title":"Designing a machine translation system for Canadian weather warnings: A case study","year":2013,"lang":"en","type":"article","venue":"Natural Language Engineering","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université de Montréal; Université du Québec à Montréal","funders":"","keywords":"Computer science; Machine translation; Natural language processing; Metric (unit); Task (project management); Quality (philosophy); Domain (mathematical analysis); Evaluation of machine translation; Translation (biology); Artificial intelligence; Machine translation software usability; Presentation (obstetrics); Example-based machine translation; Machine learning; Information retrieval; Systems engineering","score_opus":0.007204560510228801,"score_gpt":0.2309438070816249,"score_spread":0.2237392465713961,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2121929533","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12643479,0.015788931,0.85310954,0.0001661433,0.00044653783,0.0018567885,0.000006514247,0.0021464298,0.00004430395],"genre_scores_gemma":[0.6723041,2.1162916e-7,0.32738447,0.000029487162,0.000063519925,0.00015008356,0.000004355606,0.000023725568,0.000040076466],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99883705,0.00003044875,0.00021223175,0.00033648373,0.0001662069,0.00041757076],"domain_scores_gemma":[0.9992818,0.00011467623,0.00005512831,0.00030413843,0.00009302844,0.00015120677],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00027568458,0.00021890347,0.00018983036,0.00031290768,0.0001630904,0.00027568912,0.00045115288,0.000089312125,0.00000854253],"category_scores_gemma":[0.00008129715,0.00018742544,0.00006532075,0.00035338083,0.0000054508023,0.0006675928,0.000040689505,0.00031000315,0.0000075272765],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013845182,0.0000969597,0.0004866862,0.0008016344,0.00023292347,0.009077026,0.10510896,0.0011054587,0.11699447,0.0016291899,0.00029873924,0.76415414],"study_design_scores_gemma":[0.0005598853,0.000101025544,0.000027561178,0.0001263877,0.00002412201,0.0019417788,0.0028044246,0.98451054,0.009283567,0.000018934903,0.00011183404,0.0004899245],"about_ca_topic_score_codex":0.052052323,"about_ca_topic_score_gemma":0.005714921,"teacher_disagreement_score":0.9834051,"about_ca_system_score_codex":0.00024370599,"about_ca_system_score_gemma":0.00004847752,"threshold_uncertainty_score":0.9542602},"labels":[],"label_agreement":null},{"id":"W2126034021","doi":"10.1017/s1351324901002765","title":"Discovery of inference rules for question-answering","year":2001,"lang":"en","type":"article","venue":"Natural Language Engineering","topic":"Topic Modeling","field":"Computer Science","cited_by":532,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Question answering; Inference; Computer science; Dependency (UML); Set (abstract data type); Parsing; Artificial intelligence; Natural language processing; Rule of inference; Programming language","score_opus":0.00715054306742324,"score_gpt":0.2517287714730841,"score_spread":0.24457822840566085,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2126034021","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.32969204,0.0010450957,0.6687211,0.000035879526,0.00029619032,0.000058945858,0.0000016789558,0.000104483646,0.000044606903],"genre_scores_gemma":[0.85686296,0.0000082973,0.14288828,0.000014085892,0.00009429534,0.000007891576,0.0000031435031,0.0000064876212,0.00011457482],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99940544,0.000004998661,0.000143718,0.00016229316,0.00011187065,0.00017170057],"domain_scores_gemma":[0.99955714,0.000116846495,0.000033986216,0.00023600648,0.000033392484,0.000022623439],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00010354827,0.000088412016,0.00011180978,0.00007512856,0.00002051287,0.00005107102,0.0003342052,0.00003601382,0.0000012235042],"category_scores_gemma":[0.00018266862,0.000081373226,0.000049428105,0.00011230754,0.000005312778,0.00051084533,0.00007745496,0.000101462734,0.0000013340582],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017205928,0.000042692176,0.0015354784,0.00035335272,0.000057737587,0.000059234364,0.0043472713,0.12694141,0.29985327,0.332292,0.000026248754,0.2344741],"study_design_scores_gemma":[0.0001601156,0.000014796295,0.0011018283,0.00009899991,0.0000034386135,0.000011457343,0.000035080855,0.9833108,0.01479864,0.00016396646,0.00014713389,0.0001537326],"about_ca_topic_score_codex":0.000034475972,"about_ca_topic_score_gemma":0.000004136893,"teacher_disagreement_score":0.8563694,"about_ca_system_score_codex":0.000027390039,"about_ca_system_score_gemma":0.000012592507,"threshold_uncertainty_score":0.33183038},"labels":[],"label_agreement":null},{"id":"W2128424286","doi":"10.1017/s1351324911000167","title":"Query-focused multi-document summarization: automatic data annotations and supervised learning approaches","year":2011,"lang":"en","type":"article","venue":"Natural Language Engineering","topic":"Topic Modeling","field":"Computer Science","cited_by":36,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Lethbridge","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Automatic summarization; Artificial intelligence; Conditional random field; Semi-supervised learning; Supervised learning; Support vector machine; Annotation; Machine learning; Information retrieval; Natural language processing; Artificial neural network","score_opus":0.05869544911709373,"score_gpt":0.23725411456844478,"score_spread":0.17855866545135105,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2128424286","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10155777,0.0018244709,0.8955594,0.00006999616,0.00023666753,0.00014891021,0.0000020035845,0.0005202884,0.00008051448],"genre_scores_gemma":[0.6284912,0.000003520428,0.37135637,0.000015057366,0.000030503024,0.0000060091315,0.000023857772,0.000008885814,0.00006457208],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99911666,0.000028416085,0.00017109812,0.00033350612,0.00014859998,0.00020171785],"domain_scores_gemma":[0.9993098,0.00005573693,0.00003568013,0.0005166468,0.000020208863,0.000061938576],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019916748,0.00012946098,0.00011766851,0.0001006936,0.00007646188,0.00010840401,0.0005803596,0.000047059864,0.000010784627],"category_scores_gemma":[0.00015035477,0.00012173021,0.000017971559,0.00019490204,0.000009516477,0.00078794896,0.0003797776,0.00023461046,0.000004795518],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000055331534,0.0001090676,0.0039246725,0.00047503412,0.0001877856,0.00015638008,0.08322764,0.047732867,0.0062124385,0.029120324,0.000044669625,0.8288036],"study_design_scores_gemma":[0.00022515024,0.0000075704606,0.002344265,0.00002713925,0.0000069535517,0.000009617103,0.00020024493,0.99664176,0.00033303857,0.000009376288,0.00004266895,0.00015219713],"about_ca_topic_score_codex":0.00006810282,"about_ca_topic_score_gemma":0.000012093066,"teacher_disagreement_score":0.9489089,"about_ca_system_score_codex":0.000024367779,"about_ca_system_score_gemma":0.00001626395,"threshold_uncertainty_score":0.4964014},"labels":[],"label_agreement":null},{"id":"W2129174913","doi":"10.1017/s1351324908004683","title":"Industry Watch: Language technology, meet social networking","year":2008,"lang":"en","type":"article","venue":"Natural Language Engineering","topic":"Service-Oriented Architecture and Web Services","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Thread (computing); World Wide Web; Quarter (Canadian coin); Language technology; Data science; Telecommunications; Artificial intelligence; Natural language; Programming language; Comprehension approach; History","score_opus":0.0046112725476018706,"score_gpt":0.20963480101097304,"score_spread":0.20502352846337116,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2129174913","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9783779,0.0065787197,0.008864458,0.0021009897,0.0013613199,0.00013576198,0.0000032399062,0.0016618011,0.00091584906],"genre_scores_gemma":[0.98884946,0.000006507656,0.009447878,0.0005943178,0.0009246285,0.000009891718,0.000008695111,0.000023389235,0.00013523191],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987024,0.000016799388,0.00017994034,0.0003441847,0.0002588926,0.00049775257],"domain_scores_gemma":[0.99943125,0.000047707683,0.000056147113,0.00035795546,0.000034322125,0.00007260021],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000089976806,0.0002276997,0.00020400491,0.00019907032,0.00019593,0.000052101444,0.0009388284,0.0004469572,0.000009776328],"category_scores_gemma":[0.000011656391,0.00020388272,0.0000772761,0.001080254,0.000024997029,0.00027437476,0.00035135742,0.0012990949,0.000015684112],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005713178,0.00028052877,0.008473924,0.0005428713,0.0006922266,0.008859359,0.25052997,0.014118675,0.27881303,0.049895626,0.0058018486,0.38193482],"study_design_scores_gemma":[0.005658058,0.0003390803,0.019915484,0.0008962828,0.00014253239,0.0048744553,0.0146056395,0.5530086,0.27466735,0.00055678224,0.11826592,0.00706977],"about_ca_topic_score_codex":0.000072856004,"about_ca_topic_score_gemma":0.000034324603,"teacher_disagreement_score":0.53888994,"about_ca_system_score_codex":0.000041657902,"about_ca_system_score_gemma":0.000022264265,"threshold_uncertainty_score":0.83140963},"labels":[],"label_agreement":null},{"id":"W2129913068","doi":"10.1017/s135132491100012x","title":"Learning opinions in user-generated web content","year":2011,"lang":"en","type":"article","venue":"Natural Language Engineering","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Children's Hospital of Eastern Ontario; University of Ottawa","funders":"","keywords":"Computer science; Construct (python library); Information retrieval; Product (mathematics); Hierarchy; User-generated content; Natural language processing; Sentiment analysis; World Wide Web; Artificial intelligence; Web content; Web page; Social media","score_opus":0.022416421518357734,"score_gpt":0.22655476296845853,"score_spread":0.2041383414501008,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2129913068","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9710552,0.0026093435,0.023945587,0.00007365037,0.0010424597,0.00010448211,9.4577416e-7,0.0004098128,0.0007584849],"genre_scores_gemma":[0.9787441,0.000010045528,0.020676818,0.000033595028,0.000059143353,0.0000055197665,0.000013876234,0.000009129622,0.0004477894],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99920744,0.00002287206,0.00018008897,0.00021375406,0.00013400079,0.00024186901],"domain_scores_gemma":[0.9996817,0.000030114268,0.000037258673,0.00017361341,0.000025588517,0.00005172268],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00015018522,0.00011461516,0.00013820818,0.00021968612,0.000036278776,0.000054355573,0.00032262207,0.0000435067,0.00004387318],"category_scores_gemma":[0.000060177033,0.000103458304,0.00006149107,0.00047827326,0.0000048668576,0.00027041082,0.00010141681,0.00027884194,0.000024894594],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000039556704,0.00035892622,0.06958693,0.000120368946,0.00052561803,0.0011125326,0.066479586,0.061643943,0.58852905,0.088656336,0.00089433434,0.12205283],"study_design_scores_gemma":[0.00042192423,0.000029716679,0.0148421135,0.00005430286,0.0000048416023,0.0000084763715,0.00046565293,0.96924806,0.013673824,0.0000019366016,0.0009818352,0.00026730666],"about_ca_topic_score_codex":0.00007178161,"about_ca_topic_score_gemma":0.000016289192,"teacher_disagreement_score":0.9076041,"about_ca_system_score_codex":0.000032683314,"about_ca_system_score_gemma":0.000011842993,"threshold_uncertainty_score":0.4218907},"labels":[],"label_agreement":null},{"id":"W2136433925","doi":"10.1017/s1351324903003231","title":"Surface-marker-based dialog modelling: A progress report on the MAREDI project","year":2003,"lang":"en","type":"article","venue":"Natural Language Engineering","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; Université Laval; Université du Québec à Trois-Rivières","funders":"","keywords":"Computer science; Dialog box; Natural language processing; Connectionism; Semantics (computer science); Conversation; Spoken language; Artificial intelligence; Natural language; Natural language understanding; Natural language generation; Programming language; Linguistics; Artificial neural network; World Wide Web","score_opus":0.01414064130185601,"score_gpt":0.25566720439021334,"score_spread":0.24152656308835732,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2136433925","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08046877,0.023979707,0.88536674,0.001404117,0.0015701993,0.0014055419,0.000008146047,0.0043444857,0.0014523208],"genre_scores_gemma":[0.69077003,0.0000020342447,0.3087471,0.00014963948,0.00005822473,0.000037104557,0.0000072020994,0.0000272255,0.00020142757],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99811053,0.000082764804,0.000279154,0.00051779166,0.00051458477,0.00049514737],"domain_scores_gemma":[0.9985713,0.00027002936,0.00011880228,0.00087648805,0.00009870142,0.00006468871],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007363633,0.00031299016,0.00021761745,0.00014072322,0.00012808501,0.0002586252,0.00093109836,0.00013185042,0.000008843194],"category_scores_gemma":[0.0005223817,0.00020523273,0.00011727938,0.0007122201,0.00003641091,0.00028647482,0.00009618661,0.00072698784,0.0000062954095],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022550742,0.00087089103,0.0017195004,0.0012935505,0.00050521264,0.019328378,0.009685212,0.20244333,0.04647653,0.62569505,0.012635941,0.07912088],"study_design_scores_gemma":[0.00025751663,0.00006865749,0.000021312,0.00020352796,0.0000117884065,0.0002453732,0.00002739835,0.9265581,0.06835237,0.00055440026,0.0031012697,0.0005983188],"about_ca_topic_score_codex":0.000026833288,"about_ca_topic_score_gemma":0.0000020960294,"teacher_disagreement_score":0.7241147,"about_ca_system_score_codex":0.00012653018,"about_ca_system_score_gemma":0.00012315201,"threshold_uncertainty_score":0.8369148},"labels":[],"label_agreement":null},{"id":"W2137926008","doi":"10.1017/s1351324905004043","title":"Can syllabification improve pronunciation by analogy of English?","year":2006,"lang":"en","type":"article","venue":"Natural Language Engineering","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":38,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada; National Research Council Institute for Biodiagnostics","funders":"","keywords":"Syllabification; Pronunciation; Computer science; Syllable; Natural language processing; Analogy; Artificial intelligence; Speech recognition; Word (group theory); Linguistics","score_opus":0.0016253391825071673,"score_gpt":0.19236527812346438,"score_spread":0.1907399389409572,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2137926008","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15176858,0.04676037,0.794357,0.0004600663,0.002021309,0.0007221935,0.00005403603,0.0033349697,0.00052144704],"genre_scores_gemma":[0.885418,0.000002450943,0.11418799,0.000022959497,0.00017889937,0.000013239792,0.000048955408,0.0000125083525,0.00011500207],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99905354,0.000015993752,0.00023001805,0.0002527767,0.00022731475,0.00022036754],"domain_scores_gemma":[0.99925184,0.000046472294,0.00012379744,0.0003031611,0.00024557047,0.000029173887],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014860171,0.00014026552,0.00014998156,0.00014081976,0.00002762691,0.00005174293,0.0004565407,0.000097485026,0.000002294784],"category_scores_gemma":[0.0003050737,0.00012852896,0.00004331939,0.00040798687,0.000012594527,0.00033434917,0.000071128256,0.00022520464,9.43819e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000003236898,0.000029952536,0.000117139876,0.000101525875,0.000011373519,0.0000066492057,0.0012030579,0.00018864028,0.9337728,0.029750658,0.0007842364,0.034030724],"study_design_scores_gemma":[0.00022450414,0.000041194988,0.00035848946,0.000043126252,0.000008922343,0.000004311391,0.000026839172,0.062458437,0.9352837,0.0006434356,0.00058451353,0.00032248526],"about_ca_topic_score_codex":0.00026083688,"about_ca_topic_score_gemma":0.000019207066,"teacher_disagreement_score":0.73364943,"about_ca_system_score_codex":0.00012230963,"about_ca_system_score_gemma":0.000027166061,"threshold_uncertainty_score":0.52412593},"labels":[],"label_agreement":null},{"id":"W2148362501","doi":"10.1017/s1351324904003560","title":"Correcting real-word spelling errors by restoring lexical cohesion","year":2005,"lang":"en","type":"article","venue":"Natural Language Engineering","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":180,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Spelling; Computer science; Cohesion (chemistry); Natural language processing; Lexicon; Artificial intelligence; Word (group theory); Context (archaeology); Precision and recall; Recall; Speech recognition; Linguistics","score_opus":0.005958882391220053,"score_gpt":0.2512037126170917,"score_spread":0.24524483022587162,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2148362501","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.37638217,0.038820416,0.5752135,0.00077534094,0.0019636496,0.00033440447,0.0000035926107,0.0059765917,0.00053032616],"genre_scores_gemma":[0.6607376,0.000018599405,0.33838207,0.0000779281,0.0003593745,0.0000048046477,0.0000065976897,0.000028488892,0.0003845784],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.998158,0.00002959585,0.00031496628,0.0005049958,0.00043153978,0.0005609539],"domain_scores_gemma":[0.9990621,0.00016547657,0.00010241096,0.00047768236,0.000056550452,0.0001357514],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003714146,0.0002932264,0.00024842887,0.00019517996,0.00012705679,0.00020029773,0.0008950278,0.00016555702,0.000011340335],"category_scores_gemma":[0.0002943757,0.0002719601,0.00009110592,0.0005316759,0.00001652171,0.00090009824,0.0002581748,0.00087142934,0.000026527297],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014713839,0.00004012095,0.00014336054,0.00009228502,0.00002549757,0.00016686047,0.0031862454,0.0022930156,0.3500535,0.003082414,0.0017188141,0.6391832],"study_design_scores_gemma":[0.00034320448,0.000044244967,0.000100191435,0.00031034657,0.000013260564,0.00024246608,0.00012350174,0.44572204,0.5483044,0.000081243175,0.003772132,0.00094300875],"about_ca_topic_score_codex":0.00012800371,"about_ca_topic_score_gemma":0.000015216016,"teacher_disagreement_score":0.6382402,"about_ca_system_score_codex":0.00031638998,"about_ca_system_score_gemma":0.000026268452,"threshold_uncertainty_score":0.99997324},"labels":[],"label_agreement":null},{"id":"W2157616430","doi":"10.1017/s1351324908004737","title":"Multilingual pronunciation by analogy","year":2008,"lang":"en","type":"article","venue":"Natural Language Engineering","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Institute for Biodiagnostics","funders":"","keywords":"Computer science; Pronunciation; Transcription (linguistics); Natural language processing; Orthography; Spelling; Analogy; Artificial intelligence; Variation (astronomy); Phonetic transcription; Linguistics; Speech recognition","score_opus":0.004698680563171272,"score_gpt":0.2267604826131823,"score_spread":0.22206180205001103,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2157616430","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.39212367,0.055291433,0.5461189,0.00034830975,0.00097486953,0.00035672289,0.000008486305,0.004578122,0.00019943785],"genre_scores_gemma":[0.7724401,0.000010049079,0.22702183,0.00011565375,0.00009729596,0.000009342285,0.00001574393,0.0000143400675,0.00027568158],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9988987,0.000017009177,0.00017676648,0.00031306042,0.00027486216,0.00031964233],"domain_scores_gemma":[0.99944055,0.00005734099,0.000059152393,0.00030725726,0.00006834711,0.00006736026],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00011774722,0.00017632815,0.0001554626,0.00013964377,0.0000876761,0.00004844585,0.0006054852,0.00010352722,0.000006599016],"category_scores_gemma":[0.0002495014,0.00015771341,0.00005429528,0.00038627154,0.00001718809,0.0005220236,0.0001299876,0.0003858211,0.000013446897],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000134692855,0.00009012698,0.00042062573,0.00010987648,0.00005691723,0.0008007649,0.008427103,0.00039544358,0.7306762,0.0058143693,0.005573642,0.24762146],"study_design_scores_gemma":[0.0005758985,0.0000752187,0.0005774476,0.00006317936,0.000008472651,0.0005398288,0.000043559136,0.24013586,0.7539868,0.00014257501,0.0029852614,0.00086591876],"about_ca_topic_score_codex":0.000047819864,"about_ca_topic_score_gemma":0.000003284512,"teacher_disagreement_score":0.38031638,"about_ca_system_score_codex":0.0001108176,"about_ca_system_score_gemma":0.000035435627,"threshold_uncertainty_score":0.6431366},"labels":[],"label_agreement":null},{"id":"W2159087629","doi":"10.1017/s1351324911000118","title":"A hierarchical approach to mood classification in blogs","year":2011,"lang":"en","type":"article","venue":"Natural Language Engineering","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Task (project management); Mood; Hierarchy; Set (abstract data type); Artificial intelligence; Machine learning; Sentiment analysis; Training set; Orientation (vector space); Natural language processing; Data set; Psychology","score_opus":0.01986886967877055,"score_gpt":0.23441606871738657,"score_spread":0.21454719903861602,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2159087629","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4378887,0.00068223075,0.5529232,0.00014605638,0.00042257181,0.00018532529,5.7099163e-7,0.00028009634,0.0074712536],"genre_scores_gemma":[0.85308796,9.2980486e-7,0.14673455,0.000045378318,0.000040871353,0.000009765399,0.0000036782162,0.0000049942487,0.00007185154],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9993063,0.000012863226,0.00013391509,0.00022753586,0.00013547044,0.00018391307],"domain_scores_gemma":[0.99967235,0.000019111081,0.000018285815,0.00022035693,0.000011916261,0.000057953832],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001381395,0.00008316101,0.000099578836,0.00022860734,0.00001635674,0.00003681847,0.00036126576,0.00003806726,0.0000074213],"category_scores_gemma":[0.00003801255,0.00007398154,0.000040167008,0.00051642436,0.0000035483768,0.00016210173,0.00008384266,0.0001772434,0.000017947108],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000043326323,0.0007372482,0.011018869,0.00012315129,0.00018617936,0.00011911129,0.12503874,0.011099554,0.15930597,0.4355741,0.0005334883,0.25622025],"study_design_scores_gemma":[0.00016610268,0.000013447365,0.046145935,0.000016233827,0.0000027762183,0.0000056009403,0.0001819482,0.9509222,0.0022542658,0.000016882817,0.00010767029,0.00016692029],"about_ca_topic_score_codex":0.00002145864,"about_ca_topic_score_gemma":0.0000028358038,"teacher_disagreement_score":0.9398227,"about_ca_system_score_codex":0.000027906308,"about_ca_system_score_gemma":0.0000058871265,"threshold_uncertainty_score":0.30168796},"labels":[],"label_agreement":null},{"id":"W2160938081","doi":"10.1017/s1351324912000289","title":"Modeling human newspaper readers: The Fuzzy Believer approach","year":2012,"lang":"en","type":"article","venue":"Natural Language Engineering","topic":"Topic Modeling","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Newspaper; Computer science; Fuzzy logic; Set (abstract data type); Artificial intelligence; Range (aeronautics); Natural (archaeology); Fuzzy set; Information extraction; Natural language processing; Information retrieval; Data mining; Advertising; Programming language","score_opus":0.015391496316516116,"score_gpt":0.2320307436379919,"score_spread":0.21663924732147577,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2160938081","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1533765,0.00772042,0.8356439,0.00021510366,0.0007729686,0.00015294895,4.6953366e-7,0.0004773224,0.0016404003],"genre_scores_gemma":[0.9056759,0.0000022385007,0.093256846,0.00019658475,0.00061476766,0.000011132001,0.0000034080872,0.00001760693,0.00022152702],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988541,0.000020248372,0.00016442387,0.00022665833,0.00026159303,0.00047295992],"domain_scores_gemma":[0.9992811,0.000031758333,0.000022094076,0.0005597812,0.000021554293,0.00008369671],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002933752,0.00016457251,0.00012120125,0.00006507017,0.00011844819,0.000101451515,0.0007244508,0.00007234208,0.000004749652],"category_scores_gemma":[0.000041167623,0.00011512484,0.00006953281,0.00019475426,0.000008337685,0.0006675781,0.00021682336,0.00044378248,0.000014737802],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000002366242,0.00006254878,0.00016822379,0.00009242136,0.000083798666,0.0000142784165,0.043279357,0.79743147,0.029973492,0.09644469,0.00024622167,0.032201126],"study_design_scores_gemma":[0.0000998709,0.0000029384826,0.000101112244,0.000013122407,0.000005617579,0.000025780013,0.00039566332,0.9985731,0.0003408999,0.000023130133,0.00023334868,0.00018537915],"about_ca_topic_score_codex":0.000084746986,"about_ca_topic_score_gemma":0.0000021817239,"teacher_disagreement_score":0.75229937,"about_ca_system_score_codex":0.00005122065,"about_ca_system_score_gemma":0.000007597086,"threshold_uncertainty_score":0.46946546},"labels":[],"label_agreement":null},{"id":"W2167742478","doi":"10.1017/s1351324911000210","title":"Exploring patterns in dictionary definitions for synonym extraction","year":2011,"lang":"en","type":"article","venue":"Natural Language Engineering","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Synonym (taxonomy); Natural language processing; Artificial intelligence; Lexicon; Quality (philosophy)","score_opus":0.07898671688241453,"score_gpt":0.262412322812195,"score_spread":0.18342560592978047,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2167742478","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12898715,0.0039512957,0.864161,0.00006982639,0.0009628681,0.00027967797,0.000009429573,0.0014198595,0.0001588658],"genre_scores_gemma":[0.6790269,0.000022824712,0.32066417,0.000029362718,0.00007252603,0.0001420856,0.000009631547,0.000014241525,0.000018249852],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991185,0.000010938182,0.00018694712,0.00027084054,0.00013218018,0.0002806109],"domain_scores_gemma":[0.9995325,0.00009729845,0.000044360695,0.00024020908,0.00003996166,0.000045652836],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001430908,0.00014770457,0.00012138981,0.00030743424,0.00005360972,0.000047098194,0.00037886357,0.00006195451,0.00001091717],"category_scores_gemma":[0.0001186929,0.00014427248,0.00006265164,0.00031793353,0.0000059604236,0.001381437,0.0000828646,0.00032364714,0.0000039085985],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000757608,0.0003454035,0.0020644632,0.0007307218,0.00009179658,0.0008692913,0.025939215,0.0005872071,0.17715307,0.2276152,0.00012429526,0.56440353],"study_design_scores_gemma":[0.0020179718,0.0003342804,0.042471696,0.0015254938,0.00005106309,0.00069014664,0.0014337444,0.36913508,0.57140195,0.007170641,0.0009548017,0.0028131383],"about_ca_topic_score_codex":0.000101282356,"about_ca_topic_score_gemma":0.00002232096,"teacher_disagreement_score":0.56159043,"about_ca_system_score_codex":0.000111022055,"about_ca_system_score_gemma":0.00001473861,"threshold_uncertainty_score":0.5883261},"labels":[],"label_agreement":null},{"id":"W2763406350","doi":"10.1017/s1351324917000389","title":"Emerging trends: A tribute to Charles Wayne","year":2017,"lang":"en","type":"article","venue":"Natural Language Engineering","topic":"Text and Document Classification Technologies","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Alberta-Pacific Forest Industries","keywords":"Tribute; Order (exchange); Government (linguistics); Computer science; sort; Management; Law; Political science; Economics; Finance; Philosophy; Linguistics","score_opus":0.007743718129550689,"score_gpt":0.2627037147876462,"score_spread":0.2549599966580955,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2763406350","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3229645,0.008195444,0.6063191,0.04880725,0.0042364374,0.00037612751,0.000016556694,0.006801171,0.0022833908],"genre_scores_gemma":[0.9726377,0.000008446574,0.024905745,0.00005516427,0.00008310281,0.000016171069,0.0000028540642,0.000008046289,0.0022827752],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992539,0.000003459158,0.00010985364,0.00023441724,0.00015039362,0.00024797732],"domain_scores_gemma":[0.9990559,0.000020136444,0.00005406214,0.00079229305,0.000021368292,0.000056198904],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009070981,0.00011673734,0.00011234256,0.00020113718,0.0001670577,0.00035241304,0.0012847917,0.000046847334,0.0000115512885],"category_scores_gemma":[0.00023191846,0.00010192754,0.000048414677,0.00016913912,0.00001002839,0.00057507167,0.0003467984,0.00016399419,0.000046385587],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000019232461,0.000008249309,0.0000957124,0.000009701785,0.000014867111,0.00003343097,0.00095418293,0.00012998219,0.041780192,0.024301074,0.0013620628,0.9313086],"study_design_scores_gemma":[0.0015878063,0.00014626524,0.08566999,0.000233003,0.000023446393,0.000054175714,0.00066634826,0.32522935,0.31699347,0.00031210974,0.26706204,0.0020220221],"about_ca_topic_score_codex":0.000018595367,"about_ca_topic_score_gemma":0.0000067313026,"teacher_disagreement_score":0.9292866,"about_ca_system_score_codex":0.000036518544,"about_ca_system_score_gemma":0.0000051248035,"threshold_uncertainty_score":0.41564843},"labels":[],"label_agreement":null},{"id":"W2946534924","doi":"10.1017/s1351324919000135","title":"NLP commercialisation in the last 25 years","year":2019,"lang":"en","type":"article","venue":"Natural Language Engineering","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Focus (optics); Quarter (Canadian coin); Point (geometry); Artificial intelligence; Natural (archaeology); Natural language processing; History","score_opus":0.004465130453185606,"score_gpt":0.23091334490317533,"score_spread":0.22644821444998972,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2946534924","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92279434,0.015803913,0.055969447,0.001113805,0.001459777,0.0006486549,0.0000027773183,0.0013873049,0.00081998104],"genre_scores_gemma":[0.94444406,0.0000030766644,0.055025477,0.00038018575,0.000077653734,0.000008617563,0.0000058716782,0.000009549222,0.000045516757],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99920136,0.000031739004,0.00012540245,0.00018840835,0.0002376603,0.00021541964],"domain_scores_gemma":[0.9994579,0.00010610788,0.00003445727,0.00036417902,0.000018295568,0.000019048775],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00029973759,0.000109450295,0.00010600706,0.00014348124,0.00001956433,0.00013167631,0.0008929421,0.000063997795,0.0000086196005],"category_scores_gemma":[0.00008280193,0.00008136297,0.000038067636,0.00049454975,0.000006888753,0.00042766123,0.00011331922,0.0004268742,0.000033050008],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001602686,0.00012433699,0.004810014,0.0003028727,0.00004175099,0.0006596151,0.052127857,0.0019141299,0.16093978,0.22477095,0.0023164013,0.55197626],"study_design_scores_gemma":[0.003442283,0.00033619028,0.15926108,0.00114398,0.000034329845,0.00058469374,0.0026454828,0.73308665,0.06574294,0.0037074992,0.026358265,0.0036565936],"about_ca_topic_score_codex":0.00006712316,"about_ca_topic_score_gemma":0.000022457598,"teacher_disagreement_score":0.73117256,"about_ca_system_score_codex":0.00006416545,"about_ca_system_score_gemma":0.000013274023,"threshold_uncertainty_score":0.33178857},"labels":[],"label_agreement":null},{"id":"W3009120927","doi":"10.1017/s1351324920000133","title":"Nonuniform language in technical writing: Detection and correction","year":2020,"lang":"en","type":"article","venue":"Natural Language Engineering","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Natural language processing; Readability; Paraphrase; Artificial intelligence; Task (project management); Sentence; Context (archaeology); Synonym (taxonomy); Similarity (geometry); Programming language","score_opus":0.004691055894078967,"score_gpt":0.21110933476405405,"score_spread":0.20641827886997507,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3009120927","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8255678,0.00086731976,0.17213686,0.00044623762,0.00025300754,0.00013107664,6.7677917e-7,0.000468295,0.00012873362],"genre_scores_gemma":[0.99494344,0.0000033649617,0.004870839,0.00008187423,0.00007522048,0.00000644305,0.0000023862428,0.0000055327737,0.000010895639],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994424,0.000010700511,0.00012308657,0.00020021267,0.000093918636,0.00012969499],"domain_scores_gemma":[0.9997369,0.00005830625,0.000020436684,0.00012137087,0.000011490248,0.000051465828],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000107146385,0.00007709993,0.000083081526,0.00006598786,0.000024766265,0.000054686287,0.0001405825,0.00006208062,0.0000020521836],"category_scores_gemma":[0.00018870708,0.00007528801,0.000020383279,0.00032497026,0.0000068934587,0.00029153613,0.000060222097,0.00029329574,0.000004227846],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009665435,0.000015362128,0.00041074844,0.000056956185,0.000003329809,0.000035476736,0.0055369847,0.0014662223,0.6029116,0.0007825176,0.000012809805,0.38875833],"study_design_scores_gemma":[0.00017870724,0.000037672064,0.029663427,0.000019460535,0.0000018074221,0.00004793501,0.00034305194,0.93769574,0.031722534,0.0000046799987,0.00013420204,0.00015077596],"about_ca_topic_score_codex":0.00004671875,"about_ca_topic_score_gemma":0.000054675365,"teacher_disagreement_score":0.9362295,"about_ca_system_score_codex":0.000049641407,"about_ca_system_score_gemma":0.0000055341857,"threshold_uncertainty_score":0.30701557},"labels":[],"label_agreement":null},{"id":"W3042081424","doi":"10.1017/s1351324920000376","title":"Negation detection for sentiment analysis: A case study in Spanish","year":2020,"lang":"en","type":"article","venue":"Natural Language Engineering","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Negation; Computer science; Natural language processing; Sentiment analysis; Scope (computer science); Artificial intelligence; Identification (biology); Task (project management); Context (archaeology); Programming language","score_opus":0.011398076280530871,"score_gpt":0.25877069535249575,"score_spread":0.24737261907196487,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3042081424","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.67854244,0.00024533944,0.32076445,0.00006405146,0.000115054245,0.00018119511,4.4953782e-7,0.000084267485,0.0000027826216],"genre_scores_gemma":[0.9918341,3.8732895e-7,0.007986119,0.000048225742,0.0000877685,0.000021813541,0.000004345963,0.0000055685714,0.0000116469055],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99926543,0.000017134715,0.00018262476,0.00025643583,0.00013683719,0.00014155125],"domain_scores_gemma":[0.9997126,0.000042721877,0.000042973006,0.00013227867,0.000023470362,0.00004599602],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014536316,0.0000925599,0.0001541534,0.00022372835,0.000036433936,0.00010249159,0.0001393485,0.000024314568,0.0000047812164],"category_scores_gemma":[0.000043253927,0.00008964139,0.00010247506,0.0011742619,0.0000013653168,0.00022871676,0.00005120108,0.000101852194,0.0000022142065],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000055857297,0.00041109254,0.02595336,0.00015105173,0.0028859025,0.004906105,0.119291686,0.5749044,0.08446698,0.0005414458,0.00006815892,0.18636398],"study_design_scores_gemma":[0.00035461163,0.000044788307,0.0017457721,0.000003370719,0.000079318335,0.000012997782,0.002012825,0.9922911,0.003326774,4.6233157e-7,0.000020526852,0.00010747737],"about_ca_topic_score_codex":0.000105178864,"about_ca_topic_score_gemma":0.00014816185,"teacher_disagreement_score":0.4173867,"about_ca_system_score_codex":0.00003882213,"about_ca_system_score_gemma":0.0000044187764,"threshold_uncertainty_score":0.36554697},"labels":[],"label_agreement":null},{"id":"W3044693911","doi":"10.1017/s1351324920000509","title":"Comparison of rule-based and neural network models for negation detection in radiology reports","year":2020,"lang":"en","type":"article","venue":"Natural Language Engineering","topic":"Topic Modeling","field":"Computer Science","cited_by":43,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute of Population and Public Health","funders":"Engineering and Physical Sciences Research Council; Medical Research Council","keywords":"Computer science; Artificial intelligence; Natural language processing; Negation; Artificial neural network; Sentence; Syntax; Pipeline (software); Machine learning; Rule-based system; Python (programming language); Information retrieval; Programming language","score_opus":0.014563883407551955,"score_gpt":0.24777112941400728,"score_spread":0.23320724600645532,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3044693911","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.39095372,0.0012894562,0.60735744,0.00007720487,0.00017900951,0.00008836335,1.967373e-7,0.000052310115,0.0000022683919],"genre_scores_gemma":[0.9302409,5.6367253e-7,0.069596685,0.00005182119,0.00009411179,0.0000074721356,0.0000026718305,0.0000050016556,7.32634e-7],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994282,0.000011661562,0.00019871083,0.00017311472,0.000061512386,0.00012676841],"domain_scores_gemma":[0.9997228,0.000073723444,0.000058403828,0.00009897994,0.000016862441,0.000029281131],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009750339,0.00006617383,0.00014420859,0.000042602423,0.000014335788,0.000013416682,0.00008148398,0.000047612324,2.3477061e-7],"category_scores_gemma":[0.00007415071,0.00006646637,0.000023679158,0.00013682607,0.0000040260397,0.00015207265,0.000028891887,0.00012724342,3.0905536e-8],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005816586,0.0000017930937,0.00026882003,0.00003372312,0.000001988279,0.0000054687216,0.0007470753,0.9632947,0.010390855,0.00019931223,0.0000018211797,0.025048617],"study_design_scores_gemma":[0.00016376324,0.000026286127,0.00044101983,0.000012002414,0.000001978199,0.0000075290354,0.000017469667,0.9926206,0.0065832175,0.000057792025,0.000004989408,0.00006336585],"about_ca_topic_score_codex":0.000017406743,"about_ca_topic_score_gemma":0.000006143766,"teacher_disagreement_score":0.5392872,"about_ca_system_score_codex":0.000017692268,"about_ca_system_score_gemma":0.0000065895483,"threshold_uncertainty_score":0.271042},"labels":[],"label_agreement":null},{"id":"W4226024751","doi":"10.1017/s1351324922000134","title":"Real-world sentence boundary detection using multitask learning: A case study on French","year":2022,"lang":"en","type":"article","venue":"Natural Language Engineering","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Hanbat National University","keywords":"Computer science; Sentence; Punctuation; Natural language processing; Task (project management); Artificial intelligence; Boundary (topology); Multi-task learning; Speech recognition","score_opus":0.01083990589589887,"score_gpt":0.27614783946117666,"score_spread":0.26530793356527776,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4226024751","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95767796,0.0016925209,0.03753209,0.000026494969,0.0008400078,0.00036601303,0.0000027854417,0.001829287,0.000032834003],"genre_scores_gemma":[0.939446,9.030297e-7,0.060112152,0.00004276657,0.00010952999,0.000046389083,0.0000034898087,0.00003295596,0.00020582236],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981845,0.00012636067,0.00024129757,0.0005334048,0.0005230192,0.00039139637],"domain_scores_gemma":[0.9991775,0.00012283886,0.000109855726,0.00045659803,0.000055057764,0.00007812593],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00040669355,0.0002600387,0.0002057901,0.0005206574,0.000575599,0.0002095353,0.00063083874,0.00004161056,0.000012848418],"category_scores_gemma":[0.00014448189,0.00025671025,0.000077560835,0.0011819815,0.000014264204,0.0004326335,0.0005841809,0.0014493999,0.0000028830625],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000065192224,0.00080369244,0.0031198135,0.00020348866,0.00023740124,0.09134087,0.051093448,0.09150086,0.5480612,0.00095987757,0.00009105966,0.21252312],"study_design_scores_gemma":[0.0005565971,0.00044116273,0.00043048075,0.00005049872,0.000026320846,0.004651661,0.0038577884,0.9672834,0.021666205,0.000031632902,0.00026410542,0.000740142],"about_ca_topic_score_codex":0.0029707325,"about_ca_topic_score_gemma":0.000197491,"teacher_disagreement_score":0.87578255,"about_ca_system_score_codex":0.00056625356,"about_ca_system_score_gemma":0.00004625497,"threshold_uncertainty_score":0.9999885},"labels":[],"label_agreement":null},{"id":"W4284891255","doi":"10.1017/s1351324922000298","title":"Neural automated writing evaluation for Korean L2 writing","year":2022,"lang":"en","type":"article","venue":"Natural Language Engineering","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"National Research Foundation of Korea; National Research Foundation","keywords":"Computer science; Fluency; Parsing; Artificial intelligence; Natural language processing; Complement (music); Artificial neural network; Reliability (semiconductor); Linguistics","score_opus":0.009429505732520903,"score_gpt":0.2826202360865886,"score_spread":0.2731907303540677,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4284891255","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.42431736,0.06325542,0.47893336,0.0016115857,0.0033576253,0.002682338,0.00006777687,0.025529338,0.00024520193],"genre_scores_gemma":[0.7439691,5.7366503e-7,0.25539765,0.00015943637,0.00016134408,0.0001901777,0.000062011255,0.000028957906,0.000030765434],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99809855,0.000069710935,0.000312992,0.0004371761,0.0006080955,0.00047349735],"domain_scores_gemma":[0.99909705,0.00021817465,0.0001196973,0.0003599631,0.00014251168,0.00006259037],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011083739,0.00021716276,0.00019180952,0.00025874836,0.00035522357,0.00022182037,0.0009007987,0.00005639517,0.00001941663],"category_scores_gemma":[0.00043261345,0.00022453375,0.00010559852,0.0006237628,0.000009390847,0.0005960084,0.00045668517,0.0005617711,0.0000013211093],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028702008,0.00006746413,0.00009741817,0.00032817436,0.000074225005,0.00019062395,0.0052501312,0.04025569,0.26450455,0.019215826,0.0016668917,0.6683203],"study_design_scores_gemma":[0.0003380151,0.000044111057,0.00006971575,0.00003145617,0.000012573981,0.000106583044,0.0002112733,0.9869491,0.011657698,0.00015736835,0.00012282506,0.0002992755],"about_ca_topic_score_codex":0.0000255485,"about_ca_topic_score_gemma":0.0000018449681,"teacher_disagreement_score":0.9466934,"about_ca_system_score_codex":0.00034123732,"about_ca_system_score_gemma":0.000050908246,"threshold_uncertainty_score":0.91562206},"labels":[],"label_agreement":null},{"id":"W4382542296","doi":"10.1017/s1351324923000311","title":"Korean named entity recognition based on language-specific features","year":2023,"lang":"en","type":"article","venue":"Natural Language Engineering","topic":"Topic Modeling","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Morpheme; Natural language processing; Artificial intelligence; Annotation; Named-entity recognition; Scheme (mathematics); Ambiguity; Segmentation; Syllable; Word (group theory); Speech recognition; Task (project management); Linguistics","score_opus":0.010039043517492463,"score_gpt":0.22310503279439328,"score_spread":0.21306598927690082,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4382542296","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.81690615,0.0022560665,0.17099151,0.00074757333,0.0033915078,0.0003580658,0.000021652815,0.00405666,0.0012708372],"genre_scores_gemma":[0.9767797,0.0000067061173,0.022355095,0.0001599062,0.0002947002,0.000012908509,0.000067253844,0.000020128751,0.00030362728],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988479,0.000024201549,0.00013467572,0.00034872824,0.00031755024,0.00032696183],"domain_scores_gemma":[0.9992962,0.00012341113,0.000031388885,0.00045021862,0.000028328797,0.000070483264],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020738995,0.00016175045,0.00012855783,0.00028255663,0.00005891927,0.00012299702,0.0004286582,0.0000798049,0.000024314646],"category_scores_gemma":[0.00013454449,0.00015081634,0.000078588884,0.0005681364,0.0000065607173,0.00021652924,0.00008662326,0.0003828743,0.00015247273],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002699285,0.000059972186,0.000097923,0.00017446911,0.00004324383,0.0011184281,0.007662422,0.084861,0.09505205,0.0034344208,0.0037636508,0.80370545],"study_design_scores_gemma":[0.00033226877,0.000020849046,0.00204235,0.00008682072,0.0000031420088,0.000010034879,0.0001259194,0.97819036,0.018379869,0.000026088663,0.0004927356,0.0002895446],"about_ca_topic_score_codex":0.00003144908,"about_ca_topic_score_gemma":0.0000068356944,"teacher_disagreement_score":0.8933294,"about_ca_system_score_codex":0.00007175589,"about_ca_system_score_gemma":0.000011880837,"threshold_uncertainty_score":0.61501116},"labels":[],"label_agreement":null},{"id":"W4384694635","doi":"10.1017/s1351324923000360","title":"Describe the house and I will tell you the price: House price prediction with textual description data","year":2023,"lang":"en","type":"article","venue":"Natural Language Engineering","topic":"Housing Market and Economics","field":"Economics, Econometrics and Finance","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Word2vec; Computer science; House price; Boosting (machine learning); Word embedding; Artificial intelligence; Word (group theory); Machine learning; Information retrieval; Data mining; Natural language processing; Embedding; Econometrics; Linguistics; Mathematics","score_opus":0.019698140741209,"score_gpt":0.19196146109524972,"score_spread":0.17226332035404074,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384694635","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9900943,0.0033602708,0.0029211708,0.00051281054,0.0006652988,0.00032867078,0.00015157303,0.00075988256,0.0012060336],"genre_scores_gemma":[0.99801785,0.00056951446,0.00047762113,0.00007542457,0.00031707648,0.000013407932,0.00005082138,0.00007284422,0.00040546563],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990473,0.000010137228,0.00024931532,0.00033781966,0.000045320936,0.00031012337],"domain_scores_gemma":[0.99915653,0.00011003248,0.00010115904,0.0005716565,0.0000125025035,0.000048134927],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006850721,0.00016102266,0.00017093263,0.00012029596,0.00017228715,0.00022765037,0.0003889682,0.0000760459,0.000015896701],"category_scores_gemma":[0.00018874959,0.000110818895,0.000029035944,0.00034879567,0.00004211166,0.0006732836,0.0001822423,0.00034144928,0.00007378188],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012067539,0.0005511616,0.23651212,0.001917836,0.0031176333,0.00054905785,0.12929142,0.20095843,0.0101038655,0.076036386,0.09376848,0.24598686],"study_design_scores_gemma":[0.00091630366,0.00008195343,0.09746514,0.000066428554,0.00004397252,0.00009456861,0.0023428218,0.82347894,0.00009476412,0.00011035395,0.074670665,0.0006340727],"about_ca_topic_score_codex":0.00012559668,"about_ca_topic_score_gemma":0.000047400867,"teacher_disagreement_score":0.6225205,"about_ca_system_score_codex":0.00007431118,"about_ca_system_score_gemma":0.00000920407,"threshold_uncertainty_score":0.45190635},"labels":[],"label_agreement":null},{"id":"W4385552004","doi":"10.1017/s1351324923000396","title":"SSL-GAN-RoBERTa: A robust semi-supervised model for detecting Anti-Asian COVID-19 hate speech on social media","year":2023,"lang":"en","type":"article","venue":"Natural Language Engineering","topic":"Hate Speech and Cyberbullying Detection","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Social media; Transformer; Artificial intelligence; Task (project management); Coronavirus disease 2019 (COVID-19); Machine learning; Speech recognition; Data mining; Voltage","score_opus":0.025940205091409797,"score_gpt":0.26037499805348296,"score_spread":0.23443479296207317,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385552004","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.447977,0.00026780769,0.54520214,0.0010044493,0.0019434297,0.0004973617,0.000027135473,0.002951778,0.00012890043],"genre_scores_gemma":[0.9770392,0.000006530949,0.021845628,0.00023650688,0.0005002445,0.000043013977,0.00003406005,0.00004925767,0.00024554046],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99821573,0.00002435894,0.00023740345,0.0005071966,0.00035856492,0.0006567381],"domain_scores_gemma":[0.9991056,0.0002823913,0.000060686507,0.00030403148,0.000050437455,0.00019688167],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00040074252,0.00027391288,0.00025850983,0.00035432822,0.00031491098,0.00020349615,0.0005400122,0.00018194829,0.000005987353],"category_scores_gemma":[0.00084285956,0.00026887932,0.00016520331,0.0008738369,0.000012483725,0.00033910028,0.00010330145,0.00046554278,0.00004077297],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000041465777,0.000032199485,0.000011109002,0.00032114808,0.000082340346,0.00037836414,0.021768091,0.6729297,0.1386705,0.0011614485,0.001602658,0.16300099],"study_design_scores_gemma":[0.0005442609,0.000020504018,0.00009802294,0.00003279547,0.000009387298,0.000027751807,0.00028662157,0.9804564,0.017962445,0.000044229404,0.00018478427,0.00033278682],"about_ca_topic_score_codex":0.00004041855,"about_ca_topic_score_gemma":0.00007405132,"teacher_disagreement_score":0.5290622,"about_ca_system_score_codex":0.00018064471,"about_ca_system_score_gemma":0.000059177957,"threshold_uncertainty_score":0.99997634},"labels":[],"label_agreement":null},{"id":"W4388731527","doi":"10.1017/s1351324923000529","title":"Korean named entity recognition based on language-specific features – CORRIGENDUM","year":2023,"lang":"en","type":"erratum","venue":"Natural Language Engineering","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"National Research Foundation of Korea; National Research Foundation","keywords":"Computer science; Content (measure theory); Natural language processing; Information retrieval; Artificial intelligence; Database; World Wide Web","score_opus":0.012516482264891337,"score_gpt":0.24193848754718925,"score_spread":0.22942200528229792,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388731527","genre_codex":"editorial","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014430804,0.32419443,0.22919029,0.0027828189,0.3576994,0.004758612,0.0015106598,0.064105205,0.0143155325],"genre_scores_gemma":[0.13805848,0.0009024842,0.5695523,0.0027687491,0.017330967,0.0005773653,0.0155686,0.0014538743,0.25378716],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9958549,0.0001031106,0.0005042875,0.0013222452,0.0012259444,0.0009895045],"domain_scores_gemma":[0.9975082,0.00024870233,0.00031697648,0.0015113109,0.00019479735,0.00021996586],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.00048314745,0.0009500884,0.0007344171,0.0012202939,0.00018762362,0.000675779,0.002330794,0.0010381996,0.00006840099],"category_scores_gemma":[0.00069976295,0.0008698316,0.0003949572,0.0014817752,0.000044398745,0.00052029645,0.00042977283,0.004238451,0.00025095433],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030470594,0.00006589233,0.0000017541262,0.00062799134,0.00007762139,0.0019944848,0.0013453183,0.00012372699,0.0042708814,0.0005623298,0.83331716,0.15758236],"study_design_scores_gemma":[0.0035354868,0.00089924777,0.00070873596,0.014489025,0.00031914917,0.00051544805,0.00072777533,0.613713,0.12088148,0.0012614246,0.22957958,0.013369619],"about_ca_topic_score_codex":0.00017114426,"about_ca_topic_score_gemma":0.0000611939,"teacher_disagreement_score":0.6135893,"about_ca_system_score_codex":0.00057836523,"about_ca_system_score_gemma":0.00016676981,"threshold_uncertainty_score":0.9993752},"labels":[],"label_agreement":null},{"id":"W4390789641","doi":"10.1017/s1351324923000542","title":"Lightweight transformers for clinical natural language processing","year":2024,"lang":"en","type":"article","venue":"Natural Language Engineering","topic":"Topic Modeling","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"NIHR Imperial Biomedical Research Centre; Instituto de Salud Carlos III; Medical Research Council; National Institutes of Health; Kementerian Kesihatan Malaysia; All-India Institute of Medical Sciences; Horizon 2020 Framework Programme; Prince Charles Hospital Foundation; Foreign, Commonwealth and Development Office; National Institute for Health Research Health Protection Research Unit; University of Oxford; Norges Forskningsråd; Imperial College London; Conselho Nacional de Desenvolvimento Científico e Tecnológico; University of Cape Town; Public Health England; Wellcome Trust; University College Dublin; Sunnybrook Research Institute; Institut National de la Santé et de la Recherche Médicale; Canadian Institutes of Health Research; National Institute for Health and Care Research; Ministero della Salute; European Federation of Pharmaceutical Industries and Associations; European Commission; Bill and Melinda Gates Foundation","keywords":"Computer science; Transformer; Natural language processing; Artificial intelligence; Electrical engineering","score_opus":0.011690292682715328,"score_gpt":0.30424274043960325,"score_spread":0.29255244775688793,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390789641","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.055267945,0.11133777,0.8265553,0.0006176916,0.004226539,0.00032129174,0.0000059822196,0.0014482911,0.00021917516],"genre_scores_gemma":[0.92610157,0.000025193216,0.07220682,0.00013236141,0.00083825545,0.000023209346,0.000012243468,0.00003315046,0.0006272054],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99845374,0.000015415637,0.00034339743,0.0005053109,0.0002409302,0.00044122175],"domain_scores_gemma":[0.9994193,0.00019969721,0.000027132564,0.00021855858,0.000036286507,0.00009902952],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003788942,0.0002203001,0.00022753842,0.00016330896,0.00006561849,0.00029911508,0.00048849446,0.00012382166,0.00000638814],"category_scores_gemma":[0.00010867985,0.00017939546,0.00021462557,0.00033558754,0.000013694355,0.00069789216,0.00006575794,0.00062315725,0.000013567781],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006190712,0.000011044367,0.00000926721,0.00039519303,0.000045449033,0.00014758864,0.0041751564,0.00028619549,0.0075114914,0.0023656816,0.0002746684,0.9847721],"study_design_scores_gemma":[0.00022754169,0.000020881687,0.000057700065,0.00017498688,0.000014841302,0.00004178627,0.000118556345,0.9906904,0.0028864006,0.00001119344,0.0054782988,0.00027740985],"about_ca_topic_score_codex":0.000008161707,"about_ca_topic_score_gemma":0.000004925415,"teacher_disagreement_score":0.9904042,"about_ca_system_score_codex":0.00006943896,"about_ca_system_score_gemma":0.00005850483,"threshold_uncertainty_score":0.7315535},"labels":[],"label_agreement":null}]}