{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":31,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":31,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"query_hash":"2026479010f0","filters":{"venue":"Natural Language Engineering"}},"results":[{"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.00715054306742324,"gpt":0.2517287714730841,"spread":0.2445782284056608,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001035483,0.00008841202,0.0001118098,0.00007512856,0.00002051287,0.00005107102,0.0003342052,0.00003601382,0.000001223504],"category_scores_gemma":[0.0001826686,0.00008137323,0.0000494281,0.0001123075,0.000005312778,0.0005108453,0.00007745496,0.0001014627,0.000001334058],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002739004,"about_ca_system_score_gemma":0.00001259251,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003447597,"about_ca_topic_score_gemma":0.000004136893,"domain_scores_codex":[0.9994054,0.000004998661,0.000143718,0.0001622932,0.0001118706,0.0001717006],"domain_scores_gemma":[0.9995571,0.0001168465,0.00003398622,0.0002360065,0.00003339248,0.00002262344],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001720593,0.00004269218,0.001535478,0.0003533527,0.00005773759,0.00005923436,0.004347271,0.1269414,0.2998533,0.332292,0.00002624875,0.2344741],"study_design_scores_gemma":[0.0001601156,0.00001479629,0.001101828,0.00009899991,0.000003438613,0.00001145734,0.00003508086,0.9833108,0.01479864,0.0001639665,0.0001471339,0.0001537326],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.329692,0.001045096,0.6687211,0.00003587953,0.0002961903,0.00005894586,0.000001678956,0.0001044836,0.0000446069],"genre_scores_gemma":[0.856863,0.0000082973,0.1428883,0.00001408589,0.00009429534,0.000007891576,0.000003143503,0.000006487621,0.0001145748],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8563694,"threshold_uncertainty_score":0.3318304,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.005958882391220053,"gpt":0.2512037126170917,"spread":0.2452448302258716,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003714146,0.0002932264,0.0002484289,0.00019518,0.0001270568,0.0002002977,0.0008950278,0.000165557,0.00001134033],"category_scores_gemma":[0.0002943757,0.0002719601,0.00009110592,0.0005316759,0.00001652171,0.0009000982,0.0002581748,0.0008714293,0.0000265273],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00031639,"about_ca_system_score_gemma":0.00002626845,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001280037,"about_ca_topic_score_gemma":0.00001521602,"domain_scores_codex":[0.998158,0.00002959585,0.0003149663,0.0005049958,0.0004315398,0.0005609539],"domain_scores_gemma":[0.9990621,0.0001654766,0.000102411,0.0004776824,0.00005655045,0.0001357514],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001471384,0.00004012095,0.0001433605,0.00009228502,0.00002549757,0.0001668605,0.003186245,0.002293016,0.3500535,0.003082414,0.001718814,0.6391832],"study_design_scores_gemma":[0.0003432045,0.00004424497,0.0001001914,0.0003103466,0.00001326056,0.0002424661,0.0001235017,0.445722,0.5483044,0.00008124318,0.003772132,0.0009430088],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3763822,0.03882042,0.5752135,0.0007753409,0.00196365,0.0003344045,0.000003592611,0.005976592,0.0005303262],"genre_scores_gemma":[0.6607376,0.0000185994,0.3383821,0.0000779281,0.0003593745,0.000004804648,0.00000659769,0.00002848889,0.0003845784],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6382402,"threshold_uncertainty_score":0.9999732,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.002330387928883056,"gpt":0.2230677074953706,"spread":0.2207373195664875,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000172332,0.000219999,0.0001629161,0.0001295701,0.00006876089,0.000259468,0.0008081105,0.00008360177,0.00003105829],"category_scores_gemma":[0.0001071399,0.0001958623,0.00005921471,0.0002917898,0.000009428623,0.001127413,0.0002468994,0.0004385067,0.00004856339],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001497417,"about_ca_system_score_gemma":0.00001292107,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001572432,"about_ca_topic_score_gemma":0.000001639616,"domain_scores_codex":[0.9986805,0.00001467594,0.0002127352,0.0003492375,0.0003099728,0.0004328938],"domain_scores_gemma":[0.9993882,0.00005321521,0.00007094934,0.0003632827,0.00003808533,0.00008626459],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000004510795,0.00004754789,0.00006028066,0.00008939359,0.00004614429,0.00009539269,0.001388289,0.0001045901,0.5649291,0.007009497,0.003308122,0.4229171],"study_design_scores_gemma":[0.0009252927,0.00005486893,0.0002310745,0.0003124717,0.00002768702,0.0001825479,0.00005498858,0.4112251,0.5360843,0.0001253919,0.04911159,0.001664675],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1009885,0.07203068,0.8167299,0.001349984,0.001158045,0.0004962252,0.00001636378,0.006267217,0.0009631183],"genre_scores_gemma":[0.683963,0.00000617535,0.314693,0.000314484,0.0001634298,0.00001048546,0.00001505179,0.00001867854,0.0008156957],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5829745,"threshold_uncertainty_score":0.7987034,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.004724068616820104,"gpt":0.235974427016896,"spread":0.2312503584000759,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001428922,0.0002021636,0.0001667908,0.0001595439,0.000075134,0.0001937594,0.0006098269,0.0001316843,0.000002801844],"category_scores_gemma":[0.0001185654,0.0001761255,0.00009000428,0.0003814196,0.00001077591,0.0004649125,0.00008408884,0.0002881976,0.000005167272],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001410518,"about_ca_system_score_gemma":0.00002782142,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003572353,"about_ca_topic_score_gemma":0.000006763098,"domain_scores_codex":[0.9989389,0.00001245128,0.0001570152,0.0003308929,0.0002192721,0.0003414504],"domain_scores_gemma":[0.9993442,0.00008209037,0.00007524875,0.0003813068,0.00007285978,0.00004426298],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000007945687,0.00004385728,0.00004553142,0.000329842,0.00002951937,0.00006294355,0.0006545996,0.0006383057,0.6270614,0.2547209,0.01124788,0.1051572],"study_design_scores_gemma":[0.0002671319,0.00002315925,0.0006951969,0.00006448664,0.000009813653,0.00004493771,0.00001338475,0.9324474,0.06272795,0.000972021,0.002383108,0.000351436],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03101861,0.01708733,0.9461088,0.001398089,0.0006770262,0.0004479033,0.000007520124,0.003108267,0.0001464209],"genre_scores_gemma":[0.4830689,0.000001064009,0.5158736,0.00005409139,0.0002389875,0.00003635112,0.00002403481,0.00001644272,0.0006865161],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9318091,"threshold_uncertainty_score":0.7182191,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01456388340755196,"gpt":0.2477711294140073,"spread":0.2332072460064553,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009750339,0.00006617383,0.0001442086,0.00004260242,0.00001433579,0.00001341668,0.00008148398,0.00004761232,2.347706e-7],"category_scores_gemma":[0.00007415071,0.00006646637,0.00002367916,0.0001368261,0.00000402604,0.0001520727,0.00002889189,0.0001272434,3.090554e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001769227,"about_ca_system_score_gemma":0.000006589548,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001740674,"about_ca_topic_score_gemma":0.000006143766,"domain_scores_codex":[0.9994282,0.00001166156,0.0001987108,0.0001731147,0.00006151239,0.0001267684],"domain_scores_gemma":[0.9997228,0.00007372344,0.00005840383,0.00009897994,0.00001686244,0.00002928113],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000005816586,0.000001793094,0.00026882,0.00003372312,0.000001988279,0.000005468722,0.0007470753,0.9632947,0.01039086,0.0001993122,0.00000182118,0.02504862],"study_design_scores_gemma":[0.0001637632,0.00002628613,0.0004410198,0.00001200241,0.000001978199,0.000007529035,0.00001746967,0.9926206,0.006583218,0.00005779203,0.000004989408,0.00006336585],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3909537,0.001289456,0.6073574,0.00007720487,0.0001790095,0.00008836335,1.967373e-7,0.00005231012,0.000002268392],"genre_scores_gemma":[0.9302409,5.636725e-7,0.06959669,0.00005182119,0.00009411179,0.000007472136,0.000002671831,0.000005001656,7.32634e-7],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5392872,"threshold_uncertainty_score":0.271042,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.001625339182507167,"gpt":0.1923652781234644,"spread":0.1907399389409572,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001486017,0.0001402655,0.0001499816,0.0001408198,0.00002762691,0.00005174293,0.0004565407,0.00009748503,0.000002294784],"category_scores_gemma":[0.0003050737,0.000128529,0.00004331939,0.0004079869,0.00001259453,0.0003343492,0.00007112826,0.0002252046,9.43819e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001223096,"about_ca_system_score_gemma":0.00002716606,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002608369,"about_ca_topic_score_gemma":0.00001920707,"domain_scores_codex":[0.9990535,0.00001599375,0.000230018,0.0002527767,0.0002273148,0.0002203675],"domain_scores_gemma":[0.9992518,0.00004647229,0.0001237974,0.0003031611,0.0002455705,0.00002917389],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000003236898,0.00002995254,0.0001171399,0.0001015259,0.00001137352,0.000006649206,0.001203058,0.0001886403,0.9337728,0.02975066,0.0007842364,0.03403072],"study_design_scores_gemma":[0.0002245041,0.00004119499,0.0003584895,0.00004312625,0.000008922343,0.000004311391,0.00002683917,0.06245844,0.9352837,0.0006434356,0.0005845135,0.0003224853],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1517686,0.04676037,0.794357,0.0004600663,0.002021309,0.0007221935,0.00005403603,0.00333497,0.000521447],"genre_scores_gemma":[0.885418,0.000002450943,0.114188,0.0000229595,0.0001788994,0.00001323979,0.00004895541,0.00001250835,0.0001150021],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7336494,"threshold_uncertainty_score":0.5241259,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.05869544911709373,"gpt":0.2372541145684448,"spread":0.178558665451351,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001991675,0.000129461,0.0001176685,0.0001006936,0.00007646188,0.000108404,0.0005803596,0.00004705986,0.00001078463],"category_scores_gemma":[0.0001503548,0.0001217302,0.00001797156,0.000194902,0.000009516477,0.000787949,0.0003797776,0.0002346105,0.000004795518],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002436778,"about_ca_system_score_gemma":0.00001626395,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006810282,"about_ca_topic_score_gemma":0.00001209307,"domain_scores_codex":[0.9991167,0.00002841609,0.0001710981,0.0003335061,0.0001486,0.0002017178],"domain_scores_gemma":[0.9993098,0.00005573693,0.00003568013,0.0005166468,0.00002020886,0.00006193858],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000005533153,0.0001090676,0.003924672,0.0004750341,0.0001877856,0.0001563801,0.08322764,0.04773287,0.006212438,0.02912032,0.00004466962,0.8288036],"study_design_scores_gemma":[0.0002251502,0.000007570461,0.002344265,0.00002713925,0.000006953552,0.000009617103,0.0002002449,0.9966418,0.0003330386,0.000009376288,0.00004266895,0.0001521971],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1015578,0.001824471,0.8955594,0.00006999616,0.0002366675,0.0001489102,0.000002003585,0.0005202884,0.00008051448],"genre_scores_gemma":[0.6284912,0.000003520428,0.3713564,0.00001505737,0.00003050302,0.000006009132,0.00002385777,0.000008885814,0.00006457208],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9489089,"threshold_uncertainty_score":0.4964014,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01169029268271533,"gpt":0.3042427404396033,"spread":0.2925524477568879,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003788942,0.0002203001,0.0002275384,0.000163309,0.00006561849,0.0002991151,0.0004884945,0.0001238217,0.00000638814],"category_scores_gemma":[0.0001086799,0.0001793955,0.0002146256,0.0003355875,0.00001369436,0.0006978922,0.00006575794,0.0006231572,0.00001356778],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006943896,"about_ca_system_score_gemma":0.00005850483,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008161707,"about_ca_topic_score_gemma":0.000004925415,"domain_scores_codex":[0.9984537,0.00001541564,0.0003433974,0.0005053109,0.0002409302,0.0004412218],"domain_scores_gemma":[0.9994193,0.0001996972,0.00002713256,0.0002185586,0.00003628651,0.00009902952],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000006190712,0.00001104437,0.00000926721,0.000395193,0.00004544903,0.0001475886,0.004175156,0.0002861955,0.007511491,0.002365682,0.0002746684,0.9847721],"study_design_scores_gemma":[0.0002275417,0.00002088169,0.00005770006,0.0001749869,0.0000148413,0.00004178627,0.0001185563,0.9906904,0.002886401,0.00001119344,0.005478299,0.0002774099],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05526794,0.1113378,0.8265553,0.0006176916,0.004226539,0.0003212917,0.00000598222,0.001448291,0.0002191752],"genre_scores_gemma":[0.9261016,0.00002519322,0.07220682,0.0001323614,0.0008382555,0.00002320935,0.00001224347,0.00003315046,0.0006272054],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9904042,"threshold_uncertainty_score":0.7315535,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Synonym (taxonomy); Natural language processing; Artificial intelligence; Lexicon; Quality (philosophy)","retraction":null,"screen_n_in":null,"score":{"opus":0.07898671688241453,"gpt":0.262412322812195,"spread":0.1834256059297805,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001430908,0.0001477046,0.0001213898,0.0003074342,0.00005360972,0.00004709819,0.0003788636,0.00006195451,0.00001091717],"category_scores_gemma":[0.0001186929,0.0001442725,0.00006265164,0.0003179335,0.000005960424,0.001381437,0.0000828646,0.0003236471,0.000003908599],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001110221,"about_ca_system_score_gemma":0.00001473861,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001012824,"about_ca_topic_score_gemma":0.00002232096,"domain_scores_codex":[0.9991185,0.00001093818,0.0001869471,0.0002708405,0.0001321802,0.0002806109],"domain_scores_gemma":[0.9995325,0.00009729845,0.0000443607,0.0002402091,0.00003996166,0.00004565284],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0000757608,0.0003454035,0.002064463,0.0007307218,0.00009179658,0.0008692913,0.02593921,0.0005872071,0.1771531,0.2276152,0.0001242953,0.5644035],"study_design_scores_gemma":[0.002017972,0.0003342804,0.0424717,0.001525494,0.00005106309,0.0006901466,0.001433744,0.3691351,0.571402,0.007170641,0.0009548017,0.002813138],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1289871,0.003951296,0.864161,0.00006982639,0.0009628681,0.000279678,0.000009429573,0.001419859,0.0001588658],"genre_scores_gemma":[0.6790269,0.00002282471,0.3206642,0.00002936272,0.00007252603,0.0001420856,0.000009631547,0.00001424152,0.00001824985],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5615904,"threshold_uncertainty_score":0.5883261,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.019698140741209,"gpt":0.1919614610952497,"spread":0.1722633203540407,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006850721,0.0001610227,0.0001709326,0.000120296,0.0001722872,0.0002276504,0.0003889682,0.0000760459,0.0000158967],"category_scores_gemma":[0.0001887496,0.0001108189,0.00002903594,0.0003487957,0.00004211166,0.0006732836,0.0001822423,0.0003414493,0.00007378188],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007431118,"about_ca_system_score_gemma":0.00000920407,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001255967,"about_ca_topic_score_gemma":0.00004740087,"domain_scores_codex":[0.9990473,0.00001013723,0.0002493153,0.0003378197,0.00004532094,0.0003101234],"domain_scores_gemma":[0.9991565,0.0001100325,0.000101159,0.0005716565,0.0000125025,0.00004813493],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001206754,0.0005511616,0.2365121,0.001917836,0.003117633,0.0005490578,0.1292914,0.2009584,0.01010387,0.07603639,0.09376848,0.2459869],"study_design_scores_gemma":[0.0009163037,0.00008195343,0.09746514,0.00006642855,0.00004397252,0.00009456861,0.002342822,0.8234789,0.00009476412,0.0001103539,0.07467066,0.0006340727],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9900943,0.003360271,0.002921171,0.0005128105,0.0006652988,0.0003286708,0.000151573,0.0007598826,0.001206034],"genre_scores_gemma":[0.9980178,0.0005695145,0.0004776211,0.00007542457,0.0003170765,0.00001340793,0.00005082138,0.00007284422,0.0004054656],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6225205,"threshold_uncertainty_score":0.4519064,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01986886967877055,"gpt":0.2344160687173866,"spread":0.214547199038616,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001381395,0.00008316101,0.00009957884,0.0002286073,0.00001635674,0.00003681847,0.0003612658,0.00003806726,0.0000074213],"category_scores_gemma":[0.00003801255,0.00007398154,0.00004016701,0.0005164244,0.000003548377,0.0001621017,0.00008384266,0.0001772434,0.00001794711],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002790631,"about_ca_system_score_gemma":0.000005887126,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002145864,"about_ca_topic_score_gemma":0.000002835804,"domain_scores_codex":[0.9993063,0.00001286323,0.0001339151,0.0002275359,0.0001354704,0.0001839131],"domain_scores_gemma":[0.9996724,0.00001911108,0.00001828581,0.0002203569,0.00001191626,0.00005795383],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004332632,0.0007372482,0.01101887,0.0001231513,0.0001861794,0.0001191113,0.1250387,0.01109955,0.159306,0.4355741,0.0005334883,0.2562203],"study_design_scores_gemma":[0.0001661027,0.00001344736,0.04614593,0.00001623383,0.000002776218,0.00000560094,0.0001819482,0.9509222,0.002254266,0.00001688282,0.0001076703,0.0001669203],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4378887,0.0006822307,0.5529232,0.0001460564,0.0004225718,0.0001853253,5.709916e-7,0.0002800963,0.007471254],"genre_scores_gemma":[0.853088,9.298049e-7,0.1467346,0.00004537832,0.00004087135,0.000009765399,0.000003678216,0.000004994249,0.00007185154],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9398227,"threshold_uncertainty_score":0.301688,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.004005314190147125,"gpt":0.2351412818868485,"spread":0.2311359676967014,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001830186,0.0001546307,0.0002043988,0.0003241605,0.00001825683,0.0000475144,0.0006630679,0.00009467465,0.00002474975],"category_scores_gemma":[0.0001739489,0.0001386824,0.00004722364,0.0008079353,0.00001021306,0.0005769445,0.0001556228,0.0002673954,0.00001269272],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001186985,"about_ca_system_score_gemma":0.00002337517,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002814207,"about_ca_topic_score_gemma":0.00001289388,"domain_scores_codex":[0.9989499,0.00002190411,0.0002715173,0.0002318415,0.0002513835,0.0002734908],"domain_scores_gemma":[0.9994264,0.00006608152,0.00008084717,0.0003406745,0.00004232337,0.00004373221],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000005090909,0.00006796478,0.001218561,0.000172623,0.00001685807,0.0002711691,0.002353427,0.0003670846,0.7378548,0.001368385,0.0001120888,0.2561919],"study_design_scores_gemma":[0.0004094482,0.00004232893,0.01900652,0.0004177383,0.000005601054,0.00008093732,0.00002355916,0.909946,0.06938758,0.0002376055,0.00004565733,0.0003970301],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9684198,0.004058183,0.0257476,0.00007479345,0.0002097528,0.0001772641,0.000001154243,0.001077225,0.0002342235],"genre_scores_gemma":[0.7832971,0.00001710176,0.2165047,0.00001706604,0.00002904223,0.000006769532,0.000004662744,0.0000115243,0.0001120876],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9095789,"threshold_uncertainty_score":0.5655305,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01139807628053087,"gpt":0.2587706953524957,"spread":0.2473726190719649,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001453632,0.0000925599,0.0001541534,0.0002237283,0.00003643394,0.0001024916,0.0001393485,0.00002431457,0.000004781216],"category_scores_gemma":[0.00004325393,0.00008964139,0.0001024751,0.001174262,0.000001365317,0.0002287168,0.00005120108,0.0001018522,0.000002214206],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003882213,"about_ca_system_score_gemma":0.000004418776,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001051789,"about_ca_topic_score_gemma":0.0001481619,"domain_scores_codex":[0.9992654,0.00001713471,0.0001826248,0.0002564358,0.0001368372,0.0001415513],"domain_scores_gemma":[0.9997126,0.00004272188,0.00004297301,0.0001322787,0.00002347036,0.00004599602],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000558573,0.0004110925,0.02595336,0.0001510517,0.002885903,0.004906105,0.1192917,0.5749044,0.08446698,0.0005414458,0.00006815892,0.186364],"study_design_scores_gemma":[0.0003546116,0.00004478831,0.001745772,0.000003370719,0.00007931834,0.00001299778,0.002012825,0.9922911,0.003326774,4.623316e-7,0.00002052685,0.0001074774],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6785424,0.0002453394,0.3207645,0.00006405146,0.0001150542,0.0001811951,4.495378e-7,0.00008426749,0.000002782622],"genre_scores_gemma":[0.9918341,3.87329e-7,0.007986119,0.00004822574,0.0000877685,0.00002181354,0.000004345963,0.000005568571,0.00001164691],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4173867,"threshold_uncertainty_score":0.365547,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.002443327476115435,"gpt":0.2036302636457611,"spread":0.2011869361696457,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001248479,0.00005641611,0.00006553554,0.0001410894,0.00002597857,0.00005855836,0.0001002066,0.00003478833,0.000007631134],"category_scores_gemma":[0.00005080345,0.0000537969,0.00002077058,0.0002368305,0.000005139335,0.0002664452,0.00004535259,0.000225204,0.000003190257],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001243454,"about_ca_system_score_gemma":0.000003833862,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009290009,"about_ca_topic_score_gemma":0.000205815,"domain_scores_codex":[0.9996126,0.000006355926,0.0000696132,0.000134244,0.00007413563,0.0001030393],"domain_scores_gemma":[0.9997878,0.00004579844,0.00001612923,0.0001133399,0.0000105926,0.00002635473],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000003026794,0.0000210324,0.01057286,0.00001820198,0.00002681577,0.00003514563,0.004896181,0.0006906486,0.812909,0.003295321,0.00001106629,0.1675207],"study_design_scores_gemma":[0.0001948622,0.000006141304,0.1251424,0.000006912992,0.000002948382,0.00001167282,0.00008243727,0.8466616,0.02762984,0.00001034955,0.0001310025,0.0001198391],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9762372,0.0002286822,0.02288679,0.00007160596,0.0004031238,0.00003598569,2.310641e-7,0.00007546315,0.00006087699],"genre_scores_gemma":[0.9935513,0.000002145576,0.006334227,0.00001593603,0.00005769157,0.000002272397,0.000001334044,0.000003170573,0.00003196582],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8459709,"threshold_uncertainty_score":0.2193774,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.0259402050914098,"gpt":0.260374998053483,"spread":0.2344347929620732,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004007425,0.0002739129,0.0002585098,0.0003543282,0.000314911,0.0002034962,0.0005400122,0.0001819483,0.000005987353],"category_scores_gemma":[0.0008428596,0.0002688793,0.0001652033,0.0008738369,0.00001248373,0.0003391003,0.0001033014,0.0004655428,0.00004077297],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001806447,"about_ca_system_score_gemma":0.00005917796,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004041855,"about_ca_topic_score_gemma":0.00007405132,"domain_scores_codex":[0.9982157,0.00002435894,0.0002374035,0.0005071966,0.0003585649,0.0006567381],"domain_scores_gemma":[0.9991056,0.0002823913,0.00006068651,0.0003040315,0.00005043745,0.0001968817],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004146578,0.00003219948,0.000011109,0.0003211481,0.00008234035,0.0003783641,0.02176809,0.6729297,0.1386705,0.001161449,0.001602658,0.163001],"study_design_scores_gemma":[0.0005442609,0.00002050402,0.00009802294,0.00003279547,0.000009387298,0.00002775181,0.0002866216,0.9804564,0.01796244,0.0000442294,0.0001847843,0.0003327868],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.447977,0.0002678077,0.5452021,0.001004449,0.00194343,0.0004973617,0.00002713547,0.002951778,0.0001289004],"genre_scores_gemma":[0.9770392,0.000006530949,0.02184563,0.0002365069,0.0005002445,0.00004301398,0.00003406005,0.00004925767,0.0002455405],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5290622,"threshold_uncertainty_score":0.9999763,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.009429505732520903,"gpt":0.2826202360865886,"spread":0.2731907303540677,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001108374,0.0002171628,0.0001918095,0.0002587484,0.0003552236,0.0002218204,0.0009007987,0.00005639517,0.00001941663],"category_scores_gemma":[0.0004326135,0.0002245338,0.0001055985,0.0006237628,0.000009390847,0.0005960084,0.0004566852,0.0005617711,0.000001321109],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003412373,"about_ca_system_score_gemma":0.00005090825,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000255485,"about_ca_topic_score_gemma":0.000001844968,"domain_scores_codex":[0.9980986,0.00006971094,0.000312992,0.0004371761,0.0006080955,0.0004734973],"domain_scores_gemma":[0.999097,0.0002181747,0.0001196973,0.0003599631,0.0001425117,0.00006259037],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002870201,0.00006746413,0.00009741817,0.0003281744,0.000074225,0.0001906239,0.005250131,0.04025569,0.2645046,0.01921583,0.001666892,0.6683203],"study_design_scores_gemma":[0.0003380151,0.00004411106,0.00006971575,0.00003145617,0.00001257398,0.000106583,0.0002112733,0.9869491,0.0116577,0.0001573684,0.0001228251,0.0002992755],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4243174,0.06325542,0.4789334,0.001611586,0.003357625,0.002682338,0.00006777687,0.02552934,0.0002452019],"genre_scores_gemma":[0.7439691,5.73665e-7,0.2553976,0.0001594364,0.0001613441,0.0001901777,0.00006201126,0.00002895791,0.00003076543],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9466934,"threshold_uncertainty_score":0.9156221,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.007743718129550689,"gpt":0.2627037147876462,"spread":0.2549599966580955,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009070981,0.0001167373,0.0001123426,0.0002011372,0.0001670577,0.000352413,0.001284792,0.00004684733,0.00001155129],"category_scores_gemma":[0.0002319185,0.0001019275,0.00004841468,0.0001691391,0.00001002839,0.0005750717,0.0003467984,0.0001639942,0.00004638559],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003651854,"about_ca_system_score_gemma":0.000005124803,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001859537,"about_ca_topic_score_gemma":0.000006731303,"domain_scores_codex":[0.9992539,0.000003459158,0.0001098536,0.0002344172,0.0001503936,0.0002479773],"domain_scores_gemma":[0.9990559,0.00002013644,0.00005406214,0.0007922931,0.00002136829,0.0000561989],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000001923246,0.000008249309,0.0000957124,0.000009701785,0.00001486711,0.00003343097,0.0009541829,0.0001299822,0.04178019,0.02430107,0.001362063,0.9313086],"study_design_scores_gemma":[0.001587806,0.0001462652,0.08566999,0.000233003,0.00002344639,0.00005417571,0.0006663483,0.3252293,0.3169935,0.0003121097,0.267062,0.002022022],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3229645,0.008195444,0.6063191,0.04880725,0.004236437,0.0003761275,0.00001655669,0.006801171,0.002283391],"genre_scores_gemma":[0.9726377,0.000008446574,0.02490574,0.00005516427,0.00008310281,0.00001617107,0.000002854064,0.000008046289,0.002282775],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9292866,"threshold_uncertainty_score":0.4156484,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Computer science; Focus (optics); Quarter (Canadian coin); Point (geometry); Artificial intelligence; Natural (archaeology); Natural language processing; History","retraction":null,"screen_n_in":null,"score":{"opus":0.004465130453185606,"gpt":0.2309133449031753,"spread":0.2264482144499897,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002997376,0.0001094503,0.0001060071,0.0001434812,0.00001956433,0.0001316763,0.0008929421,0.0000639978,0.000008619601],"category_scores_gemma":[0.00008280193,0.00008136297,0.00003806764,0.0004945497,0.000006888753,0.0004276612,0.0001133192,0.0004268742,0.00003305001],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006416545,"about_ca_system_score_gemma":0.00001327402,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006712316,"about_ca_topic_score_gemma":0.0000224576,"domain_scores_codex":[0.9992014,0.000031739,0.0001254025,0.0001884083,0.0002376603,0.0002154196],"domain_scores_gemma":[0.9994579,0.0001061079,0.00003445727,0.000364179,0.00001829557,0.00001904878],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001602686,0.000124337,0.004810014,0.0003028727,0.00004175099,0.0006596151,0.05212786,0.00191413,0.1609398,0.2247709,0.002316401,0.5519763],"study_design_scores_gemma":[0.003442283,0.0003361903,0.1592611,0.00114398,0.00003432985,0.0005846937,0.002645483,0.7330866,0.06574294,0.003707499,0.02635827,0.003656594],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9227943,0.01580391,0.05596945,0.001113805,0.001459777,0.0006486549,0.000002777318,0.001387305,0.000819981],"genre_scores_gemma":[0.9444441,0.000003076664,0.05502548,0.0003801858,0.00007765373,0.000008617563,0.000005871678,0.000009549222,0.00004551676],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7311726,"threshold_uncertainty_score":0.3317886,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.004698680563171272,"gpt":0.2267604826131823,"spread":0.222061802050011,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001177472,0.0001763281,0.0001554626,0.0001396438,0.0000876761,0.00004844585,0.0006054852,0.0001035272,0.000006599016],"category_scores_gemma":[0.0002495014,0.0001577134,0.00005429528,0.0003862715,0.00001718809,0.0005220236,0.0001299876,0.0003858211,0.0000134469],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001108176,"about_ca_system_score_gemma":0.00003543563,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004781986,"about_ca_topic_score_gemma":0.000003284512,"domain_scores_codex":[0.9988987,0.00001700918,0.0001767665,0.0003130604,0.0002748622,0.0003196423],"domain_scores_gemma":[0.9994406,0.00005734099,0.00005915239,0.0003072573,0.00006834711,0.00006736026],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001346929,0.00009012698,0.0004206257,0.0001098765,0.00005691723,0.0008007649,0.008427103,0.0003954436,0.7306762,0.005814369,0.005573642,0.2476215],"study_design_scores_gemma":[0.0005758985,0.0000752187,0.0005774476,0.00006317936,0.000008472651,0.0005398288,0.00004355914,0.2401359,0.7539868,0.000142575,0.002985261,0.0008659188],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3921237,0.05529143,0.5461189,0.0003483098,0.0009748695,0.0003567229,0.000008486305,0.004578122,0.0001994379],"genre_scores_gemma":[0.7724401,0.00001004908,0.2270218,0.0001156537,0.00009729596,0.000009342285,0.00001574393,0.00001434007,0.0002756816],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.3803164,"threshold_uncertainty_score":0.6431366,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01003904351749246,"gpt":0.2231050327943933,"spread":0.2130659892769008,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00020739,0.0001617504,0.0001285578,0.0002825566,0.00005891927,0.000122997,0.0004286582,0.0000798049,0.00002431465],"category_scores_gemma":[0.0001345445,0.0001508163,0.00007858888,0.0005681364,0.000006560717,0.0002165292,0.00008662326,0.0003828743,0.0001524727],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007175589,"about_ca_system_score_gemma":0.00001188084,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003144908,"about_ca_topic_score_gemma":0.000006835694,"domain_scores_codex":[0.9988479,0.00002420155,0.0001346757,0.0003487282,0.0003175502,0.0003269618],"domain_scores_gemma":[0.9992962,0.0001234111,0.00003138888,0.0004502186,0.0000283288,0.00007048326],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00002699285,0.00005997219,0.000097923,0.0001744691,0.00004324383,0.001118428,0.007662422,0.084861,0.09505205,0.003434421,0.003763651,0.8037055],"study_design_scores_gemma":[0.0003322688,0.00002084905,0.00204235,0.00008682072,0.000003142009,0.00001003488,0.0001259194,0.9781904,0.01837987,0.00002608866,0.0004927356,0.0002895446],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8169062,0.002256067,0.1709915,0.0007475733,0.003391508,0.0003580658,0.00002165282,0.00405666,0.001270837],"genre_scores_gemma":[0.9767797,0.000006706117,0.02235509,0.0001599062,0.0002947002,0.00001290851,0.00006725384,0.00002012875,0.0003036273],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8933294,"threshold_uncertainty_score":0.6150112,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.007204560510228801,"gpt":0.2309438070816249,"spread":0.2237392465713961,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002756846,0.0002189035,0.0001898304,0.0003129077,0.0001630904,0.0002756891,0.0004511529,0.00008931213,0.00000854253],"category_scores_gemma":[0.00008129715,0.0001874254,0.00006532075,0.0003533808,0.000005450802,0.0006675928,0.00004068951,0.0003100031,0.000007527276],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000243706,"about_ca_system_score_gemma":0.00004847752,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.05205232,"about_ca_topic_score_gemma":0.005714921,"domain_scores_codex":[0.9988371,0.00003044875,0.0002122318,0.0003364837,0.0001662069,0.0004175708],"domain_scores_gemma":[0.9992818,0.0001146762,0.00005512831,0.0003041384,0.00009302844,0.0001512068],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001384518,0.0000969597,0.0004866862,0.0008016344,0.0002329235,0.009077026,0.105109,0.001105459,0.1169945,0.00162919,0.0002987392,0.7641541],"study_design_scores_gemma":[0.0005598853,0.0001010255,0.00002756118,0.0001263877,0.00002412201,0.001941779,0.002804425,0.9845105,0.009283567,0.0000189349,0.000111834,0.0004899245],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1264348,0.01578893,0.8531095,0.0001661433,0.0004465378,0.001856789,0.000006514247,0.00214643,0.00004430395],"genre_scores_gemma":[0.6723041,2.116292e-7,0.3273845,0.00002948716,0.00006351992,0.0001500836,0.000004355606,0.00002372557,0.00004007647],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9834051,"threshold_uncertainty_score":0.9542602,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01083990589589887,"gpt":0.2761478394611767,"spread":0.2653079335652778,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0004066936,0.0002600387,0.0002057901,0.0005206574,0.000575599,0.0002095353,0.0006308387,0.00004161056,0.00001284842],"category_scores_gemma":[0.0001444819,0.0002567102,0.00007756084,0.001181982,0.0000142642,0.0004326335,0.0005841809,0.0014494,0.000002883063],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005662536,"about_ca_system_score_gemma":0.00004625497,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002970733,"about_ca_topic_score_gemma":0.000197491,"domain_scores_codex":[0.9981845,0.0001263607,0.0002412976,0.0005334048,0.0005230192,0.0003913964],"domain_scores_gemma":[0.9991775,0.0001228389,0.0001098557,0.000456598,0.00005505776,0.00007812593],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006519222,0.0008036924,0.003119814,0.0002034887,0.0002374012,0.09134087,0.05109345,0.09150086,0.5480612,0.0009598776,0.00009105966,0.2125231],"study_design_scores_gemma":[0.0005565971,0.0004411627,0.0004304808,0.00005049872,0.00002632085,0.004651661,0.003857788,0.9672834,0.0216662,0.0000316329,0.0002641054,0.000740142],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.957678,0.001692521,0.03753209,0.00002649497,0.0008400078,0.000366013,0.000002785442,0.001829287,0.000032834],"genre_scores_gemma":[0.939446,9.030297e-7,0.06011215,0.00004276657,0.00010953,0.00004638908,0.000003489809,0.00003295596,0.0002058224],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8757825,"threshold_uncertainty_score":0.9999885,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.003863718336442225,"gpt":0.2078067341440626,"spread":0.2039430158076204,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001272765,0.0001365348,0.0001298536,0.0000779223,0.00004109731,0.00009385806,0.0008775565,0.00005629915,0.0000377268],"category_scores_gemma":[0.0002093792,0.0000847855,0.00005549593,0.000338381,0.00002138905,0.0002717786,0.0001993332,0.0003528899,0.00003685731],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003689061,"about_ca_system_score_gemma":0.000009377606,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005819524,"about_ca_topic_score_gemma":0.000001261231,"domain_scores_codex":[0.9992133,0.00001615338,0.0001487008,0.000163437,0.0002526695,0.0002057405],"domain_scores_gemma":[0.9991627,0.0002390533,0.00005944695,0.0004477537,0.00005825346,0.00003281234],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000003934455,0.00005302554,0.00005624063,0.0001260799,0.00005223009,0.00004415566,0.002654558,0.0004476991,0.4865402,0.4563461,0.009554303,0.04412145],"study_design_scores_gemma":[0.0003114835,0.000121988,0.0009766724,0.0003116814,0.00001285006,0.00007826166,0.0001075949,0.5389119,0.4494552,0.008307411,0.0006771802,0.0007277403],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5202578,0.01404734,0.4524724,0.005858913,0.001441228,0.0009730147,0.000004864136,0.002781258,0.002163196],"genre_scores_gemma":[0.8676668,0.00000196644,0.1319164,0.0002478488,0.00003684938,0.0000103994,0.000001235108,0.00001090915,0.000107573],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5384642,"threshold_uncertainty_score":0.3457452,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02241642151835773,"gpt":0.2265547629684585,"spread":0.2041383414501008,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001501852,0.0001146152,0.0001382082,0.0002196861,0.00003627878,0.00005435557,0.0003226221,0.0000435067,0.00004387318],"category_scores_gemma":[0.00006017703,0.0001034583,0.00006149107,0.0004782733,0.000004866858,0.0002704108,0.0001014168,0.0002788419,0.00002489459],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003268331,"about_ca_system_score_gemma":0.00001184299,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007178161,"about_ca_topic_score_gemma":0.00001628919,"domain_scores_codex":[0.9992074,0.00002287206,0.000180089,0.0002137541,0.0001340008,0.000241869],"domain_scores_gemma":[0.9996817,0.00003011427,0.00003725867,0.0001736134,0.00002558852,0.00005172268],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0000395567,0.0003589262,0.06958693,0.0001203689,0.000525618,0.001112533,0.06647959,0.06164394,0.5885291,0.08865634,0.0008943343,0.1220528],"study_design_scores_gemma":[0.0004219242,0.00002971668,0.01484211,0.00005430286,0.000004841602,0.000008476371,0.0004656529,0.9692481,0.01367382,0.000001936602,0.0009818352,0.0002673067],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9710552,0.002609344,0.02394559,0.00007365037,0.00104246,0.0001044821,9.457742e-7,0.0004098128,0.0007584849],"genre_scores_gemma":[0.9787441,0.00001004553,0.02067682,0.00003359503,0.00005914335,0.000005519767,0.00001387623,0.000009129622,0.0004477894],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9076041,"threshold_uncertainty_score":0.4218907,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.00247665107588323,"gpt":0.231932056132034,"spread":0.2294554050561508,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001015298,0.000138946,0.0002014273,0.0003737983,0.00002964183,0.00006680033,0.0003865779,0.00007498357,0.000004698105],"category_scores_gemma":[0.00006785031,0.0001215534,0.00009212058,0.001181258,0.00000742379,0.0002645266,0.00002988562,0.0001487788,2.34399e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008385123,"about_ca_system_score_gemma":0.00001452848,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000325519,"about_ca_topic_score_gemma":0.000003540972,"domain_scores_codex":[0.9990851,0.00001839211,0.0002103348,0.0002372163,0.0002811388,0.0001677874],"domain_scores_gemma":[0.9994185,0.00003519333,0.000117485,0.0003163714,0.00007206731,0.00004037255],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001547504,0.00004857626,0.0001225793,0.00005794257,0.0001665333,0.00002772225,0.0008003952,0.0193622,0.8804362,0.02009866,0.0002548386,0.07860892],"study_design_scores_gemma":[0.0001314914,0.00005455304,0.001253302,0.00003760364,0.00008871772,0.000003903272,0.000004923895,0.5381186,0.4597709,0.0003061426,0.00003633788,0.0001936011],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05581442,0.01118239,0.9320033,0.0001047327,0.00009182387,0.0001234208,0.000008376438,0.0006476469,0.00002394074],"genre_scores_gemma":[0.8401203,0.000003785297,0.159618,0.0001238886,0.00001622721,0.00000307029,0.00009198047,0.000005447584,0.00001734224],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7843059,"threshold_uncertainty_score":0.4956805,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01414064130185601,"gpt":0.2556672043902133,"spread":0.2415265630883573,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007363633,0.0003129902,0.0002176174,0.0001407232,0.000128085,0.0002586252,0.0009310984,0.0001318504,0.000008843194],"category_scores_gemma":[0.0005223817,0.0002052327,0.0001172794,0.0007122201,0.00003641091,0.0002864748,0.00009618661,0.0007269878,0.00000629541],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001265302,"about_ca_system_score_gemma":0.000123152,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002683329,"about_ca_topic_score_gemma":0.000002096029,"domain_scores_codex":[0.9981105,0.0000827648,0.000279154,0.0005177917,0.0005145848,0.0004951474],"domain_scores_gemma":[0.9985713,0.0002700294,0.0001188023,0.000876488,0.00009870142,0.00006468871],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002255074,0.000870891,0.0017195,0.00129355,0.0005052126,0.01932838,0.009685212,0.2024433,0.04647653,0.625695,0.01263594,0.07912088],"study_design_scores_gemma":[0.0002575166,0.00006865749,0.000021312,0.000203528,0.00001178841,0.0002453732,0.00002739835,0.9265581,0.06835237,0.0005544003,0.00310127,0.0005983188],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08046877,0.02397971,0.8853667,0.001404117,0.001570199,0.001405542,0.000008146047,0.004344486,0.001452321],"genre_scores_gemma":[0.69077,0.000002034245,0.3087471,0.0001496395,0.00005822473,0.00003710456,0.000007202099,0.0000272255,0.0002014276],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7241147,"threshold_uncertainty_score":0.8369148,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.004691055894078967,"gpt":0.2111093347640541,"spread":0.2064182788699751,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001071464,0.00007709993,0.00008308153,0.00006598786,0.00002476626,0.00005468629,0.0001405825,0.00006208062,0.000002052184],"category_scores_gemma":[0.0001887071,0.00007528801,0.00002038328,0.0003249703,0.000006893459,0.0002915361,0.0000602221,0.0002932957,0.000004227846],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004964141,"about_ca_system_score_gemma":0.000005534186,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004671875,"about_ca_topic_score_gemma":0.00005467537,"domain_scores_codex":[0.9994424,0.00001070051,0.0001230866,0.0002002127,0.00009391864,0.000129695],"domain_scores_gemma":[0.9997369,0.00005830625,0.00002043668,0.0001213709,0.00001149025,0.00005146583],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000009665435,0.00001536213,0.0004107484,0.00005695619,0.000003329809,0.00003547674,0.005536985,0.001466222,0.6029116,0.0007825176,0.00001280981,0.3887583],"study_design_scores_gemma":[0.0001787072,0.00003767206,0.02966343,0.00001946053,0.000001807422,0.00004793501,0.0003430519,0.9376957,0.03172253,0.000004679999,0.000134202,0.000150776],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8255678,0.0008673198,0.1721369,0.0004462376,0.0002530075,0.0001310766,6.767792e-7,0.000468295,0.0001287336],"genre_scores_gemma":[0.9949434,0.000003364962,0.004870839,0.00008187423,0.00007522048,0.00000644305,0.000002386243,0.000005532774,0.00001089564],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9362295,"threshold_uncertainty_score":0.3070156,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01539149631651612,"gpt":0.2320307436379919,"spread":0.2166392473214758,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002933752,0.0001645725,0.0001212013,0.00006507017,0.0001184482,0.0001014515,0.0007244508,0.00007234208,0.000004749652],"category_scores_gemma":[0.00004116762,0.0001151248,0.00006953281,0.0001947543,0.000008337685,0.0006675781,0.0002168234,0.0004437825,0.0000147378],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005122065,"about_ca_system_score_gemma":0.000007597086,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008474699,"about_ca_topic_score_gemma":0.000002181724,"domain_scores_codex":[0.9988541,0.00002024837,0.0001644239,0.0002266583,0.000261593,0.0004729599],"domain_scores_gemma":[0.9992811,0.00003175833,0.00002209408,0.0005597812,0.00002155429,0.00008369671],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000002366242,0.00006254878,0.0001682238,0.00009242136,0.00008379867,0.00001427842,0.04327936,0.7974315,0.02997349,0.09644469,0.0002462217,0.03220113],"study_design_scores_gemma":[0.0000998709,0.000002938483,0.0001011122,0.00001312241,0.000005617579,0.00002578001,0.0003956633,0.9985731,0.0003408999,0.00002313013,0.0002333487,0.0001853791],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1533765,0.00772042,0.8356439,0.0002151037,0.0007729686,0.000152949,4.695337e-7,0.0004773224,0.0016404],"genre_scores_gemma":[0.9056759,0.000002238501,0.09325685,0.0001965847,0.0006147677,0.000011132,0.000003408087,0.00001760693,0.000221527],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7522994,"threshold_uncertainty_score":0.4694655,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01251648226489134,"gpt":0.2419384875471892,"spread":0.2294220052822979,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0004831475,0.0009500884,0.0007344171,0.001220294,0.0001876236,0.000675779,0.002330794,0.0010382,0.00006840099],"category_scores_gemma":[0.000699763,0.0008698316,0.0003949572,0.001481775,0.00004439874,0.0005202965,0.0004297728,0.004238451,0.0002509543],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005783652,"about_ca_system_score_gemma":0.0001667698,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001711443,"about_ca_topic_score_gemma":0.0000611939,"domain_scores_codex":[0.9958549,0.0001031106,0.0005042875,0.001322245,0.001225944,0.0009895045],"domain_scores_gemma":[0.9975082,0.0002487023,0.0003169765,0.001511311,0.0001947974,0.0002199659],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003047059,0.00006589233,0.000001754126,0.0006279913,0.00007762139,0.001994485,0.001345318,0.000123727,0.004270881,0.0005623298,0.8333172,0.1575824],"study_design_scores_gemma":[0.003535487,0.0008992478,0.000708736,0.01448902,0.0003191492,0.000515448,0.0007277753,0.613713,0.1208815,0.001261425,0.2295796,0.01336962],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"editorial","genre_gemma":"methods","genre_scores_codex":[0.00144308,0.3241944,0.2291903,0.002782819,0.3576994,0.004758612,0.00151066,0.06410521,0.01431553],"genre_scores_gemma":[0.1380585,0.0009024842,0.5695523,0.002768749,0.01733097,0.0005773653,0.0155686,0.001453874,0.2537872],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6135893,"threshold_uncertainty_score":0.9993752,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.01503705218098906,"gpt":0.2628490486382299,"spread":0.2478119964572408,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001323281,0.0001108056,0.000164434,0.0001580325,0.00003493913,0.00003159939,0.0002364906,0.00006181744,0.00000360424],"category_scores_gemma":[0.00009097067,0.00009352991,0.00003091366,0.0003609267,0.00002617633,0.0004432208,0.0001184681,0.0001418322,1.896829e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002393148,"about_ca_system_score_gemma":0.00002437732,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002258936,"about_ca_topic_score_gemma":0.00001516274,"domain_scores_codex":[0.9992613,0.00001463244,0.0002002317,0.00017827,0.0001889795,0.0001566153],"domain_scores_gemma":[0.9995744,0.00003602299,0.0000879374,0.0001875573,0.00007552905,0.00003860261],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00000237329,0.00001189098,0.0008075627,0.00005586527,0.000009384128,0.00002856039,0.0007230564,0.0004322385,0.9835241,0.00138454,0.00001445418,0.01300593],"study_design_scores_gemma":[0.0001370465,0.00003125844,0.0003099165,0.0001365092,0.000008285559,0.0001112133,0.00007244504,0.5973214,0.4016088,0.00007400581,0.00002083452,0.000168302],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8167372,0.01572579,0.1670711,0.00003933239,0.0001694818,0.00007918,0.000002089683,0.0001607017,0.00001508898],"genre_scores_gemma":[0.7011808,0.00001342843,0.2987182,0.000009597681,0.00004473744,0.000001158087,0.000002752754,0.000005778634,0.00002363025],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5968891,"threshold_uncertainty_score":0.3814039,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.004611272547601871,"gpt":0.209634801010973,"spread":0.2050235284633712,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008997681,0.0002276997,0.0002040049,0.0001990703,0.00019593,0.00005210144,0.0009388284,0.0004469572,0.000009776328],"category_scores_gemma":[0.00001165639,0.0002038827,0.0000772761,0.001080254,0.00002499703,0.0002743748,0.0003513574,0.001299095,0.00001568411],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000416579,"about_ca_system_score_gemma":0.00002226426,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000072856,"about_ca_topic_score_gemma":0.0000343246,"domain_scores_codex":[0.9987024,0.00001679939,0.0001799403,0.0003441847,0.0002588926,0.0004977526],"domain_scores_gemma":[0.9994313,0.00004770768,0.00005614711,0.0003579555,0.00003432213,0.00007260021],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00005713178,0.0002805288,0.008473924,0.0005428713,0.0006922266,0.008859359,0.25053,0.01411868,0.278813,0.04989563,0.005801849,0.3819348],"study_design_scores_gemma":[0.005658058,0.0003390803,0.01991548,0.0008962828,0.0001425324,0.004874455,0.01460564,0.5530086,0.2746674,0.0005567822,0.1182659,0.00706977],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9783779,0.00657872,0.008864458,0.00210099,0.00136132,0.000135762,0.000003239906,0.001661801,0.0009158491],"genre_scores_gemma":[0.9888495,0.000006507656,0.009447878,0.0005943178,0.0009246285,0.000009891718,0.000008695111,0.00002338924,0.0001352319],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5388899,"threshold_uncertainty_score":0.8314096,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}