{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":3084,"total_is_capped":false,"direct_labels_cover":10,"predictions_cover":3084,"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":"faf12f59571d","filters":{"topic":"Natural Language Processing Techniques"}},"results":[{"id":"W2157331557","doi":"10.3115/v1/d14-1179","title":"Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation","year":2014,"lang":"en","type":"preprint","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":24447,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Machine translation; Computer science; Phrase; Natural language processing; Artificial intelligence; Encoder; Translation (biology); Statistical learning; Speech recognition","retraction":null,"screen_n_in":null,"score":{"opus":0.04515960229356928,"gpt":0.3691423632671048,"spread":0.3239827609735355,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005933503,0.0002904494,0.0003435196,0.000222306,0.0002511004,0.0004832166,0.0008621927,0.0002791717,0.00004274652],"category_scores_gemma":[0.0003838145,0.0002685706,0.0001261419,0.0001535412,0.00005216881,0.0003315868,0.0004916782,0.0007265231,0.000004923724],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008038641,"about_ca_system_score_gemma":0.0001652279,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002695741,"about_ca_topic_score_gemma":0.00003984808,"domain_scores_codex":[0.9978476,0.0001757952,0.0004640394,0.0008556104,0.0003375602,0.0003194068],"domain_scores_gemma":[0.9983073,0.0004718175,0.0002608958,0.0006424564,0.0002165457,0.0001010032],"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":[0.00007412431,0.0002197407,0.000388896,0.001406207,0.0001707038,0.00003567908,0.003961583,0.05365009,0.006401915,0.1893911,0.002384002,0.7419159],"study_design_scores_gemma":[0.0001837241,0.00003517094,0.000009144051,0.00007417821,0.00003427194,0.00001075712,0.00000947767,0.8724857,0.001925784,0.1245661,0.0003607268,0.0003049337],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0002338792,0.0008471452,0.9957536,0.0006601838,0.0002949208,0.0006248907,0.00003542892,0.001122505,0.0004274648],"genre_scores_gemma":[0.1995469,0.000009294705,0.7996864,0.000151089,0.000117934,0.00007016637,0.0001929611,0.00002825687,0.0001969256],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8188356,"threshold_uncertainty_score":0.9999766,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2153579005","doi":"10.48550/arxiv.1310.4546","title":"Distributed Representations of Words and Phrases and their Compositionality","year":2013,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":18086,"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; Principle of compositionality; Softmax function; Word (group theory); Natural language processing; Artificial intelligence; Simple (philosophy); Semantics (computer science); Quality (philosophy); Speedup; Linguistics; Artificial neural network","retraction":null,"screen_n_in":null,"score":{"opus":0.03203702315028123,"gpt":0.1988674381578246,"spread":0.1668304150075434,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00005151871,0.00006250681,0.00008200459,0.00005167822,0.00007305235,0.00004224532,0.0002199338,0.00002908646,0.00000878644],"category_scores_gemma":[0.00002015924,0.00005617121,0.00001805222,0.0002756902,0.0001281565,0.0004507225,0.0002090549,0.00005423026,0.000001232022],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001276808,"about_ca_system_score_gemma":0.00001234439,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001763699,"about_ca_topic_score_gemma":0.000007330932,"domain_scores_codex":[0.9995777,0.00003796461,0.00006496054,0.0002166006,0.00002471573,0.00007804816],"domain_scores_gemma":[0.9995227,0.0001059716,0.00005700915,0.0002044863,0.00006073631,0.00004913532],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00001101551,0.00009574142,0.02888297,0.0000475144,0.00003797334,0.00002020161,0.0007647659,0.0001269835,0.008708145,0.9573289,0.0003348613,0.003640936],"study_design_scores_gemma":[0.0005597782,0.00008772321,0.03252213,0.00007429695,0.00002182568,0.0000297197,0.0005661249,0.1536476,0.02593666,0.7861336,0.00007648596,0.0003439625],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4792244,0.0001808601,0.5201725,0.0001595498,0.00000888437,0.00006566297,0.00001158791,0.00008749258,0.00008903238],"genre_scores_gemma":[0.982685,0.00002847157,0.01719671,0.00003643353,0.000004284106,3.932681e-7,0.000007136844,0.000001820711,0.0000397054],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5034606,"threshold_uncertainty_score":0.2290596,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2964199361","doi":"10.3115/v1/w14-4012","title":"On the Properties of Neural Machine Translation: Encoder–Decoder Approaches","year":2014,"lang":"en","type":"preprint","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":6616,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal; Canadian Institute for Advanced Research","funders":"Compute Canada; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Canadian Institute for Advanced Research","keywords":"Computer science; Machine translation; Encoder; Translation (biology); Artificial intelligence; Speech recognition; Operating system","retraction":null,"screen_n_in":null,"score":{"opus":0.08784431085000213,"gpt":0.257640388060015,"spread":0.1697960772100129,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005004241,0.0002742777,0.0003012242,0.0001043071,0.00008432763,0.0001984236,0.00224897,0.0001947683,0.00002060857],"category_scores_gemma":[0.00006664683,0.0001394919,0.000138453,0.0001300724,0.0001134088,0.0001467022,0.0007001899,0.0006703277,0.000004396686],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001882789,"about_ca_system_score_gemma":0.00006481348,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000647788,"about_ca_topic_score_gemma":0.00001457327,"domain_scores_codex":[0.9984047,0.0001698789,0.0003354276,0.0004961696,0.0004098588,0.0001838958],"domain_scores_gemma":[0.9984059,0.0001303853,0.0002177064,0.001130546,0.00008282174,0.00003262926],"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":[0.00005942718,0.0002355162,0.00003924923,0.001234955,0.0001219187,0.000005312359,0.005674188,0.003890352,0.001971219,0.481098,0.001857101,0.5038127],"study_design_scores_gemma":[0.00006601673,0.00004606876,0.00000539863,0.0001819432,0.00001043569,0.000005826729,0.000008936367,0.8748124,0.04678997,0.07774717,0.00007939906,0.0002463798],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002260399,0.009672671,0.9725356,0.01020349,0.0002271691,0.0005701589,0.000003296376,0.0006942124,0.003833079],"genre_scores_gemma":[0.7860653,0.000007839538,0.2131466,0.000482508,0.00004361743,0.00005326804,0.000003440216,0.00001304633,0.0001843168],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8709221,"threshold_uncertainty_score":0.5688316,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2626778328","doi":"10.65215/2q58a426","title":"Attention Is All You Need","year":2025,"lang":"en","type":"preprint","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":6569,"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; Machine translation; Transformer; BLEU; Encoder; Artificial intelligence; Parallelizable manifold; Parsing; Language model; Natural language processing; Decoding methods; Task (project management); Convolutional neural network; Speech recognition; Machine learning; Algorithm","retraction":null,"screen_n_in":null,"score":{"opus":0.01958296515034699,"gpt":0.3049060813157011,"spread":0.2853231161653542,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002029375,0.00021217,0.0002062506,0.0002180632,0.00004286449,0.0003994457,0.002132497,0.0003120577,0.0000396781],"category_scores_gemma":[0.00003070384,0.0001827019,0.0001340995,0.0002149295,0.00001862764,0.0002051159,0.003602651,0.0005359327,0.00003337303],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007651981,"about_ca_system_score_gemma":0.000125054,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000215308,"about_ca_topic_score_gemma":0.000005125773,"domain_scores_codex":[0.9986245,0.00003542626,0.0002293846,0.00064158,0.0002622128,0.0002069152],"domain_scores_gemma":[0.9985954,0.00002251494,0.0001266796,0.001061818,0.0001485084,0.00004505332],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000007855316,0.0001391526,0.000262835,0.0009233367,0.0001813798,0.00005036582,0.001383962,0.000009100872,0.003690553,0.3490162,0.2192653,0.42507],"study_design_scores_gemma":[0.0002526972,0.00004266971,0.0002378002,0.0008758734,0.00006286018,0.00001405949,0.00002037299,0.05500688,0.05321063,0.8615903,0.02750007,0.001185756],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000196358,0.001738857,0.97448,0.007786571,0.0006284497,0.0002369338,0.000007048734,0.002298142,0.01262762],"genre_scores_gemma":[0.01322393,0.00004528891,0.9632493,0.00390369,0.00006639816,0.00003453991,0.00001651716,0.000006889331,0.01945349],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5125741,"threshold_uncertainty_score":0.7450366,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4243041937","doi":"10.1017/cbo9780511801686","title":"Analyzing Linguistic Data","year":2008,"lang":"en","type":"book","venue":"Cambridge University Press eBooks","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":3194,"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":"Variety (cybernetics); Computer science; Construct (python library); Variation (astronomy); Visualization; Natural language processing; Range (aeronautics); Artificial intelligence; Measure (data warehouse); Statistical model; Corpus linguistics; Linguistics; Data science; Data mining; Engineering; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.03352730678943484,"gpt":0.2424501016676691,"spread":0.2089227948782343,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","open_science"],"consensus_categories":[],"category_scores_codex":[0.0001647134,0.0003821131,0.0004245891,0.0003178238,0.000293282,0.0001710249,0.007277974,0.0003687947,3.275793e-7],"category_scores_gemma":[0.0001044985,0.0004388504,0.0001147562,0.00004794815,0.0001922633,0.0003595666,0.005019881,0.0008095668,0.00001015254],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003297087,"about_ca_system_score_gemma":0.0007030963,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001122104,"about_ca_topic_score_gemma":0.000001206846,"domain_scores_codex":[0.9978988,0.0000732858,0.0002068133,0.001090454,0.0003581694,0.0003724615],"domain_scores_gemma":[0.9961502,0.0001189438,0.0003073052,0.003008151,0.000250643,0.0001647842],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000007122977,0.000008068599,7.04613e-7,0.00009536075,0.00006228081,0.001730803,0.00005859117,2.630716e-7,0.00001404131,0.6959133,0.2977715,0.004338041],"study_design_scores_gemma":[0.0001673501,0.00002221118,8.099018e-7,0.0002582608,0.00008470839,0.0000858428,0.000001380974,0.002309012,0.0002838399,0.00009524162,0.9961405,0.0005508416],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"other","genre_scores_codex":[8.650475e-7,0.002166432,0.2422528,0.00001149354,0.0002524821,0.0001892134,0.0001410219,0.001054203,0.7539315],"genre_scores_gemma":[0.00005803938,0.0001553727,0.08881216,0.00006221509,0.0002533415,3.064272e-7,0.0002039962,0.00003217154,0.9104224],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.6983691,"threshold_uncertainty_score":0.9998063,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1592805114","doi":"","title":"Analyzing linguistic data : a practical introduction to statistics using R","year":2008,"lang":"en","type":"book","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":2077,"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":"Variety (cybernetics); Computer science; Variation (astronomy); Construct (python library); Range (aeronautics); Visualization; Natural language processing; Measure (data warehouse); Linguistics; Artificial intelligence; Statistical model; Computational statistics; Data science; Data mining; Machine learning; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.06438462978172278,"gpt":0.3688184923184362,"spread":0.3044338625367134,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003907411,0.0002893857,0.0003460018,0.0003521551,0.0001583574,0.0003418835,0.001951369,0.000218709,0.00002384113],"category_scores_gemma":[0.002779853,0.0002710465,0.00002888035,0.0003051985,0.00005436859,0.0004878668,0.002139534,0.0006756981,0.00005577589],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003658393,"about_ca_system_score_gemma":0.001286579,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004656189,"about_ca_topic_score_gemma":0.00001547973,"domain_scores_codex":[0.9976849,0.00005193052,0.0003911874,0.001096225,0.0004650002,0.0003107659],"domain_scores_gemma":[0.9967422,0.0002040592,0.0002471476,0.002251103,0.0004104658,0.0001449914],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000005678214,0.00002560586,0.000001068454,0.000081403,0.00003809564,0.0003830877,0.0001473315,0.000008215812,0.00007796589,0.2944305,0.6833264,0.02147471],"study_design_scores_gemma":[0.00009687332,0.0001194292,7.461006e-7,0.000265047,0.0001378357,0.001065829,0.000002569853,0.1615378,0.0003281508,0.1170905,0.7182302,0.001125051],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[1.757822e-7,0.0006204052,0.9902305,0.0008572221,0.0006322523,0.0002091868,0.00005331512,0.0006949083,0.006702058],"genre_scores_gemma":[0.00000812295,0.00003384636,0.9043338,0.0002480179,0.002501824,0.000002016461,0.0002212256,0.00003320919,0.09261798],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.17734,"threshold_uncertainty_score":0.9999742,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2136930489","doi":"10.1162/coli.2006.32.1.13","title":"Evaluating WordNet-based Measures of Lexical Semantic Relatedness","year":2006,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":1414,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"University of Toronto; University of Pennsylvania","keywords":"WordNet; Computer science; Semantic similarity; Natural language processing; Spelling; Artificial intelligence; Lexical database; Proxy (statistics); Similarity (geometry); Information retrieval; Measure (data warehouse); Linguistics; Machine learning; Data mining","retraction":null,"screen_n_in":null,"score":{"opus":0.0587311279945921,"gpt":0.346960390515805,"spread":0.2882292625212128,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004399797,0.0001279066,0.0001731069,0.000137932,0.0001045932,0.00007501498,0.0005196149,0.00007948533,0.000003718006],"category_scores_gemma":[0.001939885,0.0001230849,0.00005784373,0.0004018311,0.000084574,0.00003954266,0.00009851288,0.0001719385,0.000006008797],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004478522,"about_ca_system_score_gemma":0.0002521246,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003983629,"about_ca_topic_score_gemma":0.000002348397,"domain_scores_codex":[0.9984685,0.00007507822,0.0003981639,0.0002661726,0.0006191061,0.0001729418],"domain_scores_gemma":[0.9979158,0.0004566876,0.0002114476,0.0002274755,0.001149956,0.000038649],"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":[0.00001295665,0.0001373636,0.0007909734,0.00009430487,0.00001216839,0.0000272806,0.00006982309,0.1970885,0.0004811645,0.7902249,0.0006374067,0.01042317],"study_design_scores_gemma":[0.0001716767,0.00004543959,0.000435134,0.00008290158,0.00001011821,0.000003556346,0.000001052018,0.6532295,0.002272144,0.3434329,0.000193309,0.000122343],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.003044746,0.0008110262,0.9944451,0.0001129638,0.000358652,0.0000950504,0.000004088096,0.0003451139,0.0007832989],"genre_scores_gemma":[0.514506,1.704581e-7,0.4852756,0.00005659012,0.0001175206,0.000002163964,0.00001616254,0.000006224696,0.00001956101],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5114613,"threshold_uncertainty_score":0.5019257,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2140679639","doi":"","title":"A Neural Probabilistic Language Model","year":2000,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":1162,"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":"Trigram; Computer science; Artificial intelligence; Probabilistic logic; Word (group theory); Generalization; Natural language processing; Similarity (geometry); Language model; Curse of dimensionality; Sequence (biology); Representation (politics); Function (biology); Statistical model; Artificial neural network; Sentence; Probability distribution; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.01070564996388041,"gpt":0.2618203588921802,"spread":0.2511147089282998,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00007993776,0.00008663166,0.0000758081,0.00003684945,0.00004666088,0.0001197981,0.0007273837,0.00003643737,0.0001636884],"category_scores_gemma":[0.00002079681,0.00006481539,0.00003061116,0.0001968546,0.00002238465,0.0004014834,0.00008186966,0.0001010995,0.00006599564],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001844873,"about_ca_system_score_gemma":0.00002469585,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002799407,"about_ca_topic_score_gemma":0.000005898535,"domain_scores_codex":[0.9993176,0.00001567259,0.00009909568,0.0002379011,0.0001441569,0.0001855253],"domain_scores_gemma":[0.9994929,0.00001694461,0.00001584467,0.0004013033,0.00002332297,0.00004967988],"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":[0.000006419156,0.0000662095,0.00001151206,0.00002483672,0.000004108821,0.00005940023,0.001681848,0.001512182,0.003384952,0.1968781,0.002863544,0.7935069],"study_design_scores_gemma":[0.00005872364,0.00001775314,0.000005008228,0.000005665634,0.000001327423,0.00002409502,0.000003389171,0.9383848,0.002948669,0.05834093,0.00009377835,0.0001158335],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03810643,0.0009694675,0.9276152,0.001424803,0.00003857103,0.0002101665,0.000001254987,0.003315595,0.02831854],"genre_scores_gemma":[0.516384,0.000001314045,0.4782163,0.0006918309,0.00001349885,0.000008603495,6.196574e-7,0.000004306605,0.004679549],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9368727,"threshold_uncertainty_score":0.2643095,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4230872509","doi":"10.1016/b0-08-044854-2/05234-2","title":"Association for Computational Linguistics","year":2006,"lang":"en","type":"book-chapter","venue":"Elsevier eBooks","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":1154,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Association (psychology); Linguistics; Applied linguistics; Computer science; Computational linguistics; Natural language processing; Philosophy; Epistemology","retraction":null,"screen_n_in":null,"score":{"opus":0.01221444471084589,"gpt":0.2608096693829754,"spread":0.2485952246721295,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003037925,0.0002687105,0.0003031109,0.000142611,0.0001297094,0.0002010563,0.0006738742,0.0003819344,0.000005090283],"category_scores_gemma":[0.0002274684,0.0002718337,0.0001705807,0.00001479327,0.00002639944,0.00003758305,0.0001646513,0.0003244986,0.00002423479],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002994905,"about_ca_system_score_gemma":0.0001591976,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":4.114186e-7,"about_ca_topic_score_gemma":0.000003725728,"domain_scores_codex":[0.9985389,0.00001174267,0.0003580141,0.0004193608,0.000439562,0.0002323935],"domain_scores_gemma":[0.998103,0.0002570507,0.0004945369,0.0003264596,0.0007718667,0.00004706858],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000001523749,0.000003948202,0.000001380375,0.00005844034,0.00003480549,0.00000560091,0.00002310848,0.00001172923,0.000001951203,0.3943359,0.01039489,0.5951267],"study_design_scores_gemma":[0.00006955636,0.00001865772,5.727667e-7,0.00008570314,0.00002343102,0.000001473846,5.217061e-8,0.0009206648,0.00003743045,0.4412712,0.5573831,0.0001881126],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"other","genre_gemma":"other","genre_scores_codex":[4.635883e-8,0.001198228,0.1142422,0.0001087766,0.0005758046,0.0003946528,0.00004775999,0.0005114278,0.8829212],"genre_scores_gemma":[0.00005396388,0.000002261057,0.3502516,0.0002500405,0.0005698269,0.00002144323,0.00006729701,0.00003040869,0.6487532],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.5949386,"threshold_uncertainty_score":0.9999734,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2119168550","doi":"10.1162/0891201042544884","title":"The Alignment Template Approach to Statistical Machine Translation","year":2004,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":933,"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; NIST; Machine translation; Evaluation of machine translation; Natural language processing; Example-based machine translation; Artificial intelligence; Phrase; Machine translation software usability; Generalization; Transfer-based machine translation; Translation (biology); Task (project management); Context (archaeology); Feature (linguistics); Rule-based machine translation; Word (group theory); Linguistics","retraction":null,"screen_n_in":null,"score":{"opus":0.02186480999394037,"gpt":0.2953628508639949,"spread":0.2734980408700545,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002760893,0.0001209329,0.00009473804,0.00005579262,0.0003183471,0.0002380573,0.0005850637,0.00003925607,8.468202e-7],"category_scores_gemma":[0.0005605682,0.00009054558,0.00002685898,0.0002413265,0.00004955983,0.00003782843,0.0001030058,0.0001413132,0.00002181112],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008865212,"about_ca_system_score_gemma":0.0001110723,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001634068,"about_ca_topic_score_gemma":0.000002304735,"domain_scores_codex":[0.9988167,0.00003302265,0.0002493903,0.0002702501,0.0004276061,0.0002029738],"domain_scores_gemma":[0.9990401,0.0003185213,0.00006042736,0.000215184,0.0002676411,0.00009815669],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000005691914,0.00004315557,0.000005760887,0.000008354309,0.000007212757,0.000005883958,0.0002410624,0.0401843,0.000009316496,0.9418948,0.0003566287,0.01723787],"study_design_scores_gemma":[0.0002169871,0.00005442309,0.0001234103,0.00001609617,0.000006033273,0.00001470499,0.000004850746,0.2367818,0.0001639628,0.751429,0.01102459,0.000164213],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00001964043,0.0006075578,0.9957199,0.0007919773,0.0003040493,0.0001933828,0.00001904406,0.0002665497,0.002077964],"genre_scores_gemma":[0.3559318,0.000001797003,0.6435779,0.0003137761,0.0001092379,0.00001079087,0.0000333517,0.000006764776,0.00001450781],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.3559122,"threshold_uncertainty_score":0.3692342,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2100664567","doi":"10.3115/v1/p15-1001","title":"On Using Very Large Target Vocabulary for Neural Machine Translation","year":2015,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":872,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"Samsung; Compute Canada; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Canadian Institute for Advanced Research","keywords":"Machine translation; Computer science; Vocabulary; Artificial intelligence; Natural language processing; Joint (building); Computational linguistics; Artificial neural network; Translation (biology); Volume (thermodynamics); Association (psychology); Speech recognition; Linguistics; Engineering; Philosophy","retraction":null,"screen_n_in":null,"score":{"opus":0.04490222195020935,"gpt":0.312351224200445,"spread":0.2674490022502356,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003009144,0.00009826446,0.00009530745,0.00008359999,0.00006667075,0.00008895123,0.0003628797,0.00005449229,0.000004821757],"category_scores_gemma":[0.00004668352,0.00007810148,0.0000425358,0.0001627643,0.000008827958,0.0005393845,0.00005179142,0.00009063655,0.000003200706],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003563575,"about_ca_system_score_gemma":0.00004070131,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001967514,"about_ca_topic_score_gemma":0.000004375246,"domain_scores_codex":[0.9992588,0.00002765794,0.0001176312,0.0002204535,0.0001805922,0.0001949173],"domain_scores_gemma":[0.9995514,0.0000522962,0.00003978413,0.0002237916,0.00006887094,0.0000638119],"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":[0.0004520023,0.0006738876,0.0009366718,0.0002159063,0.00006380756,0.0001087859,0.004024729,0.003331001,0.01962354,0.5028878,0.02017535,0.4475065],"study_design_scores_gemma":[0.0003517732,0.0001062611,0.000004633208,0.000009875886,0.000002786524,0.000009203241,0.000003709229,0.9377556,0.01040753,0.05042594,0.0008013216,0.0001213845],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.003085866,0.001883202,0.9931664,0.0006326591,0.0002002813,0.0001831294,0.000005076132,0.0005502271,0.0002930991],"genre_scores_gemma":[0.4302039,2.939096e-7,0.5690862,0.0006095624,0.00003321874,0.000004214639,0.00000783437,0.000006369428,0.00004843116],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9344246,"threshold_uncertainty_score":0.3184886,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1599016936","doi":"","title":"The Winograd Schema Challenge","year":2011,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":865,"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; Schema (genetic algorithms); Ambiguity; Natural language processing; Artificial intelligence; Turing test; Sentence; Turing; Information retrieval; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.03539908514315045,"gpt":0.2591166325644209,"spread":0.2237175474212704,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001735176,0.00005851503,0.00004135121,0.00002161965,0.0001346606,0.00007993176,0.001150653,0.00003098905,0.00001435584],"category_scores_gemma":[0.00002338913,0.00003102257,0.0000253844,0.0001368056,0.0000410698,0.0002779919,0.000245847,0.00009017476,0.00004521696],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007147638,"about_ca_system_score_gemma":0.00001354135,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002250542,"about_ca_topic_score_gemma":0.00001052976,"domain_scores_codex":[0.999498,0.00001523091,0.00007433612,0.000142386,0.0001137737,0.0001562542],"domain_scores_gemma":[0.999422,0.00002780818,0.00002763616,0.0004500402,0.00004104484,0.00003152341],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[7.174822e-7,0.00001098416,0.00001888168,0.000001584449,0.000002331297,0.000004603509,0.0004081299,1.159747e-9,0.00008633846,0.8029541,0.0008938831,0.1956184],"study_design_scores_gemma":[0.0001128127,0.0001210236,0.0002010722,0.00001916342,0.000002733674,0.00003076485,0.00006520528,0.00211558,0.1224453,0.8469547,0.02764857,0.0002830388],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0003116237,0.005663131,0.8934596,0.002515612,0.0001726401,0.00009853968,7.483219e-8,0.001653556,0.09612528],"genre_scores_gemma":[0.4313639,0.00003956208,0.5676408,0.0002085496,0.00002034034,0.000008100546,5.246926e-8,0.000003279812,0.0007154919],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4310522,"threshold_uncertainty_score":0.2138218,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2131462252","doi":"","title":"A Scalable Hierarchical Distributed Language Model","year":2008,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":852,"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":"Language model; Computer science; Hierarchical database model; Cache language model; Artificial intelligence; Scalability; Probabilistic logic; Simple (philosophy); Feature (linguistics); Tree (set theory); Word (group theory); Binary tree; Machine learning; Natural language processing; Data mining; Algorithm; Natural language; Universal Networking Language; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.01499336283229919,"gpt":0.2616674500190941,"spread":0.2466740871867949,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009399462,0.0001017032,0.0001111514,0.00006364752,0.0001288272,0.00005869911,0.0008267736,0.00006380476,0.00002114581],"category_scores_gemma":[0.00005747326,0.00007813959,0.00004250562,0.0003484272,0.00005998401,0.000405254,0.0003027685,0.0001836994,0.00003626447],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003076807,"about_ca_system_score_gemma":0.00007323351,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002968117,"about_ca_topic_score_gemma":0.000002868743,"domain_scores_codex":[0.9991038,0.00002050101,0.0001235669,0.000273436,0.0002266187,0.0002520653],"domain_scores_gemma":[0.9993611,0.00002976363,0.00002759423,0.0004423245,0.00004734255,0.00009190135],"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":[0.00003152676,0.0003537983,0.000411819,0.00004373866,0.00002712735,0.0008807076,0.004076434,0.0004376989,0.04543844,0.8174499,0.06547085,0.06537797],"study_design_scores_gemma":[0.0002080942,0.00003356794,0.0001053402,0.00001338716,0.000001985785,0.0002101296,0.000008366916,0.8897719,0.06411434,0.04495036,0.0003100009,0.0002725639],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01303339,0.0004297775,0.9818302,0.0007310591,0.00002488633,0.00006615239,0.000004270221,0.001557075,0.002323163],"genre_scores_gemma":[0.4765717,0.000004021551,0.5219797,0.000369285,0.00001351073,0.000005737208,0.000004781419,0.000004115197,0.001047132],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8893341,"threshold_uncertainty_score":0.318644,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W36903255","doi":"10.3390/molecules28052010","title":"Hierarchical Probabilistic Neural Network Language Model.","year":2005,"lang":"en","type":"article","venue":"International Conference on Artificial Intelligence and Statistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":840,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"National Center for Advancing Translational Sciences","keywords":"Computer science; Language model; Artificial intelligence; Cluster analysis; Hierarchy; Probabilistic logic; Embedding; Generalization; Artificial neural network; Hierarchical clustering; Hierarchical database model; Natural language processing; Machine learning; Data mining; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.07106443107823439,"gpt":0.3506428053863268,"spread":0.2795783743080924,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002561734,0.0001702437,0.0001437936,0.00009275549,0.0001220186,0.0004133669,0.0007762907,0.00007063059,0.00008577844],"category_scores_gemma":[0.0003276776,0.0001515867,0.00002727343,0.0001294421,0.0001494441,0.0003038131,0.0001935557,0.0003054032,0.00005013861],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004906621,"about_ca_system_score_gemma":0.00007451949,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001546147,"about_ca_topic_score_gemma":0.00007974545,"domain_scores_codex":[0.9985691,0.00005645359,0.000338266,0.0003912126,0.0003744176,0.0002706054],"domain_scores_gemma":[0.999113,0.0002232715,0.00009530086,0.0002409107,0.0002216286,0.0001059381],"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":[0.0000195226,0.0000332528,0.00000324385,0.000003242405,0.000004545173,0.00001300692,0.0003550909,0.004484291,0.0002216198,0.6719996,0.0002502573,0.3226123],"study_design_scores_gemma":[0.00001009314,0.00004683587,0.000003926795,0.00001792441,0.00000206748,0.00001024104,0.00002191214,0.5661093,0.0006826984,0.4329358,0.00005430263,0.0001048931],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0009547558,0.0001058799,0.9921883,0.004080359,0.0002297512,0.0001225794,0.00004532927,0.0001983894,0.002074638],"genre_scores_gemma":[0.5620671,0.00002536646,0.4369541,0.000606036,0.0001609528,0.00001046988,0.00001293683,0.000005913506,0.0001570732],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.561625,"threshold_uncertainty_score":0.6181528,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2050712820","doi":"10.1145/775047.775138","title":"Discovering word senses from text","year":2002,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":597,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Word (group theory); Computer science; Cluster analysis; Precision and recall; Set (abstract data type); Similarity (geometry); Centroid; Artificial intelligence; Natural language processing; Feature (linguistics); Feature vector; Element (criminal law); Space (punctuation); Cluster (spacecraft); Domain (mathematical analysis); Recall; Information retrieval; Mathematics; Linguistics; Image (mathematics)","retraction":null,"screen_n_in":null,"score":{"opus":0.01633319923786609,"gpt":0.2386434594540469,"spread":0.2223102602161808,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00003268549,0.00007709526,0.00007211565,0.00003867755,0.00005049497,0.000212412,0.0005379531,0.00003228089,0.0002037743],"category_scores_gemma":[0.00002854806,0.00005841106,0.00002609644,0.0001744265,0.0000163987,0.0005640503,0.0002338457,0.00008485845,0.0001304213],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001791556,"about_ca_system_score_gemma":0.000003317144,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001388103,"about_ca_topic_score_gemma":0.00001409987,"domain_scores_codex":[0.9994053,0.00001217516,0.00008532764,0.0002223773,0.0001319077,0.0001429158],"domain_scores_gemma":[0.9995236,0.00005168991,0.00002691197,0.0003448596,0.00001656896,0.00003636378],"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":[0.00000136366,0.00004655933,0.0004181805,0.000007084052,0.0000103747,0.00008254681,0.001491535,0.000003523915,0.01386092,0.05488569,0.01291042,0.9162818],"study_design_scores_gemma":[0.0005045414,0.00008976293,0.001091932,0.0002307919,0.00001275967,0.00007035657,0.000129091,0.1866325,0.553677,0.230154,0.02601708,0.00139016],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01982188,0.00260279,0.9652413,0.001358657,0.0001408841,0.00005190093,0.000001184718,0.001544218,0.009237207],"genre_scores_gemma":[0.5288298,0.00001006614,0.4694398,0.0003201117,0.00003631744,0.000001645298,3.067987e-7,0.00000339955,0.001358555],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9148917,"threshold_uncertainty_score":0.2381934,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2587922133","doi":"10.1111/lang.12224","title":"Corpus Use in Language Learning: A Meta‐Analysis","year":2017,"lang":"en","type":"article","venue":"Language Learning","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":551,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Moderation; Meta-analysis; Open data; Computer science; Transfer of learning; Psychology; Sample (material); Language acquisition; Natural language processing; Open science; Applied linguistics; Artificial intelligence; Mathematics education; Linguistics; World Wide Web; Statistics; Machine learning; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.03466804115790036,"gpt":0.3161270575087146,"spread":0.2814590163508142,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0008850438,0.0003004493,0.0007112813,0.0005609647,0.0005336333,0.001569268,0.002052836,0.0001657491,0.000120504],"category_scores_gemma":[0.001566504,0.0002591445,0.0004604071,0.0007176092,0.00008191934,0.001615062,0.0008471799,0.001191529,0.0000490718],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005935782,"about_ca_system_score_gemma":0.00003723782,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003942552,"about_ca_topic_score_gemma":0.001298943,"domain_scores_codex":[0.9976377,0.0003484883,0.0003183866,0.0007171766,0.0004240384,0.0005542273],"domain_scores_gemma":[0.9977091,0.0002655052,0.0004637068,0.00137088,0.00007260648,0.0001181943],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000145245,0.0005913526,0.4028109,0.0004046298,0.04949768,0.02050996,0.1634732,0.0114455,0.07252848,0.03798174,0.0003230979,0.2402882],"study_design_scores_gemma":[0.007864079,0.00154477,0.1360241,0.0005822751,0.08681747,0.0007374294,0.01454086,0.5426634,0.1694984,0.008386542,0.01824676,0.01309389],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5496895,0.04164888,0.3966202,0.001649047,0.0002933709,0.0006475802,0.000006578797,0.004694042,0.004750804],"genre_scores_gemma":[0.8885536,0.00002213069,0.1048189,0.0002014947,0.00005312344,0.00002881642,0.00001254646,0.00002879394,0.006280566],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5312179,"threshold_uncertainty_score":0.9999861,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1965605789","doi":"10.1145/502512.502559","title":"DIRT @SBT@discovery of inference rules from text","year":2001,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":548,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Dirt; Computer science; Inference; Rule of inference; Artificial intelligence; Natural language processing; Information retrieval; Data science; Data mining; Cartography; Geography","retraction":null,"screen_n_in":null,"score":{"opus":0.01437500932298097,"gpt":0.2750401360449637,"spread":0.2606651267219827,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008121906,0.00009444715,0.0001321875,0.00006758238,0.00003020502,0.0001351588,0.0009803461,0.00005471601,0.00005208846],"category_scores_gemma":[0.00008288487,0.0000704617,0.00003783825,0.0002279086,0.00004429954,0.001023898,0.000338414,0.00009249852,0.0000315627],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001591294,"about_ca_system_score_gemma":0.00004240263,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005356756,"about_ca_topic_score_gemma":0.00002848293,"domain_scores_codex":[0.9992299,0.00002056037,0.0001668307,0.0002390377,0.000198949,0.000144692],"domain_scores_gemma":[0.9992421,0.0001244514,0.00007580617,0.0004612466,0.00006542695,0.00003094587],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0000149025,0.0001431103,0.01043038,0.00002261173,0.00002208488,0.00005429449,0.0007716984,0.000003028956,0.06457179,0.563752,0.002337176,0.3578769],"study_design_scores_gemma":[0.0002458702,0.00009409985,0.006446393,0.0001735547,0.000008025487,0.0000140309,0.0000379318,0.005794596,0.4321314,0.5524917,0.002114183,0.0004481857],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08552904,0.00125407,0.9064966,0.0003438683,0.00007456814,0.00005193636,0.000003889298,0.0004395273,0.005806473],"genre_scores_gemma":[0.5993041,0.00003185736,0.3998868,0.0001653774,0.00002083788,0.00000224813,0.000002075191,0.00000291906,0.0005837219],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5137751,"threshold_uncertainty_score":0.2873345,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W12836875","doi":"10.63317/3gh6v2hd4z55","title":"From TreeBank to PropBank","year":2002,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":539,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Treebank; Computer science; Natural language processing; Artificial intelligence; Annotation","retraction":null,"screen_n_in":null,"score":{"opus":0.01830638065933082,"gpt":0.252359065373384,"spread":0.2340526847140532,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00004608088,0.0000748735,0.00007184947,0.00006094387,0.00003800277,0.0001443996,0.0008420051,0.0000352701,0.0003347463],"category_scores_gemma":[0.00003636618,0.00005581471,0.0000219004,0.0002935355,0.000008544813,0.0003089491,0.0002183783,0.00007055077,0.000506819],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001908372,"about_ca_system_score_gemma":0.00000449541,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001177825,"about_ca_topic_score_gemma":0.000008437272,"domain_scores_codex":[0.9993243,0.00001299381,0.00008843723,0.000263634,0.000156834,0.0001537853],"domain_scores_gemma":[0.9994261,0.0000235012,0.00001829841,0.0004270843,0.00003365432,0.00007135772],"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":[0.00000128221,0.00005454522,0.00007969006,0.000003540722,0.000005948421,0.00003916878,0.001524946,5.679886e-7,0.01075057,0.05569002,0.1391087,0.792741],"study_design_scores_gemma":[0.000428259,0.0002970563,0.0002574537,0.00008945122,0.000008293186,0.00002966535,0.00003195681,0.0572231,0.5710167,0.2723257,0.09720721,0.001085224],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00199305,0.0007429907,0.9759196,0.006577743,0.00011257,0.0001152528,9.491295e-7,0.001611777,0.01292608],"genre_scores_gemma":[0.2355396,0.000001449368,0.7590678,0.001708084,0.00006891946,0.000009366921,3.599123e-7,0.00000415253,0.003600251],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7916558,"threshold_uncertainty_score":0.6514302,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2099779943","doi":"10.3115/1621969.1621986","title":"SemEval-2010 task 8","year":2009,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":497,"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":"SemEval; Computer science; Task (project management); Testbed; Natural language processing; Artificial intelligence; Information extraction; Natural language; Semantics (computer science); Information retrieval; World Wide Web; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.009039731999430325,"gpt":0.2638369322279143,"spread":0.254797200228484,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001052907,0.00006362142,0.00005844257,0.00005114825,0.00004235767,0.0001151668,0.0007103434,0.00003871255,0.00002177332],"category_scores_gemma":[0.00002442291,0.0000470227,0.00002390885,0.0002119754,0.000009152843,0.0003918764,0.00007457638,0.00008945302,0.00006085324],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001305159,"about_ca_system_score_gemma":0.00001790849,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007648766,"about_ca_topic_score_gemma":0.000001185995,"domain_scores_codex":[0.999451,0.00001070894,0.00007708192,0.0001801212,0.0001369127,0.0001441248],"domain_scores_gemma":[0.9995379,0.00001226652,0.00002326388,0.0003465161,0.00003926038,0.00004076202],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000001110643,0.00003100212,0.00002249859,0.00000257293,0.000001779279,0.00002192076,0.000151704,3.49426e-7,0.03758967,0.5105587,0.02917468,0.422444],"study_design_scores_gemma":[0.0001515283,0.0001542699,0.0006047761,0.00002009085,0.000002514306,0.00005357451,0.000004058018,0.007235683,0.2722572,0.7082964,0.01088302,0.0003369435],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0005203325,0.0006059337,0.9795578,0.005277003,0.0001090401,0.0000510446,1.336482e-7,0.001639521,0.01223924],"genre_scores_gemma":[0.3596422,0.000002570979,0.6357693,0.002504512,0.00002752722,9.001047e-7,2.933348e-7,0.000001601892,0.002051034],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.422107,"threshold_uncertainty_score":0.191753,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1578310937","doi":"10.1007/978-3-319-10106-4_7","title":"Indeterminate Pronouns: The View from Japanese","year":2017,"lang":"en","type":"book-chapter","venue":"Studies in natural language and linguistic theory","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":443,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"","keywords":"Indeterminate; Linguistics; Philosophy; Mathematics; Pure mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.01968714651575379,"gpt":0.3135701793963078,"spread":0.2938830328805541,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008538156,0.0005253067,0.0006948052,0.0001443026,0.0003971448,0.0002431684,0.00196157,0.0002709657,0.00001632594],"category_scores_gemma":[0.002389422,0.000315683,0.0001114,0.00003271993,0.0007979298,0.0001443693,0.001521577,0.001275986,0.00001461632],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009085343,"about_ca_system_score_gemma":0.00005725449,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001061572,"about_ca_topic_score_gemma":0.0001528012,"domain_scores_codex":[0.9980901,0.0001028311,0.0004093282,0.0007422531,0.0003055396,0.0003499223],"domain_scores_gemma":[0.9969141,0.001127738,0.0004327204,0.001297769,0.0001782083,0.00004946573],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00004277368,0.00001110903,0.00000308059,0.0003171487,0.000244807,0.001755403,0.05796996,5.149895e-8,0.00002022319,0.5764067,0.0003030024,0.3629257],"study_design_scores_gemma":[0.0002698892,0.00005555631,0.00001084946,0.002685378,0.0001095634,0.00006415287,0.000863805,0.00007298747,0.00007009767,0.9766012,0.01846987,0.0007266747],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"review","genre_gemma":"empirical","genre_scores_codex":[0.0001747705,0.9187628,0.000190846,0.0002470957,0.00223325,0.000601258,0.0000367281,0.0003520089,0.07740124],"genre_scores_gemma":[0.6160799,0.01028278,0.02428592,0.001644816,0.002873855,0.0001109356,0.00005235503,0.0001364042,0.344533],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.90848,"threshold_uncertainty_score":0.9999295,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2760656271","doi":"10.18653/v1/w17-4717","title":"Findings of the 2017 Conference on Machine Translation (WMT17)","year":2017,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":418,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"National Research Council Canada","funders":"European Regional Development Fund; Horizon 2020 Framework Programme; Agence Nationale de la Recherche; Univerzita Karlova v Praze; Trinity College Dublin; Science Foundation Ireland; European Commission","keywords":"Chatterjee; Translation (biology); Machine translation; Art history; Computer science; Art; Artificial intelligence; Chemistry","retraction":null,"screen_n_in":null,"score":{"opus":0.04852302411475251,"gpt":0.3154419876781849,"spread":0.2669189635634324,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001451404,0.00006154881,0.00007040248,0.0000255604,0.0001961858,0.000160395,0.001839297,0.00003873383,0.00001481289],"category_scores_gemma":[0.00005085353,0.00003495659,0.00003515734,0.00003739425,0.00006562444,0.0003486628,0.0001487665,0.0001038001,0.000006023738],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007294685,"about_ca_system_score_gemma":0.00002371422,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008447003,"about_ca_topic_score_gemma":0.00003064871,"domain_scores_codex":[0.9995026,0.00001561878,0.00008804585,0.000141283,0.0001697774,0.00008265098],"domain_scores_gemma":[0.9990057,0.00002197508,0.0001043138,0.0008046312,0.00004724625,0.00001614347],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000009460018,0.00003839729,0.001445181,0.00002563986,0.000006820905,0.000002840708,0.000542671,0.000001208979,0.02692666,0.7880321,0.00129954,0.1816695],"study_design_scores_gemma":[0.0003501592,0.0001019751,0.01201495,0.0001862667,0.000006773444,0.000009808615,0.000004233476,0.04127519,0.7868212,0.158303,0.0006877053,0.0002387044],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01410153,0.0005041358,0.8933514,0.01844274,0.0004201995,0.0003279076,0.000005629639,0.0004076781,0.07243881],"genre_scores_gemma":[0.8947958,0.000004713389,0.1044589,0.0001310707,0.000008117763,0.000001319378,2.453815e-7,0.000002108535,0.0005977398],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8806943,"threshold_uncertainty_score":0.3417901,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2531207078","doi":"10.1162/tacl_a_00067","title":"Fully Character-Level Neural Machine Translation without Explicit Segmentation","year":2017,"lang":"en","type":"article","venue":"Transactions of the Association for Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":415,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"York University; Samsung Advanced Institute of Technology; Samsung; Nvidia","keywords":"Computer science; Machine translation; Character (mathematics); Pooling; Encoder; Convolutional neural network; Artificial intelligence; Translation (biology); Natural language processing; Segmentation; Speech recognition; Task (project management); Language model; Representation (politics)","retraction":null,"screen_n_in":null,"score":{"opus":0.0388812594394734,"gpt":0.3152326302466266,"spread":0.2763513708071532,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003798039,0.0001332793,0.0001696082,0.00008567418,0.0008613162,0.0002327641,0.0008889502,0.00009183127,0.000003070911],"category_scores_gemma":[0.0007420413,0.0001172917,0.0001633846,0.0001143636,0.0000315823,0.0002992472,0.00002469526,0.000164508,0.000001709637],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001537786,"about_ca_system_score_gemma":0.00008464771,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000481871,"about_ca_topic_score_gemma":0.00002834939,"domain_scores_codex":[0.9987463,0.00005020835,0.0003708081,0.0002148792,0.0004579178,0.0001599182],"domain_scores_gemma":[0.997462,0.0003114766,0.0008655998,0.0003826049,0.0009440435,0.00003427954],"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":[0.0003536101,0.0011929,0.03445466,0.000664079,0.0009492958,0.000002528283,0.005456393,0.1344965,0.008753503,0.4301081,0.0009444132,0.3826241],"study_design_scores_gemma":[0.001111703,0.00008624076,0.01301074,0.00005492312,0.0001120921,0.000003446885,0.00001172158,0.9091198,0.007931241,0.06725673,0.001023117,0.0002782338],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0007539887,0.00009202367,0.9957358,0.001437056,0.001019021,0.0004084456,0.0002174468,0.0001360117,0.0002001537],"genre_scores_gemma":[0.664817,0.000002060736,0.3346779,0.0000673311,0.000100672,0.00002390619,0.0000346947,0.000009692662,0.0002666587],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7746233,"threshold_uncertainty_score":0.6624635,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2144746247","doi":"10.3115/1220355.1220401","title":"Confidence estimation for machine translation","year":2004,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":356,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"","keywords":"NIST; Correctness; Computer science; Machine translation; Natural language processing; Context (archaeology); Artificial intelligence; Translation (biology); Estimation; Evaluation of machine translation; Machine learning; Machine translation software usability; Example-based machine translation; Algorithm; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.01942382530659272,"gpt":0.3005074643097555,"spread":0.2810836390031628,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001088459,0.00004734179,0.00004443393,0.00003966638,0.00004887105,0.00007367315,0.0002610029,0.00002811971,0.000003174646],"category_scores_gemma":[0.00003234535,0.00003861675,0.00001976829,0.0001127597,0.000009716458,0.0005251555,0.00001419942,0.00003392669,0.000004739137],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002103739,"about_ca_system_score_gemma":0.00002639485,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004018379,"about_ca_topic_score_gemma":0.00001226277,"domain_scores_codex":[0.9996167,0.000004251599,0.00008347784,0.0001319026,0.0000845628,0.00007914317],"domain_scores_gemma":[0.9997387,0.0000339834,0.00002811622,0.000136503,0.00004400426,0.00001869881],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000001836597,0.000007591484,0.000001170333,0.00001048995,9.221537e-7,5.066653e-7,0.0001605052,0.0001616137,0.002457157,0.798916,0.00002697849,0.1982552],"study_design_scores_gemma":[0.0001744166,0.00003357645,0.000005801171,0.00001345969,0.00000134404,0.000006256897,0.000001006504,0.2103886,0.09415485,0.6950628,0.00009570091,0.00006216524],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00005899476,0.0006438774,0.9957084,0.002525911,0.00004156565,0.0001637337,6.871999e-7,0.0005931266,0.0002637129],"genre_scores_gemma":[0.4004314,0.000001075871,0.5993389,0.0001832736,0.000005900533,0.00001052829,0.000002366452,0.00000174569,0.00002474741],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4003724,"threshold_uncertainty_score":0.1574745,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2148437670","doi":"10.18653/v1/2023.acl-long","title":"Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","year":2023,"lang":"en","type":"paratext","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":354,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"Yuhan; Atomic Energy of Canada Limited; Strong; Styrelsen för Internationellt Utvecklingssamarbete","keywords":"Volume (thermodynamics); Computational linguistics; Association (psychology); Computer science; Linguistics; Natural language processing; Philosophy; Epistemology","retraction":null,"screen_n_in":null,"score":{"opus":0.01096066040400236,"gpt":0.2699824330741872,"spread":0.2590217726701849,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007303326,0.0001913809,0.0003044287,0.00008630037,0.0001891444,0.0001125242,0.001889502,0.0002870024,0.000009186173],"category_scores_gemma":[0.0029507,0.000115906,0.0002128907,0.0006890836,0.00006763871,0.0000813027,0.0007329703,0.0003446199,0.00001278889],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001656554,"about_ca_system_score_gemma":0.0002672306,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005110051,"about_ca_topic_score_gemma":0.00001384669,"domain_scores_codex":[0.9981801,0.00002729879,0.000483845,0.0003268025,0.000751697,0.0002302488],"domain_scores_gemma":[0.9956694,0.0004438933,0.001314693,0.0002074385,0.002343127,0.00002147887],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000009519425,0.00006146227,0.001582427,0.001339548,0.0001517624,2.527509e-7,0.001545864,0.0008251703,0.000529907,0.07284971,0.9186236,0.002480763],"study_design_scores_gemma":[0.002425271,0.0006829486,0.01146282,0.01212787,0.0007813218,0.00002110138,0.00119542,0.2013385,0.1325015,0.1692623,0.4642087,0.003992282],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"methods","genre_scores_codex":[0.001946059,0.005152086,0.253383,0.009157829,0.03320071,0.009987177,0.002901061,0.002659348,0.6816127],"genre_scores_gemma":[0.1711531,0.00003015482,0.4383975,0.0007497545,0.001559808,0.0001214432,0.00006970502,0.0001169811,0.3878015],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.4544149,"threshold_uncertainty_score":0.4726509,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2124474181","doi":"10.1016/j.system.2004.04.001","title":"Can learners use concordance feedback for writing errors?","year":2004,"lang":"en","type":"article","venue":"System","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":346,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Concordance; Notice; Sentence; Computer science; Natural language processing; Linguistics; Mathematics education; Psychology","retraction":null,"screen_n_in":null,"score":{"opus":0.02152784306383158,"gpt":0.2726472343495525,"spread":0.2511193912857209,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002631524,0.0001199555,0.0001578482,0.00005842081,0.0001365531,0.0002583991,0.0006380799,0.000063435,3.062579e-7],"category_scores_gemma":[0.00008717139,0.0001070551,0.00005727898,0.000229451,0.00002924998,0.0004557336,0.0001051078,0.00011055,0.000008791792],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002267182,"about_ca_system_score_gemma":0.00009640862,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002676452,"about_ca_topic_score_gemma":0.00005210189,"domain_scores_codex":[0.9989905,0.00002764716,0.0002110789,0.0003233506,0.0001684943,0.0002788783],"domain_scores_gemma":[0.9992515,0.00006413138,0.0001281813,0.0003801041,0.0001120127,0.00006407275],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001292582,0.00002310827,0.0006335253,0.0007706638,0.00002303644,0.00007842433,0.002440429,0.000171908,0.007139851,0.9683811,0.000667072,0.01965798],"study_design_scores_gemma":[0.01183144,0.001781079,0.001469238,0.01628181,0.0001300718,0.00245297,0.01201887,0.07567305,0.6795905,0.1719716,0.01993692,0.006862485],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0348651,0.0007235837,0.960386,0.001137814,0.0003736037,0.0004575502,0.000007432981,0.001717134,0.0003317354],"genre_scores_gemma":[0.6370535,5.984612e-7,0.3625846,0.0001328998,0.00005725735,0.00003040412,0.000001346977,0.000009778269,0.0001296316],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7964095,"threshold_uncertainty_score":0.4365582,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2159755860","doi":"","title":"Batch Tuning Strategies for Statistical Machine Translation","year":2012,"lang":"en","type":"article","venue":"NPARC","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":338,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"National Research Council Canada","funders":"Johns Hopkins University","keywords":"Computer science; Machine translation; Machine learning; Feature (linguistics); Artificial intelligence; Variety (cybernetics); Support vector machine; Translation (biology); Simple (philosophy); Sentence; Data mining","retraction":null,"screen_n_in":null,"score":{"opus":0.02839738380637398,"gpt":0.3112397182538902,"spread":0.2828423344475162,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002268787,0.00006764475,0.00007267568,0.00003755415,0.00006788864,0.0001108381,0.0002570978,0.00003892442,0.00003023377],"category_scores_gemma":[0.00002869063,0.00005715702,0.00001890774,0.00009119035,0.00001928016,0.0007610732,0.00002950597,0.0000816062,0.000004074841],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002063042,"about_ca_system_score_gemma":0.00002879142,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007364206,"about_ca_topic_score_gemma":0.000004900045,"domain_scores_codex":[0.999437,0.00002201036,0.00009607559,0.0001174672,0.0001180682,0.0002093506],"domain_scores_gemma":[0.9996212,0.0001272798,0.00002847975,0.0001386783,0.00003303124,0.00005134638],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000003658226,0.00001345412,0.00006438707,0.00001962563,0.000002272177,5.644524e-7,0.0004639021,3.759114e-7,0.007006436,0.6991587,0.0005720076,0.2926946],"study_design_scores_gemma":[0.0002025691,0.00006673827,0.0001121552,0.00001956291,0.000008087804,0.00001222892,0.00005142514,0.2005158,0.01017001,0.7862135,0.002432074,0.000195903],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0002033625,0.0006531744,0.9948072,0.0006903452,0.00009178645,0.0001047739,0.000009230253,0.000327194,0.003112932],"genre_scores_gemma":[0.4839375,8.329714e-7,0.515929,0.00005473134,0.00003762374,0.00001039236,0.000007446178,0.00000345445,0.00001903889],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4837342,"threshold_uncertainty_score":0.2330796,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2888541716","doi":"10.18653/v1/d18-1398","title":"Meta-Learning for Low-Resource Neural Machine Translation","year":2018,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":319,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Tencent; Samsung Advanced Institute of Technology; Canadian Institute for Advanced Research; Samsung; Nvidia","keywords":"Computer science; Machine translation; Artificial intelligence; Romanian; Natural language processing; Transfer of learning; Representation (politics); BLEU; Translation (biology); Resource (disambiguation); Machine learning; Frame (networking); Linguistics","retraction":null,"screen_n_in":null,"score":{"opus":0.03958221554592636,"gpt":0.2951378261314581,"spread":0.2555556105855317,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002608344,0.00009654289,0.0001251176,0.00006599577,0.0001434245,0.0001260526,0.0004792586,0.00004356469,0.00004384087],"category_scores_gemma":[0.00003773248,0.00006807264,0.00009069624,0.0001899614,0.0000303344,0.0003745814,0.0000593789,0.000102363,0.000007661855],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000008745717,"about_ca_system_score_gemma":0.000009146138,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001434867,"about_ca_topic_score_gemma":0.00001065211,"domain_scores_codex":[0.999295,0.00003732439,0.0001272862,0.0002392583,0.0001307893,0.0001703265],"domain_scores_gemma":[0.999546,0.00009254467,0.00005170565,0.0001996106,0.00007393125,0.00003624024],"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":[0.00002479167,0.00003045075,0.00003408533,0.00003990811,0.0001283596,0.000002736883,0.001165759,0.00004271081,0.01062027,0.02191309,0.001316547,0.9646813],"study_design_scores_gemma":[0.0001719902,0.0001661412,0.000007223409,0.000005083944,0.00006502985,0.000009069543,0.000004605351,0.9066583,0.07205158,0.006985784,0.01371199,0.0001631986],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0003464139,0.001958863,0.9939473,0.00152307,0.00004973244,0.0001487503,5.217443e-7,0.0009695186,0.001055838],"genre_scores_gemma":[0.4727885,4.639161e-7,0.5260844,0.0004638508,0.00006163114,0.00001386993,0.000002753548,0.000006261732,0.0005781632],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9645181,"threshold_uncertainty_score":0.2775922,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4389524555","doi":"10.18653/v1/2023.findings-emnlp.936","title":"RWKV: Reinventing RNNs for the Transformer Era","year":2023,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":303,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Nexen (Canada)","funders":"","keywords":"STELLA (programming language); Zhàng; Art history; Art; Humanities; Philosophy; History; Archaeology; China","retraction":null,"screen_n_in":null,"score":{"opus":0.02679878535284542,"gpt":0.3004265835493182,"spread":0.2736277981964728,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003865724,0.00006301687,0.000057041,0.00005238284,0.0001933111,0.0001480204,0.0007682479,0.00003141811,0.00001043219],"category_scores_gemma":[0.00005316527,0.00003604138,0.00006232879,0.0004346599,0.00001819229,0.0002688222,0.00005949276,0.00008984191,0.00002977082],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009299291,"about_ca_system_score_gemma":0.00002352853,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001950567,"about_ca_topic_score_gemma":0.000009972127,"domain_scores_codex":[0.9993843,0.000008580043,0.0001018886,0.0001695477,0.0001229772,0.0002126737],"domain_scores_gemma":[0.9994667,0.0001881469,0.00002367079,0.0002590623,0.00004116369,0.00002121202],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000002728708,0.000007361452,0.00002383685,0.00003435545,0.00001395158,0.000004225815,0.0008644841,0.000007545924,0.006278533,0.4668215,0.03426101,0.4916805],"study_design_scores_gemma":[0.0003342546,0.00007958911,0.0001635401,0.00005595736,0.00001567298,0.00001696118,0.0001287328,0.288977,0.2589588,0.3663395,0.08454563,0.0003842957],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0002585563,0.0003456159,0.9820135,0.01404413,0.0001578725,0.000209545,7.535662e-7,0.001551628,0.001418386],"genre_scores_gemma":[0.2705243,0.00002963119,0.720431,0.002133431,0.0001268501,0.0001233256,0.000002926793,0.00001552424,0.006612971],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4912962,"threshold_uncertainty_score":0.1486813,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2051593977","doi":"10.1162/coli_a_00002","title":"Generating Phrasal and Sentential Paraphrases: A Survey of Data-Driven Methods","year":2010,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":302,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Atomic Energy of Canada Limited; National Science Foundation","keywords":"Paraphrase; Computer science; Natural language processing; Task (project management); Artificial intelligence; Parallel corpora; Field (mathematics); Linguistics; Machine translation","retraction":null,"screen_n_in":null,"score":{"opus":0.06410955906269462,"gpt":0.401568733933962,"spread":0.3374591748712674,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009106915,0.0001117199,0.0001713811,0.00008992578,0.000100893,0.0001286425,0.0008560031,0.00006489684,0.000003132662],"category_scores_gemma":[0.005156851,0.0001068044,0.00001775721,0.0002381548,0.0001128469,0.0001109758,0.00068984,0.000231343,9.01996e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005324181,"about_ca_system_score_gemma":0.0001478878,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001245521,"about_ca_topic_score_gemma":0.00004658329,"domain_scores_codex":[0.9988407,0.0001435012,0.0002994914,0.00035194,0.0002324453,0.0001319322],"domain_scores_gemma":[0.9975768,0.0009368802,0.0001897044,0.0004174549,0.0008149914,0.00006417209],"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":[0.00004246154,0.0003656923,0.02046316,0.0002783426,0.0001873026,0.0000777918,0.001038516,0.0102211,0.02072168,0.6539841,0.002883636,0.2897362],"study_design_scores_gemma":[0.0001219476,0.00002117768,0.002478539,0.00001437184,0.000009153549,0.00001527037,0.000002057794,0.9685342,0.0007929353,0.02763526,0.0002445883,0.0001305059],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.008246019,0.0003009305,0.9905028,0.00002681942,0.0005927841,0.00007031312,0.00008251968,0.0001313574,0.00004646146],"genre_scores_gemma":[0.377103,0.000001573377,0.6225455,0.00005735033,0.0001508638,0.000001034156,0.0001318797,0.000005648833,0.000003121746],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9583131,"threshold_uncertainty_score":0.6173605,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1485211753","doi":"","title":"Continuum companion to systemic functional linguistics","year":2009,"lang":"en","type":"book","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":281,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Context (archaeology); Index (typography); Sociology; Applied linguistics; Library science; Linguistics; Art history; History; Philosophy; Archaeology; Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.01478926830740126,"gpt":0.2523402590825736,"spread":0.2375509907751723,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002167371,0.0002983437,0.0003696539,0.0002508315,0.00008069279,0.0002716672,0.001202099,0.0003128423,0.00002814175],"category_scores_gemma":[0.0002384806,0.0002607589,0.00009338539,0.0001451807,0.0000197311,0.00006483967,0.0003283706,0.0004330937,0.000283196],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003058959,"about_ca_system_score_gemma":0.0003567678,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005563939,"about_ca_topic_score_gemma":0.000006869184,"domain_scores_codex":[0.9983438,0.000025656,0.0003431815,0.0005543947,0.0004753342,0.000257604],"domain_scores_gemma":[0.998342,0.00008623574,0.0001778928,0.0006558283,0.0006093584,0.0001287085],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000001802867,0.000008014074,0.000001100544,0.00004402314,0.000007397984,0.00001720877,0.00002494313,0.000001645969,0.0000550591,0.3363411,0.6577713,0.005726357],"study_design_scores_gemma":[0.0001373108,0.0001409035,0.00001227638,0.001126438,0.00002324165,0.0001013033,0.000001581656,0.0007679716,0.0007359025,0.2105544,0.7856141,0.0007845263],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"other","genre_scores_codex":[3.16459e-7,0.001628805,0.6396964,0.0001304608,0.000879707,0.0002454085,0.000002966519,0.001502483,0.3559134],"genre_scores_gemma":[0.0005705375,0.000005310916,0.3744993,0.00142315,0.001018552,0.000007038028,0.0000317083,0.00001813059,0.6224263],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.2665128,"threshold_uncertainty_score":0.9999844,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1978620866","doi":"10.1162/coli.2008.34.2.145","title":"Semantic Role Labeling: An Introduction to the Special Issue","year":2008,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":278,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Canada Research Chairs; Artificial Intelligence in Medicine (Canada); University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Task (project management); Field (mathematics); Computational linguistics; Identification (biology); Computational model; Semantic role labeling; Artificial intelligence; Natural language processing; Data science; Key (lock); Semantics (computer science)","retraction":null,"screen_n_in":null,"score":{"opus":0.01392567728635698,"gpt":0.2788210233112759,"spread":0.2648953460249189,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000217046,0.0001162558,0.0001043644,0.00009589627,0.0003822539,0.0001290599,0.0007736772,0.00004403409,0.0000186028],"category_scores_gemma":[0.001354275,0.00009377892,0.00002753405,0.0004030199,0.00005003763,0.00008391099,0.0001822402,0.0001779516,0.0001157377],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004534355,"about_ca_system_score_gemma":0.0001056922,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001175942,"about_ca_topic_score_gemma":0.000005355355,"domain_scores_codex":[0.9988614,0.00004927093,0.0002040722,0.0003334077,0.0003739664,0.0001778591],"domain_scores_gemma":[0.9987004,0.00009517739,0.0000714055,0.0003493384,0.0007008999,0.00008276167],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001744407,0.0001612763,0.0002049295,0.00001815752,0.00001884791,0.00006771398,0.004287712,0.0540949,0.0001543782,0.7577237,0.1502345,0.03301639],"study_design_scores_gemma":[0.0001275605,0.0001353811,0.0003566821,0.00001222349,0.000008932961,0.0001145883,0.00002793166,0.2639326,0.001069882,0.209212,0.5247016,0.0003005831],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001207295,0.0002320233,0.9876962,0.006540583,0.002707141,0.0001888848,0.000004820558,0.0005171378,0.0009058755],"genre_scores_gemma":[0.2151729,0.000002049423,0.7504694,0.0009916762,0.0330867,0.000005657058,0.00002452695,0.00001116526,0.0002358862],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.5485117,"threshold_uncertainty_score":0.3824193,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3173162544","doi":"10.1145/3567592","title":"Neural Machine Translation for Low-resource Languages: A Survey","year":2022,"lang":"en","type":"review","venue":"ACM Computing Surveys","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":278,"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; Machine translation; Unavailability; Resource (disambiguation); Artificial intelligence; Natural language processing","retraction":null,"screen_n_in":null,"score":{"opus":0.09391014352774846,"gpt":0.3746552444027698,"spread":0.2807451008750214,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.009079289,0.0006676304,0.001532938,0.0004150122,0.0004503708,0.000412862,0.005309627,0.0002907999,0.00002187054],"category_scores_gemma":[0.002078848,0.0005964916,0.0005676834,0.001405233,0.00004598407,0.0002383821,0.001536014,0.000983247,0.000007866812],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001699839,"about_ca_system_score_gemma":0.0002259053,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003472169,"about_ca_topic_score_gemma":0.00009373528,"domain_scores_codex":[0.9921834,0.004539927,0.0009117185,0.001171801,0.0005325669,0.0006605163],"domain_scores_gemma":[0.9890943,0.008100435,0.0007522775,0.001841498,0.00009956503,0.0001119626],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000001825334,0.00003339578,0.00001031482,0.003031077,0.00004519512,0.00001882618,0.0001335958,0.00001054597,2.018697e-7,0.00008836402,0.0005014504,0.9961252],"study_design_scores_gemma":[0.000398255,0.0001750856,0.00003149774,0.002684197,0.0001429488,0.0001477064,0.000006162114,0.05309488,0.000004822395,0.0005150721,0.9412574,0.001541976],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[9.269289e-7,0.6071834,0.3907529,0.00002590771,0.0002640135,0.0007147845,0.0001300449,0.0008966812,0.00003128318],"genre_scores_gemma":[0.0003249538,0.5760865,0.4179554,0.0002718962,0.0004283961,0.0001762963,0.004317847,0.0002544103,0.0001843123],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9945832,"threshold_uncertainty_score":0.9996486,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4400531953","doi":"10.1145/3626772.3657878","title":"C-Pack: Packed Resources For General Chinese Embeddings","year":2024,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":269,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"","keywords":"Packed bed; Computer science; Chemistry; Chromatography","retraction":null,"screen_n_in":null,"score":{"opus":0.007724179664062534,"gpt":0.297602640136452,"spread":0.2898784604723895,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002251937,0.0001281877,0.0001106323,0.0001254015,0.00007795122,0.0006240162,0.0007127778,0.00006180863,0.00002108893],"category_scores_gemma":[0.00007262756,0.00008366622,0.00008349432,0.0004120074,0.00002587971,0.0005417261,0.0001978903,0.0001061548,0.00002149176],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002718072,"about_ca_system_score_gemma":0.00003001707,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002130343,"about_ca_topic_score_gemma":0.000005397879,"domain_scores_codex":[0.9991017,0.00001276763,0.0001323375,0.0003701969,0.0001563766,0.0002266498],"domain_scores_gemma":[0.9994806,0.0000959825,0.00002150878,0.0002937999,0.00005356854,0.00005452749],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000006959746,0.00001831857,0.00007382207,0.0001519272,0.00002363889,0.00003446474,0.001883953,0.000001061261,0.0202441,0.805116,0.04623195,0.1262138],"study_design_scores_gemma":[0.0001536883,0.0001070003,0.000087751,0.00009306168,0.000007991871,0.0000570329,0.00001430607,0.2040809,0.02872862,0.6986894,0.06756676,0.0004135052],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04253963,0.004271453,0.9438924,0.002971504,0.0003715398,0.0001969633,0.000003384326,0.003541617,0.002211565],"genre_scores_gemma":[0.2106278,0.000005147511,0.7821757,0.0005613432,0.0002289822,0.00003336373,0.000002058594,0.00001390696,0.006351721],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2040799,"threshold_uncertainty_score":0.6017402,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2143564602","doi":"10.3115/1220175.1220271","title":"An end-to-end discriminative approach to machine translation","year":2006,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":265,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Fonds Québécois de la Recherche sur la Nature et les Technologies; Microsoft Research","keywords":"Discriminative model; Computer science; Artificial intelligence; Machine translation; Phrase; Heuristic; Feature (linguistics); Machine learning; Translation (biology); Process (computing); Decoding methods; Perceptron; Natural language processing; Pattern recognition (psychology); Artificial neural network; Algorithm","retraction":null,"screen_n_in":null,"score":{"opus":0.01802462325358629,"gpt":0.2828060711697341,"spread":0.2647814479161478,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001917175,0.0001237996,0.0001049571,0.0001674421,0.0000770994,0.0001834594,0.0007362315,0.00004281207,0.00001394801],"category_scores_gemma":[0.000009215593,0.00009515673,0.00002709582,0.0004942177,0.00001549921,0.0006549979,0.00007239838,0.00009493822,0.0000133978],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003463015,"about_ca_system_score_gemma":0.00001668149,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004959152,"about_ca_topic_score_gemma":0.0001127597,"domain_scores_codex":[0.9989707,0.00004404653,0.0001418201,0.0003953145,0.0002496518,0.0001984246],"domain_scores_gemma":[0.999449,0.00001985789,0.00002717049,0.000358087,0.00005677923,0.00008917431],"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":[0.000009359938,0.0002195623,0.00006638086,0.00001574408,0.000003498649,0.000004748443,0.003138875,0.0001290268,0.02144773,0.3275932,0.0009988871,0.646373],"study_design_scores_gemma":[0.000559366,0.0006903257,0.00343492,0.00005054036,0.00002246627,0.00004731104,0.0001853271,0.4397437,0.3782307,0.170882,0.004723857,0.001429447],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0008634342,0.0001982942,0.9753556,0.001505734,0.00003463022,0.0002407915,0.000003972821,0.0007527042,0.02104485],"genre_scores_gemma":[0.4885909,1.095066e-7,0.5108249,0.0003060194,0.00002657495,0.00001473618,0.00001027602,0.00000491696,0.0002215971],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6449435,"threshold_uncertainty_score":0.3880379,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2531882892","doi":"10.1111/cogs.12414","title":"Grammaticality, Acceptability, and Probability: A Probabilistic View of Linguistic Knowledge","year":2016,"lang":"en","type":"article","venue":"Cognitive Science","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":261,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Menzies Centre for Australian Studies, King's College London, University of London; Economic and Social Research Council; University of Toronto; Chalmers Tekniska Högskola; University of Reading; Universiteit van Amsterdam; Weizmann Institute of Science; Göteborgs Universitet; University of Edinburgh; King's College London","keywords":"Grammaticality; Probabilistic logic; Natural language processing; Artificial intelligence; Computer science; Sentence; Natural language; Set (abstract data type); Linguistics; Grammar","retraction":null,"screen_n_in":null,"score":{"opus":0.03081905117699348,"gpt":0.329199145905938,"spread":0.2983800947289446,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","sts"],"consensus_categories":[],"category_scores_codex":[0.002091355,0.0001722852,0.0002718943,0.0001674099,0.0001667806,0.0001521556,0.001283221,0.00005089524,0.00001930729],"category_scores_gemma":[0.01426678,0.0001062959,0.00004363602,0.001241641,0.003365094,0.0007238806,0.001334561,0.00010714,0.00001304936],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008515517,"about_ca_system_score_gemma":0.0004547943,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008403392,"about_ca_topic_score_gemma":0.000009244533,"domain_scores_codex":[0.9978739,0.0001293779,0.0003662863,0.0008063603,0.000433855,0.0003902089],"domain_scores_gemma":[0.9968512,0.0009656138,0.0001446002,0.0005316883,0.001328758,0.0001781068],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000006825015,0.0001594071,0.002070746,0.0003438117,0.000004025264,0.000003328175,0.001453897,1.016801e-8,0.006970897,0.3067129,0.000003627998,0.6822705],"study_design_scores_gemma":[0.0002294906,0.0001633774,0.005432156,0.0005173678,0.00001358609,0.00002059146,0.00001642727,0.0006427533,0.04183927,0.950833,0.00005669315,0.0002353541],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1225454,0.001999662,0.8699222,0.0006404981,0.0002044846,0.001022827,0.00001274343,0.0004776095,0.003174526],"genre_scores_gemma":[0.8799987,0.00001202678,0.1198534,0.00004345356,0.0000194649,0.00003878005,1.708067e-7,0.00000522029,0.00002874816],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7574534,"threshold_uncertainty_score":0.9993472,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2092527610","doi":"10.1162/089120102760173625","title":"Near-Synonymy and Lexical Choice","year":2002,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":258,"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; Natural language processing; Denotation (semiotics); Artificial intelligence; Context (archaeology); Lexicon; Lexical choice; Set (abstract data type); Selection (genetic algorithm); Lexical semantics; Ontology; Lexical item; Linguistics","retraction":null,"screen_n_in":null,"score":{"opus":0.02487434097093336,"gpt":0.2844013043204678,"spread":0.2595269633495345,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00008147283,0.00009711654,0.00009454362,0.00004343636,0.0001660164,0.0002543552,0.000346433,0.00005284006,0.00001565882],"category_scores_gemma":[0.001388414,0.00009360576,0.00002055543,0.0001755878,0.00007182589,0.00006100869,0.0001816476,0.000152592,0.00003188372],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001978699,"about_ca_system_score_gemma":0.00002290535,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004117956,"about_ca_topic_score_gemma":7.84477e-7,"domain_scores_codex":[0.9992155,0.00002122591,0.0001491435,0.0002421996,0.0002251996,0.0001467707],"domain_scores_gemma":[0.9991345,0.000311794,0.00005344331,0.0001504496,0.0002694555,0.00008033056],"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":[0.000001260606,0.00006258654,0.0008228436,0.00003228877,0.00001010367,0.0000446527,0.0003137041,0.001115144,0.00001030719,0.9567891,0.006195815,0.03460224],"study_design_scores_gemma":[0.0001139283,0.00003095228,0.0004842757,0.00001872054,0.000003580005,0.00002436342,8.26975e-7,0.7646385,0.00004197348,0.203032,0.03146802,0.0001428124],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001408552,0.002171738,0.9914245,0.0006884438,0.0003626679,0.00007377549,0.000005211758,0.0005450177,0.003320078],"genre_scores_gemma":[0.4591157,0.000003348942,0.5402219,0.0003835908,0.0001840797,0.000001611671,0.000002719659,0.000004560212,0.00008254185],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7635234,"threshold_uncertainty_score":0.3817132,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2164948578","doi":"10.1162/089120103321337458","title":"Word Reordering and a Dynamic Programming Beam Search Algorithm for Statistical Machine Translation","year":2003,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":257,"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; Word (group theory); Task (project management); Machine translation; Vocabulary; Beam search; Word error rate; Sentence; Translation (biology); Artificial intelligence; Natural language processing; Dynamic programming; Search algorithm; Speech recognition; Set (abstract data type); Algorithm; Linguistics; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.01830414375166094,"gpt":0.319656416215049,"spread":0.3013522724633881,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000360497,0.0001276742,0.0001313179,0.0001035874,0.0001934615,0.0001993635,0.0001915057,0.00005628932,0.000001686864],"category_scores_gemma":[0.0008416311,0.0001309318,0.00002459237,0.0002009559,0.00006134166,0.00005973696,0.00004471504,0.0001579332,9.862298e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004220701,"about_ca_system_score_gemma":0.000100681,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005340537,"about_ca_topic_score_gemma":0.000002412773,"domain_scores_codex":[0.9989419,0.00003841783,0.0002255324,0.0003199161,0.0002463447,0.0002278759],"domain_scores_gemma":[0.9987721,0.0005896285,0.00005355659,0.0001143339,0.0003923052,0.00007808103],"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":[0.000003461803,0.00003361582,0.00002913849,0.00006003354,0.000009739777,0.000008815572,0.0001904209,0.0008268346,0.00001230049,0.2049632,0.00001441733,0.793848],"study_design_scores_gemma":[0.0002379481,0.00005790232,0.00004165336,0.00002582101,0.000007742315,0.00001873348,0.000006095666,0.8301212,0.00009455298,0.166341,0.002902819,0.0001445283],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0000749093,0.001709541,0.9973238,0.0000645002,0.0001785199,0.0002943572,0.00003061732,0.0002550227,0.00006876071],"genre_scores_gemma":[0.1729416,0.00000444744,0.8268375,0.00004869045,0.00004941965,0.00001862648,0.00007178765,0.00001334771,0.00001456124],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8292944,"threshold_uncertainty_score":0.5339246,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2132001515","doi":"10.3115/1626355.1626372","title":"Mixture-model adaptation for SMT","year":2007,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":253,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"National Research Council Canada","funders":"","keywords":"Computer science; Machine translation; Granularity; Adaptation (eye); BLEU; Translation (biology); Domain adaptation; Log-linear model; Artificial intelligence; Baseline (sea); Language model; Natural language processing; Algorithm; Linear model; Machine learning; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.02364179146064855,"gpt":0.3049751683204618,"spread":0.2813333768598132,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003191394,0.00005457127,0.00004816077,0.00005915138,0.00004964243,0.0000587484,0.000374891,0.00004653563,0.000001579509],"category_scores_gemma":[0.00004606015,0.00004312814,0.0000270447,0.0001274506,0.000008451129,0.0003194184,0.00004947123,0.00004664067,0.000003274663],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002041597,"about_ca_system_score_gemma":0.00002543984,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007816922,"about_ca_topic_score_gemma":0.00002026939,"domain_scores_codex":[0.999491,0.000003126617,0.00009510128,0.0001585031,0.0001032277,0.0001490627],"domain_scores_gemma":[0.9996144,0.00005529132,0.00003290662,0.0001771494,0.00008826527,0.0000320094],"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":[0.000005860371,0.00001336693,0.000003783325,0.000009755881,0.000001970225,0.000001546958,0.0003970059,0.00004786933,0.005890529,0.7454311,0.002783799,0.2454135],"study_design_scores_gemma":[0.00008551745,0.00002680934,0.000006071923,0.000005461947,0.00000137773,0.000003410718,0.000009751882,0.6212881,0.1058144,0.2716692,0.0009962338,0.00009363269],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001505039,0.0002595308,0.996206,0.0005008159,0.00006211818,0.0001192525,3.725555e-7,0.0006527637,0.002048672],"genre_scores_gemma":[0.263548,6.502431e-7,0.7350555,0.0006083972,0.00002435954,0.000005435936,0.000001155313,0.000003243843,0.0007532641],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6212403,"threshold_uncertainty_score":0.1758714,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4285084440","doi":"10.1038/s41587-022-01369-0","title":"Standardized annotation of translated open reading frames","year":2022,"lang":"en","type":"letter","venue":"Nature Biotechnology","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":250,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Sherbrooke","funders":"National Cancer Institute; National Human Genome Research Institute; National Institute on Aging; RIKEN; Agència de Gestió d'Ajuts Universitaris i de Recerca; Medical Research Council; Canadian Institutes of Health Research; Directorate for Biological Sciences; National Institutes of Health; European Molecular Biology Laboratory; Russian Science Foundation; Institució Catalana de Recerca i Estudis Avançats; National Institute of General Medical Sciences; University College Cork; University of Leeds; Universitat Pompeu Fabra; Fondation Leducq; Stowers Institute for Medical Research; Australian Government; Searle Scholars Program; National Science Foundation; Science Foundation Ireland; Biotechnology and Biological Sciences Research Council; Université de Sherbrooke; Wellcome Trust; European Commission; University of California, Irvine; Broad Institute; University of Pittsburgh; Howard Hughes Medical Institute; Staatssekretariat für Bildung, Forschung und Innovation; Musella Foundation For Brain Tumor Research and Information; Agencia Estatal de Investigación; Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology; Alex's Lemonade Stand Foundation for Childhood Cancer; Yale University","keywords":"Annotation; Open reading frame; Reading (process); Computer science; Information retrieval; Computational biology; Natural language processing; Biology; Artificial intelligence; Linguistics; Genetics; Philosophy; Peptide sequence","retraction":null,"screen_n_in":null,"score":{"opus":0.009975389999421257,"gpt":0.2940358937373858,"spread":0.2840605037379645,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","open_science","research_integrity"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.0004819045,0.000355363,0.0007165098,0.0009059053,0.0001487832,0.0001589349,0.006454527,0.006282832,0.00007929479],"category_scores_gemma":[0.0002799554,0.0003285433,0.0001320371,0.001528502,0.000162343,0.0003695744,0.0014012,0.009540925,0.00000218782],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001787775,"about_ca_system_score_gemma":0.0002430428,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005279392,"about_ca_topic_score_gemma":0.000003095145,"domain_scores_codex":[0.9974654,0.0001746524,0.0004586306,0.0009186135,0.0005709313,0.0004118087],"domain_scores_gemma":[0.9977127,0.0001598771,0.0005746122,0.001341462,0.0001904793,0.00002083025],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00004769458,0.00002601706,0.000002101182,0.0001976164,0.0001104974,0.0005175023,0.0002663506,6.589833e-7,0.01019492,0.04400048,0.8677922,0.07684401],"study_design_scores_gemma":[0.0002872981,0.0002038048,6.200337e-7,0.000103071,0.0000245942,0.00007469463,0.000006143201,0.0001195111,0.1159521,0.06953304,0.8133399,0.0003552197],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"commentary","genre_gemma":"methods","genre_scores_codex":[0.00005336692,0.0148349,0.1378234,0.8428898,0.0008698941,0.00083982,0.000153529,0.002129034,0.0004061913],"genre_scores_gemma":[0.003995528,0.0001642132,0.7777203,0.2168825,0.0002317001,0.0001016189,0.0003594149,0.00007674429,0.0004679052],"genre_candidate":"commentary","genre_consensus":null,"teacher_disagreement_score":0.639897,"threshold_uncertainty_score":0.9999167,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2200913422","doi":"10.33011/lilt.v9i.1321","title":"Frege in Space: A Program for Compositional Distributional Semantics","year":2014,"lang":"en","type":"article","venue":"Linguistic Issues in Language Technology","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":245,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Atomic Energy of Canada Limited","keywords":"Principle of compositionality; Meaning (existential); Computer science; Semantics (computer science); Distributional semantics; Lexicon; Lexicology; Linguistics; Syntax; Formal semantics (linguistics); Computational semantics; Lexical semantics; Natural language processing; Cognitive semantics; Artificial intelligence; Space (punctuation); Function (biology); Operational semantics; Lexical item; Programming language; Cognition; Epistemology; Psychology; Philosophy","retraction":null,"screen_n_in":null,"score":{"opus":0.005157375645620031,"gpt":0.3124737237818904,"spread":0.3073163481362703,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003582243,0.0001853761,0.0002945598,0.0005192145,0.00006107172,0.00006600421,0.0009898373,0.0002710069,0.000007607015],"category_scores_gemma":[0.002126886,0.0001828425,0.00004269656,0.0007957228,0.0001735402,0.00007097236,0.0002900114,0.0003733772,0.000006721011],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000911824,"about_ca_system_score_gemma":0.00003457654,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005879694,"about_ca_topic_score_gemma":0.0000613296,"domain_scores_codex":[0.9985482,0.00004203278,0.0003228652,0.0004542677,0.0001870867,0.0004456259],"domain_scores_gemma":[0.9990383,0.0002092202,0.0001019646,0.0004813946,0.0001347633,0.00003438191],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000008144933,0.0001624739,0.001162729,0.00006288374,0.00000412017,0.00008861347,0.0004424581,0.000004508654,0.001157272,0.9790199,0.0001506762,0.01773618],"study_design_scores_gemma":[0.001037207,0.000377627,0.0003131863,0.0003331986,0.000008470178,0.0001010476,0.0001036592,0.05623857,0.02826937,0.9001968,0.01250623,0.0005146547],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02089136,0.004796547,0.9622483,0.006788679,0.0004563272,0.001041607,0.00003565065,0.002759294,0.0009822702],"genre_scores_gemma":[0.5400058,0.000003190961,0.4596078,0.00006464236,0.000100119,0.0001345107,0.00003955916,0.000008571817,0.00003586533],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5191144,"threshold_uncertainty_score":0.7456103,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2026222783","doi":"10.7202/1025047ar","title":"Translation Skill-Sets in a Machine-Translation Age","year":2014,"lang":"en","type":"article","venue":"Meta Journal des traducteurs","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":241,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Terminology; Computer science; Machine translation; Space (punctuation); Translation (biology); Computer-assisted translation; Function (biology); Natural language processing; Artificial intelligence; Linguistics","retraction":null,"screen_n_in":null,"score":{"opus":0.03194641009699978,"gpt":0.290480704647114,"spread":0.2585342945501142,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001255125,0.0001916672,0.0002891615,0.0003635898,0.0001397998,0.0003466826,0.00074496,0.00008214139,0.00001420393],"category_scores_gemma":[0.00008548991,0.0001494617,0.0001683696,0.0005906797,0.00005798042,0.001328283,0.00001941457,0.0004990474,0.000005315432],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004632587,"about_ca_system_score_gemma":0.00002696619,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002759892,"about_ca_topic_score_gemma":0.00008742534,"domain_scores_codex":[0.9983029,0.0003533181,0.0004014639,0.0002748107,0.0003665959,0.0003009031],"domain_scores_gemma":[0.9993011,0.0001222339,0.0001466973,0.0002639604,0.00005977319,0.0001062731],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000008746002,0.00004112979,0.0001920782,0.00002095014,0.00003720676,0.00005425244,0.0007281106,0.00005587209,0.00433634,0.004890519,0.00002544663,0.9896094],"study_design_scores_gemma":[0.001435293,0.0002900001,0.006299711,0.0001745644,0.0002412476,0.00135565,0.000008243175,0.06400594,0.01599839,0.89644,0.01296369,0.0007873268],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.009174938,0.05597422,0.9331486,0.0009738645,0.0002075862,0.0001177168,0.000001059773,0.0002026818,0.0001993883],"genre_scores_gemma":[0.4734375,0.0006925598,0.5256356,0.0001430812,0.0000513198,0.000004983153,0.000002545925,0.00001334956,0.00001905132],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.988822,"threshold_uncertainty_score":0.6094872,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2152808281","doi":"10.1109/tnn.2007.912312","title":"Adaptive Importance Sampling to Accelerate Training of a Neural Probabilistic Language Model","year":2008,"lang":"en","type":"article","venue":"IEEE Transactions on Neural Networks","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":233,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Language model; Artificial neural network; Vocabulary; Probabilistic neural network; Speedup; Artificial intelligence; Probabilistic logic; Computation; Machine learning; Feedforward neural network; Sampling (signal processing); Statistical model; Training (meteorology); Backpropagation; Importance sampling; Time delay neural network; Algorithm; Statistics; Mathematics; Monte Carlo method","retraction":null,"screen_n_in":null,"score":{"opus":0.0677840225644307,"gpt":0.2919126299227441,"spread":0.2241286073583134,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001402725,0.00026208,0.0003148923,0.0001745258,0.0002485868,0.00005386811,0.0007629295,0.0001123633,0.000006295978],"category_scores_gemma":[0.00001301406,0.0002396311,0.0001327975,0.0007766355,0.00008085211,0.0005072049,0.000009942658,0.000557406,0.000001563153],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006161699,"about_ca_system_score_gemma":0.00005933135,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002553414,"about_ca_topic_score_gemma":0.00003843856,"domain_scores_codex":[0.9982831,0.00005684861,0.0003920132,0.0005271003,0.0002932349,0.0004477118],"domain_scores_gemma":[0.9989342,0.000141653,0.00014203,0.0005115244,0.0001167476,0.0001538397],"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":[0.00005792402,0.00005293938,0.000004013818,0.00001035082,0.0000114255,0.00003927288,0.002383558,0.9514742,0.002086079,0.0002551314,0.00003809709,0.043587],"study_design_scores_gemma":[0.0001672545,0.0001937094,0.00001599566,0.00005160719,0.00001037135,0.00007945515,0.00004113156,0.9937519,0.004827161,0.0006092986,0.000001216477,0.0002508653],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08499976,0.000255237,0.9133865,0.0002065515,0.0002238197,0.0003455498,0.000009034253,0.000535349,0.0000382186],"genre_scores_gemma":[0.7971423,0.00000846205,0.2021116,0.0005631095,0.00004408604,0.00005544685,0.00000100484,0.00002278089,0.00005113383],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7121426,"threshold_uncertainty_score":0.9771872,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W59585178","doi":"","title":"Proceedings of the conference on Human Language Technology and Empirical Methods in Natural Language Processing","year":2005,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":231,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Language technology; Computer science; Human language; Computational linguistics; Linguistics; Natural language; Artificial intelligence; Natural language processing; Comprehension approach","retraction":null,"screen_n_in":null,"score":{"opus":0.03212528760022702,"gpt":0.4063860398749459,"spread":0.3742607522747188,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003752719,0.0001467191,0.0001983172,0.0003455817,0.00007976372,0.00009905962,0.000984282,0.0001284727,0.000005595235],"category_scores_gemma":[0.0001334795,0.00009051561,0.00002802,0.001030969,0.0001645155,0.0003751573,0.0004657012,0.0004557709,7.766361e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004459315,"about_ca_system_score_gemma":0.00003798305,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001788041,"about_ca_topic_score_gemma":0.00003698451,"domain_scores_codex":[0.9989684,0.0000278959,0.0002351731,0.0003503844,0.0001871889,0.0002310064],"domain_scores_gemma":[0.9994974,0.00003634339,0.0001289467,0.0002185553,0.00009007461,0.00002870116],"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":[0.000004784894,0.00006184161,0.001843484,0.00006419401,0.000003327602,0.000004273651,0.005666068,2.079868e-7,0.3049895,0.09937842,0.0001050646,0.5878788],"study_design_scores_gemma":[0.0003848115,0.0001028558,0.00220905,0.000321966,0.000005961051,0.00007228731,0.001319723,0.02109661,0.9598894,0.01412545,0.0001479954,0.000323897],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9444496,0.00896261,0.02426887,0.01204089,0.00005927344,0.0005096112,9.2251e-7,0.001131028,0.008577166],"genre_scores_gemma":[0.6087673,0.000001168709,0.3906445,0.0002996986,0.00001326874,0.000007905135,1.224384e-7,0.000005094973,0.0002608961],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6548999,"threshold_uncertainty_score":0.369112,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3194817747","doi":"10.82308/39461","title":"Verb-stranding VP ellipsis : a cross-linguistic study","year":2005,"lang":"en","type":"article","venue":"eScholarship@McGill (McGill)","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":226,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"McGill University","keywords":"Linguistics; Ellipsis (linguistics); Verb; Verb phrase ellipsis; Computer science; Artificial intelligence; Natural language processing; Modal verb; Philosophy","retraction":null,"screen_n_in":null,"score":{"opus":0.02004930865468135,"gpt":0.2869970620228592,"spread":0.2669477533681779,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.001605289,0.0005715617,0.0005161962,0.0004007256,0.001439802,0.0006552308,0.002684594,0.0002634356,0.00007934347],"category_scores_gemma":[0.001265855,0.0005566322,0.0002218273,0.001145787,0.0001022341,0.002054315,0.0008994347,0.001165285,0.0003285801],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000643837,"about_ca_system_score_gemma":0.0000441171,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001268406,"about_ca_topic_score_gemma":0.0001427461,"domain_scores_codex":[0.9956298,0.0002853536,0.0008008332,0.001346376,0.0009816503,0.0009559417],"domain_scores_gemma":[0.9972181,0.0002943249,0.0003146824,0.001414383,0.0004020091,0.0003565488],"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":[0.00009292311,0.001172948,0.001224945,0.000119219,0.0001676944,0.0005881621,0.0001517802,0.0001183087,0.02550022,0.3272628,0.0000109903,0.64359],"study_design_scores_gemma":[0.006526398,0.001786032,0.003004072,0.0007291671,0.0003035028,0.0005656673,0.0001862098,0.007096676,0.4906477,0.364825,0.1188882,0.005441394],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9772025,0.001054312,0.0007298598,0.0001031609,0.0008641781,0.0009757043,0.00008832444,0.003524482,0.0154575],"genre_scores_gemma":[0.8722697,0.00001753945,0.1263657,0.000415214,0.0001124392,0.00006552859,0.000004924274,0.00006782551,0.0006810406],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6381486,"threshold_uncertainty_score":0.9998602,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2046436395","doi":"10.1162/089120100561755","title":"The Rhetorical Parsing of Unrestricted Texts: A Surface-based Approach","year":2000,"lang":"en","type":"article","venue":"Computational Linguistics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":221,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; University of Toronto","keywords":"Rhetorical question; Computer science; Automatic summarization; Parsing; Natural language processing; Artificial intelligence; Linguistics; Context (archaeology); Natural language understanding; Natural language; Philosophy; History","retraction":null,"screen_n_in":null,"score":{"opus":0.02046125002567074,"gpt":0.2820272355339836,"spread":0.2615659855083128,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002481046,0.0001172433,0.0001337122,0.00004436624,0.0002388302,0.0001347886,0.0007631826,0.00006212516,0.000004278945],"category_scores_gemma":[0.0009332905,0.00008804749,0.00005214831,0.0005499513,0.0001169018,0.00003411451,0.00006191197,0.0001793188,0.000005707053],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005360713,"about_ca_system_score_gemma":0.0002281131,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001083225,"about_ca_topic_score_gemma":2.32954e-7,"domain_scores_codex":[0.9987621,0.00007726541,0.000309685,0.0002304776,0.0004276507,0.0001928708],"domain_scores_gemma":[0.9981668,0.0008222381,0.0001206206,0.000278872,0.000555158,0.00005632362],"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":[0.000039271,0.0002425128,0.0003138606,0.00005607863,0.00002578673,0.00001619037,0.0002059412,0.2687278,0.00004154179,0.6673367,0.002226544,0.06076775],"study_design_scores_gemma":[0.0001640213,0.00003991852,0.0001714644,0.00002880459,0.000006412219,0.000004799259,0.000002372931,0.8793194,0.0003243699,0.1135528,0.006259916,0.0001256704],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001183806,0.001262976,0.994296,0.0001619985,0.0002017042,0.0001159572,0.000006106678,0.0002914435,0.002480057],"genre_scores_gemma":[0.4812593,0.000003427416,0.5185337,0.00006390238,0.00007820348,0.000001632443,0.00001112887,0.000005488559,0.00004320317],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6105916,"threshold_uncertainty_score":0.3590472,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2548230849","doi":"10.1075/nlp.2.15mey","title":"Extracting knowledge-rich contexts for terminography","year":2001,"lang":"en","type":"book-chapter","venue":"Natural language processing","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":215,"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":"Construct (python library); Computer science; Paralanguage; Domain knowledge; Domain (mathematical analysis); Knowledge extraction; Field (mathematics); Context (archaeology); Knowledge management; Natural language processing; Data science; Artificial intelligence; Psychology; Communication; Geography; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.01563003246822913,"gpt":0.3028685290154244,"spread":0.2872384965471953,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005306258,0.0009565764,0.0008628641,0.0008096725,0.0005663479,0.0009534777,0.002333633,0.0008533777,0.00003822714],"category_scores_gemma":[0.0002527835,0.0008446428,0.0004477105,0.0003492268,0.0001530006,0.001422905,0.00053997,0.001680204,0.00003280994],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002219155,"about_ca_system_score_gemma":0.0003137696,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000832424,"about_ca_topic_score_gemma":0.00002862515,"domain_scores_codex":[0.996295,0.00003278453,0.0007794738,0.001414361,0.0005919903,0.0008863951],"domain_scores_gemma":[0.9968852,0.0003504634,0.0009378355,0.0008897218,0.0007469194,0.0001898201],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000021406,0.00002721694,0.000003450084,0.0006022839,0.00004492642,0.0001559541,0.001538779,1.678437e-7,0.0006345861,0.01322338,0.00146435,0.9822835],"study_design_scores_gemma":[0.004744011,0.0008412653,0.00002128007,0.01851698,0.0009517972,0.003311776,0.0005417956,0.06881844,0.0217189,0.1768467,0.6901055,0.01358155],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"methods","genre_scores_codex":[0.00002119715,0.6957977,0.1205934,0.0002826504,0.0009542715,0.00108584,0.00002610611,0.002822111,0.1784167],"genre_scores_gemma":[0.1843339,0.0001739035,0.467833,0.0008167608,0.001707481,0.0001355013,0.0001582562,0.0003025974,0.3445386],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.968702,"threshold_uncertainty_score":0.9994004,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1848260265","doi":"","title":"Discriminative Instance Weighting for Domain Adaptation in Statistical Machine Translation","year":2010,"lang":"en","type":"article","venue":"NPARC","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":211,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Discriminative model; Weighting; Computer science; Domain adaptation; Machine translation; Artificial intelligence; Relevance (law); Granularity; Phrase; Natural language processing; Domain (mathematical analysis); Machine learning; Range (aeronautics); Adaptation (eye); Translation (biology); Pattern recognition (psychology); Mathematics; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.01834908506549149,"gpt":0.2900663894007872,"spread":0.2717173043352957,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003173819,0.00007488095,0.00008496519,0.00008082801,0.00005890542,0.0000581696,0.00026598,0.00005023411,0.000007787704],"category_scores_gemma":[0.0001239477,0.00006539722,0.00001578144,0.0001707187,0.00003281993,0.0004232314,0.00002436772,0.0002008599,0.000001032811],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002288557,"about_ca_system_score_gemma":0.00003119061,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001314368,"about_ca_topic_score_gemma":0.0003308211,"domain_scores_codex":[0.9993168,0.00003139089,0.0001520522,0.0002138785,0.0001381211,0.0001477533],"domain_scores_gemma":[0.9995245,0.0002100832,0.00005479852,0.000133075,0.00004946092,0.00002803551],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00001187791,0.00001947851,0.00004886732,0.00001665754,9.197963e-7,0.000003185199,0.002121687,0.000001276604,0.05421118,0.5966761,0.00001797726,0.3468709],"study_design_scores_gemma":[0.0002589383,0.00003720813,0.0003050488,0.0000201396,0.000001468635,0.000002707298,0.00003030878,0.2570927,0.01096806,0.7309326,0.0002526815,0.00009813065],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005338802,0.00007772345,0.9919776,0.001142548,0.00009500009,0.0002188028,0.00001168711,0.0001358367,0.00100204],"genre_scores_gemma":[0.4835339,6.011664e-7,0.5163758,0.00003386748,0.00001382243,0.00002500177,0.00000719673,0.000003385492,0.000006326423],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4781952,"threshold_uncertainty_score":0.2666821,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W179314280","doi":"","title":"Discriminative Reranking for Machine Translation","year":2004,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":207,"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":"Machine translation; Discriminative model; NIST; Computer science; Artificial intelligence; Metric (unit); Evaluation of machine translation; Natural language processing; Baseline (sea); Translation (biology); BLEU; Sentence; Language model; Machine learning; Example-based machine translation; Machine translation software usability","retraction":null,"screen_n_in":null,"score":{"opus":0.02568892978725502,"gpt":0.3028351473361521,"spread":0.2771462175488971,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001126221,0.00005914725,0.00005645767,0.00005037012,0.00007160039,0.00006908899,0.000303781,0.00002672242,0.000002522795],"category_scores_gemma":[0.00002192189,0.00004465242,0.00003121364,0.0001285364,0.00001157005,0.0004680629,0.00002620367,0.00004948025,0.000001480824],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002871016,"about_ca_system_score_gemma":0.00001812057,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003216246,"about_ca_topic_score_gemma":0.00002249821,"domain_scores_codex":[0.9995582,0.000006668849,0.00008145678,0.0001616667,0.00008799788,0.0001040394],"domain_scores_gemma":[0.9997419,0.00003686196,0.00002714581,0.000132971,0.00004309011,0.00001800696],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000003677885,0.00001593485,0.000003476602,0.00001394581,0.000002645569,0.000001450586,0.001245135,0.00001114661,0.003635317,0.6279372,0.00002613053,0.367104],"study_design_scores_gemma":[0.0003746311,0.00006763836,0.00001635921,0.00002893647,0.000003515461,0.000006489505,0.00001019032,0.01567165,0.1619809,0.8213419,0.0003714646,0.0001264148],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0001422768,0.0008566682,0.9941695,0.003093688,0.00004684839,0.0001634466,0.000001083761,0.000509529,0.001016953],"genre_scores_gemma":[0.4181218,0.000001240362,0.5816303,0.0001785832,0.00001142919,0.00001119541,0.000002069763,0.00000268547,0.00004067925],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4179795,"threshold_uncertainty_score":0.1820873,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1493557574","doi":"10.4324/9781315749129","title":"Routledge Encyclopedia of Translation Technology","year":2014,"lang":"en","type":"book","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":202,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Encyclopedia; Translation (biology); History; Library science; Computer science; Biology","retraction":null,"screen_n_in":null,"score":{"opus":0.008834097611382362,"gpt":0.2447141565008683,"spread":0.2358800588894859,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001492629,0.0001834804,0.0003095344,0.0004383529,0.00002271178,0.0000203657,0.001336308,0.0005469098,0.00002718976],"category_scores_gemma":[0.00002642632,0.0001544866,0.00007342929,0.0002066927,0.00007385625,0.0001586153,0.000163024,0.0003220681,0.00003027724],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004486332,"about_ca_system_score_gemma":0.0001883218,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003051556,"about_ca_topic_score_gemma":0.000009384828,"domain_scores_codex":[0.9989997,0.00001592733,0.0002912273,0.0003403416,0.0002064061,0.0001464202],"domain_scores_gemma":[0.9989098,0.00006194272,0.0002222373,0.0006530978,0.000126997,0.000025963],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[9.667026e-7,0.000008415046,0.00000506248,0.0001047275,0.00000946325,0.000003320593,0.00007225696,1.245057e-7,0.0001099067,0.5714281,0.01895275,0.409305],"study_design_scores_gemma":[0.00008612315,0.00007465111,0.00000118551,0.0001611685,0.00001363688,0.0000118568,5.913827e-7,0.0006323981,0.00402911,0.600715,0.3940023,0.000271949],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[3.333125e-7,0.001887066,0.5233073,0.0002194325,0.00008260361,0.00009425558,0.000001028522,0.0006507907,0.4737572],"genre_scores_gemma":[0.0001993164,0.00005443961,0.5936663,0.00005192813,0.00006606667,0.000007271958,0.000008472601,0.00001467975,0.4059315],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.409033,"threshold_uncertainty_score":0.6299782,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2759181158","doi":"10.18653/v1/2023.acl-short","title":"Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)","year":2023,"lang":"en","type":"paratext","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":201,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"Atomic Energy of Canada Limited","keywords":"Volume (thermodynamics); Computational linguistics; Computer science; Association (psychology); Natural language processing; Psychology; Physics","retraction":null,"screen_n_in":null,"score":{"opus":0.0122143289876546,"gpt":0.2760036831266697,"spread":0.2637893541390151,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007518323,0.0001938596,0.0003147855,0.00008422304,0.000180285,0.0001014336,0.001916032,0.0002943065,0.000008176713],"category_scores_gemma":[0.002711353,0.0001169059,0.0002188991,0.000665225,0.00006725714,0.00007489033,0.0007237661,0.0003441213,0.000009312045],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001629952,"about_ca_system_score_gemma":0.00026949,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003827557,"about_ca_topic_score_gemma":0.000009638524,"domain_scores_codex":[0.9981315,0.00002464523,0.0004966839,0.0003346749,0.000785202,0.0002273532],"domain_scores_gemma":[0.9961824,0.0004095053,0.0008327353,0.0002131997,0.002340231,0.00002194512],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000007376825,0.00005027457,0.0008813036,0.0008118243,0.0001273408,1.444922e-7,0.001087129,0.0005350591,0.0008459691,0.06357555,0.9297293,0.002348733],"study_design_scores_gemma":[0.001255099,0.0005769267,0.005737868,0.007980869,0.00066143,0.00001513999,0.001076667,0.1797851,0.1408825,0.1284084,0.5304136,0.003206457],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"methods","genre_scores_codex":[0.001468263,0.003102603,0.1321161,0.007445678,0.02615006,0.008376308,0.002980984,0.002176393,0.8161836],"genre_scores_gemma":[0.2343448,0.00003117333,0.4388498,0.0005331729,0.00139006,0.0001287595,0.000079998,0.0001045266,0.3245377],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.4916459,"threshold_uncertainty_score":0.4767283,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}