{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":11,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":11,"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":"34948cb5f57d","filters":{"venue":"Empirical Methods in Natural Language Processing"}},"results":[{"id":"W2117424365","doi":"","title":"Learning Noun Phrase Query Segmentation","year":2007,"lang":"en","type":"article","venue":"Empirical Methods in Natural Language Processing","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":106,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Query expansion; Web query classification; Query language; Natural language processing; RDF query language; Information retrieval; Artificial intelligence; Precision and recall; Web search query; Noun phrase; Sargable; Query optimization; Segmentation; Phrase; Set (abstract data type); Noun; Search engine","retraction":null,"screen_n_in":null,"score":{"opus":0.0283993285986766,"gpt":0.4422297324931074,"spread":0.4138304038944308,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.004115941,0.0003351475,0.0003719275,0.0005749072,0.0002468059,0.0003637788,0.000992617,0.0002400184,0.00001441745],"category_scores_gemma":[0.001896749,0.0002830808,0.0001001175,0.002014511,0.0000894193,0.001441344,0.0003885364,0.001469047,0.000008771154],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003093199,"about_ca_system_score_gemma":0.0001133174,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004958829,"about_ca_topic_score_gemma":0.00002396335,"domain_scores_codex":[0.9967754,0.0005400935,0.0006450539,0.000763454,0.0005206119,0.0007553805],"domain_scores_gemma":[0.9983721,0.0006687827,0.0002978801,0.0003612749,0.0001496522,0.0001503254],"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":[0.00002431757,0.00004639811,0.001392365,0.00008092116,0.00000460444,0.0002094115,0.005803451,0.00000672341,0.05669859,0.0002652159,0.00002819295,0.9354398],"study_design_scores_gemma":[0.002293121,0.0003747772,0.005034759,0.001183429,0.00004886329,0.0006029982,0.005862141,0.2169114,0.737013,0.02545642,0.002243066,0.002976033],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01491432,0.03962749,0.9425131,0.0004802801,0.000326103,0.0002255342,3.45414e-7,0.001145134,0.0007676853],"genre_scores_gemma":[0.3884385,0.000006830383,0.6104798,0.0007496814,0.0001139284,0.00001021023,0.000004938749,0.00002083149,0.0001752826],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9324638,"threshold_uncertainty_score":0.9999622,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2151839123","doi":"","title":"Translating Unknown Words by Analogical Learning","year":2007,"lang":"en","type":"article","venue":"Empirical Methods in Natural Language Processing","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":63,"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":"Lexicon; Computer science; Artificial intelligence; Natural language processing; Machine translation; Quality (philosophy); Translation (biology)","retraction":null,"screen_n_in":null,"score":{"opus":0.03097276130335845,"gpt":0.432158857636875,"spread":0.4011860963335165,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.004856572,0.0004220609,0.0005291502,0.0004464129,0.0002975305,0.000392742,0.001384207,0.0003626852,0.00001950848],"category_scores_gemma":[0.00204283,0.000337727,0.0001418259,0.002669525,0.0001359076,0.001050989,0.0003457964,0.002300357,0.000004005172],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002238628,"about_ca_system_score_gemma":0.00009313132,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003461298,"about_ca_topic_score_gemma":0.00002543105,"domain_scores_codex":[0.9959212,0.0006721996,0.0008047706,0.0009609296,0.0005961786,0.001044721],"domain_scores_gemma":[0.9980228,0.001003384,0.0002790694,0.0003666367,0.0001177381,0.0002104002],"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":[0.00002120544,0.00005338428,0.001053834,0.00006156891,0.000005393103,0.0001588641,0.004527202,0.000005502975,0.03736677,0.0004306199,0.00004285713,0.9562728],"study_design_scores_gemma":[0.003613478,0.0006681345,0.002992485,0.00200626,0.00008229982,0.0008181951,0.004203029,0.5684596,0.352326,0.04227624,0.01679784,0.005756494],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005569072,0.08944771,0.9010648,0.0008905859,0.0001961869,0.0001806129,5.162717e-7,0.001199808,0.001450706],"genre_scores_gemma":[0.4406113,0.000005378838,0.5584958,0.0005844925,0.00008601,0.000006739045,0.000004749328,0.00002167986,0.0001838707],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9505163,"threshold_uncertainty_score":0.9999075,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W34986029","doi":"10.1089/cmb.2021.0438","title":"Exploiting Conversation Structure in Unsupervised Topic Segmentation for Emails","year":2010,"lang":"en","type":"article","venue":"Empirical Methods in Natural Language Processing","topic":"Personal Information Management and User Behavior","field":"Decision Sciences","cited_by":22,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Latent Dirichlet allocation; Computer science; Topic model; Artificial intelligence; Natural language processing; Conversation; Segmentation; Exploit; Market segmentation; Thread (computing); Text segmentation; Information retrieval; Linguistics","retraction":null,"screen_n_in":null,"score":{"opus":0.2587489947827946,"gpt":0.5735565170127669,"spread":0.3148075222299723,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00267462,0.0001363694,0.0002303382,0.0004719557,0.0000935359,0.0003031885,0.0003377939,0.0001201748,0.0001946898],"category_scores_gemma":[0.003359394,0.0001034356,0.00006197851,0.0009179043,0.00003843133,0.001188457,0.00006209467,0.0004227288,0.000004355593],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005938674,"about_ca_system_score_gemma":0.00004177211,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000018322,"about_ca_topic_score_gemma":0.0001885326,"domain_scores_codex":[0.9980823,0.000219152,0.0006463227,0.0003210239,0.0004800114,0.0002512028],"domain_scores_gemma":[0.9984812,0.0009567597,0.000210484,0.0001622052,0.0001409364,0.00004843858],"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":[0.0000345721,0.00001660012,0.03415641,0.00003473535,0.000001615821,0.000003212827,0.01510369,0.00002410936,0.05885969,0.00006713976,0.00005587734,0.8916423],"study_design_scores_gemma":[0.005711562,0.0000951246,0.3952571,0.0001901106,0.00004566216,0.00001544265,0.09290363,0.395819,0.08027226,0.02516065,0.00333476,0.001194628],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9556915,0.0002855244,0.04198299,0.000927624,0.0004877356,0.000400962,0.000005300035,0.00003840705,0.0001799337],"genre_scores_gemma":[0.6626474,5.192638e-7,0.3365772,0.0005134796,0.00007866661,0.0000246687,0.00001789125,0.000006018422,0.0001341133],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8904477,"threshold_uncertainty_score":0.4217983,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3213820586","doi":"","title":"How to Select One Among All? An Extensive Empirical Study Towards the Robustness of Knowledge Distillation in Natural Language Understanding.","year":2021,"lang":"en","type":"article","venue":"Empirical Methods in Natural Language Processing","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo; Queen's University","funders":"","keywords":"Robustness (evolution); Computer science; Adversarial system; Distillation; Artificial intelligence; Machine learning; Benchmark (surveying); Domain knowledge; Natural language; Artificial neural network; Theoretical computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.1018436876354653,"gpt":0.4440969145619636,"spread":0.3422532269264983,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002810686,0.0004113159,0.0007588373,0.0004516329,0.0002164434,0.0004467233,0.001141025,0.0002071784,0.00000732534],"category_scores_gemma":[0.007180945,0.0003079489,0.0001200775,0.003927593,0.000155722,0.001075802,0.0009116746,0.001693806,6.763905e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005647023,"about_ca_system_score_gemma":0.0003197724,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001137195,"about_ca_topic_score_gemma":0.001030266,"domain_scores_codex":[0.9934838,0.003352826,0.0006683785,0.001104063,0.0007057841,0.0006851104],"domain_scores_gemma":[0.9969469,0.001593173,0.0003098342,0.0006558951,0.0003338946,0.0001603305],"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":[0.000234778,0.001084221,0.06356785,0.0002860995,0.0001022507,0.0006473039,0.2178968,0.0150819,0.004791423,0.0001946324,0.00003735459,0.6960754],"study_design_scores_gemma":[0.001233748,0.0001870639,0.1691274,0.0003470544,0.0000536111,0.00004367035,0.04061834,0.7854391,0.001983682,0.0002942358,0.00001911679,0.000653034],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4414481,0.004485593,0.5513006,0.001726963,0.000418104,0.0004351607,0.000001016823,0.0001062832,0.00007819655],"genre_scores_gemma":[0.7291704,0.000001595904,0.2702582,0.0002260201,0.00018634,0.00002286973,0.000008113249,0.00003063695,0.00009588261],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7703572,"threshold_uncertainty_score":0.9999372,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1569397218","doi":"","title":"Utilizing Extra-Sentential Context for Parsing","year":2010,"lang":"en","type":"article","venue":"Empirical Methods in Natural Language Processing","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"","keywords":"Treebank; Parsing; Computer science; Natural language processing; Artificial intelligence; Context (archaeology); Consistency (knowledge bases); Conditional random field; Generative grammar; Set (abstract data type); Feature (linguistics); Linguistics; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.05448447238682705,"gpt":0.4465676489612256,"spread":0.3920831765743986,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00216786,0.0003928923,0.0005089827,0.0004072031,0.000313713,0.0005875306,0.00153366,0.0003363698,0.000014883],"category_scores_gemma":[0.002845242,0.000329358,0.000193395,0.001083719,0.0001619848,0.001271519,0.0003930228,0.001598802,0.000002843995],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009413638,"about_ca_system_score_gemma":0.0001674274,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003961436,"about_ca_topic_score_gemma":0.0000646707,"domain_scores_codex":[0.9968623,0.0002941127,0.0006564897,0.00095568,0.0003851508,0.0008462884],"domain_scores_gemma":[0.997816,0.0009231498,0.0002824934,0.0005786067,0.000233857,0.0001659339],"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":[0.00002727172,0.00004956289,0.0002187799,0.0001057461,0.000005567016,0.00003545203,0.002102491,4.562685e-7,0.1366746,0.002110929,0.00008523027,0.8585839],"study_design_scores_gemma":[0.002276807,0.0001603762,0.0005568934,0.000752644,0.00005145219,0.0004415581,0.001690784,0.4262227,0.4972451,0.06125576,0.00730732,0.00203869],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01091721,0.03161757,0.953011,0.001395889,0.001335166,0.0005003957,0.000002627256,0.0009325986,0.0002875288],"genre_scores_gemma":[0.4470566,0.0000022803,0.5517959,0.0008094808,0.0001932852,0.00004418857,0.000003827702,0.00002604343,0.00006844875],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8565452,"threshold_uncertainty_score":0.9999158,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3089160253","doi":"","title":"Semantic Similarity Frontiers: From Concepts to Documents","year":2015,"lang":"en","type":"article","venue":"Empirical Methods in Natural Language Processing","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Semantic similarity; Similarity (geometry); Semantics (computer science); Natural language processing; Information retrieval; Sentence; SemEval; Artificial intelligence; Word (group theory); Semantic computing; Component (thermodynamics); Semantic Web; Linguistics","retraction":null,"screen_n_in":null,"score":{"opus":0.07529857966887143,"gpt":0.4671359010380242,"spread":0.3918373213691527,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00126334,0.0002144853,0.0003662659,0.000171694,0.00006934028,0.0002908559,0.001042906,0.0001314226,0.00000747528],"category_scores_gemma":[0.001594405,0.0001827501,0.00005534931,0.0007823197,0.00003590989,0.0007759496,0.0005698829,0.0005199993,0.00001471375],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002055264,"about_ca_system_score_gemma":0.0001371715,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002315057,"about_ca_topic_score_gemma":0.00002187835,"domain_scores_codex":[0.9974476,0.0005518741,0.0003959787,0.0007059301,0.0004431284,0.0004555464],"domain_scores_gemma":[0.9988149,0.0002237542,0.00009846788,0.000483926,0.0001016344,0.0002772476],"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":[0.00001986182,0.00004386618,0.005573899,0.00002163697,0.000009660027,0.00009224698,0.0189201,0.0002143918,0.001169386,0.00005360104,0.0008722548,0.9730091],"study_design_scores_gemma":[0.00128963,0.00006346596,0.002925541,0.0002598941,0.00001770892,0.00001515681,0.002165546,0.9583789,0.007329362,0.02333709,0.003428039,0.0007897062],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04856025,0.01069447,0.9368423,0.001973785,0.001045849,0.0001822592,0.000001238725,0.0001946557,0.0005051718],"genre_scores_gemma":[0.3486829,9.403016e-7,0.6490756,0.001987621,0.0001281952,0.000008671129,0.000001816768,0.000009349011,0.0001048853],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9722194,"threshold_uncertainty_score":0.7452333,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2186073939","doi":"","title":"Sentiment Analysis of Social Media Texts","year":2014,"lang":"en","type":"article","venue":"Empirical Methods in Natural Language Processing","topic":"Sentiment Analysis and Opinion Mining","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"SemEval; Computer science; Sentiment analysis; Negation; Lexicon; Task (project management); Artificial intelligence; Natural language processing; Focus (optics); Social media; Scope (computer science); World Wide Web","retraction":null,"screen_n_in":null,"score":{"opus":0.03825425648608814,"gpt":0.4293544643095399,"spread":0.3911002078234517,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001813758,0.0001533546,0.0005396386,0.0007432697,0.00008912983,0.00010529,0.0005673915,0.00008619641,0.00005664415],"category_scores_gemma":[0.0005983587,0.0001230341,0.0002455947,0.003572401,0.00005332624,0.0002569276,0.0002214588,0.0002371344,0.000002752689],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004256527,"about_ca_system_score_gemma":0.00002633367,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007165239,"about_ca_topic_score_gemma":0.00001226825,"domain_scores_codex":[0.9977928,0.0005859751,0.0005040034,0.0004239102,0.0004108794,0.0002823804],"domain_scores_gemma":[0.9986097,0.0007483925,0.0002617724,0.0002430466,0.00007882484,0.00005832591],"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":[0.000005943334,0.00006576365,0.005233546,0.00002466891,0.0001486065,0.000004220957,0.01517476,0.00008067155,0.004120231,0.0007277371,0.00004999362,0.9743639],"study_design_scores_gemma":[0.0003482107,0.00001397152,0.0502922,0.00003640064,0.0002608753,0.000001169021,0.0006169374,0.9376463,0.009434585,0.0005876841,0.0004716423,0.0002899791],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08146571,0.003887133,0.9124312,0.0006482418,0.0002924187,0.000064904,9.274559e-7,0.00008731833,0.001122114],"genre_scores_gemma":[0.5682076,9.369114e-7,0.4314898,0.0001829256,0.00006287398,0.000002334578,0.000004971203,0.000004514196,0.00004407],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9740739,"threshold_uncertainty_score":0.5017185,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3088099248","doi":"","title":"Memory Augmented Neural Networks for Natural Language Processing","year":2017,"lang":"en","type":"article","venue":"Empirical Methods in Natural Language Processing","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Montréal","funders":"","keywords":"Computer science; Artificial intelligence; Artificial neural network; Scalability; Set (abstract data type); Focus (optics); Auxiliary memory; Deep learning; Machine learning; Theoretical computer science; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.04028696249901548,"gpt":0.4603588160291883,"spread":0.4200718535301728,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001689604,0.0004311321,0.000532785,0.0002438282,0.00117508,0.001214471,0.002526447,0.0002219427,0.000007850549],"category_scores_gemma":[0.00282198,0.0003614298,0.0001772822,0.0005634868,0.0001901236,0.001342225,0.0007465034,0.001446939,0.000003457629],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001652821,"about_ca_system_score_gemma":0.0001089735,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002217375,"about_ca_topic_score_gemma":0.00004844307,"domain_scores_codex":[0.9966563,0.0004407523,0.0005958211,0.001053883,0.0003821896,0.0008710735],"domain_scores_gemma":[0.9972156,0.0007166532,0.0006053072,0.001107346,0.0001799636,0.0001751758],"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":[0.0000356622,0.00005911157,0.00121685,0.0001284018,0.000009368355,0.00002934985,0.003517116,0.0007393339,0.003106517,0.00004128214,0.0000442566,0.9910728],"study_design_scores_gemma":[0.0008557303,0.00003031981,0.01832401,0.0001443246,0.00001758863,0.00003622402,0.0003009897,0.9780121,0.00145895,0.000221578,0.0001255131,0.0004726028],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.05030762,0.0272004,0.9156943,0.004002791,0.0008103686,0.0008172406,0.000003127824,0.0006191671,0.0005449879],"genre_scores_gemma":[0.5435899,0.000001512329,0.4551488,0.0006434617,0.0002728008,0.0001014854,0.00001084881,0.00003107774,0.0002000969],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9906002,"threshold_uncertainty_score":0.9998838,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2252227670","doi":"","title":"Resolving “This-issue†Anaphora","year":2012,"lang":"en","type":"article","venue":"Empirical Methods in Natural Language Processing","topic":"Syntax, Semantics, Linguistic Variation","field":"Arts and Humanities","cited_by":0,"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":"Anaphora (linguistics); Computer science; Natural language processing; Artificial intelligence; Resolution (logic)","retraction":null,"screen_n_in":null,"score":{"opus":0.07225211446287715,"gpt":0.4151775315217796,"spread":0.3429254170589024,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001836411,0.0002373993,0.0003414143,0.0002562098,0.0002882932,0.0002543752,0.0002443767,0.0001195125,0.0006019328],"category_scores_gemma":[0.003381843,0.0001951112,0.00007790263,0.0002048081,0.0001389586,0.0005010242,0.0001072464,0.0005965248,0.00003855746],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001381572,"about_ca_system_score_gemma":0.00004317057,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004511582,"about_ca_topic_score_gemma":0.0002237568,"domain_scores_codex":[0.9978594,0.0004370737,0.0004834016,0.0003119479,0.0003006622,0.0006074994],"domain_scores_gemma":[0.9986997,0.0006288862,0.0001952308,0.0002259825,0.0001341243,0.0001160496],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.00005009808,0.0001492147,0.006383854,0.0002717145,0.00002852806,0.00003383813,0.5361682,0.000003586169,0.00184677,0.02849056,0.0003069606,0.4262666],"study_design_scores_gemma":[0.004742533,0.0003361872,0.03632319,0.003238111,0.0006290154,0.0001912684,0.3644049,0.07727357,0.02532265,0.1737414,0.3069191,0.00687808],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5104458,0.1779156,0.1170884,0.03939846,0.02471567,0.001716356,0.00003433704,0.001995421,0.1266899],"genre_scores_gemma":[0.7111987,0.000003530713,0.2846829,0.0005899086,0.002513903,0.00001034777,0.000009310981,0.00003333701,0.0009580393],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4193886,"threshold_uncertainty_score":0.7956405,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3044276988","doi":"","title":"Low-Resource Neural Network Modelling for Universal Dependency Parsing","year":2015,"lang":"en","type":"article","venue":"Empirical Methods in Natural Language Processing","topic":"Neural Networks and Applications","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of New Brunswick","funders":"","keywords":"Computer science; Parsing; Dependency grammar; Dependency (UML); Artificial neural network; Artificial intelligence; Resource (disambiguation); Natural language processing; Computer network","retraction":null,"screen_n_in":null,"score":{"opus":0.07949367515106834,"gpt":0.4100113437268794,"spread":0.330517668575811,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001066201,0.0002145534,0.0002828628,0.0000964081,0.0002208532,0.0002361136,0.0007874848,0.0001199377,0.000001284943],"category_scores_gemma":[0.0001648544,0.0001844408,0.00009287571,0.001044952,0.00004953751,0.0005926299,0.0002498645,0.0005106644,0.000001511681],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001074192,"about_ca_system_score_gemma":0.00009743714,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001283033,"about_ca_topic_score_gemma":0.000006666765,"domain_scores_codex":[0.997931,0.0002897341,0.0003536237,0.0005713038,0.0002456333,0.0006086953],"domain_scores_gemma":[0.9986542,0.0005914646,0.0001436892,0.0003164658,0.0001005286,0.0001936485],"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":[0.00003241791,0.00004328811,0.0001356524,0.00003394744,0.000004607319,0.00002325618,0.001937942,0.2058351,0.0003196402,0.0009405983,0.0004197489,0.7902738],"study_design_scores_gemma":[0.0003823302,0.00003003355,0.00001922527,0.00007589812,0.000007615041,0.00002026706,0.0002305194,0.9885294,0.0005926422,0.008215018,0.00164478,0.0002522508],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0116349,0.007694722,0.9782944,0.001245388,0.0002923324,0.0002874044,8.492706e-7,0.000210631,0.0003394209],"genre_scores_gemma":[0.3641905,0.000001947147,0.634731,0.0006394839,0.0003173522,0.00001893879,0.00000390893,0.00001533882,0.0000815909],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7900215,"threshold_uncertainty_score":0.7521278,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2996912688","doi":"","title":"Discreteness in Neural Natural Language Processing","year":2019,"lang":"en","type":"article","venue":"Empirical Methods in Natural Language Processing","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Artificial intelligence; Artificial neural network; Focus (optics); Process (computing); Point (geometry); Space (punctuation); Natural language processing; Natural language; Machine learning; Programming language; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.03199366781166351,"gpt":0.4167666648137828,"spread":0.3847729970021193,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001600486,0.0004258492,0.0006324568,0.0004980108,0.0001106518,0.000444901,0.001488034,0.0002222826,0.00002219571],"category_scores_gemma":[0.0006899273,0.0003442243,0.0001232981,0.001894685,0.00007012305,0.001743932,0.0006413469,0.001553838,0.00001298266],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002477734,"about_ca_system_score_gemma":0.0001729922,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001199366,"about_ca_topic_score_gemma":0.00008135447,"domain_scores_codex":[0.9959178,0.0006814858,0.0007464127,0.001149494,0.0005623692,0.0009424483],"domain_scores_gemma":[0.9984743,0.0004317101,0.0002355022,0.0006461782,0.00008440309,0.0001279321],"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":[0.00002638449,0.00004388447,0.01016629,0.0002462309,0.000003446771,0.0001732388,0.01220056,0.000360352,0.01052344,0.00005713252,0.000003852527,0.9661952],"study_design_scores_gemma":[0.0007710177,0.00002485557,0.008908586,0.0003841771,0.000005308407,0.00006876692,0.001637487,0.9842237,0.003016985,0.0003359645,0.0000598391,0.0005633407],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.698521,0.06723304,0.2293354,0.001542359,0.001295279,0.0005659743,0.000001256894,0.0004608353,0.001044897],"genre_scores_gemma":[0.6051608,0.000002121472,0.3936971,0.0007247521,0.0001142714,0.00001633198,0.000003593947,0.00002486295,0.0002561848],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9838633,"threshold_uncertainty_score":0.999901,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}