{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":19,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":19,"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":"b4e2a36aa5f9","filters":{"venue":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing"}},"results":[{"id":"W3152698349","doi":"10.18653/v1/2021.emnlp-main.230","title":"Masked Language Modeling and the Distributional Hypothesis: Order Word Matters Pre-training for Little","year":2021,"lang":"en","type":"article","venue":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing","topic":"Topic Modeling","field":"Computer Science","cited_by":182,"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; Word (group theory); Natural language processing; Artificial intelligence; Word order; Language model; Downstream (manufacturing); Order (exchange); Parametric statistics; Linguistics; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.07636691541448742,"gpt":0.3862203416242639,"spread":0.3098534262097765,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001870851,0.0002261407,0.0004033016,0.00007884572,0.0002148773,0.0003685529,0.0009118242,0.0001115139,0.000007884013],"category_scores_gemma":[0.004471921,0.0001377908,0.0001166379,0.0007115842,0.0001589739,0.0003659466,0.0004990299,0.0005436991,3.208969e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006224908,"about_ca_system_score_gemma":0.0002046844,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001425403,"about_ca_topic_score_gemma":0.000003758969,"domain_scores_codex":[0.997997,0.0001289172,0.0004594805,0.0005843429,0.0004390718,0.0003911924],"domain_scores_gemma":[0.998121,0.0008075233,0.0002324658,0.000234176,0.0005454685,0.00005938307],"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":[0.0002065022,0.00007319539,0.0002971615,0.0004367492,0.00004784437,0.000004518339,0.03589173,0.0003752779,0.03054211,0.02637488,0.00003646452,0.9057136],"study_design_scores_gemma":[0.0008619824,0.0000123253,0.0001628048,0.0005348476,0.00002648223,0.00002456478,0.007942137,0.9533445,0.01130675,0.02552713,0.00003071303,0.0002257317],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1890912,0.004977314,0.7662941,0.03801954,0.0003275738,0.0005947074,0.00001068046,0.00007990595,0.0006049736],"genre_scores_gemma":[0.5688958,0.000008683237,0.4300471,0.0007740436,0.00006291036,0.00004386071,0.000001225209,0.000009917489,0.0001564631],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9529693,"threshold_uncertainty_score":0.5618944,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3153046263","doi":"10.18653/v1/2021.emnlp-main.168","title":"Neural Path Hunter: Reducing Hallucination in Dialogue Systems via Path Grounding","year":2021,"lang":"en","type":"article","venue":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing","topic":"Topic Modeling","field":"Computer Science","cited_by":75,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Canadian Institute for Advanced Research; University of Alberta","funders":"Alberta Machine Intelligence Institute; Compute Canada; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Computer science; Path (computing); Security token; Artificial neural network; Focus (optics); Artificial intelligence; Suite; Graph; Deep neural networks; Machine learning; Theoretical computer science; History","retraction":null,"screen_n_in":null,"score":{"opus":0.0556578091105373,"gpt":0.3775607902916954,"spread":0.3219029811811581,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001909389,0.0002865607,0.0005212372,0.0002752946,0.000130574,0.0004588098,0.001145163,0.0001759784,0.000005660553],"category_scores_gemma":[0.001880284,0.0002197513,0.0001028781,0.001572588,0.00006375878,0.0009438494,0.0006116756,0.0009892657,8.689562e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002579718,"about_ca_system_score_gemma":0.0001744536,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001094201,"about_ca_topic_score_gemma":0.00001218186,"domain_scores_codex":[0.9970465,0.0002790141,0.0007640274,0.0008446011,0.0005632493,0.0005026054],"domain_scores_gemma":[0.9984741,0.0002918032,0.0004428079,0.0003007223,0.0004164347,0.0000741248],"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":[0.00002654382,0.0001455218,0.005825401,0.0006139281,0.00001112551,0.00004245437,0.01292047,0.0005030039,0.1266517,0.00657112,0.000007041096,0.8466817],"study_design_scores_gemma":[0.0003732201,0.00003342812,0.003220503,0.001702081,0.00000958943,0.00005473842,0.001976476,0.9759703,0.01361846,0.002732117,0.000008144219,0.0003009192],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.62996,0.008041443,0.3524436,0.003554706,0.002097578,0.0006535067,0.000002554086,0.0001463469,0.003100298],"genre_scores_gemma":[0.7652932,0.00001491378,0.234324,0.0001558667,0.000101092,0.00002459328,0.000001254603,0.00001477093,0.00007029976],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9754673,"threshold_uncertainty_score":0.8961197,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3214455632","doi":"10.18653/v1/2021.emnlp-main.77","title":"Contextualized Query Embeddings for Conversational Search","year":2021,"lang":"en","type":"article","venue":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing","topic":"Topic Modeling","field":"Computer Science","cited_by":41,"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; Canada First Research Excellence Fund","keywords":"Computer science; Leverage (statistics); Inference; Security token; Relevance (law); Pipeline (software); Information retrieval; Query expansion; Query language; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.092333595524727,"gpt":0.4395395092037929,"spread":0.3472059136790658,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001528358,0.0002092998,0.000406463,0.0001410444,0.0001425354,0.0002663512,0.001095299,0.0001382064,0.00003392003],"category_scores_gemma":[0.002933444,0.0001554843,0.0001574349,0.0008547008,0.0001143692,0.0004999717,0.0004836491,0.000560144,0.00000127803],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000109687,"about_ca_system_score_gemma":0.0004046171,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001117802,"about_ca_topic_score_gemma":0.000002822563,"domain_scores_codex":[0.9978356,0.0001133703,0.0004976453,0.0006551637,0.0005029588,0.000395313],"domain_scores_gemma":[0.9978395,0.0006282433,0.0002411876,0.0002224463,0.0009941956,0.00007447814],"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":[0.0001031106,0.000139312,0.001474496,0.000526541,0.00003350245,0.000006205812,0.01286653,0.00003979215,0.1856029,0.09630091,0.0001195604,0.7027871],"study_design_scores_gemma":[0.001147327,0.00004950101,0.0006241996,0.0007332677,0.00001815083,0.00002719991,0.004115626,0.6975945,0.2719545,0.02313994,0.0002231293,0.0003726969],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1644545,0.004331561,0.8044723,0.01841967,0.0009631083,0.0009185073,0.00001029069,0.000147779,0.006282305],"genre_scores_gemma":[0.5235511,0.000006272351,0.4754031,0.0005803296,0.00005810444,0.00002474042,0.00000114491,0.000009250772,0.0003659665],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7024144,"threshold_uncertainty_score":0.6340467,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3203338521","doi":"10.18653/v1/2021.emnlp-main.328","title":"Language-Aligned Waypoint (LAW) Supervision for Vision-and-Language Navigation in Continuous Environments","year":2021,"lang":"en","type":"article","venue":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":39,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"Western Canada Research Grid; Compute Canada; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Waypoint; Computer science; Task (project management); Human–computer interaction; Embodied cognition; Path (computing); Natural language; Work (physics); Measure (data warehouse); Metric (unit); Shortest path problem; Artificial intelligence; Multimedia; Programming language; Real-time computing; Engineering; Theoretical computer science; Database","retraction":null,"screen_n_in":null,"score":{"opus":0.02622123682191114,"gpt":0.3976567197951307,"spread":0.3714354829732195,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001229989,0.0002605593,0.0004338133,0.0001383935,0.0001489283,0.0002317611,0.0007892852,0.0001559829,0.00001162535],"category_scores_gemma":[0.001561126,0.0001927003,0.0001004442,0.0007765341,0.0001233186,0.0004354326,0.0005507428,0.000525122,0.000001772367],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001040568,"about_ca_system_score_gemma":0.00007817574,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000150018,"about_ca_topic_score_gemma":0.00001434211,"domain_scores_codex":[0.9978101,0.0001658942,0.0005381184,0.0007474286,0.0003774822,0.0003609932],"domain_scores_gemma":[0.9986753,0.0005018642,0.0002943062,0.0002911235,0.0001597719,0.00007767023],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003682004,0.0001605095,0.001671973,0.0002278211,0.000007340699,0.000006621366,0.01576307,0.00001783308,0.4991747,0.006088323,0.000006236454,0.4768388],"study_design_scores_gemma":[0.00189017,0.0001703519,0.02438025,0.001847337,0.0000330355,0.00004782879,0.009068174,0.4867206,0.4641786,0.01088793,0.0001040176,0.0006716737],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9554206,0.003546801,0.03358014,0.00547829,0.0001473571,0.0007318463,0.000006478539,0.00006364192,0.001024921],"genre_scores_gemma":[0.6880661,0.00001122082,0.3114011,0.0003114289,0.00002891671,0.0000620965,0.000005809175,0.00001480376,0.00009858154],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4867028,"threshold_uncertainty_score":0.785809,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4231122779","doi":"10.18653/v1/2021.emnlp-main.288","title":"Automated Generation of Accurate & Fluent Medical X-ray Reports","year":2021,"lang":"en","type":"article","venue":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing","topic":"Topic Modeling","field":"Computer Science","cited_by":38,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Fluency; Embedding; Generator (circuit theory); Transformer; Natural language processing; Artificial intelligence; Information retrieval; Linguistics","retraction":null,"screen_n_in":null,"score":{"opus":0.09840819144765348,"gpt":0.4311545131288209,"spread":0.3327463216811675,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002099289,0.000210727,0.0004511312,0.0001406998,0.0000854824,0.0001536536,0.0009055932,0.0001951491,0.0000552703],"category_scores_gemma":[0.006296829,0.0001474508,0.0001156545,0.001190049,0.0001044897,0.0004301162,0.0006095886,0.0006226657,7.792056e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007274555,"about_ca_system_score_gemma":0.000476146,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001734417,"about_ca_topic_score_gemma":0.00001060311,"domain_scores_codex":[0.9970958,0.0001773294,0.0008771544,0.0006425262,0.0008973333,0.000309829],"domain_scores_gemma":[0.997941,0.0001981262,0.0006099169,0.0003536959,0.0008021703,0.00009508977],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001549944,0.0001884237,0.001650784,0.0003719779,0.00002634293,0.00004410133,0.005228139,0.0002207124,0.5184672,0.003524655,0.0001438938,0.4701182],"study_design_scores_gemma":[0.0002089572,0.00001917606,0.0008382465,0.0007299479,0.00001330646,0.00007523274,0.0003159424,0.7957698,0.1997274,0.002016811,0.00007821244,0.0002070109],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6914437,0.004686092,0.2891923,0.009736587,0.001388772,0.0004262011,0.000001946038,0.0002790397,0.002845421],"genre_scores_gemma":[0.5906454,0.00001305685,0.4089021,0.0002539236,0.00006156299,0.000008629899,0.000001246828,0.000007533083,0.0001065019],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.795549,"threshold_uncertainty_score":0.7538347,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3120832022","doi":"10.18653/v1/2021.emnlp-main.526","title":"Towards Zero-Shot Knowledge Distillation for Natural Language Processing","year":2021,"lang":"en","type":"article","venue":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing","topic":"Topic Modeling","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Distillation; Task (project management); Benchmark (surveying); Artificial intelligence; Knowledge transfer; Natural language processing; Transfer of learning; Domain knowledge; Variety (cybernetics); Shot (pellet); Machine learning; Domain (mathematical analysis); Knowledge management; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.08645918045858457,"gpt":0.4336183586249349,"spread":0.3471591781663503,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00132858,0.0003849658,0.0005906972,0.0002130041,0.0002548936,0.000499028,0.001422153,0.000209614,0.00001240338],"category_scores_gemma":[0.003207074,0.0002803313,0.0002153476,0.001533679,0.0001243279,0.0008338341,0.0006889859,0.000869882,0.000001502009],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001943538,"about_ca_system_score_gemma":0.0005263403,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001261499,"about_ca_topic_score_gemma":0.00001130381,"domain_scores_codex":[0.9970633,0.0001308855,0.0007093885,0.0009708176,0.0005270311,0.0005985322],"domain_scores_gemma":[0.9977541,0.000314502,0.000469534,0.0003396566,0.001018411,0.0001038227],"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":[0.0000367019,0.00009015189,0.0003310889,0.0006037488,0.00001208854,0.000004311628,0.01025128,0.00001530748,0.07508254,0.003835751,0.0000313815,0.9097056],"study_design_scores_gemma":[0.0007611783,0.00005352912,0.001331054,0.001479248,0.00003923463,0.00004027698,0.002960736,0.8170574,0.1661569,0.009350971,0.0001921178,0.0005772885],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1905611,0.05128775,0.7307347,0.008224932,0.002156371,0.00143702,0.00001465273,0.0003926049,0.01519086],"genre_scores_gemma":[0.6142212,0.000008536137,0.3849525,0.0001995598,0.0001300736,0.0000345247,0.000003005717,0.00001990828,0.0004307117],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9091284,"threshold_uncertainty_score":0.9999649,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3200130628","doi":"10.18653/v1/2021.emnlp-main.122","title":"Conditional probing: measuring usable information beyond a baseline","year":2021,"lang":"en","type":"article","venue":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing","topic":"Topic Modeling","field":"Computer Science","cited_by":24,"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; National Science Foundation","keywords":"Baseline (sea); USable; Representation (politics); Computer science; Word (group theory); Property (philosophy); Identity (music); Natural language processing; Artificial intelligence; Speech recognition; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.05992423051901477,"gpt":0.3690637550504681,"spread":0.3091395245314533,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001636078,0.0002062415,0.0003194269,0.0001802948,0.0001520078,0.0003591051,0.0009267881,0.0001171263,0.00003433302],"category_scores_gemma":[0.002299751,0.0001537158,0.00009881689,0.001155187,0.00007211012,0.001596427,0.0004073569,0.0006685505,0.000003507406],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000972817,"about_ca_system_score_gemma":0.0003183481,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007011138,"about_ca_topic_score_gemma":0.000002072315,"domain_scores_codex":[0.9979332,0.0001127577,0.0005825192,0.0004243411,0.0006028978,0.0003443049],"domain_scores_gemma":[0.9983127,0.0002114967,0.0003517098,0.0002215985,0.0008316123,0.00007087248],"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":[0.0000288514,0.0001170812,0.001080561,0.0004767421,0.00001849079,0.000006424037,0.006868131,0.0002631702,0.08288294,0.03435062,0.00007671498,0.8738303],"study_design_scores_gemma":[0.0005747359,0.00002921559,0.0006044231,0.0008219858,0.00001582847,0.00005556452,0.001390572,0.7257151,0.2306124,0.03947164,0.0003370058,0.0003715196],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07204081,0.004151265,0.8936958,0.01162127,0.0007981763,0.000618497,0.000008526075,0.000190671,0.01687493],"genre_scores_gemma":[0.562755,0.00001000793,0.4364134,0.0006235649,0.00005015413,0.0000178486,0.000002746876,0.000006057494,0.0001211819],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8734587,"threshold_uncertainty_score":0.6268346,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3197275000","doi":"10.18653/v1/2021.emnlp-main.181","title":"Unsupervised Conversation Disentanglement through Co-Training","year":2021,"lang":"en","type":"article","venue":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing","topic":"Topic Modeling","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Queen's University","funders":"","keywords":"Conversation; Computer science; Classifier (UML); Session (web analytics); Artificial intelligence; Machine learning; Reinforcement learning; Training set; Speech recognition; World Wide Web","retraction":null,"screen_n_in":null,"score":{"opus":0.1138268762368847,"gpt":0.4306470469350119,"spread":0.3168201706981271,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008683087,0.0002234103,0.0003663537,0.00008999485,0.0001257892,0.0002469372,0.000992402,0.0001086068,0.00004645347],"category_scores_gemma":[0.001101523,0.0001652533,0.0001147455,0.0009596451,0.00009094131,0.0006800954,0.0004149994,0.0005677343,0.000002051733],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00012883,"about_ca_system_score_gemma":0.0002579921,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001142511,"about_ca_topic_score_gemma":0.000003088054,"domain_scores_codex":[0.997815,0.000128023,0.0005064066,0.0006318286,0.0005403863,0.0003783323],"domain_scores_gemma":[0.9988037,0.0002112725,0.0002803793,0.0002625583,0.0003817378,0.0000603353],"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":[0.00002758117,0.0001235977,0.003793812,0.0002957644,0.0000249542,0.00001454093,0.05404985,0.00003052326,0.1551296,0.02097037,0.00004038207,0.7654991],"study_design_scores_gemma":[0.00121523,0.00006481392,0.002415319,0.001437686,0.00003535653,0.00004029653,0.02620299,0.4426259,0.4933661,0.03169112,0.000265792,0.0006394196],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.43537,0.006207095,0.500186,0.02867191,0.001560003,0.0009410989,0.000007579742,0.0002779801,0.02677826],"genre_scores_gemma":[0.607336,0.00001357089,0.3918849,0.0006067611,0.0000510395,0.00001179131,0.000001250987,0.000008463164,0.00008621411],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7648596,"threshold_uncertainty_score":0.6738834,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3213180921","doi":"10.18653/v1/2021.emnlp-main.603","title":"Universal-KD: Attention-based Output-Grounded Intermediate Layer Knowledge Distillation","year":2021,"lang":"en","type":"article","venue":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing","topic":"Topic Modeling","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Layer (electronics); Distillation; Matching (statistics); Interpretability; Projection (relational algebra); Base (topology); Space (punctuation); Architecture; Artificial intelligence; Deep learning; Computer architecture; Machine learning; Algorithm; Mathematics; Nanotechnology; Chromatography; Operating system; Materials science; Chemistry","retraction":null,"screen_n_in":null,"score":{"opus":0.07139261601228206,"gpt":0.3974343703737435,"spread":0.3260417543614614,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008527695,0.0002367561,0.0003583735,0.0001908473,0.0001290096,0.0002700357,0.001021373,0.0001411289,0.00001928073],"category_scores_gemma":[0.001398537,0.0001768341,0.0001441482,0.001190857,0.0001036087,0.0005192872,0.0004914308,0.0006171339,0.000003437983],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001813978,"about_ca_system_score_gemma":0.0003234548,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001192993,"about_ca_topic_score_gemma":0.00001257149,"domain_scores_codex":[0.9979978,0.0001611217,0.0004650662,0.0006452379,0.0003916377,0.0003391556],"domain_scores_gemma":[0.9983684,0.0002990369,0.0003243437,0.0002715064,0.0006595681,0.00007716658],"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":[0.00004430267,0.0001948558,0.005383664,0.0004079418,0.00002625667,0.00001198843,0.00546249,0.00008385377,0.06636719,0.01196829,0.00003621514,0.910013],"study_design_scores_gemma":[0.0007080266,0.00003823698,0.01104244,0.001090848,0.00003204455,0.000009347238,0.001574158,0.9253258,0.05249839,0.007180464,0.0001146685,0.0003856334],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3435652,0.003309703,0.6312937,0.006508523,0.00137135,0.0004401724,0.000004475752,0.0001927762,0.01331412],"genre_scores_gemma":[0.7555471,0.000004856316,0.2437306,0.0001727623,0.00006304575,0.000007893663,0.000001577716,0.00001124146,0.0004609142],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9252419,"threshold_uncertainty_score":0.7211084,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3209039755","doi":"10.18653/v1/2021.emnlp-main.821","title":"IndoNLI: A Natural Language Inference Dataset for Indonesian","year":2021,"lang":"en","type":"article","venue":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing","topic":"Topic Modeling","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Universitas Indonesia; York University; Samsung; National Science Foundation","keywords":"Annotation; Indonesian; Sentence; Test set; Set (abstract data type); Inference; Data set","retraction":null,"screen_n_in":null,"score":{"opus":0.06648941278896932,"gpt":0.43358885394361,"spread":0.3670994411546407,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001189104,0.00035333,0.0005679241,0.0002156662,0.0001766001,0.0004095632,0.00204899,0.0001911326,0.00001641295],"category_scores_gemma":[0.004242244,0.0002563889,0.0001544448,0.001421815,0.0001262284,0.0008144082,0.001001663,0.001035344,0.000001789162],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001072036,"about_ca_system_score_gemma":0.0003976043,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002483911,"about_ca_topic_score_gemma":0.00002147299,"domain_scores_codex":[0.9971326,0.0001426829,0.0006491729,0.0009387123,0.0005470959,0.0005897254],"domain_scores_gemma":[0.9978175,0.0005991604,0.0004222767,0.0004970225,0.0005575809,0.0001064947],"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":[0.00006070506,0.0001450058,0.001691619,0.0004837433,0.00002523101,0.00001879834,0.007102371,0.00001353722,0.1052891,0.00727343,0.0001371231,0.8777593],"study_design_scores_gemma":[0.001893794,0.0001187055,0.002991418,0.001898179,0.00006099793,0.00009603138,0.006483946,0.657691,0.3147393,0.01225447,0.0006293923,0.001142726],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4812248,0.0240161,0.4641148,0.02112343,0.002969742,0.002420486,0.0002827436,0.000374964,0.003472929],"genre_scores_gemma":[0.5931575,0.00000937684,0.4058751,0.0006722309,0.00008595378,0.00003906156,0.00001948997,0.00001456661,0.000126734],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8766165,"threshold_uncertainty_score":0.9999889,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3200285169","doi":"10.18653/v1/2021.emnlp-main.779","title":"PICARD: Parsing Incrementally for Constrained Auto-Regressive Decoding from Language Models","year":2021,"lang":"en","type":"preprint","venue":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University; University of Toronto","funders":"","keywords":"Computer science; Decoding methods; Parsing; Language model; Natural language processing; Artificial intelligence; Code (set theory); Programming language; Compiler; Algorithm; Set (abstract data type)","retraction":null,"screen_n_in":null,"score":{"opus":0.07064381815737095,"gpt":0.4144700036335565,"spread":0.3438261854761855,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.002074232,0.0009895816,0.001612364,0.000519568,0.0003218084,0.001518421,0.004573331,0.0008734342,0.00002417613],"category_scores_gemma":[0.003512418,0.0007533261,0.0005878755,0.001235644,0.0003693929,0.001215651,0.004061878,0.003076923,5.450121e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005212605,"about_ca_system_score_gemma":0.0009505381,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001812571,"about_ca_topic_score_gemma":0.00002823347,"domain_scores_codex":[0.99413,0.0003214512,0.001414924,0.002082405,0.001084288,0.00096695],"domain_scores_gemma":[0.9949386,0.0009993778,0.001807228,0.0008305313,0.001236328,0.0001878979],"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":[0.0001573801,0.0002309112,0.0002895589,0.001578742,0.0001507389,0.00004285729,0.02253228,0.00007352937,0.2412997,0.004694725,0.00009351339,0.728856],"study_design_scores_gemma":[0.0008674943,0.00007771164,0.00008703404,0.01001715,0.0001438567,0.00002534278,0.004891908,0.5860032,0.317344,0.07935237,0.000008317571,0.001181654],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1111609,0.07104825,0.8051189,0.004927959,0.001763297,0.002864613,0.000145042,0.0008216914,0.002149282],"genre_scores_gemma":[0.4737535,0.00003715678,0.5253844,0.0004296361,0.0001388668,0.0001332786,0.00002539382,0.00004665595,0.00005117034],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7276744,"threshold_uncertainty_score":0.9995181,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3093808828","doi":"10.18653/v1/2021.emnlp-main.740","title":"BARThez: a Skilled Pretrained French Sequence-to-Sequence Model","year":2021,"lang":"en","type":"preprint","venue":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Polytechnique Montréal","funders":"Centre National de la Recherche Scientifique","keywords":"Automatic summarization; Discriminative model; Computer science; Generative grammar; Benchmark (surveying); Transfer of learning; Artificial intelligence; Natural language processing; Sequence (biology); Code (set theory); Generative model; Field (mathematics); Language model; Machine learning; Programming language; Cartography","retraction":null,"screen_n_in":null,"score":{"opus":0.08687262609204593,"gpt":0.4277476868274459,"spread":0.3408750607354,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","scholarly_communication","open_science","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.002793452,0.001150227,0.001672074,0.0008342165,0.0002774275,0.001448615,0.007593039,0.0009976652,0.00003296914],"category_scores_gemma":[0.00664901,0.000843959,0.0005170854,0.003268233,0.0003804595,0.001067605,0.00628146,0.004780704,0.000002847825],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005872741,"about_ca_system_score_gemma":0.001655061,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009818989,"about_ca_topic_score_gemma":0.00002488599,"domain_scores_codex":[0.9927507,0.0003607739,0.001532185,0.002555933,0.001614623,0.001185809],"domain_scores_gemma":[0.9947481,0.0004177414,0.001340405,0.001259966,0.001909174,0.0003246525],"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":[0.00008709292,0.0003692879,0.0003753769,0.00228173,0.00007971298,0.00006905394,0.03018728,0.0005030702,0.2994623,0.006796404,0.0001914751,0.6595972],"study_design_scores_gemma":[0.0004420668,0.0001031796,0.0001176364,0.007939691,0.00006280664,0.00005506111,0.0007920922,0.7507824,0.1646333,0.07368595,0.0000121358,0.00137369],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1406069,0.03566253,0.7881901,0.01985449,0.002325417,0.004801399,0.00009138572,0.001766446,0.006701295],"genre_scores_gemma":[0.4673168,0.00003700615,0.5311901,0.0008659969,0.00008034822,0.0001615142,0.000006192831,0.00004644716,0.0002956625],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7502793,"threshold_uncertainty_score":0.999588,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3211384195","doi":"10.18653/v1/2021.emnlp-main.130","title":"Translation-based Supervision for Policy Generation in Simultaneous Neural Machine Translation","year":2021,"lang":"en","type":"article","venue":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Machine translation; Artificial intelligence; Translation (biology); Security token; Oracle; Reinforcement learning; Heuristic; Action (physics); Inference; Machine learning; Quality (philosophy); Sentence; Natural language processing; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.07715591203049524,"gpt":0.4211824962246504,"spread":0.3440265841941551,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001049592,0.0003052721,0.0004378253,0.0004240292,0.0001390853,0.0002862283,0.0009426899,0.000226107,0.000007409702],"category_scores_gemma":[0.003110882,0.0002284227,0.0001566325,0.002234497,0.00008386987,0.0006805769,0.0001108952,0.0006840932,2.548587e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001659075,"about_ca_system_score_gemma":0.0003734848,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004663869,"about_ca_topic_score_gemma":0.00006829936,"domain_scores_codex":[0.9975741,0.0001765853,0.0006664563,0.0007102178,0.000462753,0.0004098934],"domain_scores_gemma":[0.9979856,0.0008591975,0.0002883534,0.0002352291,0.0005692727,0.00006236022],"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":[0.00005781275,0.00009037625,0.0001965776,0.0002178941,0.000003210317,0.000005160153,0.001818266,0.000377043,0.1831548,0.001133242,0.000003349425,0.8129423],"study_design_scores_gemma":[0.0005604483,0.00005151132,0.00004465067,0.0002986028,0.000008282763,0.000006755138,0.00009840327,0.7843733,0.2090973,0.005218614,0.0000238531,0.0002182646],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04146829,0.05486046,0.8663818,0.03438788,0.0004319056,0.001632315,0.00002328454,0.0003159713,0.0004981517],"genre_scores_gemma":[0.5263477,0.000009176552,0.4731128,0.0004008157,0.00005956931,0.00002852498,0.000008839016,0.00001348211,0.00001907656],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8127241,"threshold_uncertainty_score":0.9314808,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3200853751","doi":"10.18653/v1/2021.emnlp-main.71","title":"Predicting emergent linguistic compositions through time: Syntactic frame extension via multimodal chaining","year":2021,"lang":"en","type":"article","venue":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing","topic":"Language, Metaphor, and Cognition","field":"Psychology","cited_by":6,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Vector Institute; University of Toronto","funders":"Social Sciences and Humanities Research Council of Canada; Natural Sciences and Engineering Research Council of Canada; University of Toronto","keywords":"Computer science; Chaining; Natural language processing; Artificial intelligence; Linguistics; Noun; Psychology","retraction":null,"screen_n_in":null,"score":{"opus":0.05792580951332454,"gpt":0.4257146922206785,"spread":0.3677888827073539,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009603692,0.0003562466,0.0005887008,0.0001527936,0.0003038474,0.0001233318,0.0004369729,0.0002746075,0.0007537924],"category_scores_gemma":[0.00387151,0.0002690683,0.0002133709,0.001095196,0.0001680895,0.000233923,0.0002525434,0.00130101,0.00002180495],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001047441,"about_ca_system_score_gemma":0.0001118875,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008718757,"about_ca_topic_score_gemma":0.000006746299,"domain_scores_codex":[0.9971101,0.000324663,0.0007249986,0.0007983195,0.0004948641,0.0005470917],"domain_scores_gemma":[0.9977543,0.0005586662,0.0005129711,0.0002605934,0.0008179729,0.00009554067],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0003828653,0.0009096667,0.004067584,0.000504387,0.0001675202,0.0001046487,0.06421575,0.0000138318,0.6353359,0.002660943,0.00007870902,0.2915582],"study_design_scores_gemma":[0.005494845,0.0007759967,0.03511653,0.01135119,0.001369935,0.0009419905,0.1027865,0.3068766,0.4796034,0.0521649,0.0003330414,0.003185115],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9302216,0.01102714,0.01338022,0.002268019,0.002273347,0.0007757909,0.00002466494,0.0002195549,0.0398097],"genre_scores_gemma":[0.8924829,0.00001839116,0.1058975,0.0006321503,0.0003078196,0.00005037672,0.00001424616,0.00004150176,0.0005551359],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3068627,"threshold_uncertainty_score":0.9999762,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3201341200","doi":"10.18653/v1/2021.emnlp-main.42","title":"Mitigating Language-Dependent Ethnic Bias in BERT","year":2021,"lang":"en","type":"preprint","venue":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing","topic":"Topic Modeling","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Kootenay Association for Science & Technology","funders":"Ministry of Science and ICT, South Korea; National Research Foundation of Korea; National Research Foundation","keywords":"Categorical variable; Computer science; Ethnic group; German; Turkish; Natural language processing; Metric (unit); Language model; Linguistics; Arabic; Gender bias; Word (group theory); Artificial intelligence; Psychology; Machine learning; Sociology; Social psychology","retraction":null,"screen_n_in":null,"score":{"opus":0.1389738437343006,"gpt":0.44294323317028,"spread":0.3039693894359795,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.00341118,0.0006098373,0.001083116,0.0004929094,0.0001040924,0.0006559828,0.003456197,0.0006001926,0.0000280216],"category_scores_gemma":[0.004886336,0.0004694732,0.000294429,0.001628519,0.0001406528,0.0005375389,0.004271333,0.004159542,0.000001511088],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000362532,"about_ca_system_score_gemma":0.0006179531,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002725924,"about_ca_topic_score_gemma":0.00011052,"domain_scores_codex":[0.9949394,0.0004199713,0.001263432,0.00159534,0.001028883,0.0007529196],"domain_scores_gemma":[0.9971314,0.0005690432,0.0009790106,0.0006969838,0.0005005389,0.000123007],"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":[0.00002406915,0.0001706505,0.00330039,0.001405034,0.00002994481,0.00005567894,0.04818734,0.0003724118,0.0475841,0.0009772104,0.000007799454,0.8978854],"study_design_scores_gemma":[0.0008848872,0.0000528455,0.004773921,0.01255929,0.00005037079,0.00005099981,0.01708641,0.8057991,0.1461475,0.01127354,0.000006764019,0.001314376],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.921169,0.02498014,0.04105638,0.005124675,0.001551102,0.001009563,0.000005599928,0.0001901768,0.004913353],"genre_scores_gemma":[0.6134404,0.00004622275,0.3857994,0.0003651028,0.0001038441,0.00005339186,0.000002216561,0.0000274414,0.0001619281],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.896571,"threshold_uncertainty_score":0.9997757,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3200172683","doi":"10.18653/v1/2021.emnlp-main.516","title":"Mind the Context: The Impact of Contextualization in Neural Module Networks for Grounding Visual Referring Expressions","year":2021,"lang":"en","type":"article","venue":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing","topic":"Multimodal Machine Learning Applications","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"","keywords":"Contextualization; Computer science; Generalization; Context (archaeology); Set (abstract data type); Exploit; Parameterized complexity; Artificial intelligence; Test set; Embedding; Cube (algebra); Machine learning; Algorithm; Mathematics; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.06160955148695172,"gpt":0.4607618939277148,"spread":0.399152342440763,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001587611,0.0002182813,0.0003717706,0.0001176688,0.0002577488,0.0002222773,0.001260813,0.0001150902,0.000008913917],"category_scores_gemma":[0.003504386,0.0001124176,0.0001769391,0.001443013,0.0001589965,0.0003570558,0.0004782177,0.0008295822,1.915006e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001106192,"about_ca_system_score_gemma":0.0001522618,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001790519,"about_ca_topic_score_gemma":0.00003143307,"domain_scores_codex":[0.9980257,0.000286964,0.000576772,0.0004634743,0.0002991046,0.0003480055],"domain_scores_gemma":[0.9972944,0.001368234,0.0005339389,0.0002793272,0.0004793116,0.00004482003],"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":[0.00008803403,0.0001887376,0.01570872,0.000107182,0.00002704742,0.000001112276,0.01397472,0.004712285,0.08177587,0.006997934,0.0000185534,0.8763998],"study_design_scores_gemma":[0.000366586,0.00004520221,0.03191762,0.0004655492,0.00001148016,0.000008360422,0.002586969,0.9513921,0.01176837,0.001292449,0.000006796859,0.000138557],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7771295,0.002388463,0.2157785,0.003402621,0.0001741653,0.0007532968,0.000003456631,0.00002680726,0.0003431587],"genre_scores_gemma":[0.9409637,0.000007461574,0.05866545,0.0001541181,0.0000585635,0.00008852058,0.000002125423,0.00001494994,0.00004506943],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9466798,"threshold_uncertainty_score":0.4584257,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3198457396","doi":"10.18653/v1/2021.emnlp-main.259","title":"Learning from Multiple Noisy Augmented Data Sets for Better Cross-Lingual Spoken Language Understanding","year":2021,"lang":"en","type":"article","venue":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Benchmark (surveying); Focus (optics); Noise (video); Code (set theory); Artificial intelligence; Training set; Machine learning; Spoken language; Resource (disambiguation); Noise reduction; Natural language processing; Speech recognition; Image (mathematics); Set (abstract data type)","retraction":null,"screen_n_in":null,"score":{"opus":0.1489856121254087,"gpt":0.4560963868956432,"spread":0.3071107747702345,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001854907,0.0004763986,0.0006907755,0.0002482856,0.0003758682,0.0009428226,0.003264668,0.0003163807,0.00003166546],"category_scores_gemma":[0.009259205,0.0003598461,0.0001797755,0.001448199,0.0002141622,0.00139279,0.002294722,0.001528368,0.000001662672],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002649171,"about_ca_system_score_gemma":0.0003164459,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006484587,"about_ca_topic_score_gemma":0.00003291322,"domain_scores_codex":[0.9960976,0.0002089891,0.0007934426,0.00145903,0.0007228011,0.0007181902],"domain_scores_gemma":[0.9965478,0.001376985,0.0006789412,0.0006639127,0.0006115467,0.0001208398],"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":[0.0002259188,0.0002145348,0.01199978,0.0006084258,0.00008400754,0.00005283427,0.01433812,0.00001253613,0.2832991,0.001548971,0.0001231851,0.6874926],"study_design_scores_gemma":[0.001700248,0.0001119776,0.001034267,0.002605308,0.0000780221,0.00003666307,0.007955085,0.43087,0.5311243,0.02348682,0.00008126267,0.0009160277],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4408099,0.02410701,0.5258783,0.005320973,0.0009976893,0.0012054,0.0001043915,0.0007135327,0.0008628137],"genre_scores_gemma":[0.5306469,0.00001000721,0.4686252,0.0003963271,0.0001051019,0.00002167561,0.00003827536,0.00002974012,0.0001267683],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6865766,"threshold_uncertainty_score":0.9998854,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3152747197","doi":"10.18653/v1/2021.emnlp-main.234","title":"Linguistic Dependencies and Statistical Dependence","year":2021,"lang":"en","type":"preprint","venue":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing","topic":"Language and cultural evolution","field":"Social Sciences","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":"Dependency (UML); Pointwise mutual information; Pointwise; Computer science; Context (archaeology); Natural language processing; ENCODE; Artificial intelligence; Simple (philosophy); Linguistics; Mathematics; Mutual information; Geography","retraction":null,"screen_n_in":null,"score":{"opus":0.06719722973920086,"gpt":0.4482117086445764,"spread":0.3810144789053755,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001892847,0.0003569592,0.000639284,0.0001284605,0.000368141,0.0005529243,0.0008518521,0.0004958503,0.0001389382],"category_scores_gemma":[0.01334164,0.0002480139,0.0001308474,0.0005971837,0.0006588843,0.0002455554,0.0009597686,0.001956574,0.000001089508],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002309767,"about_ca_system_score_gemma":0.0007049905,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009217671,"about_ca_topic_score_gemma":0.0006288913,"domain_scores_codex":[0.9968927,0.0003652138,0.0005656108,0.0007877686,0.0008700239,0.000518674],"domain_scores_gemma":[0.9978799,0.0004925005,0.0004842958,0.0001712188,0.0008284105,0.0001436615],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"qualitative","study_design_scores_codex":[0.000149063,0.0002362298,0.00712843,0.002092063,0.00007269245,0.00006502424,0.2518945,0.000009264505,0.02132433,0.01874438,0.00009850261,0.6981855],"study_design_scores_gemma":[0.0026278,0.0003799029,0.05597788,0.03053712,0.001220928,0.0001382218,0.6095311,0.05497144,0.06045274,0.1766897,0.001427783,0.006045369],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8854271,0.05347152,0.004001977,0.006066965,0.002364943,0.001720732,0.00005750412,0.0002006584,0.04668859],"genre_scores_gemma":[0.8908983,0.0002990557,0.1077754,0.0002051309,0.0002665179,0.00003345385,0.000006952771,0.0000188002,0.0004963257],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6921402,"threshold_uncertainty_score":0.9999972,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3211439810","doi":"10.18653/v1/2021.emnlp-main.835","title":"Types of Out-of-Distribution Texts and How to Detect Them","year":2021,"lang":"en","type":"article","venue":"Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"York University","keywords":"Computer science; Categorization; Artificial intelligence; Calibration; Natural language processing; Data mining; Statistics; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.0736749441821645,"gpt":0.3899331424867225,"spread":0.316258198304558,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007588257,0.0001359033,0.0003335481,0.00006521167,0.00004254384,0.00008310398,0.0006012589,0.0000874218,0.000005174188],"category_scores_gemma":[0.002204647,0.00009509638,0.00006016432,0.0007099042,0.00007426301,0.0002290641,0.0004827747,0.0002956404,2.720384e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003300538,"about_ca_system_score_gemma":0.0001132238,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004461249,"about_ca_topic_score_gemma":0.000002834814,"domain_scores_codex":[0.9987881,0.00007261799,0.0002790832,0.0003694251,0.0002969694,0.0001938513],"domain_scores_gemma":[0.9988232,0.000199549,0.0002552066,0.0001717785,0.0005013617,0.00004886835],"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":[0.00001725014,0.00002447564,0.000826182,0.0002549466,0.000008080502,0.000001286183,0.00330253,0.000005873067,0.1962206,0.003531967,0.00001048644,0.7957963],"study_design_scores_gemma":[0.0002341944,0.00005779259,0.001770415,0.0009370066,0.00001743144,0.00001687811,0.001105645,0.05909836,0.9247481,0.01177516,0.00004183721,0.0001971791],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5934435,0.004173688,0.3932896,0.006707844,0.0003993262,0.0003216608,0.00000781529,0.00004340883,0.001613192],"genre_scores_gemma":[0.6291451,0.00000731649,0.3707127,0.0000510056,0.00001708511,0.000003390461,2.642273e-7,0.000003796457,0.00005938558],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7955992,"threshold_uncertainty_score":0.3877918,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}