{"meta":{"query_hash":"20522714e91c","filters":{"venue":"Findings of the Association for Computational Linguistics: ACL 2022"},"cohort_total":9,"direct_labels_cover":0,"predictions_cover":9,"exported":9,"export_cap":100000,"truncated":false,"label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"permalink":"https://metacan.xera.ac/q/20522714e91c","api":"https://metacan.xera.ac/api/v1/cohort?venue=Findings+of+the+Association+for+Computational+Linguistics%3A+ACL+2022"},"results":[{"id":"W3205231356","doi":"10.18653/v1/2022.findings-acl.135","title":"Morphosyntactic Tagging with Pre-trained Language Models for Arabic and its Dialects","year":2022,"lang":"en","type":"article","venue":"Findings of the Association for Computational Linguistics: ACL 2022","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"York University; New York University Abu Dhabi","keywords":"Transformer; Arabic; Computer science; Modern Standard Arabic; Natural language processing; Artificial intelligence; Language model; Training set; Resource (disambiguation); Linguistics; Engineering; Voltage","score_opus":0.008924129542520672,"score_gpt":0.25229433331955636,"score_spread":0.2433702037770357,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3205231356","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06648106,0.0013763056,0.92341477,0.002836395,0.0013396735,0.002644379,0.0010372485,0.000498022,0.00037214832],"genre_scores_gemma":[0.8595336,0.0000010287372,0.13939787,0.00025809853,0.000094346404,0.00013717749,0.00006717026,0.000017893914,0.00049279095],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986441,0.000056143577,0.0002474711,0.00028892778,0.00054736953,0.00021596454],"domain_scores_gemma":[0.9976488,0.0011027101,0.00051466434,0.00013973915,0.00056158425,0.000032538872],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00070767215,0.00012720261,0.00018524974,0.00013214919,0.0005454268,0.00009623699,0.0006181544,0.0000414701,0.0000033142385],"category_scores_gemma":[0.0028094847,0.00011091578,0.000082217965,0.0003407768,0.000015017933,0.00012712076,0.00031827186,0.00018195361,1.99851e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016146513,0.00013675142,0.0011282295,0.00026973154,0.00019304836,0.0000025368092,0.0044463435,0.100710005,0.0014401323,0.88836485,0.0024703592,0.0006765378],"study_design_scores_gemma":[0.00087558525,0.00021910177,0.0005516494,0.00004449783,0.00006236912,0.0000073419387,0.000061952764,0.7444204,0.0028670738,0.24957278,0.0010701776,0.00024707287],"about_ca_topic_score_codex":0.000011996505,"about_ca_topic_score_gemma":0.0000024604208,"teacher_disagreement_score":0.79305255,"about_ca_system_score_codex":0.00031973617,"about_ca_system_score_gemma":0.0001520891,"threshold_uncertainty_score":0.45230144},"labels":[],"label_agreement":null},{"id":"W3206786886","doi":"10.18653/v1/2022.findings-acl.316","title":"Zero-Shot Dense Retrieval with Momentum Adversarial Domain Invariant Representations","year":2022,"lang":"en","type":"article","venue":"Findings of the Association for Computational Linguistics: ACL 2022","topic":"Domain Adaptation and Few-Shot Learning","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Invariant (physics); Classifier (UML); Source code; Embedding; Adversarial system; Artificial intelligence; Encoder; Autoencoder; Theoretical computer science; Pattern recognition (psychology); Algorithm; Deep learning; Mathematics","score_opus":0.01593641139419208,"score_gpt":0.2523305473785822,"score_spread":0.2363941359843901,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3206786886","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03454777,0.00005693357,0.9366372,0.0078101507,0.007041763,0.0021382126,0.00091393647,0.00030736832,0.010546656],"genre_scores_gemma":[0.92929757,0.0000013642722,0.065618955,0.0005569895,0.00025884307,0.000064139465,0.00027402226,0.000029110868,0.003898984],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9970789,0.00026836057,0.000520206,0.00041030245,0.001420644,0.0003015837],"domain_scores_gemma":[0.9965203,0.0013754275,0.0008927069,0.00031481238,0.0008246159,0.000072152696],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015087691,0.00016307314,0.00023090691,0.00021074786,0.0011736626,0.00015149168,0.0009229237,0.000053935048,0.00007037628],"category_scores_gemma":[0.0030911283,0.00015557633,0.00017962206,0.0009180433,0.0000459853,0.00011440439,0.00051890255,0.0003389961,0.000008750399],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023443626,0.00016736897,0.0074687214,0.000020675274,0.00021518697,0.0000034092689,0.0022305606,0.38218158,0.00024332179,0.59005463,0.01713188,0.00004820948],"study_design_scores_gemma":[0.007911782,0.00081276515,0.036801033,0.000053951462,0.00019185863,0.000028885996,0.0013248007,0.39092365,0.00061531353,0.3293136,0.23107798,0.0009443933],"about_ca_topic_score_codex":0.000023180024,"about_ca_topic_score_gemma":0.0000027878477,"teacher_disagreement_score":0.8947498,"about_ca_system_score_codex":0.0006752394,"about_ca_system_score_gemma":0.0004108189,"threshold_uncertainty_score":0.9026982},"labels":[],"label_agreement":null},{"id":"W4226145103","doi":"10.18653/v1/2022.findings-acl.326","title":"On the data requirements of probing","year":2022,"lang":"en","type":"article","venue":"Findings of the Association for Computational Linguistics: ACL 2022","topic":"Topic Modeling","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vector Institute; University of Toronto","funders":"","keywords":"Computer science; Reliability (semiconductor); Context (archaeology); Construct (python library); Data mining; Machine learning; Artificial intelligence; Power (physics)","score_opus":0.054162738601187525,"score_gpt":0.291028757242492,"score_spread":0.23686601864130447,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4226145103","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17012796,0.00015432049,0.77274746,0.018288042,0.016840499,0.004351182,0.0044061868,0.0002535122,0.012830813],"genre_scores_gemma":[0.9873166,3.8247344e-7,0.011608156,0.00032361972,0.00010990077,0.000026169111,0.00009821661,0.000009006897,0.0005079626],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981132,0.00011557023,0.00039840487,0.00025984648,0.0009631282,0.00014986185],"domain_scores_gemma":[0.99663067,0.0016124519,0.0007406149,0.0005787236,0.00042199934,0.000015529273],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001935687,0.00008009798,0.00013327318,0.000072028524,0.00048067642,0.00003929638,0.0023411985,0.00002351638,0.000019968684],"category_scores_gemma":[0.006392225,0.00006375978,0.00008454422,0.00030891143,0.000017460257,0.00005148807,0.0015131835,0.0001723826,0.0000019444574],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008756242,0.00006504196,0.001995301,0.000016747877,0.00006538478,1.0766505e-7,0.0004120751,0.16443384,0.000045756515,0.82289517,0.009920309,0.00014152758],"study_design_scores_gemma":[0.00039667264,0.00007553019,0.0017809042,0.000025828054,0.000027019452,4.8738286e-7,0.000056443867,0.73764557,0.00023084879,0.24937667,0.010274575,0.00010946109],"about_ca_topic_score_codex":0.000010370341,"about_ca_topic_score_gemma":9.1014243e-7,"teacher_disagreement_score":0.8171886,"about_ca_system_score_codex":0.00027266567,"about_ca_system_score_gemma":0.0001566893,"threshold_uncertainty_score":0.7652552},"labels":[],"label_agreement":null},{"id":"W4280645526","doi":"10.18653/v1/2022.findings-acl.164","title":"Richer Countries and Richer Representations","year":2022,"lang":"en","type":"article","venue":"Findings of the Association for Computational Linguistics: ACL 2022","topic":"Language and cultural evolution","field":"Social Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada; National Science Foundation","keywords":"Embedding; Space (punctuation); Vocabulary; Inequality; Computer science; Word lists by frequency; Word (group theory); Power (physics); Work (physics); Natural language processing; Artificial intelligence; Econometrics; Linguistics; Economics; Mathematics; Engineering","score_opus":0.011301511035746859,"score_gpt":0.2913571103954506,"score_spread":0.28005559935970376,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4280645526","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.77753884,0.0021670866,0.0029631164,0.04112996,0.014243763,0.004831013,0.004846826,0.00044628777,0.15183309],"genre_scores_gemma":[0.9815366,0.000008716802,0.0007078441,0.00042167204,0.0003707726,0.00004840012,0.00011680991,0.000008200016,0.016780932],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99871594,0.00014626535,0.00020430888,0.00013721503,0.00064811023,0.00014818176],"domain_scores_gemma":[0.9983123,0.000684189,0.000310003,0.00006214724,0.00060321734,0.00002813005],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.00089178595,0.000059972142,0.00009939229,0.000045331515,0.001554275,0.000051266925,0.00019022198,0.000041460073,0.00021881987],"category_scores_gemma":[0.0050646365,0.000055186592,0.000081334714,0.00027918644,0.00006393354,0.00004638763,0.00011537827,0.00011510126,0.0000041576636],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000037926453,0.000084157175,0.12740216,0.000023851051,0.00013954936,4.087957e-7,0.01961311,0.014888928,0.000036658414,0.7263254,0.1113366,0.000111275396],"study_design_scores_gemma":[0.00078464614,0.00005572439,0.09726987,0.00001011489,0.00013745725,7.1947545e-7,0.007958835,0.0027797522,0.000039301554,0.11980134,0.7709326,0.00022965207],"about_ca_topic_score_codex":0.00037572146,"about_ca_topic_score_gemma":0.00007615402,"teacher_disagreement_score":0.65959597,"about_ca_system_score_codex":0.00044291565,"about_ca_system_score_gemma":0.00014703046,"threshold_uncertainty_score":0.99974555},"labels":[],"label_agreement":null},{"id":"W4281263937","doi":"10.18653/v1/2022.findings-acl.117","title":"Two-Step Question Retrieval for Open-Domain QA","year":2022,"lang":"en","type":"article","venue":"Findings of the Association for Computational Linguistics: ACL 2022","topic":"Topic Modeling","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Ministry of Science and ICT, South Korea; National Research Foundation of Korea; National Research Foundation","keywords":"Search engine indexing; Inference; Computer science; Information retrieval; Labrador Retriever; Pipeline (software); Squid; Domain (mathematical analysis); Artificial intelligence; Open domain; Question answering; Mathematics; Programming language","score_opus":0.01875750815666395,"score_gpt":0.2925474942045004,"score_spread":0.27378998604783644,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4281263937","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008560319,0.000062652405,0.9779735,0.0029485903,0.005866357,0.0018363356,0.0008311225,0.00009973332,0.0018213921],"genre_scores_gemma":[0.6672058,7.500026e-7,0.32867354,0.0005642948,0.0005328861,0.00014835522,0.0002442392,0.000027528731,0.0026025875],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9978446,0.00016027968,0.0005187328,0.0003884351,0.0008249358,0.00026304025],"domain_scores_gemma":[0.99656105,0.0013927193,0.0007741456,0.0002953341,0.0009346213,0.00004211784],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027521271,0.00013056271,0.0002299901,0.00009888577,0.000883749,0.00017320503,0.0018284892,0.000050035567,0.000015964863],"category_scores_gemma":[0.0055752834,0.00013687527,0.00019035216,0.00040828704,0.000016634982,0.00010122694,0.0011519311,0.00019997114,0.0000027921362],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000053251653,0.00007026852,0.002161713,0.000021358277,0.000055240755,2.1384157e-7,0.00024646753,0.13132982,0.00005418372,0.858124,0.0077114888,0.00017198756],"study_design_scores_gemma":[0.0016430528,0.00014040656,0.0015401655,0.000016410284,0.00003195504,0.0000018744789,0.00005904793,0.5443206,0.00016606034,0.39763418,0.054246284,0.00019996341],"about_ca_topic_score_codex":0.000028965202,"about_ca_topic_score_gemma":0.0000040861637,"teacher_disagreement_score":0.6586455,"about_ca_system_score_codex":0.0008473317,"about_ca_system_score_gemma":0.00029697412,"threshold_uncertainty_score":0.67971724},"labels":[],"label_agreement":null},{"id":"W4285148079","doi":"10.18653/v1/2022.findings-acl.293","title":"Local Structure Matters Most: Perturbation Study in NLU","year":2022,"lang":"en","type":"article","venue":"Findings of the Association for Computational Linguistics: ACL 2022","topic":"Topic Modeling","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Institute for Advanced Research; McGill University; Polytechnique Montréal; Mila - Quebec Artificial Intelligence Institute","funders":"Canada First Research Excellence Fund; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Computer science; Perturbation (astronomy); Word order; Phenomenon; Artificial neural network; Invariant (physics); Artificial intelligence; Natural language processing; Mathematics; Physics","score_opus":0.010150799814172976,"score_gpt":0.24417974456153907,"score_spread":0.2340289447473661,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285148079","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.43826318,0.000066234694,0.5405857,0.007873446,0.008687241,0.0028119015,0.00078585756,0.00017640827,0.00075001945],"genre_scores_gemma":[0.99072874,1.4241152e-7,0.008002929,0.0005906869,0.00010368405,0.00004059561,0.0000646445,0.000011976867,0.0004565819],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980074,0.00014838748,0.0004467425,0.0003124869,0.0008855384,0.00019945129],"domain_scores_gemma":[0.99833447,0.0006135527,0.00043596423,0.0002246009,0.00036657357,0.00002484093],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008035807,0.000114538496,0.00017952199,0.0001791077,0.00035868422,0.00006285012,0.00087670906,0.00004115809,0.000024543642],"category_scores_gemma":[0.0014405487,0.000115122406,0.000084680265,0.000545637,0.0000133648255,0.000063331056,0.00050733925,0.00026377602,0.0000014875052],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014913633,0.00013546631,0.046868596,0.000014510869,0.000044012217,8.918118e-7,0.00228234,0.86793137,0.000018002493,0.08018631,0.0021983406,0.00030524927],"study_design_scores_gemma":[0.0010703804,0.00012199331,0.047833312,0.000009183535,0.00002198444,0.0000015320551,0.00049248437,0.842502,0.000045445147,0.10378275,0.003933719,0.0001852107],"about_ca_topic_score_codex":0.000047216126,"about_ca_topic_score_gemma":0.00001672237,"teacher_disagreement_score":0.55246556,"about_ca_system_score_codex":0.0009062517,"about_ca_system_score_gemma":0.00015638085,"threshold_uncertainty_score":0.46945554},"labels":[],"label_agreement":null},{"id":"W4285152239","doi":"10.18653/v1/2022.findings-acl.225","title":"Extracting Person Names from User Generated Text: Named-Entity Recognition for Combating Human Trafficking","year":2022,"lang":"en","type":"article","venue":"Findings of the Association for Computational Linguistics: ACL 2022","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Samsung; Institut de Valorisation des Données; Canadian Institute for Advanced Research","keywords":"Computer science; Named-entity recognition; Punctuation; Natural language processing; Domain (mathematical analysis); Task (project management); Artificial intelligence; Grammar; Named entity; Information retrieval; Linguistics","score_opus":0.043147769997126245,"score_gpt":0.2892943644149413,"score_spread":0.24614659441781503,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285152239","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5595523,0.00010221086,0.4275176,0.0015056605,0.0059606098,0.0015157479,0.003060806,0.00029570336,0.0004893571],"genre_scores_gemma":[0.94409853,4.2745964e-7,0.05318997,0.00021732596,0.00037099453,0.00009717923,0.0014927072,0.000023250872,0.000509593],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977863,0.00023568531,0.0005429546,0.0004009484,0.00073598715,0.00029812596],"domain_scores_gemma":[0.99507314,0.002305043,0.0012133471,0.00016713377,0.0011946118,0.00004670422],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.002072914,0.0001621509,0.0002465115,0.00014200086,0.0021716154,0.00021299682,0.0006850574,0.00008834267,0.00005181324],"category_scores_gemma":[0.0072593098,0.0001773106,0.00026197673,0.00044873354,0.000020513306,0.00013817332,0.000240201,0.00035347292,0.0000033481492],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021021617,0.0008247927,0.13740282,0.00027455806,0.0010196292,0.0000025841914,0.013902601,0.4114616,0.0072830366,0.3954584,0.024313517,0.007846281],"study_design_scores_gemma":[0.001885789,0.00016848363,0.018231435,0.000072613955,0.0001351239,0.0000018955612,0.0007752608,0.8964689,0.003433125,0.06324502,0.015057214,0.0005251674],"about_ca_topic_score_codex":0.00005117513,"about_ca_topic_score_gemma":0.000008948737,"teacher_disagreement_score":0.4850073,"about_ca_system_score_codex":0.00057205564,"about_ca_system_score_gemma":0.00015201235,"threshold_uncertainty_score":0.99912745},"labels":[],"label_agreement":null},{"id":"W4285155190","doi":"10.18653/v1/2022.findings-acl.168","title":"Question Generation for Reading Comprehension Assessment by Modeling How and What to Ask","year":2022,"lang":"en","type":"article","venue":"Findings of the Association for Computational Linguistics: ACL 2022","topic":"Topic Modeling","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Reading comprehension; Computer science; Comprehension; Reading (process); Focus (optics); Artificial intelligence; Natural language processing; Mathematics education; Linguistics; Psychology","score_opus":0.02239636680911099,"score_gpt":0.2829373594837503,"score_spread":0.2605409926746393,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285155190","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03809086,0.00007331541,0.9552134,0.0034314708,0.002190955,0.00077823445,0.0001493393,0.000045444853,0.000026945208],"genre_scores_gemma":[0.8495212,0.0000054733473,0.14907618,0.00041942496,0.00025584898,0.00013827236,0.0002700254,0.00001579678,0.00029779068],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9982722,0.00011265652,0.00034540525,0.0003918821,0.00067320623,0.00020469603],"domain_scores_gemma":[0.9980315,0.0005873343,0.00037885417,0.00018330854,0.0007699325,0.000049053964],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013840517,0.00012577027,0.00018874541,0.00012767003,0.000818965,0.00037726114,0.000422081,0.00004999765,0.0000019379856],"category_scores_gemma":[0.0014747554,0.00013358661,0.00009540474,0.00021845869,0.0000071900795,0.00023660035,0.00040478713,0.00014455045,3.1933072e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010405208,0.00003879185,0.0007179411,0.000025745167,0.00003620726,6.431815e-8,0.00039291047,0.80537236,0.0013982065,0.18576851,0.0050399816,0.0011988952],"study_design_scores_gemma":[0.00041649878,0.00009218402,0.00021158127,0.000022710143,0.000023190276,8.036712e-7,0.00010223057,0.97108704,0.00019776482,0.02127923,0.0064270697,0.00013967876],"about_ca_topic_score_codex":0.000013545341,"about_ca_topic_score_gemma":0.0000018597591,"teacher_disagreement_score":0.81143034,"about_ca_system_score_codex":0.0006711242,"about_ca_system_score_gemma":0.00010438057,"threshold_uncertainty_score":0.62988997},"labels":[],"label_agreement":null},{"id":"W4285255856","doi":"10.18653/v1/2022.findings-acl.177","title":"ChartQA: A Benchmark for Question Answering about Charts with Visual and Logical Reasoning","year":2022,"lang":"en","type":"article","venue":"Findings of the Association for Computational Linguistics: ACL 2022","topic":"Data Visualization and Analytics","field":"Computer Science","cited_by":246,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Question answering; Benchmark (surveying); Vocabulary; Chart; Visual reasoning; Artificial intelligence; Qualitative reasoning; Variety (cybernetics); Natural language processing; Linguistics","score_opus":0.00984609113906177,"score_gpt":0.2772540827683285,"score_spread":0.26740799162926676,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285255856","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.051231354,0.00009587705,0.9426915,0.0013993764,0.0016432581,0.0011545327,0.0011050332,0.00014171156,0.0005373669],"genre_scores_gemma":[0.97387546,0.0000031071359,0.024541767,0.00034128988,0.00019780867,0.000075693584,0.000436613,0.000014894078,0.00051339157],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99859494,0.00006930058,0.00030311814,0.00028631618,0.00055235677,0.00019394698],"domain_scores_gemma":[0.9980562,0.00072964036,0.0004786123,0.00011291611,0.0005785397,0.000044133914],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009637872,0.00011435193,0.00017905184,0.00010721139,0.00070209097,0.00012803577,0.0003711482,0.000037958478,0.000009585857],"category_scores_gemma":[0.002997548,0.00010330335,0.000079649624,0.00032876385,0.000026247233,0.00008537086,0.00029568985,0.00011963167,6.0289915e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006087657,0.00013689988,0.03254679,0.00006951487,0.000105528576,6.297278e-7,0.00060275535,0.043048702,0.00004593078,0.9187155,0.004246948,0.0004199284],"study_design_scores_gemma":[0.0010522482,0.00033597133,0.02319528,0.000048347385,0.0000535307,0.000004370799,0.00007413731,0.9250005,0.00010079757,0.017291093,0.032619264,0.00022444437],"about_ca_topic_score_codex":0.000005535547,"about_ca_topic_score_gemma":0.0000021386113,"teacher_disagreement_score":0.9226441,"about_ca_system_score_codex":0.00021144107,"about_ca_system_score_gemma":0.000107505395,"threshold_uncertainty_score":0.5399987},"labels":[],"label_agreement":null}]}