{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":268,"total_is_capped":false,"direct_labels_cover":1,"predictions_cover":268,"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":"f43fd6fb7c73","filters":{"topic":"Text Readability and Simplification"}},"results":[{"id":"W2596405055","doi":"10.1037/pag0000151","title":"The effects of word frequency and word predictability during first- and second-language paragraph reading in bilingual older and younger adults.","year":2017,"lang":"en","type":"article","venue":"Psychology and Aging","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":71,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University; Centre for Research on Brain Language and Music","funders":"Canadian Institutes of Health Research; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs; Centre for Research on Brain, Language and Music","keywords":"Psychology; Word lists by frequency; Reading (process); Word recognition; Word processing; Word (group theory); Predictability; Linguistics; PsycINFO; Audiology; Sentence; Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.006247044410424345,"gpt":0.2715102706400481,"spread":0.2652632262296238,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000532583,0.000105493,0.0001568274,0.00006120869,0.0004590022,0.0001110807,0.0002169256,0.00007739142,0.000001246211],"category_scores_gemma":[0.0002173079,0.00008067704,0.00001466099,0.00006100424,0.0004188832,0.0003676375,0.0001416462,0.0001751183,1.260989e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000005782618,"about_ca_system_score_gemma":0.000007480081,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001241049,"about_ca_topic_score_gemma":0.0005026006,"domain_scores_codex":[0.9990304,0.00008287507,0.0001971019,0.0004399491,0.00005561527,0.0001941185],"domain_scores_gemma":[0.9988955,0.0004080571,0.0001149608,0.0005098651,0.00001718408,0.00005447719],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00003555348,0.00004010785,0.8294478,0.0003533456,0.00001461457,0.00001407946,0.01507629,1.37544e-7,0.005021894,0.001271597,0.000002798931,0.1487218],"study_design_scores_gemma":[0.0006270554,0.00003059399,0.9949765,0.0001344597,0.000004905236,0.00003747172,0.0001586115,0.0001772343,0.0005392057,0.003211602,0.00001654445,0.00008578932],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9941345,0.004352247,0.0002946823,0.0007373168,0.0001507618,0.0002022175,0.000001262741,0.00002087512,0.0001060818],"genre_scores_gemma":[0.9989042,0.0005392247,0.0004575585,0.00004569341,0.00002068851,0.00001250384,3.913936e-7,0.000003542647,0.00001615405],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1655287,"threshold_uncertainty_score":0.3530321,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2291325286","doi":"10.7202/1041023ar","title":"Translation Methods and Experience: A Comparative Analysis of Human Translation and Post-editing with Students and Professional Translators","year":2017,"lang":"en","type":"article","venue":"Meta Journal des traducteurs","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":67,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Keystroke logging; Computer science; Quality (philosophy); Translation (biology); Newspaper; Natural language processing; Machine translation; Eye tracking; Product (mathematics); Human–computer interaction; Artificial intelligence; Multimedia; Advertising","retraction":null,"screen_n_in":null,"score":{"opus":0.1432983315187718,"gpt":0.4373159612485989,"spread":0.294017629729827,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001174241,0.0001553052,0.0004574729,0.0002642712,0.0008776735,0.0004215814,0.0003336154,0.00005218035,0.000005435263],"category_scores_gemma":[0.00002298157,0.000110633,0.00008847346,0.0002524397,0.0004575903,0.00151739,0.0000199652,0.0001843242,3.021455e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009594194,"about_ca_system_score_gemma":0.00002141709,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000395154,"about_ca_topic_score_gemma":0.0001186177,"domain_scores_codex":[0.9984219,0.0003805925,0.0003798424,0.0003132542,0.0003579565,0.0001464318],"domain_scores_gemma":[0.9989675,0.0001652976,0.0003560989,0.0002438164,0.0001391633,0.0001281586],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00009025756,0.0001631029,0.1223031,0.00006688789,0.002106723,0.000003955853,0.07215948,0.00005546943,0.03713952,0.00209542,5.490403e-7,0.7638155],"study_design_scores_gemma":[0.000657137,0.0002267469,0.9847153,0.00003437751,0.00155196,0.00006124951,0.0007851434,0.006708399,0.003153971,0.001894342,0.00005721297,0.000154132],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7972584,0.003089562,0.1991258,0.000303337,0.00003937829,0.0001518618,0.000004577706,0.000009912729,0.00001718812],"genre_scores_gemma":[0.9300503,0.0003006304,0.0696038,0.00001044909,0.0000146501,0.000008421716,0.000002720106,0.000003926462,0.000005140619],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8624122,"threshold_uncertainty_score":0.6750444,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2883325825","doi":"10.1037/xlm0000547","title":"Contributions of reader- and text-level characteristics to eye-movement patterns during passage reading.","year":2018,"lang":"en","type":"article","venue":"Journal of Experimental Psychology Learning Memory and Cognition","topic":"Text Readability and Simplification","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":"McMaster University","funders":"Eunice Kennedy Shriver National Institute of Child Health and Human Development","keywords":"Eye movement; Cognitive psychology; Reading (process); Vocabulary; Cognition; Psychology; Computer science; Psycholinguistics; Reading comprehension; Artificial intelligence; Linguistics","retraction":null,"screen_n_in":null,"score":{"opus":0.02853277318405379,"gpt":0.3342459401356617,"spread":0.3057131669516079,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000422428,0.00009577395,0.0001903615,0.0001327881,0.0001834406,0.00004054976,0.0001278056,0.00007071767,0.00003177965],"category_scores_gemma":[0.00009359732,0.00009163046,0.00003521312,0.00009338789,0.0001200022,0.0002668232,0.00006524591,0.0001907665,0.000005324827],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002778727,"about_ca_system_score_gemma":0.00001341334,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002855428,"about_ca_topic_score_gemma":6.05888e-7,"domain_scores_codex":[0.9989937,0.0001395476,0.0003918245,0.0001986404,0.0001362988,0.0001399952],"domain_scores_gemma":[0.9991853,0.00005562108,0.0003344742,0.000124958,0.0001955882,0.000104124],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.0002171529,0.0002432204,0.006738011,0.00002013913,0.00004386174,0.00001179846,0.004764741,0.000001076076,0.966077,0.0006411282,0.00006228135,0.02117953],"study_design_scores_gemma":[0.001389426,0.001890061,0.5733436,0.0001727467,0.00002701481,0.0002243911,0.001702481,0.0001121512,0.4200414,0.0006186355,0.0003023761,0.0001756826],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9485372,0.00008716964,0.04988424,0.0008735592,0.0002108096,0.0001000944,0.00000939962,0.0000133265,0.0002842226],"genre_scores_gemma":[0.9982645,0.00004274187,0.001131002,0.0003599655,0.0001293158,0.000005014258,0.000003651955,0.00000485406,0.00005893896],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5666056,"threshold_uncertainty_score":0.3736582,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2005151783","doi":"10.1016/j.jslw.2014.03.001","title":"Summary writing in a Thai EFL university context","year":2014,"lang":"en","type":"article","venue":"Journal of Second Language Writing","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":60,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Concordia University","funders":"","keywords":"Paragraph; Copying; Rhetorical question; Appropriation; Computer science; Class (philosophy); Linguistics; Context (archaeology); Second language writing; Academic writing; Psychology; Mathematics education; Artificial intelligence; History; World Wide Web; Second language; Philosophy","retraction":null,"screen_n_in":null,"score":{"opus":0.009962077365459262,"gpt":0.2272621375145557,"spread":0.2173000601490965,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001466756,0.00007507939,0.0001858864,0.0001726314,0.00007334688,0.00008811311,0.0004836088,0.00005289081,0.00004955749],"category_scores_gemma":[0.0001664906,0.00007448118,0.00007600357,0.0002155884,0.00002646114,0.0007523064,0.00008192429,0.0003007667,0.000005255458],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007719698,"about_ca_system_score_gemma":0.00005674355,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004624185,"about_ca_topic_score_gemma":0.0002102966,"domain_scores_codex":[0.9989767,0.0001693696,0.0003741603,0.0001383507,0.0001626362,0.0001787835],"domain_scores_gemma":[0.9989831,0.0003848161,0.0002846313,0.0001924866,0.00008254047,0.00007237521],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00002966256,0.0001313358,0.02243386,0.0001213617,0.00002354131,0.0003754205,0.01617128,0.00006273418,0.02038395,0.0307012,0.0003159121,0.9092497],"study_design_scores_gemma":[0.01167455,0.001211329,0.591598,0.003794798,0.00007410893,0.002835443,0.2471532,0.06963205,0.02437543,0.007141866,0.03830942,0.002199754],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9673544,0.0004370351,0.02656843,0.0004870234,0.00007717778,0.00004285969,0.000001611794,0.00002219209,0.005009231],"genre_scores_gemma":[0.9942454,0.000006968099,0.005183578,0.0003128053,0.0001294445,1.193592e-7,6.967869e-7,0.000004084175,0.0001169179],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.90705,"threshold_uncertainty_score":0.3037255,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3034886066","doi":"10.18653/v1/2020.acl-main.707","title":"Iterative Edit-Based Unsupervised Sentence Simplification","year":2020,"lang":"en","type":"article","venue":"","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":60,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta; University of Waterloo","funders":"Compute Canada; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Computer science; Sentence; Phrase; Artificial intelligence; Simplicity; Natural language processing; Set (abstract data type); Fluency; Word (group theory); Machine learning; Mathematics; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.03701943317026513,"gpt":0.246221930022016,"spread":0.2092024968517509,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001222968,0.0001000324,0.00009842966,0.00003041669,0.00009648412,0.0001544941,0.0006024976,0.00004390069,0.00006272602],"category_scores_gemma":[0.000109899,0.00008690063,0.00004698514,0.0004474459,0.00003713165,0.0005053443,0.00005709776,0.00008576327,0.000250587],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002595071,"about_ca_system_score_gemma":0.00007910819,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000139187,"about_ca_topic_score_gemma":0.000002932726,"domain_scores_codex":[0.9989408,0.00007105617,0.0001989528,0.0004212454,0.0002164007,0.0001515622],"domain_scores_gemma":[0.9991189,0.0001099123,0.00005105812,0.0004445766,0.0001359729,0.0001396069],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006811465,0.0004874137,0.006694167,0.0001331995,0.0000318814,0.00001126887,0.01145383,0.00214002,0.1630706,0.6025634,0.01740251,0.1959436],"study_design_scores_gemma":[0.0003854641,0.0001371391,0.01143833,0.000006772924,0.000004138822,0.000001475443,0.0001329573,0.9174316,0.05407515,0.002194467,0.01392742,0.0002651078],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.008027425,0.00001091388,0.9518311,0.0378824,0.00008882419,0.000185596,0.000002960778,0.0003539341,0.001616872],"genre_scores_gemma":[0.9594853,0.0000011881,0.03444787,0.005896446,0.0000818295,0.00001945979,0.00001478969,0.00000407953,0.0000490311],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9514579,"threshold_uncertainty_score":0.3543705,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2017541092","doi":"10.1145/1090785.1090809","title":"Semantic knowledge in word completion","year":2005,"lang":"en","type":"article","venue":"","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":47,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Natural language processing; Artificial intelligence; Context (archaeology); Semantic similarity; Noun; Semantic compression; Word (group theory); Knowledge base; Semantic computing; Explicit semantic analysis; Semantics (computer science); Rank (graph theory); Information retrieval; Semantic Web; Semantic technology; Linguistics; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.02680282494524568,"gpt":0.2757580693432861,"spread":0.2489552443980404,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002014309,0.000042575,0.00005950514,0.00006440534,0.00002779557,0.00004100361,0.0002670441,0.00002472749,0.00003998158],"category_scores_gemma":[0.000009860139,0.00003822808,0.00001706503,0.0002522817,0.00001370847,0.000281387,0.00005189629,0.00004920724,0.0005058198],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004661835,"about_ca_system_score_gemma":0.00001786642,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003627637,"about_ca_topic_score_gemma":0.0007646286,"domain_scores_codex":[0.9994997,0.00003445292,0.0001269616,0.000167501,0.00006385886,0.0001075472],"domain_scores_gemma":[0.9996167,0.00004472195,0.00001559477,0.0002749613,0.00002175386,0.00002630161],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.000001656723,0.0002280987,0.00453197,0.000009472037,0.000001242332,5.270181e-7,0.001110172,0.0001459678,0.0008724048,0.4317343,0.0009378755,0.5604263],"study_design_scores_gemma":[0.0002877438,0.00002141927,0.5507277,0.00001294921,9.708235e-7,0.000007002038,0.00004340247,0.3840118,0.001602753,0.008356005,0.05475505,0.0001731733],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2439152,0.00005768184,0.7315438,0.004103417,0.00007570125,0.0001054933,1.30348e-7,0.0001566185,0.02004187],"genre_scores_gemma":[0.9774354,0.000002613196,0.02186496,0.000131053,0.00002925106,0.000005105087,0.000001006097,0.000001432391,0.0005291509],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7335202,"threshold_uncertainty_score":0.6501459,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2962986840","doi":"10.18653/v1/n18-2013","title":"Sentence Simplification with Memory-Augmented Neural Networks","year":2018,"lang":"en","type":"preprint","venue":"","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":47,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Microsoft (Canada)","funders":"","keywords":"Computer science; Sentence; Computational linguistics; Natural language processing; Artificial intelligence; Artificial neural network; Volume (thermodynamics); Linguistics; Cognitive science; Psychology; Philosophy","retraction":null,"screen_n_in":null,"score":{"opus":0.0229213919673922,"gpt":0.2520713905550904,"spread":0.2291499985876982,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0003919169,0.0003269623,0.0002797938,0.0001031009,0.0001684659,0.0004521898,0.001779889,0.0002643684,0.0000439138],"category_scores_gemma":[0.00003203792,0.0002558136,0.00008803624,0.0003429181,0.0001671322,0.0003710441,0.0009372996,0.0004796312,0.00005138487],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001118461,"about_ca_system_score_gemma":0.0001155339,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001663487,"about_ca_topic_score_gemma":0.00007810709,"domain_scores_codex":[0.9975178,0.0001363926,0.0004083903,0.00115169,0.0004180004,0.0003677748],"domain_scores_gemma":[0.9967064,0.0000908014,0.0003131641,0.002358007,0.0003870326,0.0001446366],"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":[0.0002849591,0.001402165,0.01144325,0.0006099871,0.0004247792,0.0000444316,0.003567809,0.2868993,0.0008700885,0.07766847,0.02166462,0.5951202],"study_design_scores_gemma":[0.0001563093,0.00008737137,0.01003611,0.00003783007,0.00001640469,0.00001882849,0.00003189522,0.9859364,0.0004542019,0.002450499,0.0004054406,0.000368715],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02728537,0.00005516679,0.9663415,0.002460774,0.0006230277,0.0006668449,0.000003893711,0.0006326734,0.001930762],"genre_scores_gemma":[0.9702901,0.00001571899,0.02828853,0.0005193353,0.0002289458,0.0001058845,0.00009012414,0.00001760815,0.0004437751],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9430047,"threshold_uncertainty_score":0.9999894,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2479635814","doi":"10.1017/cbo9781107447257.015","title":"Bilingual lexical accessduring written sentence comprehension","year":2015,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":41,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Wilfrid Laurier University","funders":"","keywords":"Linguistics; Sentence; Natural language processing; Comprehension; Computer science; Artificial intelligence; Psychology; Philosophy","retraction":null,"screen_n_in":null,"score":{"opus":0.06808983027765364,"gpt":0.2451105236864577,"spread":0.1770206934088041,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000213736,0.0003656853,0.0004091695,0.0001870061,0.0002343002,0.0001547337,0.001790117,0.0004005627,0.000002039503],"category_scores_gemma":[0.00002145132,0.0004104389,0.0001884186,0.00002058808,0.0002600678,0.0003650947,0.001372559,0.0005729767,0.00003772957],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000293987,"about_ca_system_score_gemma":0.00032479,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000131195,"about_ca_topic_score_gemma":0.000004191996,"domain_scores_codex":[0.9978849,0.00006944265,0.0002708865,0.0009075066,0.0005382054,0.0003291095],"domain_scores_gemma":[0.9976867,0.0001094915,0.0002350008,0.001268093,0.000404018,0.0002966803],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00003384568,0.00001841478,0.000004834106,0.00005918372,0.0000344694,0.0001649818,0.000090237,0.00001776307,0.0001170812,0.9829583,0.006360702,0.01014014],"study_design_scores_gemma":[0.0004586183,0.00006906144,0.00009964142,0.0001565818,0.00006137841,0.00005685925,0.00002888612,0.00337532,0.0005023404,0.0002398392,0.9943254,0.0006260503],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.0008706268,0.000159591,0.04005732,0.00009141456,0.0003839313,0.0003901781,0.00005428028,0.0004612929,0.9575314],"genre_scores_gemma":[0.01489852,0.00003503107,0.001717076,0.00007321753,0.0001556949,5.135907e-7,0.00004013574,0.00002792459,0.9830519],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.9879647,"threshold_uncertainty_score":0.9998347,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3032992654","doi":"10.1558/cj.36523","title":"Using Grammar Checkers in an ESL Context","year":2020,"lang":"en","type":"article","venue":"CALICO Journal","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":40,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université du Québec à Trois-Rivières","funders":"","keywords":"TUTOR; Grammar; Computer science; Set (abstract data type); Context (archaeology); Word (group theory); Natural language processing; English grammar; Identification (biology); Corrective feedback; Artificial intelligence; Linguistics; Psychology; Mathematics education; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.1651347308356335,"gpt":0.3264333420404734,"spread":0.16129861120484,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003058657,0.00006809727,0.0001082474,0.00004607956,0.00009468855,0.0002412752,0.0004871165,0.00004591919,0.00001811756],"category_scores_gemma":[0.00007234377,0.00006238228,0.00004359488,0.0002532226,0.00003255832,0.000660433,0.00004568983,0.0002627361,0.00001490325],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007336769,"about_ca_system_score_gemma":0.0001042178,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002015068,"about_ca_topic_score_gemma":0.00001585554,"domain_scores_codex":[0.9991488,0.0001108034,0.0002297364,0.0001775381,0.0001591372,0.0001740048],"domain_scores_gemma":[0.9994325,0.00001992862,0.00007663201,0.0001797098,0.00005684395,0.0002344019],"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":[0.00009110641,0.0003904917,0.08956924,0.00004761002,0.00003115198,0.0003100152,0.03585348,0.003754359,0.0781275,0.0730485,0.001745564,0.717031],"study_design_scores_gemma":[0.00156505,0.0003629913,0.05161107,0.00004950975,0.00001141031,0.0005695767,0.001598066,0.8991699,0.005708541,0.01010338,0.02869605,0.0005545152],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5836527,0.00007805778,0.4125882,0.003413222,0.0001332188,0.00004759921,5.637817e-7,0.0000286473,0.00005771209],"genre_scores_gemma":[0.9886992,0.000004028603,0.009656615,0.001494977,0.0001356463,6.82114e-7,5.755044e-7,0.000004070794,0.000004222175],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8954155,"threshold_uncertainty_score":0.2543876,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4229836027","doi":"10.1075/bct.61.07lan","title":"Texto4Science","year":2014,"lang":"en","type":"book-chapter","venue":"Benjamins current topics","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":38,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"Université de Montréal","funders":"","keywords":"Period (music); Library science; Geography; History; Computer science; Art","retraction":null,"screen_n_in":null,"score":{"opus":0.04848193635037118,"gpt":0.2750569926266092,"spread":0.226575056276238,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002368722,0.0002886071,0.0002844919,0.0001344407,0.000140343,0.0001852005,0.001588706,0.0002165817,0.00007439921],"category_scores_gemma":[0.00004884368,0.0002740351,0.0001536539,0.00006389225,0.0001221628,0.000179239,0.0003575769,0.0004033167,0.0005193108],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009978002,"about_ca_system_score_gemma":0.0001453313,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002601093,"about_ca_topic_score_gemma":0.00001290423,"domain_scores_codex":[0.9981316,0.00002031647,0.0003714329,0.0007232635,0.000481995,0.0002713868],"domain_scores_gemma":[0.9979945,0.00006623903,0.0002173862,0.001460155,0.0001265234,0.0001351762],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[2.153268e-7,0.000008976948,0.000006802162,0.00002522626,0.000002113571,6.16034e-7,0.00004572994,0.000001502417,0.000002191102,0.5590856,0.002463188,0.4383578],"study_design_scores_gemma":[0.00006186031,0.00003523019,0.0003136267,0.00006843601,0.000009062733,0.000005444441,5.818555e-7,0.001558197,0.0000227768,0.06264572,0.9349764,0.0003026459],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"other","genre_scores_codex":[0.00001981525,0.001056655,0.5640147,0.001211297,0.002680676,0.0003244895,0.00001581688,0.0003029401,0.4303736],"genre_scores_gemma":[0.006249857,0.0007186929,0.008402592,0.0003884503,0.001717202,0.00002581386,0.00008678294,0.00004634609,0.9823642],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.9325132,"threshold_uncertainty_score":0.9999712,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2162940749","doi":"10.64152/10125/44156","title":"Evaluating automatic detection of misspellings in German","year":2008,"lang":"en","type":"article","venue":"Language learning & technology","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":37,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Spell; Computer science; Edit distance; Natural language processing; German; Artificial intelligence; Competence (human resources); Linguistics; Psychology; Philosophy","retraction":null,"screen_n_in":null,"score":{"opus":0.02104914928922183,"gpt":0.3133695975337752,"spread":0.2923204482445534,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003601354,0.00007082299,0.0001440705,0.0003353393,0.00006995388,0.000007631648,0.0003658559,0.0001301073,0.00001017766],"category_scores_gemma":[0.0004118577,0.00007297812,0.00002700948,0.0007515202,0.00007967519,0.0001156057,0.00007766549,0.0003120369,0.00002922409],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004390106,"about_ca_system_score_gemma":0.00002533782,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001242223,"about_ca_topic_score_gemma":0.00003141105,"domain_scores_codex":[0.9991395,0.000087009,0.0002436677,0.0002313103,0.0001317647,0.0001667523],"domain_scores_gemma":[0.9993559,0.00008555333,0.0001395086,0.0003650298,0.00003871607,0.00001530686],"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":[0.000002277334,0.0000476651,0.006358929,0.00003277501,0.000004346198,0.00002459631,0.009170025,0.0006690644,0.3157609,0.001927674,8.451733e-7,0.666001],"study_design_scores_gemma":[0.0004915147,0.0003868756,0.04193254,0.00006655647,0.000006043987,0.0002452364,0.000569694,0.722401,0.2298347,0.003469396,0.0003496104,0.000246835],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8822106,0.0001901865,0.1167275,0.0002333854,0.00002924043,0.00008717628,6.242084e-8,0.0004076048,0.0001142605],"genre_scores_gemma":[0.9829243,0.000006043328,0.01694719,0.00001574563,0.000007856658,0.000009240352,7.946438e-7,0.000005355007,0.00008346921],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.721732,"threshold_uncertainty_score":0.2975961,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3205584125","doi":"10.64152/10125/67407","title":"Research Investigating Lexical Coverage and Lexical Profiling: What We Know, What We Don’t Know, and What Needs to be Examined","year":2021,"lang":"en","type":"article","venue":"Reading in a Foreign Language","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":37,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University","funders":"","keywords":"Need to know; Profiling (computer programming); Psychology; Linguistics; Natural language processing; Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.06034828346412041,"gpt":0.3346003613303287,"spread":0.2742520778662083,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001877123,0.000254859,0.0003751153,0.0004207992,0.0002705154,0.004154182,0.0004937812,0.0002335673,0.00001798469],"category_scores_gemma":[0.0007546196,0.0002437473,0.00005320631,0.00146953,0.0002552679,0.00507138,0.0007473055,0.0006147734,0.0000117882],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001772853,"about_ca_system_score_gemma":0.0001835763,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000776403,"about_ca_topic_score_gemma":0.0001241201,"domain_scores_codex":[0.996866,0.0005156418,0.0004509295,0.000887383,0.0005901802,0.0006898949],"domain_scores_gemma":[0.9974606,0.001139394,0.00007036085,0.000786179,0.0001379348,0.0004055516],"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":[0.00002995849,0.0001416478,0.001411745,0.0003287179,0.00001847162,0.0001941385,0.0463328,0.000045499,0.03833522,0.1812133,0.0001255222,0.731823],"study_design_scores_gemma":[0.003315166,0.001255086,0.007512805,0.01347549,0.00004836284,0.0009105065,0.4996475,0.09490281,0.2604057,0.09547354,0.02049449,0.002558478],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9512384,0.02546729,0.01000504,0.01167262,0.0001946932,0.0006213459,0.000003097764,0.0001480169,0.000649484],"genre_scores_gemma":[0.9743111,0.01077138,0.01330828,0.0007914037,0.0001339911,0.00008003152,0.00002915841,0.00002876217,0.0005459188],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7292645,"threshold_uncertainty_score":0.9968796,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4401873941","doi":"10.19173/irrodl.v25i3.7779","title":"Does AI Simplification of Authentic Blog Texts Improve Reading Comprehension, Inferencing, and Anxiety? A One-Shot Intervention in Turkish EFL Context","year":2024,"lang":"en","type":"article","venue":"The International Review of Research in Open and Distributed Learning","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Reading comprehension; Turkish; Reading (process); Comprehension; Context (archaeology); Psychology; Anxiety; Intervention (counseling); Foreign language; Mathematics education; Computer science; Linguistics","retraction":null,"screen_n_in":null,"score":{"opus":0.08136452976121444,"gpt":0.42053083430275,"spread":0.3391663045415356,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005202727,0.00009263949,0.0002472263,0.0002269944,0.00007497147,0.000317672,0.0008435143,0.00004842398,0.00002592337],"category_scores_gemma":[0.001152431,0.00005945785,0.00004485313,0.0006113759,0.0001668078,0.0005560881,0.000727306,0.0005136959,0.000002847124],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001057721,"about_ca_system_score_gemma":0.0001053902,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007845768,"about_ca_topic_score_gemma":0.0001141017,"domain_scores_codex":[0.9978771,0.000544188,0.0005982755,0.0003678856,0.0004441698,0.000168343],"domain_scores_gemma":[0.9983233,0.0008467408,0.0001536357,0.0002772858,0.0003536146,0.00004547739],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00008115473,0.0003061697,0.06007199,0.006536345,0.0000649825,0.000005742698,0.002000249,0.00004253445,0.007289488,0.2005334,0.000205224,0.7228627],"study_design_scores_gemma":[0.00267211,0.0006964811,0.3989647,0.09748182,0.00005936694,0.0000588364,0.00680567,0.2970254,0.007435258,0.1542808,0.03383131,0.0006882577],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9015629,0.03267819,0.03254093,0.02910437,0.000368589,0.002602104,0.00008572469,0.00006265972,0.0009944941],"genre_scores_gemma":[0.9912943,0.008280548,0.0001614212,0.0000570847,0.00001395027,0.00005490812,0.00006946726,0.000004616345,0.00006375753],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7221744,"threshold_uncertainty_score":0.3063319,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2977455214","doi":"10.4000/books.aaccademia.4437","title":"Evalita 2018: Overview on the 6th Evaluation Campaign of Natural Language Processing and Speech Tools for Italian","year":2018,"lang":"en","type":"book-chapter","venue":"Accademia University Press eBooks","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"National Research Council Canada; Università degli Studi di Napoli Federico II","keywords":"Natural (archaeology); Computer science; Natural language processing; Linguistics; Psychology; Speech recognition; History; Archaeology; Philosophy","retraction":null,"screen_n_in":null,"score":{"opus":0.1062257194990996,"gpt":0.3005297298892182,"spread":0.1943040103901186,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009407715,0.0002184028,0.0002531777,0.0000840416,0.0002136873,0.0001173356,0.0009312379,0.0003199595,0.00001265819],"category_scores_gemma":[0.0001219496,0.0001793218,0.0001058605,0.00001804871,0.0002038767,0.0004074186,0.000273476,0.0003271697,0.000002651768],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001546662,"about_ca_system_score_gemma":0.0001632373,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004674114,"about_ca_topic_score_gemma":0.00001688301,"domain_scores_codex":[0.9985678,0.0001098466,0.0002114219,0.0004886197,0.0004496021,0.0001727147],"domain_scores_gemma":[0.9981583,0.0004448576,0.0003649011,0.0006702606,0.0003082071,0.00005341235],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00008164559,0.00001446884,0.000002756751,0.0003836488,0.00008097608,0.000002560577,0.005443378,0.000004057017,0.0002179045,0.5041206,0.002948777,0.4866992],"study_design_scores_gemma":[0.002232176,0.0006111331,0.0004688133,0.002480658,0.0009968693,0.00003193946,0.001511964,0.03612586,0.00885375,0.04259567,0.90232,0.001771117],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.01641485,0.006748274,0.02048475,0.001449001,0.0007384604,0.008667788,0.0004283745,0.0003943589,0.9446741],"genre_scores_gemma":[0.4341006,0.0002116879,0.004792223,0.0006327506,0.0004083499,0.00001892236,0.0001342195,0.00006834519,0.5596329],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.8993713,"threshold_uncertainty_score":0.731253,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2427123482","doi":"10.1037/xlm0000258","title":"Effects of morphology and semantic transparency on typing latencies in english compound and pseudocompound words.","year":2016,"lang":"en","type":"article","venue":"Journal of Experimental Psychology Learning Memory and Cognition","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Morpheme; Transparency (behavior); Natural language processing; Computer science; Opacity; Linguistics; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.01849367680416219,"gpt":0.2839141551949791,"spread":0.2654204783908169,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003535534,0.00009312373,0.0002123847,0.0001645921,0.00006458203,0.00001946077,0.00008853253,0.00007768336,0.000005939321],"category_scores_gemma":[0.00007077264,0.00007135003,0.00002453373,0.00007790115,0.0002097441,0.0003102571,0.0000234876,0.0001797643,9.618232e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001303763,"about_ca_system_score_gemma":0.00000921794,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002427231,"about_ca_topic_score_gemma":9.744617e-7,"domain_scores_codex":[0.9990798,0.0002341064,0.0002971269,0.000198749,0.0000772874,0.0001128773],"domain_scores_gemma":[0.9992674,0.0003609209,0.0002048654,0.00006942891,0.00004888386,0.00004850027],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.0003689944,0.0003733668,0.01005181,0.0000658373,0.00003087337,0.00004766476,0.008343372,0.000005249738,0.9404122,0.0009563129,0.00001527047,0.03932909],"study_design_scores_gemma":[0.01137268,0.006101736,0.6480362,0.001399767,0.0000675606,0.001805037,0.002996961,0.0002761935,0.3155872,0.01166749,0.0001742716,0.0005148938],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9927438,0.001215594,0.005252107,0.0003090527,0.0001802079,0.000094839,3.241414e-7,0.00001129406,0.0001928091],"genre_scores_gemma":[0.9990664,0.000305538,0.0004769636,0.0001046355,0.00003043205,0.000003543685,4.879013e-7,0.000003889834,0.00000813338],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6379844,"threshold_uncertainty_score":0.290957,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2791769113","doi":"10.2196/medinform.8611","title":"Assessing the Readability of Medical Documents: A Ranking Approach","year":2018,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"U.S. National Library of Medicine; U.S. Department of Veterans Affairs","keywords":"Readability; Computer science; Ranking (information retrieval); Concordance; Natural language processing; Information retrieval; Set (abstract data type); Artificial intelligence; Feature (linguistics); Machine learning; Data science; Medicine; Linguistics","retraction":null,"screen_n_in":null,"score":{"opus":0.03470953272105674,"gpt":0.3604011198138306,"spread":0.3256915870927738,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004384662,0.0001184771,0.0002189737,0.00005479217,0.0001937598,0.0002290645,0.002221502,0.000243368,0.0001470704],"category_scores_gemma":[0.0009659556,0.0000703901,0.00007416253,0.0005026791,0.0008042832,0.001262512,0.000540338,0.0004163831,0.00003139778],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004875187,"about_ca_system_score_gemma":0.0004441749,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003303467,"about_ca_topic_score_gemma":0.000004986926,"domain_scores_codex":[0.9958535,0.0001682814,0.0009030704,0.0001468204,0.00265834,0.0002699828],"domain_scores_gemma":[0.9979508,0.0004165149,0.0002765367,0.0009423653,0.000184579,0.0002291921],"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":[0.000007919911,0.0004809566,0.001883251,0.0004010399,0.00004191608,0.000001672544,0.03619571,0.000002418113,0.00001291792,0.09305896,0.002928915,0.8649843],"study_design_scores_gemma":[0.0005737546,0.0001607743,0.009211279,0.0002838316,0.00001580192,0.0001191865,0.00518316,0.9483618,0.0007363188,0.01188651,0.0231391,0.0003285312],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.171885,0.00001687731,0.8130813,0.003258864,0.0002135872,0.0003046884,7.126047e-7,0.0001128555,0.01112609],"genre_scores_gemma":[0.9727356,0.000009219592,0.02577335,0.001279344,0.0001453658,0.00003463461,0.000005093803,0.000003906708,0.00001348419],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9483593,"threshold_uncertainty_score":0.412814,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4285793742","doi":"10.1007/s10579-022-09602-7","title":"Speech acts in the Dutch COVID-19 Press Conferences","year":2022,"lang":"en","type":"article","venue":"Language Resources and Evaluation","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek; Canadian Institute of Steel Construction","keywords":"Speech act; Computer science; Metadata; Linguistics; Reciprocal; Coronavirus disease 2019 (COVID-19); Direct speech; Natural language processing; Mean reciprocal rank; Artificial intelligence; Classifier (UML); Transformer; British National Corpus; World Wide Web; Medicine; Philosophy","retraction":null,"screen_n_in":null,"score":{"opus":0.07035566898821673,"gpt":0.3433580144822387,"spread":0.273002345494022,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002372817,0.00005534855,0.00006367545,0.00004601123,0.0002442792,0.0001566095,0.0004284138,0.00002048951,0.00008311733],"category_scores_gemma":[0.0001780518,0.00003996944,0.0000162361,0.0002002375,0.00002720474,0.0001188568,0.0001196993,0.0001085448,0.000001822509],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005352507,"about_ca_system_score_gemma":0.00007720602,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001416369,"about_ca_topic_score_gemma":0.0004828204,"domain_scores_codex":[0.9983601,0.000660178,0.000125482,0.0002171905,0.0005279579,0.0001090927],"domain_scores_gemma":[0.9993416,0.0002430005,0.00006161502,0.0002948227,0.00002237384,0.00003657343],"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":[0.00004400947,0.000220492,0.008580747,0.0000722308,0.00001315921,0.00002467424,0.4020616,0.005805436,0.0009459436,0.02996774,0.001233746,0.5510303],"study_design_scores_gemma":[0.001581089,0.0003210434,0.1836633,0.00001217277,0.00003878077,0.0001540384,0.07491803,0.4730579,0.0003281731,0.01562825,0.2498587,0.0004384498],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9889928,0.001089763,0.002761061,0.004367359,0.0000530876,0.0003953821,0.000005208447,0.00003579145,0.002299572],"genre_scores_gemma":[0.9987834,0.00001411833,0.0002451121,0.0007540997,0.00002817556,0.00009432803,0.00001674931,0.00000164206,0.00006233972],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5505918,"threshold_uncertainty_score":0.2141136,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4391227797","doi":"10.1111/emip.12590","title":"Using OpenAI GPT to Generate Reading Comprehension Items","year":2024,"lang":"en","type":"article","venue":"Educational Measurement Issues and Practice","topic":"Text Readability and Simplification","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 Alberta","funders":"","keywords":"Reading comprehension; Comprehension; Reading (process); Sentence; Computer science; Cognition; Natural language processing; Artificial intelligence; Sample (material); Psychology; Cognitive psychology; Linguistics","retraction":null,"screen_n_in":null,"score":{"opus":0.2292006550062576,"gpt":0.4155313631435855,"spread":0.1863307081373279,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001704657,0.0001047963,0.00009004534,0.00009532482,0.0002226522,0.000774877,0.0002056665,0.000032653,0.00002960349],"category_scores_gemma":[0.0006401949,0.00009690991,0.00002161835,0.0003286944,0.00001569259,0.001271681,0.00008151884,0.00009931235,0.0001067519],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001414958,"about_ca_system_score_gemma":0.0002199734,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003025889,"about_ca_topic_score_gemma":0.000005727326,"domain_scores_codex":[0.9985257,0.0002062378,0.0001985759,0.0004062213,0.0005169924,0.0001462632],"domain_scores_gemma":[0.9987654,0.0004283536,0.00004776786,0.0002811834,0.0003633639,0.0001139023],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00007012863,0.0004982131,0.0003934867,0.0002686988,0.0001461469,0.000009297942,0.01374296,0.001700214,0.1939696,0.6359912,0.03557215,0.1176379],"study_design_scores_gemma":[0.00007562586,0.00006630782,0.003512979,0.0002037378,0.00003635377,0.0001331102,0.0002806189,0.02679518,0.00274914,0.005684999,0.9601875,0.0002744761],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04994125,0.02207053,0.5330088,0.3808956,0.005057779,0.001035916,0.000006668714,0.0002831639,0.007700377],"genre_scores_gemma":[0.8433148,0.0001380662,0.154156,0.001317128,0.000539774,0.00002584427,0.000006179279,0.00001019621,0.0004920173],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9246153,"threshold_uncertainty_score":0.7472157,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2116208975","doi":"10.1177/0011128712453689","title":"Measuring the Reading Complexity and Oral Comprehension of Canadian Youth Waiver Forms","year":2012,"lang":"en","type":"article","venue":"Crime & Delinquency","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"Memorial University of Newfoundland; Bishop's University","funders":"","keywords":"Waiver; Readability; Sentence; Comprehension; Reading (process); Psychology; Sample (material); Linguistics; Computer science; Law; Political science; Natural language processing","retraction":null,"screen_n_in":null,"score":{"opus":0.1719935833986763,"gpt":0.2807526811983297,"spread":0.1087590977996533,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005513242,0.00009618383,0.0001322491,0.0001304939,0.0002488098,0.00004785369,0.0003861171,0.00005091237,0.0000083803],"category_scores_gemma":[0.00005572793,0.0000670293,0.00003627135,0.0002956651,0.0001460999,0.0005226111,0.00009472401,0.0001139237,0.00001453834],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005734354,"about_ca_system_score_gemma":0.00007503715,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.05118258,"about_ca_topic_score_gemma":0.004363501,"domain_scores_codex":[0.9990577,0.00007548101,0.000225028,0.0001792998,0.0001670263,0.0002955386],"domain_scores_gemma":[0.9990918,0.00005165446,0.00007025845,0.0004767379,0.0001274964,0.000182033],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.00001678429,0.0001482641,0.06609589,0.000118223,0.0000413855,0.000002029909,0.04930225,0.00003423869,0.008567506,0.7479705,0.0003903498,0.1273126],"study_design_scores_gemma":[0.0005275405,0.0001052292,0.9330117,0.0001132678,0.00007731502,0.00006061702,0.003003557,0.01516883,0.01052202,0.03090174,0.005880734,0.0006274435],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9684024,0.0006073855,0.02630975,0.0006488667,0.0002197196,0.0002270483,0.000009838852,0.00005738668,0.00351758],"genre_scores_gemma":[0.9945565,0.00001977781,0.005208785,0.0001589038,0.00003229815,0.000002549222,0.000006136264,0.000004782351,0.00001023179],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8669158,"threshold_uncertainty_score":0.9551357,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4389294437","doi":"10.1080/15434303.2023.2288253","title":"Validity Arguments for Automated Essay Scoring of Young Students’ Writing Traits","year":2023,"lang":"en","type":"article","venue":"Language Assessment Quarterly","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Writing assessment; Consistency (knowledge bases); Context (archaeology); Vocabulary; Psychology; Inference; Argument (complex analysis); Formative assessment; Trait; Artificial intelligence; Natural language processing; Computer science; Mathematics education; Linguistics","retraction":null,"screen_n_in":null,"score":{"opus":0.0296680655231284,"gpt":0.359881211422216,"spread":0.3302131458990876,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001113247,0.0001393121,0.0002202543,0.0001334027,0.0001303798,0.0002162125,0.0007928991,0.00005846357,0.000006747511],"category_scores_gemma":[0.00002646708,0.0001383288,0.0000959745,0.0004695973,0.00002138302,0.0005182773,0.00006507311,0.0000880709,0.00001430536],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009068496,"about_ca_system_score_gemma":0.00007510196,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006737553,"about_ca_topic_score_gemma":0.00003418868,"domain_scores_codex":[0.9982348,0.0001219398,0.0004217942,0.0003978873,0.0004916967,0.0003318607],"domain_scores_gemma":[0.9989762,0.0002295976,0.0001845904,0.0004533818,0.0000901913,0.00006602624],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00003311682,0.00147708,0.153676,0.001031753,0.0002530589,0.00007972993,0.09369092,0.0002957399,0.1997186,0.03360007,0.001006978,0.5151369],"study_design_scores_gemma":[0.001115786,0.0006074037,0.8524105,0.0001003498,0.00002777803,0.000006214538,0.005072051,0.1351477,0.003642167,0.00149702,0.00004980215,0.0003232574],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7880567,0.0000082329,0.2101454,0.0001180656,0.0002157385,0.0004129795,0.00001994741,0.0008196266,0.0002032719],"genre_scores_gemma":[0.9802725,9.708205e-7,0.01933962,0.00002606102,0.00005208327,0.0001117667,0.00004693149,0.00001196375,0.0001381106],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6987345,"threshold_uncertainty_score":0.5640885,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3183940262","doi":"10.1561/1100000089","title":"Readability Research: An Interdisciplinary Approach","year":2022,"lang":"en","type":"article","venue":"Foundations and Trends® in Human–Computer Interaction","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":21,"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":"Readability; Data science; Computer science; Information retrieval; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.1707777209889459,"gpt":0.4425319273195456,"spread":0.2717542063305997,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.00152034,0.0001426766,0.0001624461,0.0009788101,0.001556818,0.0004713835,0.0006447487,0.00004711888,0.0001688574],"category_scores_gemma":[0.00001014582,0.000151574,0.00005884071,0.001080567,0.000117008,0.001781895,0.001316546,0.0006750158,0.000007204985],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003991872,"about_ca_system_score_gemma":0.00002911035,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003165599,"about_ca_topic_score_gemma":0.0002492573,"domain_scores_codex":[0.9973254,0.0007806126,0.0004235267,0.0008069366,0.0003813357,0.0002821781],"domain_scores_gemma":[0.9987093,0.0001644265,0.0001031818,0.0008267282,0.0001088243,0.0000875973],"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":[0.00004222889,0.002118365,0.002106907,0.00002679546,0.00002138933,0.000007633626,0.01434617,0.004562465,0.0003008122,0.1556745,0.001329845,0.819463],"study_design_scores_gemma":[0.0006081894,0.001242669,0.2281518,0.0000214511,0.000009783475,0.0002209494,0.002815201,0.6702983,0.00008047822,0.07744272,0.01854915,0.0005593075],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7075609,0.00002250387,0.28322,0.001623578,0.0008134408,0.0003227408,0.00001181418,0.0002389901,0.006186032],"genre_scores_gemma":[0.9877316,0.000001251523,0.01134417,0.00004280001,0.0001311097,0.0002120246,0.0002673221,0.000009718215,0.0002600492],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8189036,"threshold_uncertainty_score":0.999743,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4309376528","doi":"10.2196/38095","title":"Medical Text Simplification Using Reinforcement Learning (TESLEA): Deep Learning–Based Text Simplification Approach","year":2022,"lang":"en","type":"article","venue":"JMIR Medical Informatics","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":true,"about_ca":false},"ca_institutions":"NOSM University; Lakehead University","funders":"Natural Sciences and Engineering Research Council of Canada; Compute Canada; Lakehead University","keywords":"Computer science; Reinforcement learning; Readability; Annotation; Jargon; Fluency; Artificial intelligence; Natural language processing; Text simplification; Quality (philosophy); Relevance (law); Information retrieval; Linguistics","retraction":null,"screen_n_in":null,"score":{"opus":0.02522489423537592,"gpt":0.2855421848158192,"spread":0.2603172905804432,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.003457372,0.0003619314,0.0004261716,0.0003766144,0.001358779,0.0002845875,0.002230915,0.0003636944,0.0009085513],"category_scores_gemma":[0.001173788,0.0003547733,0.0001808739,0.001409143,0.000255843,0.0009593893,0.0008346532,0.001994221,0.0001428281],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005865489,"about_ca_system_score_gemma":0.0008554881,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003446995,"about_ca_topic_score_gemma":0.000002149922,"domain_scores_codex":[0.9924575,0.0005305547,0.00170807,0.0004938526,0.004085995,0.0007240352],"domain_scores_gemma":[0.9966801,0.0005236838,0.0008560448,0.001053959,0.0002391603,0.0006470571],"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":[0.00008345672,0.001216411,0.001758612,0.0006418399,0.0000875066,0.00001290992,0.02394315,0.4246352,0.000240176,0.0535692,0.001342767,0.4924688],"study_design_scores_gemma":[0.00071151,0.0002019188,0.0006082261,0.00002900346,0.0000146863,0.00007339813,0.002695997,0.9421018,0.00007286251,0.0002244808,0.05287806,0.0003880484],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02889597,0.00006400915,0.9653757,0.001404428,0.000235998,0.0008291014,0.000001873867,0.0005983739,0.002594505],"genre_scores_gemma":[0.9815225,0.00001829529,0.01537146,0.001950613,0.0001313895,0.000428726,0.0003674202,0.00003067453,0.0001789275],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9526265,"threshold_uncertainty_score":0.9999413,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2945464291","doi":"10.1037/xlm0000717","title":"Benefits from morphological regularities in dyslexia are task dependent.","year":2019,"lang":"en","type":"article","venue":"Journal of Experimental Psychology Learning Memory and Cognition","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":18,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Canadian Institutes of Health Research; Azrieli Foundation; Israel Science Foundation; German-Israeli Foundation for Scientific Research and Development; International Development Research Centre","keywords":"Dyslexia; Task (project management); Psychology; Cognitive psychology; Linguistics; Computer science; Reading (process); Philosophy; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.02486016120334763,"gpt":0.286088772061162,"spread":0.2612286108578144,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000397643,0.0001023933,0.0002102154,0.0001271649,0.00006501986,0.00005603299,0.0002221585,0.0001358668,0.00008399916],"category_scores_gemma":[0.00004137987,0.00009396314,0.00005004312,0.00009673252,0.00006911239,0.0005008074,0.0000573779,0.0003919679,0.00002806378],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000282049,"about_ca_system_score_gemma":0.00001207064,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006641038,"about_ca_topic_score_gemma":0.000002255625,"domain_scores_codex":[0.998838,0.0002539744,0.0003336378,0.0002645559,0.0001710963,0.0001387393],"domain_scores_gemma":[0.9993449,0.0001055846,0.0002905307,0.0001442291,0.0000570909,0.00005760812],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.0009769533,0.001401995,0.0843483,0.0000174409,0.00008311948,0.0002625185,0.005364542,0.0006344243,0.853909,0.002980856,0.0002841082,0.04973672],"study_design_scores_gemma":[0.004411609,0.001643575,0.9227944,0.0001780384,0.00001920915,0.001245748,0.00532158,0.0005806779,0.05154281,0.01161303,0.0002743217,0.0003750265],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9935371,0.001954307,0.002615997,0.0004984849,0.0003611995,0.00008597109,0.000001587925,0.00001968397,0.0009256232],"genre_scores_gemma":[0.9981716,0.00006624055,0.001187038,0.0004485623,0.00005963473,0.000003815764,0.000005881202,0.000004595627,0.00005264713],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8384461,"threshold_uncertainty_score":0.3831705,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2738478726","doi":"10.5430/ijhe.v6n4p54","title":"Error Analysis of Students Essays: A Case of First Year Students of the University of Health and Allied Sciences","year":2017,"lang":"en","type":"article","venue":"International Journal of Higher Education","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Academic writing; Communicative competence; Literacy; Mathematics education; Argument (complex analysis); Competence (human resources); Scripting language; Psychology; Error analysis; Pedagogy; First language; Linguistics; Sociology; Computer science; Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.041035925270454,"gpt":0.3862038974468522,"spread":0.3451679721763982,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007111912,0.00004023706,0.0001688495,0.0001979584,0.0001033596,0.00003547521,0.001547595,0.00002091143,0.00001488708],"category_scores_gemma":[0.00006082582,0.00003162305,0.00007663659,0.0001702654,0.0002108324,0.0003154582,0.0001738301,0.00004669706,1.450551e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005367598,"about_ca_system_score_gemma":0.000250404,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007214411,"about_ca_topic_score_gemma":0.0001463337,"domain_scores_codex":[0.9988698,0.00008035258,0.0003505306,0.00009043459,0.0005666425,0.00004218473],"domain_scores_gemma":[0.9975255,0.00006969705,0.001600681,0.0002409425,0.0005320531,0.00003119831],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00002312719,0.0005933786,0.9836538,0.00002280448,0.0003301246,0.000001054578,0.004105144,0.0001691669,0.0001311076,0.00805754,0.00009017567,0.002822566],"study_design_scores_gemma":[0.0002278286,0.00007387206,0.9973456,0.00007343511,0.00006092432,0.00001038221,0.0008631535,0.0001957108,0.0001798397,0.0008129523,0.0001311162,0.00002521999],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9964399,0.0001071069,0.001163736,0.001766352,0.000381958,0.00005450343,0.000007750203,8.867671e-7,0.00007783034],"genre_scores_gemma":[0.9985974,0.00003854193,0.001257088,0.0000149582,0.00001356705,1.358607e-7,7.563376e-7,9.72918e-7,0.00007651167],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01369176,"threshold_uncertainty_score":0.2875842,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2789586388","doi":"10.5539/elt.v11n4p1","title":"Critical Reading Skills and Translation Ability of Thai EFL Students: Pragmatic, Syntactic, and Semantic Aspects","year":2018,"lang":"en","type":"article","venue":"English Language Teaching","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":15,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Psychology; Reading (process); Critical reading; Linguistics; Mathematics education; Error analysis","retraction":null,"screen_n_in":null,"score":{"opus":0.007723869247560229,"gpt":0.2972760731860103,"spread":0.28955220393845,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001630659,0.0001175195,0.0001961255,0.00007613801,0.0001761189,0.0002125036,0.0002513431,0.00006802574,0.000009720579],"category_scores_gemma":[0.00283682,0.0001086435,0.00002774872,0.0001016438,0.0001564602,0.0009437841,0.0001122319,0.0002278545,0.00000177417],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002970138,"about_ca_system_score_gemma":0.00001681139,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000830484,"about_ca_topic_score_gemma":0.0000292228,"domain_scores_codex":[0.9985607,0.0003237324,0.0002797246,0.0003724657,0.0002782287,0.0001851018],"domain_scores_gemma":[0.9982856,0.001059393,0.0000753163,0.0004340806,0.00006429321,0.00008132639],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"observational","study_design_scores_codex":[0.0000105986,0.0005134783,0.02395246,0.0004279261,0.00003719673,0.00001015323,0.7092181,0.000002099251,0.02272459,0.07052519,0.0000100538,0.1725681],"study_design_scores_gemma":[0.004090469,0.001690764,0.7244074,0.001779934,0.0003924654,0.0002350939,0.09366681,0.05878856,0.05428081,0.05775801,0.0004955916,0.002414111],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8823821,0.0001446731,0.1152287,0.0001828416,0.0001391634,0.000188596,0.000002834951,0.0001309415,0.0016002],"genre_scores_gemma":[0.9788564,0.000004028391,0.02096017,0.00004291142,0.000115523,0.00000485052,0.000002390177,0.000007338926,0.00000640061],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7004549,"threshold_uncertainty_score":0.4430352,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2130005887","doi":"10.1037/a0028494","title":"Assessing the influence of letter position in reading normal and transposed texts using a letter detection task.","year":2012,"lang":"en","type":"article","venue":"Canadian Journal of Experimental Psychology/Revue canadienne de psychologie expérimentale","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Moncton","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Reading (process); Task (project management); Position (finance); Computer science; Natural language processing; Psychology; Artificial intelligence; Speech recognition; Audiology; Linguistics; Cognitive psychology; Medicine; Philosophy; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.03707125158914994,"gpt":0.3167735947120583,"spread":0.2797023431229084,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001207509,0.0001995923,0.0002625301,0.0004501392,0.0002051919,0.00009664198,0.0006334196,0.000161281,0.00001641077],"category_scores_gemma":[0.00004219447,0.0001861536,0.00008832891,0.0004050309,0.0003233625,0.001584028,0.00002410039,0.0003944912,0.00000184669],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007258579,"about_ca_system_score_gemma":0.0001294222,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003592279,"about_ca_topic_score_gemma":0.004561316,"domain_scores_codex":[0.9979381,0.0002712341,0.0006147268,0.0003190447,0.00008781688,0.0007690607],"domain_scores_gemma":[0.9985739,0.00008241851,0.0003625168,0.0004343086,0.00006107044,0.0004858022],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.00002989533,0.0001162588,0.03918458,0.00001130667,0.00002479135,0.00007098216,0.01154241,0.0001592417,0.9455419,0.000223847,0.000164819,0.002929986],"study_design_scores_gemma":[0.001533232,0.0004438293,0.8516274,0.0001942475,0.0000293256,0.003712741,0.002671632,0.000436456,0.1374791,0.0005084727,0.0009169925,0.000446588],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9894508,0.0007403523,0.006752642,0.001892792,0.0007800699,0.000213543,0.000005301986,0.000008886568,0.0001555725],"genre_scores_gemma":[0.9936084,0.000004531847,0.003215339,0.002940984,0.0002002745,0.00001030525,0.000001912193,0.00001455996,0.00000366573],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8124428,"threshold_uncertainty_score":0.7591125,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2128471136","doi":"10.5539/jel.v2n1p176","title":"Information and Communication Technology Profiles of College Students with Learning Disabilities and Adequate and Very Poor Readers","year":2013,"lang":"en","type":"article","venue":"Journal of Education and Learning","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":14,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":true,"about_ca":true},"ca_institutions":"Cegep de Sainte Foy; Cégep du Vieux Montréal; Dawson College; Cégep André Laurendeau; Collège Montmorency; Quebec Rehabilitation Research Network; McGill University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Reading comprehension; Psychology; ICTS; Reading (process); Comprehension; Test (biology); Learning disability; Information and Communications Technology; Mathematics education; Pedagogy; Medical education; Developmental psychology; Computer science; Linguistics; Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.01027746944414604,"gpt":0.2594481319128362,"spread":0.2491706624686901,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004577105,0.0000602627,0.0001189031,0.0001849992,0.0001730506,0.0001322254,0.0001086673,0.00004594913,0.000003495215],"category_scores_gemma":[0.000302879,0.00004813346,0.000007484578,0.0001405215,0.0001723468,0.001336507,0.00006228,0.0002420428,5.061134e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001720984,"about_ca_system_score_gemma":0.00006861091,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004781077,"about_ca_topic_score_gemma":0.000002651077,"domain_scores_codex":[0.9993624,0.0001212643,0.0002613529,0.0000657093,0.0001234059,0.00006586171],"domain_scores_gemma":[0.9990821,0.0001951129,0.0003595457,0.00008870429,0.0002268617,0.00004762963],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00002499251,0.0001016658,0.6210169,0.0001410718,0.00003336454,6.946015e-8,0.05076995,0.00006280447,0.0003974185,0.01135097,0.00006977958,0.3160311],"study_design_scores_gemma":[0.0004715754,0.0005356244,0.8044043,0.0002063846,0.0000195944,0.0001375737,0.1889788,0.001675717,0.0001681064,0.001823632,0.001463799,0.0001148689],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9937773,0.0007794274,0.002457765,0.002752454,0.00002570931,0.0001280144,1.835095e-7,0.00001095979,0.00006822313],"genre_scores_gemma":[0.9934779,0.0002767142,0.006102314,0.00003107172,0.000007416088,0.000008479259,0.000001429629,0.000002223669,0.00009242338],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3159162,"threshold_uncertainty_score":0.1962825,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2169539950","doi":"10.1017/s1366728904001622","title":"Letter detection for homographs with different meanings in different language texts","year":2004,"lang":"en","type":"article","venue":"Bilingualism Language and Cognition","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Moncton","funders":"","keywords":"Fluency; Computer science; Interpretation (philosophy); Context (archaeology); Linguistics; Affect (linguistics); Natural language processing; Psychology; Communication","retraction":null,"screen_n_in":null,"score":{"opus":0.009127837991078538,"gpt":0.236192373283436,"spread":0.2270645352923574,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001407938,0.0001722683,0.0001688529,0.0001734474,0.0001023773,0.0001231141,0.0001370671,0.00008085543,0.000003324058],"category_scores_gemma":[0.00003914196,0.0001247546,0.00005259229,0.0001987111,0.00004586436,0.0002421409,0.00003335032,0.0001083732,0.00000164489],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004122466,"about_ca_system_score_gemma":0.00001432327,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001685085,"about_ca_topic_score_gemma":0.001420071,"domain_scores_codex":[0.9989538,0.00004382205,0.0001994221,0.0004094355,0.0001684217,0.0002251148],"domain_scores_gemma":[0.9994763,0.00008580119,0.00007632138,0.0002509943,0.00005130203,0.0000592702],"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":[0.0003169852,0.001013838,0.001491812,0.0003782559,0.00006878831,0.000119745,0.1179252,0.00003853366,0.2673895,0.008220862,0.00002480456,0.6030117],"study_design_scores_gemma":[0.01016027,0.001592658,0.0775021,0.0005623105,0.0001540185,0.0002082504,0.00929064,0.002116655,0.8563798,0.04008123,0.0004233317,0.001528736],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.862064,0.0001944213,0.1365955,0.0004977451,0.00005236984,0.0004246679,0.000007136942,0.0001162601,0.00004791313],"genre_scores_gemma":[0.9978933,0.00001032391,0.001116841,0.0006634427,0.0001124199,0.0001255946,0.0000463418,0.00001176394,0.00001994416],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6014829,"threshold_uncertainty_score":0.5087346,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2108070002","doi":"10.7202/603125ar","title":"Varying Approaches to Readability Measurement","year":2009,"lang":"en","type":"article","venue":"Revue québécoise de linguistique","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"U.S. Navy; American Educational Research Association","keywords":"Readability; Sentence; Judgement; Computer science; Cognition; Natural language processing; Reliability (semiconductor); Qualitative research; Meaning (existential); Measure (data warehouse); Linguistics; Artificial intelligence; Cognitive psychology; Psychology; Data science; Information retrieval; Data mining; Epistemology; Sociology; Social science","retraction":null,"screen_n_in":null,"score":{"opus":0.1130471822831362,"gpt":0.2731314378407082,"spread":0.160084255557572,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001478646,0.0001755501,0.0002211882,0.00009463228,0.0001351661,0.0001320941,0.000646771,0.000107086,0.000002971092],"category_scores_gemma":[0.001697664,0.0001820506,0.00009600241,0.0003793297,0.00002048664,0.0001182241,0.00006181162,0.0002017522,0.00003660229],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004328903,"about_ca_system_score_gemma":0.0003015342,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000706066,"about_ca_topic_score_gemma":0.0005909849,"domain_scores_codex":[0.9982284,0.0001487501,0.0003598657,0.000615615,0.0002859537,0.0003613854],"domain_scores_gemma":[0.9982126,0.00008136186,0.00008692126,0.001156194,0.0002118502,0.0002510235],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00003425215,0.0004049818,0.0008803008,0.0001099053,0.00001422922,0.00003211194,0.006686528,0.00160557,0.004649634,0.8091713,0.0002266593,0.1761846],"study_design_scores_gemma":[0.0006081386,0.001034041,0.1789116,0.000598437,0.00006700501,0.000281779,0.0001113271,0.08514842,0.04262037,0.5263739,0.1618393,0.00240569],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04549238,0.0002850315,0.8980065,0.02112438,0.0003038334,0.0008772326,0.000003271052,0.000706156,0.03320123],"genre_scores_gemma":[0.9249818,0.000004854465,0.07372964,0.0009072375,0.0002661657,0.0000374308,0.000001937451,0.000007645355,0.00006327766],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8794894,"threshold_uncertainty_score":0.7423808,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2102137313","doi":"10.1002/j.2048-7940.2010.tb00284.x","title":"How to Choose and Develop Written Educational Materials","year":2010,"lang":"en","type":"article","venue":"Rehabilitation Nursing","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Reseau canadien de recherche respiratoire","keywords":"Computer science; Mathematics education; Psychology","retraction":null,"screen_n_in":null,"score":{"opus":0.009490039935537474,"gpt":0.2730680900962374,"spread":0.2635780501606999,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004531479,0.00008384866,0.00009400236,0.000118059,0.0001466235,0.0003844454,0.0002168779,0.00005815494,0.00001459846],"category_scores_gemma":[0.001372097,0.00008415354,0.00001491787,0.0003205634,0.00008201437,0.0006610961,0.00003014337,0.00007556257,0.000022403],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006654448,"about_ca_system_score_gemma":0.000115731,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000957355,"about_ca_topic_score_gemma":0.000008230958,"domain_scores_codex":[0.999115,0.0000675643,0.000170653,0.000337531,0.0001622346,0.0001469376],"domain_scores_gemma":[0.9988141,0.0004113747,0.00005129536,0.0003612401,0.0002513515,0.0001106049],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.000007288676,0.0001092916,0.001956936,0.00002908464,0.000002661738,8.216252e-8,0.008595527,0.000002862489,0.2449556,0.3806094,0.0009048204,0.3628265],"study_design_scores_gemma":[0.0001377603,0.0000699621,0.8991295,0.00004664074,0.000003244078,0.00001456267,0.0003019701,0.0002491832,0.009307888,0.08527831,0.005263625,0.0001973782],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8193082,0.00001177308,0.05239045,0.1272087,0.0006232538,0.0002460193,0.000002658934,0.00006489653,0.0001440112],"genre_scores_gemma":[0.7532066,3.71991e-7,0.2464078,0.0001253532,0.00008279959,0.00002960641,0.000005522916,0.000004380245,0.000137598],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8971725,"threshold_uncertainty_score":0.3707216,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3162983511","doi":"10.1037/xge0001038","title":"Prevalence of spelling errors affects reading behavior across languages.","year":2021,"lang":"en","type":"article","venue":"Journal of Experimental Psychology General","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"McMaster University","funders":"Vector Institute; Ontario Ministry of Research and Innovation; Social Sciences and Humanities Research Council of Canada; Canada Research Chairs; Canada Foundation for Innovation","keywords":"Spelling; Phonology; Linguistics; Sentence; Psycholinguistics; Orthography; Psychology; Natural language processing; Word recognition; Written language; Cognitive psychology; Artificial intelligence; Reading (process); Computer science; Cognition","retraction":null,"screen_n_in":null,"score":{"opus":0.03865048356363132,"gpt":0.3995392918604656,"spread":0.3608888082968342,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005118773,0.0001031501,0.0002153757,0.00005686321,0.00006974651,0.00003213798,0.0005152911,0.00008596205,0.00005495896],"category_scores_gemma":[0.00003641892,0.00009604997,0.0001388958,0.0001749071,0.00009151593,0.0003330092,0.0001030826,0.0002136659,0.000006222845],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000478797,"about_ca_system_score_gemma":0.0000464843,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003816054,"about_ca_topic_score_gemma":0.000001140589,"domain_scores_codex":[0.9987382,0.0001709381,0.0004023328,0.0002399095,0.0002221866,0.0002264711],"domain_scores_gemma":[0.9990091,0.00004722003,0.000349275,0.0004030274,0.0001075348,0.00008389523],"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":[0.00002207912,0.0004161831,0.0120207,0.00001501949,0.00001802045,0.0001348327,0.002767794,0.00004038927,0.9794831,0.001130858,0.0002752779,0.003675749],"study_design_scores_gemma":[0.0005707073,0.0003059011,0.07646808,0.00003104017,0.00001193274,0.00109779,0.0006094924,0.0001869733,0.9203262,0.0001100648,0.0001613197,0.0001204941],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9808636,0.002235599,0.01539981,0.0002338414,0.0007741876,0.0000620938,0.000002963507,0.00001153417,0.0004164001],"genre_scores_gemma":[0.9694874,0.00005368694,0.02991062,0.0001977688,0.0001350136,0.00000236336,9.52468e-7,0.000006382783,0.00020585],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.06444738,"threshold_uncertainty_score":0.3916804,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4367558144","doi":"10.3390/math11092063","title":"Text Simplification to Specific Readability Levels","year":2023,"lang":"en","type":"article","venue":"Mathematics","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; King Saud University","keywords":"Readability; Computer science; Sentence; Classifier (UML); Artificial intelligence; Natural language processing; Task (project management); Text simplification; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.08187653957215646,"gpt":0.3015701657841328,"spread":0.2196936262119763,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0009028498,0.0001270414,0.0001678906,0.0001403566,0.0001305177,0.0001713447,0.0008365552,0.00006554354,0.0000376917],"category_scores_gemma":[0.0002556613,0.000116916,0.00005752687,0.001114084,0.00003334799,0.0002474801,0.0002006872,0.00008540606,0.003910338],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008071404,"about_ca_system_score_gemma":0.00003491737,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004909887,"about_ca_topic_score_gemma":0.000003929351,"domain_scores_codex":[0.9985428,0.00004574579,0.0003787094,0.0004177219,0.0003403291,0.0002746807],"domain_scores_gemma":[0.9978534,0.0003173532,0.00008213331,0.001520269,0.0001052059,0.0001216275],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000003982635,0.000397732,0.0003601767,0.0002137677,0.00001471772,0.000004599261,0.01450352,0.0004315707,0.02618199,0.6935411,0.02242622,0.2419206],"study_design_scores_gemma":[0.0002020739,0.0001244659,0.09633032,0.00006451621,0.000009831244,0.00002149161,0.0007967006,0.08836628,0.02622128,0.6960785,0.09098529,0.0007992412],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1689024,0.000007015596,0.8233212,0.003917016,0.0001718509,0.0004430681,0.00001007441,0.0008074846,0.002419867],"genre_scores_gemma":[0.8753983,0.000005007154,0.1232006,0.0001625921,0.00006002461,0.00006739092,0.00001000042,0.00001503156,0.001081067],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7064959,"threshold_uncertainty_score":0.9968652,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2753133191","doi":"10.37514/jwa-j.2017.1.1.08","title":"Discovering the Predictive Power of Five Baseline Writing Competences","year":2017,"lang":"en","type":"article","venue":"The Journal of Writing Analytics","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Athabasca University","funders":"","keywords":"Baseline (sea); Benchmark (surveying); Computer science; Credibility; Consistency (knowledge bases); Constructive; State (computer science); Artificial intelligence; Data science; Machine learning; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.02459756427332719,"gpt":0.2848382890596801,"spread":0.2602407247863529,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004051672,0.00008142799,0.0001896961,0.00004336427,0.0006051685,0.0002251467,0.001556837,0.00002684779,0.000003061675],"category_scores_gemma":[0.001041835,0.00004361938,0.0001095304,0.0001005029,0.0002683829,0.0005077301,0.0002338257,0.000289979,0.000001004949],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002673806,"about_ca_system_score_gemma":0.00008240181,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006268072,"about_ca_topic_score_gemma":0.00001227527,"domain_scores_codex":[0.9986287,0.000189639,0.0005487204,0.00008821282,0.0003994509,0.0001452373],"domain_scores_gemma":[0.9965936,0.001103666,0.001183452,0.0006755666,0.000403893,0.00003981316],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000652897,0.001363857,0.1905322,0.0005147376,0.002118057,0.0001707235,0.1539736,0.3175808,0.02189749,0.1512411,0.002526385,0.1574281],"study_design_scores_gemma":[0.0005135771,0.0003948477,0.1731794,0.0006558712,0.0001971462,0.0003109455,0.02298792,0.7875863,0.004060292,0.009705863,0.0001854135,0.000222376],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6965514,0.0001918879,0.2965019,0.005768549,0.0001386229,0.00006194425,0.000005022169,0.000009380039,0.0007711938],"genre_scores_gemma":[0.9969156,0.00006254755,0.002784719,0.00006020544,0.0001456191,2.555838e-7,1.742651e-7,0.000003602592,0.00002721206],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4700055,"threshold_uncertainty_score":0.4654528,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2610650708","doi":"10.18806/tesl.v34i1.1257","title":"Steps for Creating a Specialized Corpus and Developing an Annotated Frequency-Based Vocabulary List","year":2017,"lang":"en","type":"article","venue":"TESL Canada Journal","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Vocabulary; Corpus linguistics; Linguistics; Computer science; Humanities; Library science; Psychology; Artificial intelligence; Art; Philosophy","retraction":null,"screen_n_in":null,"score":{"opus":0.03666660018396091,"gpt":0.2821312117248886,"spread":0.2454646115409277,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0006003031,0.0001192106,0.000170907,0.00005066017,0.001660519,0.0009484289,0.0007443408,0.0000447011,0.00005329943],"category_scores_gemma":[0.0004712705,0.0001115039,0.00002946535,0.00006313102,0.00006284466,0.0006385546,0.00004768205,0.0001572808,2.194599e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002713967,"about_ca_system_score_gemma":0.002682062,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.05898476,"about_ca_topic_score_gemma":0.1688569,"domain_scores_codex":[0.9988531,0.00006682172,0.0002919619,0.0002470174,0.0002707491,0.000270309],"domain_scores_gemma":[0.9985614,0.000141252,0.0003444473,0.000475229,0.0002703991,0.0002072256],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0003672183,0.0002995598,0.04551859,0.0004199415,0.0002534152,0.0009158557,0.004060277,0.0004463046,0.02471691,0.1802927,0.0157137,0.7269955],"study_design_scores_gemma":[0.007186564,0.0007784122,0.5883985,0.0005235057,0.00008575169,0.001316277,0.0003580708,0.2519757,0.009717119,0.06432715,0.07325159,0.002081374],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3294747,0.001362831,0.6599392,0.007512571,0.0008572904,0.0004209092,0.00004049544,0.00007702913,0.0003150033],"genre_scores_gemma":[0.8298388,0.000007271115,0.1642135,0.005580562,0.0002847856,0.0000116938,0.00001172481,0.00001355494,0.00003818679],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7249141,"threshold_uncertainty_score":0.9996392,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2962734277","doi":"10.1037/xlm0000748","title":"Detecting spelling errors in compound and pseudocompound words.","year":2019,"lang":"en","type":"article","venue":"Journal of Experimental Psychology Learning Memory and Cognition","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":12,"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","keywords":"Morpheme; Orthography; Spelling; Compound; Natural language processing; Word (group theory); Speech recognition; Task (project management); Control (management); Artificial intelligence; Linguistics; Computer science; Word recognition; Psychology; Communication; Reading (process)","retraction":null,"screen_n_in":null,"score":{"opus":0.02387598674403773,"gpt":0.3108783492838626,"spread":0.2870023625398249,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006438635,0.00009303541,0.0001784892,0.0001723976,0.00008561249,0.00006878866,0.0001240612,0.00007296728,0.00002631509],"category_scores_gemma":[0.00002707878,0.00009097099,0.00003254907,0.0001263162,0.00006808259,0.0005186088,0.00004146901,0.0003995867,0.00001504973],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002372395,"about_ca_system_score_gemma":0.00001179632,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003296008,"about_ca_topic_score_gemma":0.000001472562,"domain_scores_codex":[0.9990172,0.000191371,0.0003241021,0.0002184293,0.000114713,0.0001341362],"domain_scores_gemma":[0.9994303,0.0001346113,0.000247854,0.00009473365,0.00003697076,0.00005553829],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.0004426647,0.0004806797,0.04118721,0.00004595529,0.00004814046,0.00008348192,0.01296098,0.0004207608,0.8725368,0.0008386442,0.00002402786,0.07093062],"study_design_scores_gemma":[0.02620085,0.01061348,0.4622673,0.001396499,0.0001110221,0.01921806,0.05521443,0.05036906,0.3325113,0.03636485,0.003244021,0.002489169],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9899715,0.0007801121,0.007261865,0.0002286325,0.0002815412,0.00009836672,9.154518e-8,0.00001406349,0.001363893],"genre_scores_gemma":[0.9969238,0.00004443595,0.002784217,0.0001711829,0.00004382103,0.000001354735,9.077675e-7,0.000004973404,0.00002528831],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5400256,"threshold_uncertainty_score":0.3709689,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2286878760","doi":"10.5539/ells.v6n1p81","title":"Syntactic Complexity of EFL Chinese Students’ Writing","year":2016,"lang":"en","type":"article","venue":"English Language and Literature Studies","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"Central University of Finance and Economics; Iowa State University","keywords":"Sentence; Computer science; Task (project management); Linguistics; Natural language processing","retraction":null,"screen_n_in":null,"score":{"opus":0.01654081162246815,"gpt":0.3020156164261348,"spread":0.2854748048036667,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003039623,0.0001171581,0.0002114457,0.00005463398,0.00009658279,0.000101034,0.0002977768,0.00004013042,0.000003449094],"category_scores_gemma":[0.0006742781,0.00006551892,0.0000421424,0.0001829726,0.0001395134,0.0004737952,0.0002359503,0.00008183324,9.776627e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001937708,"about_ca_system_score_gemma":0.00000779634,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000803193,"about_ca_topic_score_gemma":0.00001894821,"domain_scores_codex":[0.9991735,0.00007843885,0.000195506,0.0002557467,0.0001593854,0.00013743],"domain_scores_gemma":[0.9990388,0.0003052913,0.00007733682,0.0003383883,0.0002022462,0.00003796616],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"observational","study_design_scores_codex":[0.00002586996,0.0001647871,0.0823713,0.0003692349,0.0002261767,0.00004714965,0.7932386,3.535489e-7,0.006754617,0.05874555,0.000435174,0.05762116],"study_design_scores_gemma":[0.004330108,0.0009025547,0.8120289,0.003318396,0.0001170406,0.0001059595,0.1242979,0.0001388498,0.008400754,0.03898664,0.005601211,0.001771594],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.989167,0.008025805,0.001622779,0.0004303794,0.0001777885,0.00009941919,0.00002195472,0.00009274959,0.0003620623],"genre_scores_gemma":[0.9978237,0.0001689334,0.001665025,0.00004791753,0.0001600712,0.000008090169,0.00000310784,0.000003758938,0.0001194521],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7296576,"threshold_uncertainty_score":0.2671784,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4394844693","doi":"10.1371/journal.pdig.0000489","title":"Biomedical text readability after hypernym substitution with fine-tuned large language models","year":2024,"lang":"en","type":"article","venue":"PLOS Digital Health","topic":"Text Readability and Simplification","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":"McMaster University; University of Toronto","funders":"","keywords":"Readability; Computer science; Substitution (logic); Unified Medical Language System; Natural language processing; Text simplification; Automatic summarization; Artificial intelligence; Sentence; Comprehension; Biomedical text mining; Language model; Text mining","retraction":null,"screen_n_in":null,"score":{"opus":0.01983503389309309,"gpt":0.2663777210944307,"spread":0.2465426872013376,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000332165,0.0001657623,0.0002060331,0.0001059529,0.0001043759,0.0004408233,0.0003438719,0.00007791587,0.00001654987],"category_scores_gemma":[0.00004680593,0.0001221843,0.00005971562,0.0005399858,0.0001142313,0.001726063,0.0001065569,0.0002070925,0.0001681993],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002266597,"about_ca_system_score_gemma":0.0004803689,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006525447,"about_ca_topic_score_gemma":0.00009165597,"domain_scores_codex":[0.9980803,0.00005516594,0.000323567,0.0006247238,0.0004835719,0.0004326392],"domain_scores_gemma":[0.9988393,0.0001229528,0.00004433303,0.0006739081,0.00005762503,0.0002618452],"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":[0.0003008859,0.004384396,0.005970475,0.003119842,0.0001337089,0.0002955072,0.01775353,0.0000763016,0.0003998879,0.3192532,0.00131755,0.6469947],"study_design_scores_gemma":[0.001764729,0.003102771,0.03283994,0.001914306,0.00005655324,0.0004237714,0.00110763,0.8333518,0.002294075,0.07830669,0.04246571,0.002372028],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.591002,0.0009287627,0.4007359,0.004804768,0.0001424793,0.0004386216,0.0001971538,0.0007406494,0.001009563],"genre_scores_gemma":[0.9973135,0.000008754238,0.002000186,0.0002800597,0.00007307357,0.00005389552,0.00009636773,0.00001271681,0.0001614415],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8332755,"threshold_uncertainty_score":0.498253,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2170030837","doi":"10.5539/elt.v5n8p57","title":"Announcement of Retraction","year":2012,"lang":"en","type":"article","venue":"English Language Teaching","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":12,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Psychology; Linguistics; Philosophy","retraction":null,"screen_n_in":null,"score":{"opus":0.01155681744574033,"gpt":0.2638416912237179,"spread":0.2522848737779776,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001051317,0.00005405095,0.00007155049,0.00004605363,0.00006011155,0.00002872703,0.0002337519,0.00004313185,0.00001609286],"category_scores_gemma":[0.0003519992,0.00004977279,0.00003158435,0.00008374796,0.00001136451,0.0008552966,0.00005252349,0.0001926218,0.000008113756],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004353419,"about_ca_system_score_gemma":0.000009627604,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006384358,"about_ca_topic_score_gemma":0.000002576474,"domain_scores_codex":[0.9993184,0.0001003223,0.0001429458,0.0001118473,0.000174788,0.000151652],"domain_scores_gemma":[0.9994139,0.00007248312,0.00007547617,0.0003697371,0.00002330913,0.00004507491],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000004776034,0.0003620515,0.008425463,0.00004274343,0.00001596394,0.000001162987,0.5043554,0.00003403401,0.0360766,0.1869516,0.0005772132,0.2631529],"study_design_scores_gemma":[0.002529247,0.0006509119,0.1862812,0.000313406,0.0001053064,0.00007122558,0.1690793,0.01876587,0.2961331,0.002964953,0.320533,0.002572568],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7588863,0.0002370852,0.2267955,0.00008568112,0.0007312291,0.00007740664,0.000001544035,0.0001762075,0.01300911],"genre_scores_gemma":[0.9840178,0.000001497979,0.01556017,0.00003721005,0.0002739268,0.000003666133,0.00000557776,0.000003173308,0.00009691351],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3352762,"threshold_uncertainty_score":0.2029675,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2124547832","doi":"10.1109/wse.2008.4655399","title":"Evolution of legal statements on the web","year":2008,"lang":"en","type":"article","venue":"","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Victoria","funders":"","keywords":"Viewpoints; Computer science; Readability; World Wide Web; The Internet; Data science; Web standards; Information retrieval","retraction":null,"screen_n_in":null,"score":{"opus":0.03856406689603698,"gpt":0.2789877685045692,"spread":0.2404237016085322,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001435411,0.00002914788,0.00003323194,0.00002015544,0.00006921413,0.00000947693,0.0002690036,0.00001164378,0.00002285429],"category_scores_gemma":[0.00001908747,0.00001729403,0.00001845052,0.0001257437,0.00003567635,0.0002202284,0.00003105493,0.00003059185,0.00004844092],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003077117,"about_ca_system_score_gemma":0.00005070627,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008498136,"about_ca_topic_score_gemma":0.00001220607,"domain_scores_codex":[0.9995641,0.00003415208,0.00009677182,0.00009426827,0.0001501058,0.00006062138],"domain_scores_gemma":[0.999554,0.00004846514,0.00003120961,0.0003181172,0.00003509761,0.00001314256],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.000002419785,0.0000633848,0.00143906,0.000001595165,0.000002212653,3.076733e-7,0.0001723762,0.00005782629,0.00190197,0.9919165,0.002365976,0.002076333],"study_design_scores_gemma":[0.0007410033,0.0006083925,0.5949285,0.00002235501,0.0000055717,0.00002829273,0.0002892787,0.2268065,0.0584974,0.04606866,0.07163619,0.0003679005],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7067447,0.000007674957,0.2756328,0.002379159,0.00007612222,0.0001011653,0.000001007128,0.00004824892,0.01500914],"genre_scores_gemma":[0.9979509,0.000003336704,0.001260008,0.00009585536,0.000006801448,0.000003393915,3.226158e-7,7.943113e-7,0.000678632],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9458479,"threshold_uncertainty_score":0.070523,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4380318953","doi":"10.1037/xge0001407","title":"Comparing word frequency, semantic diversity, and semantic distinctiveness in lexical organization.","year":2023,"lang":"en","type":"article","venue":"Journal of Experimental Psychology General","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Optimal distinctiveness theory; Lexical decision task; Variety (cybernetics); Context (archaeology); Word lists by frequency; Variance (accounting); Computer science; Natural language processing; Word (group theory); Lexical diversity; Linguistics; Contrast (vision); Psychology; Semantic similarity; Metric (unit); Artificial intelligence; Cognition; Social psychology; History","retraction":null,"screen_n_in":null,"score":{"opus":0.05729411256604949,"gpt":0.3309632280050827,"spread":0.2736691154390332,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003842117,0.00009390267,0.000206958,0.0002119454,0.0002436565,0.00004144539,0.0004318114,0.00006433496,0.00001197021],"category_scores_gemma":[0.00003381661,0.00008790506,0.00003526958,0.000565901,0.00009755332,0.0003523121,0.0005089386,0.0001839917,0.00001146659],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006289817,"about_ca_system_score_gemma":0.00002043695,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003451873,"about_ca_topic_score_gemma":0.00001129067,"domain_scores_codex":[0.9989771,0.0001437348,0.0003145932,0.0002219005,0.0001687754,0.000173926],"domain_scores_gemma":[0.9995033,0.00004947465,0.0001341175,0.0001780632,0.00005919197,0.00007581566],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0000253877,0.0002671468,0.9235188,0.000007919421,0.00002152765,0.0001046879,0.00374317,0.0001262414,0.06503154,0.00615506,0.0002103692,0.0007881058],"study_design_scores_gemma":[0.0007353719,0.0001060512,0.9888718,0.00001468517,0.000004177322,0.0002430005,0.0001817621,0.00274624,0.003524677,0.003453661,0.00001373225,0.0001049058],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9772238,0.0001616031,0.0211401,0.0008078182,0.0004774738,0.00006031355,3.458483e-7,0.00002871668,0.00009984684],"genre_scores_gemma":[0.9978884,0.00002045812,0.001843784,0.0001518159,0.00006991676,0.000001005764,0.000001949854,0.000005454485,0.00001722696],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.06535289,"threshold_uncertainty_score":0.3584664,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4412438704","doi":"10.1145/3730436.3730449","title":"AltGen: AI-Driven Alt Text Generation for Enhancing EPUB Accessibility","year":2025,"lang":"en","type":"article","venue":"","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":11,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Multimedia; World Wide Web","retraction":null,"screen_n_in":null,"score":{"opus":0.02950165979052712,"gpt":0.3233822716840986,"spread":0.2938806118935715,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004733953,0.00009283738,0.0001201979,0.00007192978,0.0002114497,0.0002404295,0.0005516746,0.00007359057,0.00002727548],"category_scores_gemma":[0.0001507095,0.00008186975,0.00006662394,0.0003063903,0.00002463316,0.0006828038,0.0001228422,0.0000654778,0.00001891656],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009173315,"about_ca_system_score_gemma":0.0001736922,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004199844,"about_ca_topic_score_gemma":0.0005843063,"domain_scores_codex":[0.9988435,0.00005499161,0.0002957429,0.0005023775,0.0001168491,0.0001865237],"domain_scores_gemma":[0.9988685,0.0001368045,0.00005461078,0.0007167218,0.0001787991,0.00004456519],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000009035279,0.0001564642,0.002002747,0.00008285776,0.00001897273,2.038397e-7,0.0004606603,0.0003267338,0.08977181,0.4651417,0.008016486,0.4340123],"study_design_scores_gemma":[0.0003631132,0.00006015895,0.02061302,0.00001415067,0.00001077778,9.082545e-7,0.00003717086,0.7075495,0.2232145,0.03375593,0.01414832,0.0002324365],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03666257,0.00003341047,0.9547707,0.005281324,0.0003473573,0.0004350479,0.000002015317,0.0001645915,0.002302964],"genre_scores_gemma":[0.9415105,0.00000275766,0.05522071,0.001551334,0.00007350106,0.00008963424,0.00001223968,0.000002905618,0.001536432],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9048479,"threshold_uncertainty_score":0.3338552,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4407842065","doi":"10.1145/3706468.3706483","title":"Got It! Prompting Readability Using ChatGPT to Enhance Academic Texts for Diverse Learning Needs","year":2025,"lang":"en","type":"article","venue":"","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":11,"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":"Readability; Computer science; Multimedia; World Wide Web; Natural language processing; Mathematics education; Psychology; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.04025664368284644,"gpt":0.3625063414730358,"spread":0.3222496977901894,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001079858,0.0001462579,0.0001889792,0.0001332239,0.000393939,0.0001189803,0.0007353565,0.0001251824,0.00001160342],"category_scores_gemma":[0.0007577018,0.00014007,0.0000728043,0.0008880073,0.00004180536,0.0005597394,0.0003927102,0.0003395935,0.00002280833],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001828488,"about_ca_system_score_gemma":0.0001384518,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009701745,"about_ca_topic_score_gemma":0.00002746725,"domain_scores_codex":[0.9984314,0.00009200467,0.0003652398,0.0005616749,0.0001835657,0.0003661227],"domain_scores_gemma":[0.9987295,0.0003591973,0.00009424445,0.0005538524,0.0001698135,0.00009335748],"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":[0.00005250972,0.0001162923,0.009042855,0.0002293228,0.00002578214,5.378039e-7,0.00807568,0.004472625,0.07623139,0.06114043,0.0008819889,0.8397306],"study_design_scores_gemma":[0.0004319132,0.0002942739,0.0187385,0.0004825171,0.00004596161,0.00000676698,0.002876879,0.7200707,0.1903445,0.01984575,0.04579958,0.001062637],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3091338,0.00002303327,0.6842667,0.0048697,0.0001588723,0.0005576698,9.550007e-7,0.0001971069,0.0007921443],"genre_scores_gemma":[0.933813,0.000003281709,0.0632712,0.0007734484,0.00004841194,0.00005785882,0.000002083024,0.000005662438,0.002025036],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8386679,"threshold_uncertainty_score":0.571189,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2013933696","doi":"10.5539/elt.v4n1p11","title":"Use of Syntactic Elaboration Techniques to Enhance Comprehensibility of EST Texts","year":2011,"lang":"en","type":"article","venue":"English Language Teaching","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Elaboration; Syntax; Lexis; Linguistics; Reading comprehension; Comprehension; Psychology; Computer science; Reading (process); Natural language processing; Artificial intelligence; Humanities","retraction":null,"screen_n_in":null,"score":{"opus":0.0280590860492004,"gpt":0.29140460104287,"spread":0.2633455149936696,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007349069,0.00009964171,0.0001846588,0.0001033626,0.0000499253,0.00003583308,0.0004259276,0.00006005552,0.00001132595],"category_scores_gemma":[0.001406988,0.00009574678,0.00004345332,0.0002335967,0.00003688805,0.0009145481,0.0001248772,0.0001891807,0.000002926979],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000392859,"about_ca_system_score_gemma":0.00003354515,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008315502,"about_ca_topic_score_gemma":0.0001039794,"domain_scores_codex":[0.9987931,0.000234943,0.0003501838,0.0003002623,0.0001889266,0.000132583],"domain_scores_gemma":[0.9985145,0.0002273394,0.0001825604,0.0008716706,0.0001499115,0.00005396515],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00003002417,0.0004926252,0.003961207,0.0001297829,0.00001808157,0.000003728522,0.3801365,0.00002333203,0.2569817,0.02845085,0.00005479498,0.3297173],"study_design_scores_gemma":[0.00004629854,0.0001725854,0.01389403,0.00009298771,0.00001053324,0.000001756637,0.002524988,0.000761839,0.9813049,0.0005626366,0.0004247439,0.0002027258],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.747517,0.0000246194,0.2509567,0.000020659,0.0000724109,0.0002061407,0.000005370281,0.0001828309,0.001014226],"genre_scores_gemma":[0.8336222,9.042975e-7,0.1662756,0.00003994463,0.00002569352,0.000008700151,0.000003304592,0.000005468102,0.00001814972],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7243232,"threshold_uncertainty_score":0.390444,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4403510607","doi":"10.1523/jneurosci.0374-24.2024","title":"The Spatiotemporal Dynamics of Bottom–Up and Top–Down Processing during At-a-Glance Reading","year":2024,"lang":"en","type":"article","venue":"Journal of Neuroscience","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"York University; New York University Abu Dhabi; National Science Foundation","keywords":"Top-down and bottom-up design; Dynamics (music); Reading (process); Computer science; Physics; Linguistics; Acoustics; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.01674059201527363,"gpt":0.2681636207854258,"spread":0.2514230287701522,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000697872,0.00006628731,0.0001027309,0.00008093855,0.0002870634,0.000349687,0.0005870006,0.00002348214,2.718417e-7],"category_scores_gemma":[0.0002105429,0.00004381631,0.00003864726,0.0004468632,0.0001847831,0.0009243603,0.0001407215,0.0001914057,4.10348e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007340019,"about_ca_system_score_gemma":0.0001281651,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003814543,"about_ca_topic_score_gemma":0.000006375689,"domain_scores_codex":[0.9989232,0.00004549913,0.0003396606,0.0001931032,0.0003510339,0.0001474718],"domain_scores_gemma":[0.9992687,0.0001336239,0.0002453082,0.0001988516,0.00009463859,0.00005886015],"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":[0.00005570456,0.00006875517,0.02006233,0.0004521429,0.000006058543,0.0001085167,0.00415374,0.0004146103,0.5370215,0.03799779,0.0001304453,0.3995284],"study_design_scores_gemma":[0.0001830818,0.0002161833,0.3166258,0.0003294665,0.0000095199,0.001384483,0.0001001424,0.6484072,0.02531235,0.005053578,0.002195164,0.0001830531],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9297909,0.0004229227,0.06582259,0.003153808,0.0006799239,0.00004924438,9.797162e-7,0.00002103154,0.00005860432],"genre_scores_gemma":[0.9980519,0.000122387,0.001560463,0.00003572853,0.0000366791,5.869823e-7,4.800723e-8,0.000003186709,0.0001889986],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6479926,"threshold_uncertainty_score":0.337204,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4226024717","doi":"10.1037/xlm0001119","title":"A reexamination of the impact of morphology on transposed character priming effects.","year":2022,"lang":"en","type":"article","venue":"Journal of Experimental Psychology Learning Memory and Cognition","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":10,"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","keywords":"Morpheme; Priming (agriculture); Psychology; Character (mathematics); Linguistics; Lexical decision task; Repetition priming; Communication; Mathematics; Cognition; Biology; Neuroscience; Philosophy","retraction":null,"screen_n_in":null,"score":{"opus":0.02019737658067601,"gpt":0.3151418303554844,"spread":0.2949444537748084,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005907336,0.00007261278,0.0001685723,0.0001283254,0.0001371532,0.000006547298,0.0002193586,0.00004359776,0.00003246174],"category_scores_gemma":[0.00004760797,0.00005432269,0.0001234267,0.0001510805,0.00009492072,0.0001618626,0.00003645959,0.000332303,4.178074e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004000665,"about_ca_system_score_gemma":0.00002595913,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003127627,"about_ca_topic_score_gemma":6.308178e-8,"domain_scores_codex":[0.9986989,0.0006034152,0.0003086365,0.0001315415,0.0001755775,0.00008191297],"domain_scores_gemma":[0.999079,0.0001556987,0.0005459184,0.0001320239,0.00006259665,0.00002469465],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.0003680752,0.0005068826,0.001202835,0.00001103464,0.00003597718,0.000005185096,0.003445083,0.000302788,0.973571,0.0002393499,0.00001541937,0.02029634],"study_design_scores_gemma":[0.002213673,0.007032424,0.5484211,0.00006230732,0.00003138679,0.0005818026,0.0007332634,0.0006829134,0.4391907,0.0009115061,0.00002663175,0.0001123372],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.996065,0.0001356119,0.002902247,0.0002030035,0.0002371243,0.0001220128,0.000001301592,0.000005766773,0.0003279352],"genre_scores_gemma":[0.9996675,0.000007000255,0.0001721986,0.0001065389,0.00002165076,0.000006702642,0.000002391035,0.000003882801,0.00001213858],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5472182,"threshold_uncertainty_score":0.2215215,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2460540981","doi":"10.5430/ijba.v7n4p1","title":"Syntactic and Lexical Complexity of Reading Correlates with Complexity of Writing in Adults","year":2016,"lang":"en","type":"article","venue":"International Journal of Business Administration","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Newspaper; Computer science; Sentence; Reading (process); Linguistics; Natural language processing; Lexical density; Artificial intelligence; Syntax; Lexical item; Sociology","retraction":null,"screen_n_in":null,"score":{"opus":0.04449037570043224,"gpt":0.2892062474579364,"spread":0.2447158717575042,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003996447,0.00007571183,0.0001927034,0.000167716,0.00002121795,0.00003978383,0.0003193161,0.00004132245,0.000007649467],"category_scores_gemma":[0.0002629746,0.00005310615,0.00002888765,0.000180168,0.0002840784,0.000851282,0.00004240346,0.00007790112,3.601162e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005798387,"about_ca_system_score_gemma":0.0001591298,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000443037,"about_ca_topic_score_gemma":0.00007659844,"domain_scores_codex":[0.9987009,0.00005668235,0.0006501991,0.0001297497,0.0003869953,0.00007545353],"domain_scores_gemma":[0.9979036,0.0002469238,0.000720697,0.0001133471,0.000977619,0.00003784984],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.001788216,0.0008887341,0.3978238,0.0002254875,0.0001010084,0.00007034754,0.001352747,0.0001341345,0.03172269,0.4935083,0.000009884047,0.07237468],"study_design_scores_gemma":[0.001083056,0.0002883008,0.9609017,0.001203738,0.000008315583,0.0004863706,0.0001323971,0.003698248,0.01069858,0.02139864,0.000006504893,0.00009420315],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8009082,0.00001528029,0.1957143,0.003100574,0.0001125464,0.00005237308,0.000006372777,0.000004995748,0.00008533544],"genre_scores_gemma":[0.9904525,0.00002137256,0.009464835,0.00001216084,0.00004034133,9.464929e-7,0.000002722309,0.000002927638,0.000002243713],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5630779,"threshold_uncertainty_score":0.2165606,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2905305848","doi":"10.5539/elt.v12n1p56","title":"Paraphrasing Strategy in EFL Ecuadorian B1 Students and Implications on Reading Comprehension","year":2018,"lang":"en","type":"article","venue":"English Language Teaching","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Reading comprehension; Psychology; Paraphrase; Mathematics education; Comprehension; Test (biology); Reciprocal teaching; Competence (human resources); Literacy; Linguistics; Reading (process); Pedagogy; Social psychology","retraction":null,"screen_n_in":null,"score":{"opus":0.02145483721000772,"gpt":0.3203907298057573,"spread":0.2989358925957495,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007318433,0.0001252288,0.0001357582,0.0001633794,0.0002742791,0.000295396,0.0004768963,0.0000647063,0.000003903576],"category_scores_gemma":[0.0002414912,0.0001216524,0.00002412384,0.0002048663,0.00004876947,0.0004804849,0.0001471258,0.0003261344,0.000009528488],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007162956,"about_ca_system_score_gemma":0.00001631012,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001952708,"about_ca_topic_score_gemma":0.000118102,"domain_scores_codex":[0.9986956,0.0002172052,0.000225431,0.0004342122,0.0001907557,0.0002368717],"domain_scores_gemma":[0.9990451,0.0002120543,0.00007167368,0.0005616142,0.00003114192,0.0000784677],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00002629334,0.0004274742,0.06980792,0.00003571795,0.00002041822,0.00002185782,0.2936852,0.0001537145,0.02070063,0.1048925,0.0001540405,0.5100742],"study_design_scores_gemma":[0.001756429,0.0005394145,0.9383277,0.0004177676,0.00001883245,0.00003177349,0.02958742,0.01479748,0.005625428,0.006277736,0.001643852,0.0009761988],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9801356,0.0000521109,0.01494295,0.000154823,0.0001477994,0.000178377,0.000001876317,0.0002101091,0.004176373],"genre_scores_gemma":[0.9960437,0.000003256256,0.003548529,0.0001469706,0.0001981155,0.000009468869,0.000007303758,0.000009029908,0.00003365016],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8685197,"threshold_uncertainty_score":0.496084,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4400663124","doi":"10.54254/2755-2721/76/20240608","title":"A review of methods for alleviating hallucination issues in large language models","year":2024,"lang":"en","type":"review","venue":"Applied and Computational Engineering","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Milton District Hospital","funders":"","keywords":"Psychology; Computer science; Linguistics; Philosophy","retraction":null,"screen_n_in":null,"score":{"opus":0.04260581369658373,"gpt":0.3892562671185863,"spread":0.3466504534220026,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008790761,0.0001763745,0.000641937,0.0001794273,0.00001902835,0.00003807905,0.000212592,0.00008207597,7.5675e-7],"category_scores_gemma":[0.00005175592,0.000157841,0.0001061313,0.0003433822,0.000005745094,0.0001078238,0.00009475322,0.000137171,0.000001283516],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004094974,"about_ca_system_score_gemma":0.00006226378,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002749249,"about_ca_topic_score_gemma":3.271805e-7,"domain_scores_codex":[0.9989246,0.00003334797,0.0005071291,0.0003224487,0.00008643641,0.0001260444],"domain_scores_gemma":[0.9992014,0.0004471907,0.0001262193,0.0001586349,0.00004122931,0.00002535248],"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":[1.502252e-7,0.000009754374,5.705304e-9,0.08518486,0.00001732948,1.367546e-7,0.0001762398,0.003735394,0.000001019203,0.207141,0.00001243043,0.7037217],"study_design_scores_gemma":[0.00006943286,0.000007882169,8.853671e-7,0.02566669,0.00007325201,0.000005168918,0.000006380975,0.8287368,6.736884e-7,0.006471451,0.1387838,0.0001776388],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[9.852523e-8,0.5088325,0.4907283,0.0000231572,0.00002466443,0.0003262867,0.000006966939,0.00003370699,0.00002438532],"genre_scores_gemma":[0.00002751564,0.6650732,0.3345787,0.00002462212,0.00002117853,0.0001830549,0.0000762269,0.00001132769,0.000004206469],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.8250014,"threshold_uncertainty_score":0.643657,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4303437283","doi":"10.7202/1092190ar","title":"Revisiting simplification in corpus-based translation studies: Insights from readability research","year":2022,"lang":"en","type":"article","venue":"Meta Journal des traducteurs","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Readability; Computer science; Natural language processing; Linguistics; Artificial intelligence; Set (abstract data type); Sentence; Vocabulary","retraction":null,"screen_n_in":null,"score":{"opus":0.2309234669878421,"gpt":0.3783169797667931,"spread":0.147393512778951,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005677468,0.0001737854,0.0003919407,0.0004707641,0.001148846,0.0002473088,0.001067846,0.00004883869,0.00004459025],"category_scores_gemma":[0.0007047323,0.0001550102,0.0001845839,0.001861768,0.0002003316,0.0008999239,0.00009228622,0.001061026,0.000006649544],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006582049,"about_ca_system_score_gemma":0.0002234132,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001338742,"about_ca_topic_score_gemma":0.00006530516,"domain_scores_codex":[0.9936767,0.003457011,0.0008084956,0.000618781,0.001071943,0.0003671055],"domain_scores_gemma":[0.9967119,0.001723754,0.0002577466,0.0007697422,0.0004096903,0.0001271775],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00009659707,0.0003653269,0.003617491,0.00006136671,0.0001785609,0.00003564787,0.004454503,0.005876519,0.01555892,0.01000498,0.00007119563,0.9596789],"study_design_scores_gemma":[0.001210879,0.000509745,0.1697516,0.00009440492,0.0002102047,0.00009488661,0.001476414,0.04960646,0.007966699,0.7181695,0.05018804,0.0007212292],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7926846,0.05244048,0.1493547,0.004594233,0.0003324174,0.0004545285,0.0000118495,0.00008701954,0.00004020632],"genre_scores_gemma":[0.9787678,0.001797146,0.01907118,0.0001114335,0.000111165,0.00009629436,0.00001827877,0.00001404902,0.00001268461],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9589577,"threshold_uncertainty_score":0.883611,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2563494058","doi":"10.5539/ies.v10n1p47","title":"Comparison of Oral Reading Errors between Contextual Sentences and Random Words among Schoolchildren","year":2016,"lang":"en","type":"article","venue":"International Education Studies","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Reading (process); Sentence; Set (abstract data type); Psychology; Mathematics; Linguistics; Computer science; Natural language processing","retraction":null,"screen_n_in":null,"score":{"opus":0.08323997651935867,"gpt":0.4093566218493974,"spread":0.3261166453300387,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003390963,0.00009703984,0.0002310382,0.0001392622,0.00009372859,0.00005157893,0.0003645359,0.00003292228,0.00000837339],"category_scores_gemma":[0.0007857834,0.00006732619,0.00003996911,0.0001279471,0.0002385424,0.0006493201,0.0001358592,0.00005463167,0.000007959816],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006595803,"about_ca_system_score_gemma":0.00007740066,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001291373,"about_ca_topic_score_gemma":0.00004305655,"domain_scores_codex":[0.9989251,0.00006868057,0.000380165,0.0002608178,0.0002650442,0.0001001765],"domain_scores_gemma":[0.9983783,0.0004586614,0.0002401484,0.000180584,0.0006948209,0.00004743098],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000010267,0.00005859321,0.8366734,0.000005715805,0.000104966,4.170706e-8,0.002700529,0.000001770546,0.0001839829,0.009415197,0.0008820519,0.1499635],"study_design_scores_gemma":[0.0005797512,0.00004537362,0.982062,0.0001516145,0.00001920406,0.000002330527,0.003996015,0.0001870762,0.00184181,0.00833948,0.002633858,0.0001415268],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9363446,0.0004669133,0.0557206,0.005974509,0.0009849027,0.0001248347,0.000007417568,0.00004362527,0.0003325673],"genre_scores_gemma":[0.9956608,0.00008491008,0.003696419,0.00004578106,0.00008362431,0.0000251934,0.000004841443,0.000003180412,0.0003952225],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.149822,"threshold_uncertainty_score":0.2745482,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}