{"meta":{"query_hash":"f43fd6fb7c73","filters":{"topic":"Text Readability and Simplification"},"cohort_total":268,"direct_labels_cover":1,"predictions_cover":268,"exported":268,"export_cap":100000,"truncated":false,"label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"permalink":"https://metacan.xera.ac/q/f43fd6fb7c73","api":"https://metacan.xera.ac/api/v1/cohort?topic=Text+Readability+and+Simplification"},"results":[{"id":"W138511995","doi":"","title":"Strategies for Teaching Word Recognition to Children with Reading Deficiencies.","year":2000,"lang":"en","type":"article","venue":"Early childhood education","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Reading (process); Word (group theory); Psychology; Word recognition; Linguistics; Computer science; Philosophy","score_opus":0.012410120996237773,"score_gpt":0.2436448387961709,"score_spread":0.23123471779993313,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W138511995","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8560469,0.00002176957,0.13896951,0.0011574979,0.00010936966,0.00071073364,0.00000551548,0.00018763878,0.0027910492],"genre_scores_gemma":[0.92565215,0.0000026214616,0.07334227,0.00040125946,0.00016675044,0.00016938112,0.000058243877,0.000012206546,0.00019509703],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9988268,0.000053767202,0.0002020314,0.0004679231,0.00018697388,0.0002625117],"domain_scores_gemma":[0.9992222,0.00006002882,0.0000681319,0.00045265988,0.0000903187,0.000106635365],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033558474,0.00013933265,0.00010912561,0.00013017701,0.00037103254,0.00048341023,0.00041126492,0.000053823383,0.000022696397],"category_scores_gemma":[0.00004553675,0.00012824882,0.000039818344,0.0003424898,0.000026129424,0.001319702,0.000017202448,0.00013650396,0.000107446904],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005760641,0.00023158989,0.00093432516,0.0000028926072,0.000008623415,2.6730737e-8,0.025762279,0.00012069029,0.00011919691,0.008675963,0.0004969352,0.9636417],"study_design_scores_gemma":[0.00020615988,0.00029011632,0.9788688,0.00006567033,0.000014905713,0.000022631215,0.0011539978,0.00009046052,0.0004098525,0.017099015,0.0014642851,0.0003141501],"about_ca_topic_score_codex":0.0002433955,"about_ca_topic_score_gemma":0.000025304804,"teacher_disagreement_score":0.9779344,"about_ca_system_score_codex":0.000081163766,"about_ca_system_score_gemma":0.00049496157,"threshold_uncertainty_score":0.52298355},"labels":[],"label_agreement":null},{"id":"W1586471131","doi":"","title":"A Readability Study and Its Relevance to Simplification on Translations of Lun Yu","year":2014,"lang":"en","type":"article","venue":"Studies in literature and language","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Readability; Sentence; Reading (process); Linguistics; Index (typography); Computer science; Relevance (law); Natural language processing; Philosophy; World Wide Web","score_opus":0.0239070417033075,"score_gpt":0.3340671695770551,"score_spread":0.31016012787374764,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1586471131","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9922167,0.0032515768,0.002449852,0.0011459397,0.00006171568,0.0004551693,0.000009822574,0.00003128696,0.0003779535],"genre_scores_gemma":[0.9983886,0.00006422992,0.0012891858,0.00014288821,0.0000247594,0.00003690065,0.0000025612553,0.0000028727452,0.00004798619],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.99908763,0.00013479537,0.00021274359,0.0003490855,0.000113989176,0.00010177328],"domain_scores_gemma":[0.999106,0.0003523121,0.000044797962,0.00038052164,0.00008113821,0.00003526478],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00049798517,0.000095257055,0.00017966278,0.00008822061,0.000070748865,0.000034652923,0.00013885462,0.000037485846,5.119702e-7],"category_scores_gemma":[0.0004227617,0.000075275624,0.000015198261,0.0003842498,0.00004003429,0.00017522805,0.000053970332,0.000101955935,8.1385264e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008459149,0.000592297,0.008181618,0.00039762736,0.000042980148,0.000004916753,0.6194567,0.000048782324,0.0044725947,0.09163943,0.00012878558,0.27494967],"study_design_scores_gemma":[0.0017850177,0.0028921228,0.93000144,0.0008126067,0.00005291834,0.000016872418,0.018762536,0.005787437,0.0050725387,0.028051915,0.0058514276,0.00091315707],"about_ca_topic_score_codex":0.000008004646,"about_ca_topic_score_gemma":0.00010191334,"teacher_disagreement_score":0.9218198,"about_ca_system_score_codex":0.000013987367,"about_ca_system_score_gemma":0.000005548725,"threshold_uncertainty_score":0.30696508},"labels":[],"label_agreement":null},{"id":"W1588239581","doi":"10.14264/158129","title":"Acquisition of word order in Chinese as a foreign language: An error taxonomy","year":2006,"lang":"en","type":"dissertation","venue":"The University of Queensland","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Word order; Linguistics; Second-language acquisition; Computer science; Sentence; Natural language processing; Verb; Chinese as a foreign language; Foreign language; Taxonomy (biology); Artificial intelligence","score_opus":0.011351428564590968,"score_gpt":0.2381980508552892,"score_spread":0.22684662229069824,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1588239581","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98443896,0.000071714276,0.0067755096,0.00009539258,0.000040008323,0.00030710286,0.000013336944,0.000023725695,0.008234258],"genre_scores_gemma":[0.99573016,0.0000068292698,0.0023619616,0.000009836017,0.000014737697,7.656263e-7,0.00028578064,0.0000044138833,0.0015854943],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.9992716,0.00010336651,0.00014921352,0.00021293503,0.0001616039,0.00010132604],"domain_scores_gemma":[0.99909896,0.000061938124,0.00022994402,0.0004651368,0.000120003,0.000024009494],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002070636,0.000111623056,0.00020691245,0.00014762272,0.000066220695,0.00001215551,0.0006255577,0.0001268684,0.000035659545],"category_scores_gemma":[0.00001394927,0.00009580216,0.000057785343,0.0003408801,0.000058160545,0.00024291303,0.0000358331,0.00012845274,0.0000059428485],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0049177324,0.0042455974,0.17568219,0.0031805453,0.00047972111,0.000251105,0.31745282,0.00807537,0.015320458,0.15019946,0.0051117344,0.31508327],"study_design_scores_gemma":[0.0012480689,0.00020885721,0.9669893,0.00018197816,0.000058463305,0.0000067809297,0.012173085,0.006126958,0.00091359083,0.010733954,0.0009567779,0.00040220827],"about_ca_topic_score_codex":0.007122929,"about_ca_topic_score_gemma":0.010774891,"teacher_disagreement_score":0.7913071,"about_ca_system_score_codex":0.000036167574,"about_ca_system_score_gemma":0.0001085889,"threshold_uncertainty_score":0.9994887},"labels":[],"label_agreement":null},{"id":"W1794926608","doi":"10.7202/1029140ar","title":"Mise sur pied d’une mesure de la compréhension de textes en langue seconde","year":2015,"lang":"fr","type":"article","venue":"Nouveaux cahiers de la recherche en éducation","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université Laval; Université du Québec à Trois-Rivières; Université TÉLUQ","funders":"","keywords":"Humanities; Philosophy; Art","score_opus":0.13363193737850956,"score_gpt":0.3773233387236118,"score_spread":0.24369140134510223,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1794926608","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7393828,0.002362176,0.20729673,0.022522511,0.0010913116,0.00052272395,0.00002087251,0.00029716248,0.026503714],"genre_scores_gemma":[0.8970814,0.0003623819,0.09143689,0.0011280631,0.00045929023,0.00006897734,0.000076347635,0.000052655952,0.009333998],"study_design_codex":"qualitative","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9767396,0.02102422,0.00047680462,0.0006790838,0.00039358556,0.0006867296],"domain_scores_gemma":[0.9828389,0.015007671,0.0002480705,0.00094379473,0.00042911273,0.00053244154],"candidate_categories":["metaresearch","metaepi_narrow","research_integrity"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.026891146,0.00035761145,0.00036061768,0.0001731503,0.00019654368,0.00038326424,0.00087775296,0.0025503985,0.00007148091],"category_scores_gemma":[0.013671454,0.00039893508,0.00015219355,0.0008380621,0.00049908226,0.0006941951,0.000104813575,0.0025330535,0.0001345124],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000117772775,0.0012174615,0.005349754,0.00036344252,0.00011238701,0.000041631454,0.6891599,0.0019209774,0.033055242,0.06941148,0.044463485,0.15478644],"study_design_scores_gemma":[0.0029222036,0.00041868188,0.18336189,0.00049652124,0.00033332192,0.0009623524,0.043059353,0.11443125,0.021738399,0.36372593,0.26677284,0.0017772531],"about_ca_topic_score_codex":0.0035924166,"about_ca_topic_score_gemma":0.00041673516,"teacher_disagreement_score":0.6461006,"about_ca_system_score_codex":0.007163716,"about_ca_system_score_gemma":0.0048076534,"threshold_uncertainty_score":0.9998463},"labels":[],"label_agreement":null},{"id":"W194107648","doi":"10.55016/ojs/ajer.v47i1.54843","title":"Implicit and Explicit Awareness of a Phonics Rule in the Word Recognition of Students With and Without Learning Disabilities","year":2001,"lang":"en","type":"article","venue":"Alberta Journal of Educational Research","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Brock University","funders":"University of Oxford","keywords":"Phonics; Psychology; Word (group theory); Word recognition; Learning disability; Mathematics education; Linguistics; Cognitive psychology; Primary education; Developmental psychology; Reading (process)","score_opus":0.09379435475860663,"score_gpt":0.4029971680632219,"score_spread":0.30920281330461524,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W194107648","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99624485,0.00019802571,0.00019046161,0.0028147534,0.000016855358,0.00012299881,6.096247e-7,2.8445916e-7,0.00041118552],"genre_scores_gemma":[0.9989736,0.00022279352,0.00053518754,0.000013472934,0.000025153342,0.000012921827,0.0000016438045,0.0000032507423,0.00021195888],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9985134,0.00030847138,0.00032242158,0.00013593001,0.0005812992,0.0001384656],"domain_scores_gemma":[0.99240214,0.006729596,0.00016769921,0.00017315161,0.0004763147,0.00005107699],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016239946,0.000058314814,0.00014497274,0.00018214686,0.00009773535,0.00007239511,0.0004354633,0.000028994198,0.000040585343],"category_scores_gemma":[0.0020315116,0.00003876446,0.000019562518,0.0004313238,0.00017673252,0.00037673578,0.00007363512,0.00024749848,0.000001110292],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008806692,0.0002832377,0.9813242,0.000042427368,0.000014492217,9.508117e-8,0.008570826,0.000027163851,0.0003321971,0.0034574645,0.000012815457,0.0058469945],"study_design_scores_gemma":[0.0003811696,0.000283777,0.98281944,0.00016118513,0.000006937868,0.00012678553,0.005904952,0.00019255445,0.0002662796,0.009642329,0.00015797214,0.00005659809],"about_ca_topic_score_codex":0.0010067424,"about_ca_topic_score_gemma":0.00071600755,"teacher_disagreement_score":0.006421124,"about_ca_system_score_codex":0.000038017566,"about_ca_system_score_gemma":0.0003054065,"threshold_uncertainty_score":0.24320558},"labels":[],"label_agreement":null},{"id":"W1961156749","doi":"10.18438/b84301","title":"Selecting Which Databases to Teach Students in Communication Disorders by Considering Database Pairs that Index Core Journals in the Field","year":2015,"lang":"en","type":"article","venue":"Evidence Based Library and Information Practice","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"CINAHL; PsycINFO; Session (web analytics); Database; Computer science; MEDLINE; Citation; Online database; Search engine indexing; Library science; Web of science; World Wide Web; Psychology","score_opus":0.0687348282726331,"score_gpt":0.3485507417334791,"score_spread":0.279815913460846,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1961156749","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25638995,0.0014059216,0.31813785,0.42105687,0.00014707918,0.0014666262,0.000019944464,0.00016980973,0.0012059669],"genre_scores_gemma":[0.9469286,0.00055452395,0.0100796735,0.042319056,0.00000787136,0.00004861773,0.000054592045,0.0000031049603,0.0000039577594],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.99808365,0.00067909696,0.0004270675,0.00017505836,0.00046824696,0.00016687349],"domain_scores_gemma":[0.99394673,0.0049851243,0.00027068894,0.0006435143,0.00006007782,0.00009384851],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.003514786,0.000106558,0.000105402076,0.00021647071,0.00016064232,0.0009005154,0.0009171281,0.000043223496,0.000008800916],"category_scores_gemma":[0.006227727,0.00008922234,0.0000113698525,0.0010422567,0.000020845571,0.1527803,0.0003387641,0.00042187434,0.000007689156],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004395202,0.0004546658,0.861927,0.00014797194,0.000012898398,0.000003552434,0.022296865,0.0026871802,0.000090277754,0.023453765,0.03591591,0.05257044],"study_design_scores_gemma":[0.002098396,0.00044127365,0.37023515,0.0019407666,0.000024347208,0.00007650725,0.04863241,0.13099155,0.002015467,0.0010045166,0.44168276,0.000856883],"about_ca_topic_score_codex":0.00020969138,"about_ca_topic_score_gemma":0.000034471297,"teacher_disagreement_score":0.69053864,"about_ca_system_score_codex":0.000023666042,"about_ca_system_score_gemma":0.00017763965,"threshold_uncertainty_score":0.86836904},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.009962077365459262,"score_gpt":0.22726213751455573,"score_spread":0.21730006014909647,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2005151783","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9673544,0.00043703514,0.026568428,0.0004870234,0.00007717778,0.000042859694,0.0000016117939,0.000022192085,0.0050092307],"genre_scores_gemma":[0.9942454,0.0000069680987,0.005183578,0.00031280526,0.00012944447,1.1935923e-7,6.967869e-7,0.000004084175,0.00011691786],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9989767,0.00016936958,0.00037416033,0.00013835075,0.00016263624,0.00017878346],"domain_scores_gemma":[0.99898314,0.00038481614,0.0002846313,0.00019248658,0.00008254047,0.00007237521],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014667563,0.00007507939,0.00018588643,0.00017263142,0.000073346884,0.00008811311,0.0004836088,0.000052890806,0.00004955749],"category_scores_gemma":[0.00016649064,0.000074481184,0.00007600357,0.00021558838,0.000026461139,0.0007523064,0.000081924285,0.0003007667,0.000005255458],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029662557,0.00013133576,0.022433862,0.00012136167,0.000023541306,0.00037542052,0.016171278,0.00006273418,0.02038395,0.0307012,0.00031591207,0.9092497],"study_design_scores_gemma":[0.011674554,0.001211329,0.59159803,0.0037947977,0.00007410893,0.0028354425,0.24715322,0.06963205,0.024375426,0.0071418663,0.03830942,0.0021997544],"about_ca_topic_score_codex":0.000046241854,"about_ca_topic_score_gemma":0.0002102966,"teacher_disagreement_score":0.90705,"about_ca_system_score_codex":0.00007719698,"about_ca_system_score_gemma":0.00005674355,"threshold_uncertainty_score":0.30372545},"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,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_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","score_opus":0.028059086049200398,"score_gpt":0.29140460104286997,"score_spread":0.2633455149936696,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2013933696","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.74751705,0.000024619398,0.2509567,0.000020658996,0.000072410905,0.00020614066,0.000005370281,0.00018283086,0.0010142261],"genre_scores_gemma":[0.8336222,9.0429745e-7,0.1662756,0.000039944633,0.000025693516,0.000008700151,0.0000033045917,0.0000054681022,0.000018149723],"study_design_codex":"qualitative","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9987931,0.000234943,0.0003501838,0.00030026227,0.00018892661,0.00013258297],"domain_scores_gemma":[0.99851453,0.00022733945,0.0001825604,0.0008716706,0.00014991147,0.000053965152],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00073490693,0.00009964171,0.00018465877,0.000103362596,0.0000499253,0.000035833076,0.00042592763,0.000060055525,0.000011325953],"category_scores_gemma":[0.0014069885,0.00009574678,0.00004345332,0.00023359667,0.000036888046,0.0009145481,0.00012487717,0.00018918072,0.0000029269786],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030024168,0.00049262523,0.0039612073,0.00012978291,0.000018081571,0.0000037285215,0.38013655,0.000023332026,0.2569817,0.028450847,0.000054794982,0.32971734],"study_design_scores_gemma":[0.00004629854,0.0001725854,0.013894033,0.000092987706,0.0000105332365,0.0000017566371,0.0025249878,0.00076183904,0.9813049,0.00056263665,0.00042474386,0.00020272585],"about_ca_topic_score_codex":0.0008315502,"about_ca_topic_score_gemma":0.00010397944,"teacher_disagreement_score":0.72432315,"about_ca_system_score_codex":0.000039285896,"about_ca_system_score_gemma":0.000033545148,"threshold_uncertainty_score":0.39044404},"labels":[],"label_agreement":null},{"id":"W2014841664","doi":"10.5539/ijel.v1n1p37","title":"A Comparison between the Difficulty Level (Readability) of English Medical Texts and Their Persian Translations","year":2011,"lang":"en","type":"article","venue":"International Journal of English Linguistics","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Readability; Persian; Significant difference; Index (typography); Linguistics; Syllabus; Psychology; Natural language processing; Computer science; History; Mathematics education; Mathematics; Statistics; Philosophy; World Wide Web","score_opus":0.07237472604349313,"score_gpt":0.3096337522581213,"score_spread":0.23725902621462816,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2014841664","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.33229476,0.0006111937,0.61780345,0.00077404786,0.016494786,0.00038817158,0.00022686677,0.00010885619,0.0312979],"genre_scores_gemma":[0.9917915,0.000022080463,0.0052982983,0.000038615308,0.0028304488,0.0000012087571,0.0000055015844,0.000005782586,0.00000657842],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9981601,0.0001252477,0.0007796427,0.00016276208,0.00064558786,0.00012666055],"domain_scores_gemma":[0.98456717,0.0008698899,0.00044444067,0.0002691186,0.013708221,0.00014119224],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0009336632,0.0001220845,0.00025823156,0.00012514723,0.00007080056,0.00006761992,0.001347073,0.00010444399,0.000024599742],"category_scores_gemma":[0.04463605,0.000080822174,0.0001280243,0.00014778264,0.00023746282,0.00013717612,0.00010904422,0.00038241266,4.9974e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015597796,0.0018681729,0.3166989,0.000076309356,0.0009162175,0.00001765227,0.25260824,0.00017985093,0.00004127775,0.23210925,0.0021623918,0.19316575],"study_design_scores_gemma":[0.0017212988,0.0007345732,0.6406335,0.0003278916,0.0001933673,0.000016347563,0.0064694937,0.0092024105,0.006697961,0.034228243,0.29909116,0.0006837142],"about_ca_topic_score_codex":0.000025638283,"about_ca_topic_score_gemma":0.00003341731,"teacher_disagreement_score":0.6594967,"about_ca_system_score_codex":0.000042785065,"about_ca_system_score_gemma":0.0001821322,"threshold_uncertainty_score":0.9634114},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.026802824945245676,"score_gpt":0.27575806934328606,"score_spread":0.2489552443980404,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2017541092","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24391523,0.00005768184,0.73154384,0.004103417,0.00007570125,0.00010549331,1.3034798e-7,0.00015661845,0.020041874],"genre_scores_gemma":[0.9774354,0.0000026131963,0.021864956,0.00013105299,0.000029251065,0.0000051050865,0.0000010060971,0.0000014323907,0.00052915094],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9994997,0.00003445292,0.00012696163,0.00016750104,0.00006385886,0.00010754716],"domain_scores_gemma":[0.9996167,0.00004472195,0.00001559477,0.0002749613,0.000021753864,0.00002630161],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002014309,0.000042575004,0.000059505135,0.00006440534,0.000027795571,0.00004100361,0.00026704415,0.000024727493,0.000039981584],"category_scores_gemma":[0.0000098601395,0.000038228078,0.000017065027,0.0002522817,0.000013708468,0.00028138695,0.00005189629,0.00004920724,0.0005058198],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000016567232,0.00022809874,0.0045319702,0.000009472037,0.0000012423322,5.270181e-7,0.0011101725,0.00014596777,0.00087240484,0.43173432,0.0009378755,0.5604263],"study_design_scores_gemma":[0.00028774378,0.00002141927,0.5507277,0.000012949206,9.708235e-7,0.000007002038,0.000043402466,0.38401183,0.0016027528,0.008356005,0.054755054,0.00017317334],"about_ca_topic_score_codex":0.000036276375,"about_ca_topic_score_gemma":0.0007646286,"teacher_disagreement_score":0.7335202,"about_ca_system_score_codex":0.000046618352,"about_ca_system_score_gemma":0.000017866418,"threshold_uncertainty_score":0.6501459},"labels":[],"label_agreement":null},{"id":"W2024022825","doi":"10.1017/s0140525x0346010x","title":"Eye-movement control in reading: Models and predictions","year":2003,"lang":"en","type":"article","venue":"Behavioral and Brain Sciences","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Eye movement; Word (group theory); Reading (process); Computer science; Control (management); Word processing; Encoding (memory); Natural language processing; Visual processing; Cognitive psychology; Artificial intelligence; Psychology; Speech recognition; Linguistics; Neuroscience","score_opus":0.05916790786284594,"score_gpt":0.31845350920583787,"score_spread":0.25928560134299194,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2024022825","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.85470176,0.000119494754,0.14105067,0.003134542,0.00007548372,0.00018172362,0.0000030704932,0.000039340175,0.0006939128],"genre_scores_gemma":[0.9961248,0.000010296993,0.0034165527,0.00033148157,0.0000048183674,0.000019168161,2.820545e-7,0.0000010034574,0.00009160089],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99915886,0.000062347084,0.0001379203,0.00031707317,0.00016182003,0.00016197396],"domain_scores_gemma":[0.9996981,0.000054764074,0.000039268733,0.00012440784,0.000018053364,0.00006542762],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00069232605,0.00006426248,0.000080845726,0.000078138655,0.00020446387,0.00016949607,0.00017118982,0.000030573563,0.000003106635],"category_scores_gemma":[0.000025082163,0.000050533246,0.000012345694,0.00028552386,0.00021873171,0.0006620702,0.000032985063,0.00005021716,7.489403e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000040214045,0.00032986066,0.22316718,0.000008674326,0.0000019465836,0.000004175658,0.0030387603,0.00056740374,0.005705619,0.69811046,0.00019767277,0.06886425],"study_design_scores_gemma":[0.0013440587,0.0007499376,0.4869747,0.00004365674,0.0000133381445,0.000026194308,0.0012317918,0.26231408,0.0009258538,0.2428018,0.00306005,0.0005145736],"about_ca_topic_score_codex":0.00013391189,"about_ca_topic_score_gemma":0.00007067008,"teacher_disagreement_score":0.45530862,"about_ca_system_score_codex":0.000014154072,"about_ca_system_score_gemma":0.000039337825,"threshold_uncertainty_score":0.2060686},"labels":[],"label_agreement":null},{"id":"W2076265438","doi":"10.1016/s0885-3924(00)00239-6","title":"Impact of the Edmonton Labeled Visual Information System on Physician Recall of Metastatic Cancer Patient Histories","year":2001,"lang":"en","type":"article","venue":"Journal of Pain and Symptom Management","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Grey Nuns Community Hospital","funders":"","keywords":"Medicine; Memorization; Recall; Preference; Cancer; Crossover study; Internal medicine; Pathology; Alternative medicine; Statistics; Psychology","score_opus":0.009816664753489034,"score_gpt":0.2565186429546267,"score_spread":0.24670197820113765,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2076265438","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9613538,0.00009517636,0.037126992,0.00032594753,0.00019754826,0.00022574066,0.0000023437494,0.0000073065767,0.0006651491],"genre_scores_gemma":[0.99938613,0.000036828173,0.0004635253,0.00007456658,0.000013033017,0.000003814974,3.711105e-7,0.0000017316171,0.000019992769],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99887717,0.00018233694,0.00045544215,0.000060208935,0.0003419708,0.00008287107],"domain_scores_gemma":[0.99890566,0.000060313254,0.00066922244,0.00018101257,0.00015126163,0.000032542037],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007319039,0.00007350454,0.00017554565,0.000101208694,0.00004568094,0.000030878087,0.00021531295,0.0000146849725,0.0000017104895],"category_scores_gemma":[0.000021909153,0.000043662807,0.00010022272,0.00020388082,0.00002568518,0.00032953816,0.000044857632,0.000055105742,3.1807002e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024384027,0.0005793732,0.01798556,0.0008364245,0.00058266445,0.0000056166346,0.014774623,0.0059912223,0.00069168623,0.046233863,0.001259171,0.91081595],"study_design_scores_gemma":[0.0026593327,0.0053835884,0.8689567,0.0016399493,0.00029253244,0.00002213953,0.006408665,0.09984226,0.0012971782,0.0014180549,0.011641807,0.0004377895],"about_ca_topic_score_codex":0.00005517534,"about_ca_topic_score_gemma":0.00000773208,"teacher_disagreement_score":0.91037816,"about_ca_system_score_codex":0.00022915051,"about_ca_system_score_gemma":0.000034127475,"threshold_uncertainty_score":0.17805177},"labels":[],"label_agreement":null},{"id":"W2078046066","doi":"10.7202/900315ar","title":"L’influence de la compréhension en lecture sur les résultats aux tests utilisés en éducation","year":2009,"lang":"fr","type":"article","venue":"Revue des sciences de l éducation","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Humanities; Psychology; Philosophy","score_opus":0.194212707731148,"score_gpt":0.3950219222366014,"score_spread":0.2008092145054534,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2078046066","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.85214233,0.0031097461,0.11840911,0.023592051,0.0006179365,0.00037714455,0.0000064249402,0.000152023,0.0015932337],"genre_scores_gemma":[0.96475667,0.00065566815,0.03285904,0.00057760964,0.0003279786,0.000021285045,0.000016819082,0.000011339823,0.0007735696],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9955542,0.0018352018,0.0005223399,0.0009225229,0.00044847268,0.0007172444],"domain_scores_gemma":[0.996238,0.0018766135,0.00031281708,0.00069998985,0.0006173389,0.0002552703],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00453734,0.00031173503,0.00026654778,0.00025076125,0.0012366989,0.00086650846,0.0012989664,0.00040409036,0.000028201284],"category_scores_gemma":[0.0039097397,0.00032916226,0.000108498534,0.0016908243,0.0013275135,0.0021773337,0.00008709123,0.00045511097,0.0000839296],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000192079,0.0010597651,0.01068049,0.00041640658,0.000012285242,0.000010821084,0.19344282,0.05558283,0.044598024,0.2756462,0.0017830032,0.41674814],"study_design_scores_gemma":[0.0001811084,0.00039708035,0.6644015,0.00055061013,0.000039925304,0.00048604066,0.0012775942,0.19125499,0.002939976,0.1272464,0.010741769,0.00048306078],"about_ca_topic_score_codex":0.0017995303,"about_ca_topic_score_gemma":0.0006014755,"teacher_disagreement_score":0.653721,"about_ca_system_score_codex":0.0021247244,"about_ca_system_score_gemma":0.0029482192,"threshold_uncertainty_score":0.999916},"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,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Reseau canadien de recherche respiratoire","keywords":"Computer science; Mathematics education; Psychology","score_opus":0.009490039935537474,"score_gpt":0.2730680900962374,"score_spread":0.2635780501606999,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2102137313","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8193082,0.000011773081,0.05239045,0.12720874,0.0006232538,0.0002460193,0.0000026589344,0.00006489653,0.00014401122],"genre_scores_gemma":[0.75320655,3.71991e-7,0.24640782,0.00012535321,0.00008279959,0.000029606412,0.000005522916,0.000004380245,0.00013759802],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99911505,0.000067564295,0.000170653,0.000337531,0.00016223457,0.0001469376],"domain_scores_gemma":[0.9988141,0.0004113747,0.000051295363,0.00036124006,0.0002513515,0.000110604924],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045314786,0.00008384866,0.00009400236,0.00011805895,0.00014662353,0.00038444542,0.00021687787,0.00005815494,0.000014598463],"category_scores_gemma":[0.0013720973,0.00008415354,0.000014917866,0.0003205634,0.00008201437,0.00066109607,0.00003014337,0.000075562566,0.000022402997],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000072886764,0.00010929164,0.001956936,0.000029084638,0.0000026617379,8.216252e-8,0.008595527,0.0000028624886,0.24495555,0.38060942,0.0009048204,0.36282647],"study_design_scores_gemma":[0.00013776026,0.0000699621,0.89912945,0.00004664074,0.000003244078,0.000014562674,0.00030197014,0.00024918318,0.009307888,0.08527831,0.005263625,0.00019737816],"about_ca_topic_score_codex":0.0000095735495,"about_ca_topic_score_gemma":0.000008230958,"teacher_disagreement_score":0.8971725,"about_ca_system_score_codex":0.00006654448,"about_ca_system_score_gemma":0.000115730974,"threshold_uncertainty_score":0.3707216},"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,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_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","score_opus":0.11304718228313618,"score_gpt":0.2731314378407082,"score_spread":0.16008425555757202,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2108070002","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04549238,0.00028503154,0.8980065,0.021124383,0.0003038334,0.0008772326,0.0000032710516,0.00070615596,0.03320123],"genre_scores_gemma":[0.92498183,0.000004854465,0.07372964,0.0009072375,0.0002661657,0.000037430797,0.000001937451,0.000007645355,0.00006327766],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99822843,0.00014875008,0.00035986575,0.00061561505,0.0002859537,0.00036138544],"domain_scores_gemma":[0.99821264,0.00008136186,0.00008692126,0.001156194,0.0002118502,0.00025102348],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014786464,0.00017555007,0.00022118817,0.00009463228,0.00013516608,0.00013209405,0.00064677105,0.00010708604,0.000002971092],"category_scores_gemma":[0.001697664,0.0001820506,0.00009600241,0.0003793297,0.00002048664,0.00011822411,0.000061811625,0.00020175219,0.00003660229],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000034252145,0.00040498175,0.00088030077,0.00010990529,0.000014229218,0.000032111937,0.006686528,0.00160557,0.004649634,0.80917126,0.00022665928,0.17618456],"study_design_scores_gemma":[0.00060813857,0.0010340412,0.17891157,0.00059843704,0.000067005014,0.00028177898,0.0001113271,0.085148424,0.04262037,0.5263739,0.16183934,0.0024056896],"about_ca_topic_score_codex":0.00070606597,"about_ca_topic_score_gemma":0.00059098494,"teacher_disagreement_score":0.8794894,"about_ca_system_score_codex":0.00043289035,"about_ca_system_score_gemma":0.0003015342,"threshold_uncertainty_score":0.7423808},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.17199358339867635,"score_gpt":0.2807526811983297,"score_spread":0.10875909779965334,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2116208975","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96840245,0.0006073855,0.026309747,0.0006488667,0.00021971959,0.00022704828,0.000009838852,0.00005738668,0.0035175795],"genre_scores_gemma":[0.99455655,0.00001977781,0.0052087847,0.0001589038,0.000032298154,0.000002549222,0.000006136264,0.0000047823514,0.000010231786],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99905765,0.00007548101,0.00022502802,0.00017929982,0.00016702633,0.00029553863],"domain_scores_gemma":[0.9990918,0.000051654464,0.00007025845,0.0004767379,0.00012749637,0.00018203299],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00055132416,0.00009618383,0.0001322491,0.00013049388,0.00024880984,0.000047853686,0.00038611714,0.000050912367,0.0000083803],"category_scores_gemma":[0.00005572793,0.0000670293,0.000036271354,0.00029566512,0.00014609989,0.00052261114,0.00009472401,0.00011392367,0.000014538343],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016784288,0.00014826414,0.06609589,0.00011822298,0.000041385498,0.0000020299087,0.049302246,0.000034238692,0.0085675055,0.7479705,0.00039034983,0.12731257],"study_design_scores_gemma":[0.0005275405,0.00010522924,0.9330117,0.00011326777,0.00007731502,0.00006061702,0.0030035565,0.015168831,0.010522023,0.030901738,0.0058807344,0.00062744354],"about_ca_topic_score_codex":0.051182576,"about_ca_topic_score_gemma":0.0043635014,"teacher_disagreement_score":0.8669158,"about_ca_system_score_codex":0.000057343543,"about_ca_system_score_gemma":0.00007503715,"threshold_uncertainty_score":0.9551357},"labels":[],"label_agreement":null},{"id":"W2119111309","doi":"10.7202/603128ar","title":"Analyse de l’intelligibilité de textes prescriptifs","year":2009,"lang":"fr","type":"article","venue":"Revue québécoise de linguistique","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Collège de Valleyfield; Université du Québec à Montréal","funders":"","keywords":"Humanities; Philosophy; Psychology","score_opus":0.023703465618321592,"score_gpt":0.2973335498781101,"score_spread":0.2736300842597885,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2119111309","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22357523,0.025196383,0.6754586,0.039689414,0.0015614063,0.0010196309,0.000053158907,0.00076132896,0.032684833],"genre_scores_gemma":[0.9286337,0.0008834154,0.056917626,0.0024011657,0.0017295108,0.00002880513,0.000011667496,0.00003172287,0.009362397],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9960973,0.0007594678,0.0008049048,0.0009844216,0.00022417908,0.0011296895],"domain_scores_gemma":[0.9962772,0.0006608706,0.0002820243,0.0016643914,0.00049415923,0.0006213467],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.002362774,0.00042063236,0.000505223,0.00019000239,0.00024147799,0.0004805361,0.0010763734,0.0005247623,0.000064925596],"category_scores_gemma":[0.006366692,0.0004999133,0.0003616015,0.0007213662,0.00020982859,0.00028919737,0.000092775415,0.00075844256,0.00013173718],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000057528407,0.00084855163,0.0067290342,0.00042619553,0.00005841163,0.00045914098,0.019713366,0.0041050017,0.005560466,0.78525597,0.0016762104,0.17511015],"study_design_scores_gemma":[0.00028752815,0.00044282438,0.05587867,0.0007723066,0.00018942711,0.0009782092,0.00018151845,0.27335814,0.010491761,0.30807802,0.34838042,0.00096117693],"about_ca_topic_score_codex":0.021045389,"about_ca_topic_score_gemma":0.008485678,"teacher_disagreement_score":0.70505846,"about_ca_system_score_codex":0.0010392285,"about_ca_system_score_gemma":0.0018371112,"threshold_uncertainty_score":0.99974525},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.03856406689603698,"score_gpt":0.2789877685045692,"score_spread":0.24042370160853221,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2124547832","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7067447,0.000007674957,0.2756328,0.0023791592,0.00007612222,0.00010116531,0.0000010071282,0.000048248916,0.015009143],"genre_scores_gemma":[0.99795085,0.0000033367044,0.0012600083,0.000095855365,0.000006801448,0.0000033939152,3.2261585e-7,7.943113e-7,0.000678632],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99956405,0.000034152083,0.00009677182,0.00009426827,0.00015010581,0.000060621383],"domain_scores_gemma":[0.999554,0.00004846514,0.000031209613,0.00031811718,0.00003509761,0.000013142561],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014354108,0.000029147881,0.000033231943,0.000020155441,0.000069214126,0.00000947693,0.0002690036,0.000011643783,0.000022854289],"category_scores_gemma":[0.000019087473,0.000017294029,0.000018450517,0.00012574371,0.000035676352,0.0002202284,0.000031054926,0.000030591855,0.00004844092],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000024197855,0.000063384796,0.0014390595,0.0000015951648,0.0000022126526,3.0767328e-7,0.00017237618,0.00005782629,0.0019019697,0.99191654,0.0023659756,0.0020763327],"study_design_scores_gemma":[0.0007410033,0.0006083925,0.5949285,0.000022355005,0.0000055716996,0.000028292727,0.00028927872,0.22680646,0.0584974,0.04606866,0.071636185,0.0003679005],"about_ca_topic_score_codex":0.00008498136,"about_ca_topic_score_gemma":0.000012206074,"teacher_disagreement_score":0.94584787,"about_ca_system_score_codex":0.000030771167,"about_ca_system_score_gemma":0.000050706272,"threshold_uncertainty_score":0.070523},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_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","score_opus":0.010277469444146037,"score_gpt":0.25944813191283617,"score_spread":0.24917066246869013,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2128471136","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9937773,0.00077942736,0.002457765,0.0027524538,0.000025709307,0.00012801438,1.835095e-7,0.000010959792,0.00006822313],"genre_scores_gemma":[0.99347794,0.00027671424,0.0061023138,0.00003107172,0.0000074160876,0.000008479259,0.0000014296293,0.0000022236693,0.00009242338],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9993624,0.000121264326,0.00026135286,0.0000657093,0.00012340595,0.00006586171],"domain_scores_gemma":[0.99908215,0.00019511285,0.00035954572,0.00008870429,0.00022686174,0.000047629626],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00045771053,0.000060262704,0.00011890312,0.00018499921,0.00017305058,0.00013222542,0.00010866732,0.00004594913,0.0000034952154],"category_scores_gemma":[0.000302879,0.000048133457,0.000007484578,0.00014052149,0.00017234679,0.0013365073,0.00006228,0.00024204279,5.061134e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024992505,0.00010166584,0.62101686,0.00014107178,0.000033364537,6.946015e-8,0.050769955,0.00006280447,0.00039741845,0.011350969,0.000069779584,0.31603107],"study_design_scores_gemma":[0.00047157545,0.0005356244,0.8044043,0.00020638462,0.000019594403,0.0001375737,0.1889788,0.0016757174,0.00016810643,0.0018236324,0.0014637993,0.00011486892],"about_ca_topic_score_codex":0.000047810772,"about_ca_topic_score_gemma":0.0000026510766,"teacher_disagreement_score":0.31591618,"about_ca_system_score_codex":0.000017209837,"about_ca_system_score_gemma":0.000068610905,"threshold_uncertainty_score":0.19628254},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.03707125158914994,"score_gpt":0.31677359471205835,"score_spread":0.2797023431229084,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2130005887","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9894508,0.0007403523,0.0067526423,0.0018927922,0.0007800699,0.00021354301,0.000005301986,0.000008886568,0.00015557249],"genre_scores_gemma":[0.9936084,0.0000045318475,0.0032153388,0.0029409837,0.00020027446,0.000010305249,0.0000019121926,0.000014559956,0.0000036657304],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9979381,0.00027123408,0.0006147268,0.00031904472,0.00008781688,0.0007690607],"domain_scores_gemma":[0.9985739,0.00008241851,0.0003625168,0.00043430863,0.000061070445,0.00048580221],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012075086,0.00019959232,0.00026253005,0.00045013922,0.00020519193,0.00009664198,0.0006334196,0.00016128102,0.00001641077],"category_scores_gemma":[0.000042194468,0.00018615363,0.00008832891,0.0004050309,0.0003233625,0.0015840277,0.000024100389,0.00039449125,0.0000018466899],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029895335,0.00011625875,0.039184578,0.000011306673,0.000024791349,0.00007098216,0.011542412,0.00015924168,0.94554186,0.00022384696,0.000164819,0.0029299855],"study_design_scores_gemma":[0.0015332322,0.00044382934,0.8516274,0.00019424748,0.000029325602,0.0037127414,0.0026716322,0.00043645597,0.13747907,0.00050847273,0.00091699255,0.00044658798],"about_ca_topic_score_codex":0.003592279,"about_ca_topic_score_gemma":0.004561316,"teacher_disagreement_score":0.81244284,"about_ca_system_score_codex":0.0007258579,"about_ca_system_score_gemma":0.00012942217,"threshold_uncertainty_score":0.7591125},"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,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.021049149289221834,"score_gpt":0.31336959753377525,"score_spread":0.2923204482445534,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2162940749","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8822106,0.00019018647,0.11672746,0.00023338542,0.000029240426,0.00008717628,6.242084e-8,0.00040760482,0.00011426045],"genre_scores_gemma":[0.9829243,0.000006043328,0.01694719,0.00001574563,0.000007856658,0.000009240352,7.946438e-7,0.000005355007,0.00008346921],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991395,0.000087009,0.00024366767,0.0002313103,0.00013176474,0.00016675232],"domain_scores_gemma":[0.9993559,0.00008555333,0.00013950856,0.0003650298,0.000038716065,0.000015306856],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036013543,0.000070822985,0.00014407047,0.00033533934,0.00006995388,0.000007631648,0.00036585593,0.0001301073,0.000010177663],"category_scores_gemma":[0.00041185768,0.00007297812,0.000027009479,0.0007515202,0.00007967519,0.00011560567,0.00007766549,0.00031203686,0.000029224086],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000022773336,0.000047665104,0.0063589294,0.00003277501,0.000004346198,0.000024596311,0.009170025,0.0006690644,0.31576085,0.0019276744,8.451733e-7,0.66600096],"study_design_scores_gemma":[0.00049151474,0.00038687556,0.041932542,0.00006655647,0.000006043987,0.0002452364,0.00056969404,0.722401,0.22983469,0.0034693961,0.00034961043,0.000246835],"about_ca_topic_score_codex":0.0001242223,"about_ca_topic_score_gemma":0.000031411048,"teacher_disagreement_score":0.72173196,"about_ca_system_score_codex":0.00004390106,"about_ca_system_score_gemma":0.000025337818,"threshold_uncertainty_score":0.29759613},"labels":[],"label_agreement":null},{"id":"W2165544104","doi":"10.18806/tesl.v31i1.1168","title":"Students’ Source Misuse in Language Classrooms: Sharing Experiences","year":2014,"lang":"fr","type":"article","venue":"TESL Canada Journal","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Pedagogy; Psychology; Documentation; Sociology; Humanities; Linguistics; Philosophy; Computer science","score_opus":0.020254791121554705,"score_gpt":0.27278346954462795,"score_spread":0.25252867842307325,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2165544104","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9337745,0.023621215,0.034039803,0.00595245,0.0020665363,0.00011530709,0.000002040306,0.000027123928,0.00040103914],"genre_scores_gemma":[0.986573,0.0000390222,0.0009443738,0.008197988,0.0004893564,0.000008944835,0.000001059888,0.000012945704,0.0037333388],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9972981,0.00025352582,0.00054155226,0.00039513386,0.0009121132,0.00059954845],"domain_scores_gemma":[0.9986187,0.00020691635,0.0002254093,0.0004983228,0.0001014896,0.00034911174],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0014104968,0.00019120253,0.00024182994,0.000107896856,0.00029269024,0.0007490547,0.0017501771,0.00009245054,0.0030055852],"category_scores_gemma":[0.00035646552,0.0001917317,0.00005948272,0.00038644858,0.000105589155,0.00063339673,0.00023598305,0.0006189615,0.000014463822],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000047244062,0.0007332224,0.085229486,0.0002157919,0.00008763906,0.0007807744,0.2412569,0.0039192634,0.00058406603,0.0139118545,0.032423716,0.62081003],"study_design_scores_gemma":[0.0017934426,0.00030843075,0.12350737,0.0006552647,0.000032995405,0.0014610142,0.0515361,0.101695105,0.00062672567,0.0023463985,0.7148805,0.0011566223],"about_ca_topic_score_codex":0.26804444,"about_ca_topic_score_gemma":0.44425747,"teacher_disagreement_score":0.6824568,"about_ca_system_score_codex":0.00074735016,"about_ca_system_score_gemma":0.0009481409,"threshold_uncertainty_score":0.9979058},"labels":[],"label_agreement":null},{"id":"W2166039043","doi":"10.1044/aac17.4.156","title":"Words We Would Want: Comparison of Three Pre-programmed Vocabulary Sets With Frequently Used Words in English","year":2008,"lang":"en","type":"article","venue":"Perspectives on Augmentative and Alternative Communication","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Glenrose Rehabilitation Hospital","funders":"","keywords":"Vocabulary; Computer science; Word (group theory); Gateway (web page); Set (abstract data type); English vocabulary; Natural language processing; Word lists by frequency; Artificial intelligence; Speech recognition; Linguistics; World Wide Web","score_opus":0.06367648814629527,"score_gpt":0.3369147263330553,"score_spread":0.27323823818676,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2166039043","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.925882,0.0016119976,0.06920666,0.0015024155,0.00004066629,0.0007650736,0.000014914182,0.0000887757,0.0008874876],"genre_scores_gemma":[0.98535246,0.001065599,0.013330064,0.00004131501,0.000014753052,0.00013358363,0.000026709524,0.000013709733,0.000021794467],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.99787843,0.00046671167,0.00042688785,0.00055656704,0.00043252273,0.00023886457],"domain_scores_gemma":[0.9978381,0.00047265258,0.00039847274,0.00090544694,0.00030347204,0.00008189405],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036624775,0.000249244,0.00038376704,0.00025793823,0.0002360459,0.00006593725,0.0008741466,0.00008928329,0.000009698102],"category_scores_gemma":[0.00009288542,0.00021591963,0.00005560182,0.00059809594,0.0006401993,0.0007730542,0.00021688676,0.00056373514,0.0000024718827],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00037677938,0.0019039153,0.14823802,0.00003356945,0.00015779005,0.000005453758,0.7502274,0.000400524,0.00072591245,0.05038866,0.000022446888,0.04751953],"study_design_scores_gemma":[0.00547097,0.0025861792,0.76075125,0.0006076294,0.00004202202,0.000013054638,0.13204655,0.04928231,0.02610544,0.021857763,0.0002860131,0.00095081143],"about_ca_topic_score_codex":0.00045770867,"about_ca_topic_score_gemma":0.00062644004,"teacher_disagreement_score":0.6181809,"about_ca_system_score_codex":0.00024946596,"about_ca_system_score_gemma":0.000065611435,"threshold_uncertainty_score":0.8804947},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.009127837991078538,"score_gpt":0.23619237328343595,"score_spread":0.22706453529235743,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2169539950","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.862064,0.00019442131,0.13659546,0.0004977451,0.00005236984,0.0004246679,0.0000071369423,0.0001162601,0.000047913134],"genre_scores_gemma":[0.99789333,0.000010323914,0.0011168405,0.0006634427,0.000112419875,0.00012559458,0.0000463418,0.000011763938,0.000019944158],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99895376,0.000043822052,0.0001994221,0.00040943554,0.00016842171,0.00022511477],"domain_scores_gemma":[0.9994763,0.00008580119,0.00007632138,0.00025099432,0.000051302028,0.0000592702],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00014079383,0.00017226832,0.00016885292,0.00017344738,0.000102377286,0.00012311414,0.00013706707,0.000080855425,0.0000033240576],"category_scores_gemma":[0.00003914196,0.00012475465,0.000052592288,0.00019871113,0.00004586436,0.00024214087,0.000033350323,0.000108373184,0.0000016448903],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031698516,0.0010138379,0.0014918123,0.00037825594,0.000068788315,0.00011974495,0.11792525,0.000038533657,0.26738948,0.008220862,0.000024804558,0.60301167],"study_design_scores_gemma":[0.010160272,0.0015926576,0.0775021,0.0005623105,0.00015401846,0.00020825042,0.00929064,0.002116655,0.8563798,0.04008123,0.0004233317,0.0015287356],"about_ca_topic_score_codex":0.00016850852,"about_ca_topic_score_gemma":0.0014200715,"teacher_disagreement_score":0.6014829,"about_ca_system_score_codex":0.000041224663,"about_ca_system_score_gemma":0.0000143232655,"threshold_uncertainty_score":0.50873464},"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,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology; Linguistics; Philosophy","score_opus":0.011556817445740332,"score_gpt":0.2638416912237179,"score_spread":0.2522848737779776,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2170030837","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7588863,0.00023708516,0.22679548,0.000085681124,0.00073122914,0.000077406636,0.0000015440348,0.00017620751,0.013009109],"genre_scores_gemma":[0.98401785,0.0000014979793,0.01556017,0.000037210055,0.00027392677,0.0000036661331,0.00000557776,0.0000031733075,0.00009691351],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.9993184,0.000100322286,0.00014294584,0.00011184726,0.00017478802,0.000151652],"domain_scores_gemma":[0.9994139,0.00007248312,0.00007547617,0.00036973713,0.000023309134,0.000045074914],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010513171,0.000054050954,0.000071550494,0.00004605363,0.000060111553,0.00002872703,0.00023375191,0.000043131848,0.000016092865],"category_scores_gemma":[0.0003519992,0.000049772785,0.00003158435,0.00008374796,0.000011364506,0.0008552966,0.00005252349,0.00019262177,0.000008113756],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004776034,0.00036205153,0.008425463,0.00004274343,0.00001596394,0.000001162987,0.50435543,0.000034034012,0.0360766,0.18695164,0.0005772132,0.2631529],"study_design_scores_gemma":[0.002529247,0.0006509119,0.18628117,0.00031340597,0.00010530635,0.00007122558,0.16907927,0.01876587,0.29613307,0.0029649527,0.320533,0.002572568],"about_ca_topic_score_codex":0.00006384358,"about_ca_topic_score_gemma":0.000002576474,"teacher_disagreement_score":0.3352762,"about_ca_system_score_codex":0.000043534186,"about_ca_system_score_gemma":0.000009627604,"threshold_uncertainty_score":0.20296752},"labels":[],"label_agreement":null},{"id":"W2252260887","doi":"","title":"Building Readability Lexicons with Unannotated Corpora","year":2012,"lang":"en","type":"article","venue":"","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Readability; Computer science; Lexicon; Natural language processing; Annotation; Artificial intelligence; Word (group theory); Information retrieval; Resource (disambiguation); Simple (philosophy); Term (time); Linguistics","score_opus":0.02464466633386138,"score_gpt":0.2583301695586538,"score_spread":0.23368550322479242,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2252260887","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.31091523,0.000019409426,0.68232936,0.0008368721,0.000083904386,0.0001296085,8.47507e-7,0.00030628563,0.0053784964],"genre_scores_gemma":[0.8535013,5.558789e-7,0.14609896,0.00013977072,0.0000237351,0.000009906563,0.0000016201598,0.0000038416647,0.00022030399],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99903893,0.000063013424,0.00016126456,0.00026031065,0.00018073239,0.00029571616],"domain_scores_gemma":[0.9988893,0.000107936154,0.00006253838,0.00071634626,0.00008278238,0.00014108517],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047158243,0.000098216486,0.000105316925,0.000041150462,0.00010558204,0.0000759341,0.00038696616,0.000044230543,0.00004605813],"category_scores_gemma":[0.00004372825,0.000069745416,0.000026506368,0.0003890908,0.00007985742,0.0009466049,0.00008288055,0.00008955772,0.000080676335],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010113369,0.00022818612,0.07764527,0.000012170088,0.000010904977,9.192836e-7,0.0005277505,0.000020613026,0.0032817323,0.86864394,0.00044044683,0.049177945],"study_design_scores_gemma":[0.0006386472,0.0003545196,0.7829315,0.00003683088,0.000029064819,0.00018147571,0.00015350203,0.019917356,0.10143044,0.04525874,0.04787725,0.0011906484],"about_ca_topic_score_codex":0.000115210496,"about_ca_topic_score_gemma":0.000015655058,"teacher_disagreement_score":0.8233852,"about_ca_system_score_codex":0.000052362368,"about_ca_system_score_gemma":0.000053691627,"threshold_uncertainty_score":0.28441358},"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,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_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","score_opus":0.016540811622468145,"score_gpt":0.3020156164261348,"score_spread":0.28547480480366666,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2286878760","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98916703,0.0080258055,0.0016227786,0.00043037935,0.00017778852,0.000099419194,0.000021954716,0.000092749586,0.0003620623],"genre_scores_gemma":[0.99782366,0.00016893342,0.0016650253,0.000047917532,0.0001600712,0.000008090169,0.0000031078405,0.0000037589384,0.00011945214],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.9991735,0.00007843885,0.00019550601,0.00025574665,0.00015938541,0.00013742996],"domain_scores_gemma":[0.99903876,0.00030529127,0.00007733682,0.0003383883,0.00020224618,0.000037966158],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030396227,0.000117158095,0.00021144573,0.00005463398,0.00009658279,0.000101033955,0.00029777683,0.000040130424,0.000003449094],"category_scores_gemma":[0.0006742781,0.00006551892,0.000042142405,0.00018297264,0.0001395134,0.00047379517,0.00023595031,0.00008183324,9.776627e-7],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025869957,0.00016478711,0.0823713,0.00036923485,0.00022617666,0.000047149653,0.79323864,3.5354893e-7,0.0067546167,0.05874555,0.000435174,0.057621162],"study_design_scores_gemma":[0.004330108,0.0009025547,0.81202894,0.0033183957,0.00011704059,0.00010595953,0.12429795,0.0001388498,0.008400754,0.038986642,0.0056012115,0.0017715936],"about_ca_topic_score_codex":0.00000803193,"about_ca_topic_score_gemma":0.000018948207,"teacher_disagreement_score":0.72965765,"about_ca_system_score_codex":0.00001937708,"about_ca_system_score_gemma":0.00000779634,"threshold_uncertainty_score":0.2671784},"labels":[],"label_agreement":null},{"id":"W2290020483","doi":"10.71781/19246","title":"Réorganisation neurofonctionnelle permettant le maintien des habiletés d’évocation lexicale lors du vieillissement","year":2013,"lang":"fr","type":"dissertation","venue":"Open MIND","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Institutes of Health Research","keywords":"Humanities; Philosophy; Sociology","score_opus":0.04647746829042797,"score_gpt":0.28657836449146656,"score_spread":0.24010089620103858,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2290020483","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8367984,0.00020776174,0.14235157,0.0047538406,0.0021944256,0.0026486444,0.000026866162,0.000019994603,0.010998486],"genre_scores_gemma":[0.9428915,0.00014060004,0.03577253,0.00014032629,0.00030411323,0.00029319726,0.0011428989,0.000058210222,0.019256633],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.995738,0.00051776995,0.001082764,0.0014727477,0.0006115194,0.0005771532],"domain_scores_gemma":[0.9968384,0.00023145732,0.00069181336,0.001175493,0.0007872823,0.00027559194],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0010664623,0.0005381765,0.0005113675,0.00020030163,0.0013273179,0.0022034845,0.0018840324,0.00044435498,0.004008964],"category_scores_gemma":[0.00036006857,0.00056824094,0.00019111788,0.00074655574,0.00029838053,0.0029889492,0.00037842148,0.0004107707,0.003536681],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000090878035,0.0018102827,0.0019800568,0.00025045103,0.00010966828,0.00000898143,0.059742574,0.0016762498,0.043945376,0.047686234,0.0014952398,0.841204],"study_design_scores_gemma":[0.0023371982,0.001409956,0.31778255,0.0008290054,0.00038822228,0.00012193685,0.031679403,0.21495287,0.16739298,0.021810897,0.23826197,0.0030330117],"about_ca_topic_score_codex":0.0049638613,"about_ca_topic_score_gemma":0.0012125681,"teacher_disagreement_score":0.838171,"about_ca_system_score_codex":0.0005022012,"about_ca_system_score_gemma":0.0009301479,"threshold_uncertainty_score":0.9999728},"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,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_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","score_opus":0.14329833151877183,"score_gpt":0.4373159612485989,"score_spread":0.29401762972982703,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2291325286","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7972584,0.003089562,0.19912578,0.00030333703,0.000039378294,0.00015186175,0.0000045777056,0.000009912729,0.000017188118],"genre_scores_gemma":[0.93005025,0.00030063043,0.0696038,0.000010449089,0.000014650103,0.000008421716,0.0000027201063,0.0000039264623,0.000005140619],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9984219,0.00038059248,0.00037984236,0.00031325422,0.00035795648,0.00014643178],"domain_scores_gemma":[0.99896747,0.00016529758,0.0003560989,0.00024381642,0.00013916325,0.0001281586],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011742406,0.00015530524,0.00045747292,0.0002642712,0.0008776735,0.00042158138,0.0003336154,0.000052180352,0.0000054352627],"category_scores_gemma":[0.000022981572,0.00011063303,0.00008847346,0.00025243973,0.00045759027,0.0015173903,0.000019965199,0.00018432425,3.021455e-8],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000090257556,0.00016310294,0.1223031,0.00006688789,0.0021067227,0.000003955853,0.072159484,0.000055469434,0.037139524,0.0020954197,5.490403e-7,0.7638155],"study_design_scores_gemma":[0.00065713696,0.00022674691,0.98471534,0.000034377506,0.0015519599,0.000061249506,0.0007851434,0.0067083994,0.003153971,0.0018943422,0.000057212972,0.00015413195],"about_ca_topic_score_codex":0.0000395154,"about_ca_topic_score_gemma":0.000118617674,"teacher_disagreement_score":0.8624122,"about_ca_system_score_codex":0.000009594194,"about_ca_system_score_gemma":0.000021417089,"threshold_uncertainty_score":0.6750444},"labels":[],"label_agreement":null},{"id":"W2315912864","doi":"10.1016/s0735-1097(16)30804-x","title":"MULTI-FACETED KNOWLEDGE TRANSLATION TO IMPROVE CARE OF PATIENTS WITH ATRIAL FIBRILLATION: PRELIMINARY RESULTS FROM THE INTEGRATE/FACILITER PROJECTS","year":2016,"lang":"en","type":"article","venue":"Journal of the American College of Cardiology","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University Health Centre","funders":"","keywords":"Medicine; Atrial fibrillation; Translation (biology); Intensive care medicine; Knowledge translation; Internal medicine; Knowledge management; Computer science","score_opus":0.02291550618767262,"score_gpt":0.25737126248070774,"score_spread":0.2344557562930351,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2315912864","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9536631,0.00012648452,0.042456683,0.002177942,0.00038635815,0.00053525,0.00060071994,0.0000069192533,0.000046512363],"genre_scores_gemma":[0.9915286,0.000010345933,0.008239717,0.000018755052,0.00017689922,0.0000017988194,0.00000276421,0.0000050380986,0.00001611399],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99824977,0.0005835003,0.00059042027,0.0002067581,0.00024287742,0.00012664519],"domain_scores_gemma":[0.996628,0.0010081572,0.000884774,0.0005864516,0.0008484086,0.00004422597],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039478217,0.00011523942,0.00043762402,0.00007289848,0.000058292648,0.0000071753925,0.00068017276,0.000047488593,7.4650865e-7],"category_scores_gemma":[0.0004694772,0.000049002294,0.00024933208,0.00043460037,0.0002650202,0.00016805978,0.00008984379,0.0000841041,9.84354e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.033295393,0.00012032574,0.23353234,0.00005717877,0.0010761891,0.00000813042,0.02868224,0.0070083784,0.026339386,0.00026684746,0.001803438,0.66781014],"study_design_scores_gemma":[0.0045152185,0.005265294,0.97637504,0.00014276948,0.00012286931,0.000018558721,0.0012396399,0.00062539504,0.0041168286,0.0001220964,0.0072647845,0.00019151389],"about_ca_topic_score_codex":0.000026750433,"about_ca_topic_score_gemma":0.00002270541,"teacher_disagreement_score":0.7428427,"about_ca_system_score_codex":0.000079777376,"about_ca_system_score_gemma":0.0002667525,"threshold_uncertainty_score":0.19982557},"labels":[],"label_agreement":null},{"id":"W2329263293","doi":"10.5539/ijel.v6n2p21","title":"The Comprehensibility of Readable English Texts and Their Back-Translations","year":2016,"lang":"en","type":"article","venue":"International Journal of English Linguistics","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Universitas Negeri Semarang","keywords":"Readability; Linguistics; Source text; Sentence; Indonesian; Reading (process); Relation (database); Meaning (existential); Reading comprehension; Computer science; Comprehension; Equivalence (formal languages); Psychology; Philosophy","score_opus":0.01822342450664839,"score_gpt":0.26253578429449664,"score_spread":0.24431235978784827,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2329263293","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16937669,0.0024711872,0.7205632,0.0027686504,0.052024186,0.0005677546,0.00024276398,0.00015323443,0.05183235],"genre_scores_gemma":[0.99148875,0.00017464746,0.00646759,0.000031513144,0.0017724171,7.218306e-7,9.929074e-7,0.000004788642,0.00005859457],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99873674,0.00008621583,0.00059065095,0.00013817412,0.0003341389,0.000114065835],"domain_scores_gemma":[0.97854424,0.0017510687,0.0004105768,0.00031503342,0.018909201,0.00006990034],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00076701096,0.00009121024,0.00015117126,0.00007207653,0.00007538109,0.00010525816,0.00086981856,0.000050348706,0.000010527619],"category_scores_gemma":[0.028945876,0.000049488746,0.00008413527,0.000080049045,0.00018546091,0.00017822621,0.000096290285,0.00012778137,0.0000015719062],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028548125,0.0006619459,0.025767718,0.0000516203,0.0005433583,0.000009033106,0.015173949,0.00037282932,0.0019899243,0.70833176,0.008927923,0.23788445],"study_design_scores_gemma":[0.0010558546,0.00018133387,0.019553848,0.00014196943,0.000019537125,0.0000070582823,0.00034465033,0.0012698506,0.0074667274,0.07371407,0.89604247,0.00020262203],"about_ca_topic_score_codex":0.0000063868906,"about_ca_topic_score_gemma":0.000017000993,"teacher_disagreement_score":0.8871146,"about_ca_system_score_codex":0.000047039484,"about_ca_system_score_gemma":0.00012179803,"threshold_uncertainty_score":0.97923374},"labels":[],"label_agreement":null},{"id":"W2338913574","doi":"10.14288/1.0078320","title":"The effect of mode variation on syntactic complexity in adult E.S.L. composition writing","year":2010,"lang":"en","type":"article","venue":"cIRcle (University of British Columbia)","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Composition (language); Variation (astronomy); Mode (computer interface); Linguistics; Computer science; Philosophy; Human–computer interaction; Physics","score_opus":0.008591675061803864,"score_gpt":0.2010138906762786,"score_spread":0.19242221561447473,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2338913574","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9842262,0.0000035246467,0.014740155,0.00026095923,0.000114319366,0.00023553353,0.000018071529,0.000037841233,0.00036337093],"genre_scores_gemma":[0.998612,0.000006022305,0.001342413,0.000011004573,0.0000098084165,7.635348e-7,0.0000070946603,0.00000293571,0.000007990205],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9990744,0.00017474545,0.00014515895,0.0002495572,0.00022000926,0.00013615539],"domain_scores_gemma":[0.9988504,0.00042139506,0.00016303195,0.00039043682,0.00013596739,0.000038762697],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004991167,0.000032409513,0.00015411612,0.00003549876,0.00025728965,0.00009876974,0.0005024832,0.00007386589,0.000004231039],"category_scores_gemma":[0.00008277947,0.00008171616,0.00006200184,0.00026146148,0.00017907412,0.00039288052,0.0000799294,0.00020354053,0.0000045979596],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000053867378,0.00022923286,0.03597741,0.00013336317,0.000019325775,0.000013325434,0.0006563572,0.00015535254,0.016301043,0.0027500351,0.00006946685,0.94364125],"study_design_scores_gemma":[0.00048153917,0.00013699166,0.96490055,0.00006495052,0.0000065291442,0.0000115909725,0.000063359446,0.03253292,0.000069820555,0.0016553237,0.0000042956513,0.00007210912],"about_ca_topic_score_codex":0.05029788,"about_ca_topic_score_gemma":0.1819199,"teacher_disagreement_score":0.9435691,"about_ca_system_score_codex":0.000050585895,"about_ca_system_score_gemma":0.000028594352,"threshold_uncertainty_score":0.95602626},"labels":[],"label_agreement":null},{"id":"W2422594387","doi":"10.5489/cuaj.3811","title":"CUA brochure readability: On the right track","year":2016,"lang":"en","type":"article","venue":"Canadian Urological Association Journal","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Vernon Jubilee Hospital","funders":"","keywords":"Brochure; Readability; Track (disk drive); Computer science; Programming language; Linguistics; Operating system; Philosophy","score_opus":0.01390322376259373,"score_gpt":0.2051051085000915,"score_spread":0.19120188473749777,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2422594387","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.29199037,0.00004082717,0.018214388,0.6823859,0.0005724149,0.00021478762,0.000023282808,0.00009359915,0.006464422],"genre_scores_gemma":[0.9914741,0.000012685684,0.00023549791,0.007203542,0.000226998,0.000007668871,8.4312563e-7,0.0000037195875,0.00083495927],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9981586,0.00047426217,0.00028319316,0.0002646709,0.00039128796,0.00042803815],"domain_scores_gemma":[0.99772793,0.001087731,0.00020425468,0.00037163534,0.00021203645,0.00039644155],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016531462,0.00011090026,0.00012813257,0.00007642002,0.00052699354,0.00025890252,0.0008105568,0.00019122896,0.0004719912],"category_scores_gemma":[0.0019297517,0.000052093437,0.00011179677,0.0002382369,0.00004900166,0.00029372264,0.00002320193,0.00038645256,0.00033666234],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024918403,0.00015330204,0.19388059,0.0000023476516,0.00007220411,0.000043265314,0.0004901733,0.00003058224,0.00084035576,0.4897186,0.1289547,0.18578897],"study_design_scores_gemma":[0.00017976963,0.0001667409,0.50917065,0.000008144626,0.0000071865056,0.000059661572,0.000012044159,0.00018889345,0.0002570217,0.11524926,0.37452352,0.0001771113],"about_ca_topic_score_codex":0.000126307,"about_ca_topic_score_gemma":0.0007081366,"teacher_disagreement_score":0.6994837,"about_ca_system_score_codex":0.0009689359,"about_ca_system_score_gemma":0.00030910896,"threshold_uncertainty_score":0.51679724},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.018493676804162185,"score_gpt":0.28391415519497915,"score_spread":0.26542047839081695,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2427123482","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9927438,0.0012155941,0.005252107,0.00030905273,0.00018020786,0.000094839,3.2414144e-7,0.000011294058,0.00019280914],"genre_scores_gemma":[0.99906635,0.000305538,0.00047696364,0.00010463552,0.00003043205,0.0000035436847,4.879013e-7,0.000003889834,0.00000813338],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9990798,0.00023410642,0.0002971269,0.00019874904,0.0000772874,0.00011287731],"domain_scores_gemma":[0.9992674,0.00036092094,0.0002048654,0.00006942891,0.000048883863,0.00004850027],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035355345,0.00009312373,0.00021238472,0.0001645921,0.000064582026,0.000019460775,0.00008853253,0.00007768336,0.0000059393205],"category_scores_gemma":[0.00007077264,0.000071350034,0.000024533727,0.000077901146,0.00020974413,0.00031025714,0.000023487595,0.00017976426,9.618232e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00036899443,0.0003733668,0.010051811,0.000065837296,0.000030873365,0.000047664762,0.0083433725,0.0000052497376,0.94041216,0.00095631287,0.000015270467,0.03932909],"study_design_scores_gemma":[0.01137268,0.006101736,0.6480362,0.0013997669,0.0000675606,0.0018050375,0.0029969614,0.0002761935,0.3155872,0.011667487,0.00017427155,0.0005148938],"about_ca_topic_score_codex":0.0000024272306,"about_ca_topic_score_gemma":9.744617e-7,"teacher_disagreement_score":0.6379844,"about_ca_system_score_codex":0.000013037629,"about_ca_system_score_gemma":0.00000921794,"threshold_uncertainty_score":0.29095697},"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,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_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","score_opus":0.04449037570043224,"score_gpt":0.28920624745793644,"score_spread":0.2447158717575042,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2460540981","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8009082,0.00001528029,0.19571431,0.0031005736,0.00011254638,0.00005237308,0.0000063727766,0.0000049957475,0.000085335436],"genre_scores_gemma":[0.99045247,0.00002137256,0.009464835,0.000012160836,0.000040341325,9.464929e-7,0.0000027223086,0.0000029276382,0.0000022437127],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9987009,0.000056682355,0.0006501991,0.00012974972,0.00038699526,0.00007545353],"domain_scores_gemma":[0.9979036,0.0002469238,0.00072069705,0.00011334709,0.000977619,0.00003784984],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003996447,0.000075711825,0.0001927034,0.00016771605,0.000021217946,0.000039783834,0.00031931608,0.000041322448,0.000007649467],"category_scores_gemma":[0.00026297465,0.000053106145,0.000028887649,0.00018016798,0.0002840784,0.000851282,0.000042403462,0.00007790112,3.601162e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017882156,0.0008887341,0.39782378,0.00022548749,0.00010100835,0.00007034754,0.001352747,0.00013413455,0.03172269,0.49350828,0.000009884047,0.07237468],"study_design_scores_gemma":[0.0010830564,0.00028830083,0.9609017,0.0012037384,0.000008315583,0.00048637055,0.00013239714,0.0036982484,0.010698579,0.021398636,0.0000065048935,0.00009420315],"about_ca_topic_score_codex":0.000044303702,"about_ca_topic_score_gemma":0.00007659844,"teacher_disagreement_score":0.56307787,"about_ca_system_score_codex":0.000057983867,"about_ca_system_score_gemma":0.00015912985,"threshold_uncertainty_score":0.21656057},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Wilfrid Laurier University","funders":"","keywords":"Linguistics; Sentence; Natural language processing; Comprehension; Computer science; Artificial intelligence; Psychology; Philosophy","score_opus":0.06808983027765364,"score_gpt":0.24511052368645772,"score_spread":0.17702069340880408,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2479635814","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00087062677,0.00015959104,0.04005732,0.00009141456,0.00038393127,0.00039017806,0.000054280277,0.00046129286,0.9575314],"genre_scores_gemma":[0.014898523,0.00003503107,0.0017170763,0.00007321753,0.00015569494,5.135907e-7,0.00004013574,0.000027924587,0.9830519],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99788487,0.00006944265,0.00027088646,0.0009075066,0.00053820544,0.00032910955],"domain_scores_gemma":[0.99768674,0.00010949146,0.00023500084,0.001268093,0.000404018,0.0002966803],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00021373601,0.00036568526,0.00040916953,0.00018700611,0.00023430021,0.00015473373,0.001790117,0.00040056268,0.0000020395025],"category_scores_gemma":[0.000021451318,0.00041043886,0.00018841859,0.000020588077,0.00026006778,0.00036509466,0.0013725585,0.0005729767,0.000037729566],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000033845678,0.000018414783,0.000004834106,0.000059183716,0.000034469398,0.00016498182,0.000090237,0.000017763074,0.00011708115,0.9829583,0.006360702,0.0101401415],"study_design_scores_gemma":[0.0004586183,0.00006906144,0.00009964142,0.00015658175,0.000061378414,0.000056859248,0.000028886123,0.0033753205,0.0005023404,0.00023983917,0.9943254,0.0006260503],"about_ca_topic_score_codex":0.00013119499,"about_ca_topic_score_gemma":0.0000041919957,"teacher_disagreement_score":0.98796475,"about_ca_system_score_codex":0.00029398696,"about_ca_system_score_gemma":0.00032479005,"threshold_uncertainty_score":0.9998347},"labels":[],"label_agreement":null},{"id":"W2563219476","doi":"10.30466/ijltr.2015.20399","title":"Suggestions toward Some Discourse-analytic Approaches to Text Difficulty: With Special Reference to ‘T-unit Configuration’ in the Textual Unfolding","year":2015,"lang":"en","type":"article","venue":"DOAJ (DOAJ: Directory of Open Access Journals)","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Algonquin College","funders":"","keywords":"Readability; Computer science; Focus (optics); Linguistics; Cognition; Process (computing); Artificial intelligence; Natural language processing; Mathematics education; Psychology; Philosophy","score_opus":0.6070767752316734,"score_gpt":0.5257118819032537,"score_spread":0.08136489332841967,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2563219476","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.90741384,0.00043754393,0.06600599,0.013360982,0.00026117926,0.0015511654,0.000039244707,0.0000656485,0.010864389],"genre_scores_gemma":[0.9975007,0.000043472788,0.0013924342,0.0004760735,0.00025734882,0.00010999443,0.000014971918,0.000015381056,0.00018962847],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.996771,0.00043300347,0.0007194827,0.0006245109,0.0010450013,0.0004070056],"domain_scores_gemma":[0.99757016,0.00041741147,0.00037935935,0.0009334091,0.00029797375,0.00040169762],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0019841236,0.00028734424,0.00051703834,0.0006930631,0.00026414063,0.0027380285,0.0051379995,0.00008275393,0.00026851645],"category_scores_gemma":[0.00051090744,0.00019445395,0.0000755643,0.0022322556,0.00013295047,0.0034077968,0.0006301152,0.0004094312,0.00006106956],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008280892,0.002869249,0.20739277,0.00013888303,0.00035203068,0.00011702883,0.044558715,0.039556444,0.014503961,0.4496496,0.061237324,0.17879592],"study_design_scores_gemma":[0.0006872791,0.000104109866,0.9631562,0.00028099443,0.00007364316,0.000043927175,0.005116047,0.0014743867,0.0029108662,0.014360334,0.010998446,0.00079376367],"about_ca_topic_score_codex":0.0006759669,"about_ca_topic_score_gemma":0.0006724518,"teacher_disagreement_score":0.7557634,"about_ca_system_score_codex":0.00017617382,"about_ca_system_score_gemma":0.00039425452,"threshold_uncertainty_score":0.9982972},"labels":[],"label_agreement":null},{"id":"W2563306247","doi":"10.18653/v1/w16-3620","title":"On the Contribution of Discourse Structure on Text Complexity Assessment","year":2016,"lang":"en","type":"preprint","venue":"","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Treebank; Cohesion (chemistry); Coherence (philosophical gambling strategy); Computer science; Natural language processing; Artificial intelligence; Feature (linguistics); Linguistics; Feature selection; Mathematics; Parsing; Statistics; Physics","score_opus":0.039335622359669004,"score_gpt":0.3296522695321306,"score_spread":0.29031664717246164,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2563306247","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.140655,0.0000076061174,0.8234716,0.027944654,0.0005736056,0.0007770579,0.00014889226,0.00009706134,0.0063245343],"genre_scores_gemma":[0.9975481,0.0000029247672,0.001910737,0.0003207485,0.00005279472,0.000022303211,0.00003922731,0.000004613116,0.00009852748],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9982651,0.00026229632,0.00031027786,0.0005120674,0.00047448574,0.00017581035],"domain_scores_gemma":[0.9971813,0.0005239476,0.00030692195,0.001760444,0.00017987254,0.000047514364],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004721654,0.00019970258,0.00025526446,0.00005371046,0.000116909796,0.000104999046,0.0012546805,0.0001742459,0.00016238837],"category_scores_gemma":[0.00010334818,0.00009767696,0.00012065269,0.00008078491,0.00020120491,0.00008140439,0.00052800914,0.00042370052,0.000018949297],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009082951,0.000091551614,0.00014495155,0.000010402272,0.000017904638,2.0255231e-7,0.00006605595,0.000112382055,0.00043210512,0.9899668,0.0007863391,0.008362212],"study_design_scores_gemma":[0.0001747347,0.00011584564,0.062249053,0.00011323975,0.000008707356,8.426047e-7,0.000018132067,0.008559117,0.0054938486,0.9227238,0.00036020612,0.00018246273],"about_ca_topic_score_codex":0.000044686152,"about_ca_topic_score_gemma":0.00004629205,"teacher_disagreement_score":0.8568931,"about_ca_system_score_codex":0.00017729102,"about_ca_system_score_gemma":0.00018392642,"threshold_uncertainty_score":0.39831507},"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,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Reading (process); Sentence; Set (abstract data type); Psychology; Mathematics; Linguistics; Computer science; Natural language processing","score_opus":0.08323997651935867,"score_gpt":0.40935662184939736,"score_spread":0.3261166453300387,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2563494058","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9363446,0.00046691333,0.055720598,0.0059745093,0.0009849027,0.00012483467,0.0000074175678,0.000043625267,0.00033256726],"genre_scores_gemma":[0.99566084,0.000084910076,0.0036964186,0.00004578106,0.000083624305,0.000025193396,0.0000048414427,0.0000031804116,0.00039522254],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9989251,0.000068680565,0.00038016503,0.00026081776,0.00026504422,0.000100176505],"domain_scores_gemma":[0.99837834,0.00045866135,0.00024014842,0.00018058404,0.0006948209,0.00004743098],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033909627,0.00009703984,0.00023103823,0.00013926219,0.000093728595,0.000051578925,0.00036453592,0.00003292228,0.00000837339],"category_scores_gemma":[0.0007857834,0.00006732619,0.00003996911,0.00012794709,0.00023854245,0.0006493201,0.00013585915,0.000054631673,0.000007959816],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010266997,0.000058593207,0.8366734,0.000005715805,0.000104966,4.170706e-8,0.0027005288,0.0000017705457,0.00018398289,0.009415197,0.00088205194,0.1499635],"study_design_scores_gemma":[0.00057975115,0.00004537362,0.982062,0.00015161445,0.00001920406,0.0000023305272,0.003996015,0.00018707616,0.0018418102,0.00833948,0.002633858,0.00014152682],"about_ca_topic_score_codex":0.00012913729,"about_ca_topic_score_gemma":0.00004305655,"teacher_disagreement_score":0.14982197,"about_ca_system_score_codex":0.000065958026,"about_ca_system_score_gemma":0.00007740066,"threshold_uncertainty_score":0.2745482},"labels":[],"label_agreement":null},{"id":"W2586150748","doi":"10.5539/elt.v10n3p95","title":"On Improving Text Readability by Creating a Personal Writing Style","year":2017,"lang":"en","type":"article","venue":"English Language Teaching","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Readability; Writing style; Psychology; Affect (linguistics); Style (visual arts); Mathematics education; Computer science; Linguistics; Communication; Literature","score_opus":0.00898343470308837,"score_gpt":0.2624338728074199,"score_spread":0.25345043810433154,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2586150748","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92061436,0.0000846593,0.05504315,0.00028159074,0.00021735551,0.00017801634,0.0000128565125,0.000463311,0.023104727],"genre_scores_gemma":[0.9885097,5.0505724e-7,0.010621728,0.00014711951,0.00031498255,0.000017576082,0.000012489488,0.000017135044,0.00035873114],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979901,0.0002431975,0.00029861415,0.00068835024,0.00037430332,0.00040548522],"domain_scores_gemma":[0.9975195,0.00058824127,0.000282301,0.0014363896,0.000050839993,0.00012270671],"candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.002153625,0.00020110131,0.00020599819,0.000054889737,0.001797292,0.0012956021,0.0012682473,0.00009983101,0.000028569902],"category_scores_gemma":[0.006675198,0.00019260902,0.00009863879,0.00004621217,0.00007596819,0.0013289035,0.00035163373,0.0007289059,0.000016436401],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010835238,0.00018556566,0.003420943,0.00005935067,0.000014073535,0.000016417654,0.19104351,0.000008524343,0.014122473,0.017275548,0.00030781046,0.77353495],"study_design_scores_gemma":[0.005210284,0.0015266701,0.076216586,0.0015347756,0.00013591336,0.00010959285,0.25244877,0.5768027,0.064192474,0.007355742,0.0077399253,0.006726614],"about_ca_topic_score_codex":0.0010947878,"about_ca_topic_score_gemma":0.000045894612,"teacher_disagreement_score":0.76680833,"about_ca_system_score_codex":0.00015280824,"about_ca_system_score_gemma":0.000042493666,"threshold_uncertainty_score":0.99974114},"labels":[],"label_agreement":null},{"id":"W2588260181","doi":"10.29173/cais733","title":"Development of an Integrated Bilingual Thesaurus in Gerontology and Geriatrics","year":2013,"lang":"en","type":"article","venue":"Proceedings of the Annual Conference of CAIS / Actes du congrès annuel de l ACSI","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Centre des Aînés Côte-des-Neiges; McGill University","funders":"","keywords":"Geriatrics; Thesaurus; Gerontology; Medicine; Psychology; Linguistics; Philosophy; Psychiatry","score_opus":0.03102252310985177,"score_gpt":0.2569396952453352,"score_spread":0.22591717213548346,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2588260181","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9978788,0.000053875716,0.00070883933,0.0005244515,0.00005244984,0.0002957127,0.00000914428,0.000024737566,0.00045200513],"genre_scores_gemma":[0.9772102,0.000017237928,0.022669697,0.00003629812,0.000010402758,0.000019078341,0.0000016238693,0.0000060384527,0.000029416235],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99857795,0.00003174779,0.00058854435,0.0003104512,0.00024248216,0.00024880888],"domain_scores_gemma":[0.9848793,0.00012054086,0.00053348,0.00022292245,0.01416076,0.0000830074],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006754006,0.00016257072,0.00035734806,0.000172035,0.00005473443,0.0006528833,0.001495866,0.00013689302,0.000006964146],"category_scores_gemma":[0.0042683966,0.00011984882,0.00004341476,0.00042610255,0.00027031582,0.0057722838,0.00041719386,0.00016965398,8.6577637e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010879202,0.00062309916,0.20311646,0.00048307184,0.000053004616,7.5603054e-7,0.22135818,0.000008468755,0.1075029,0.059567023,0.00009703581,0.40708122],"study_design_scores_gemma":[0.0006295359,0.00034208116,0.8593276,0.00014636769,0.000018953748,0.000028785802,0.006229061,0.0059029344,0.11005212,0.01204656,0.004918094,0.000357901],"about_ca_topic_score_codex":0.0004687022,"about_ca_topic_score_gemma":0.00012566506,"teacher_disagreement_score":0.65621114,"about_ca_system_score_codex":0.000043325046,"about_ca_system_score_gemma":0.0004412059,"threshold_uncertainty_score":0.62957686},"labels":[],"label_agreement":null},{"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.006247044410424345,"score_gpt":0.2715102706400481,"score_spread":0.2652632262296238,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2596405055","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99413455,0.0043522473,0.00029468228,0.0007373168,0.00015076177,0.00020221746,0.0000012627407,0.00002087512,0.00010608182],"genre_scores_gemma":[0.9989042,0.00053922465,0.00045755855,0.000045693407,0.000020688514,0.000012503836,3.913936e-7,0.0000035426467,0.000016154054],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99903035,0.00008287507,0.00019710185,0.00043994913,0.00005561527,0.0001941185],"domain_scores_gemma":[0.99889547,0.0004080571,0.00011496082,0.00050986506,0.000017184078,0.00005447719],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000532583,0.00010549301,0.00015682737,0.00006120869,0.00045900224,0.000111080655,0.00021692559,0.00007739142,0.0000012462106],"category_scores_gemma":[0.00021730787,0.00008067704,0.000014660994,0.000061004244,0.0004188832,0.00036763755,0.00014164625,0.00017511834,1.260989e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003555348,0.000040107854,0.8294478,0.00035334565,0.000014614569,0.000014079462,0.015076294,1.3754398e-7,0.005021894,0.0012715975,0.0000027989308,0.14872178],"study_design_scores_gemma":[0.0006270554,0.00003059399,0.9949765,0.00013445974,0.0000049052364,0.000037471716,0.00015861148,0.00017723428,0.00053920574,0.0032116023,0.000016544453,0.000085789325],"about_ca_topic_score_codex":0.00012410489,"about_ca_topic_score_gemma":0.00050260057,"teacher_disagreement_score":0.16552874,"about_ca_system_score_codex":0.000005782618,"about_ca_system_score_gemma":0.0000074800814,"threshold_uncertainty_score":0.35303205},"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,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Vocabulary; Corpus linguistics; Linguistics; Computer science; Humanities; Library science; Psychology; Artificial intelligence; Art; Philosophy","score_opus":0.03666660018396091,"score_gpt":0.28213121172488864,"score_spread":0.24546461154092775,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2610650708","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3294747,0.001362831,0.65993917,0.007512571,0.0008572904,0.00042090923,0.000040495444,0.00007702913,0.00031500327],"genre_scores_gemma":[0.82983875,0.0000072711146,0.16421346,0.005580562,0.00028478558,0.000011693804,0.000011724811,0.0000135549435,0.000038186787],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99885315,0.00006682172,0.00029196191,0.00024701736,0.0002707491,0.00027030896],"domain_scores_gemma":[0.99856144,0.00014125196,0.0003444473,0.000475229,0.0002703991,0.00020722556],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.00060030306,0.00011921062,0.00017090696,0.000050660172,0.001660519,0.0009484289,0.00074434077,0.000044701097,0.000053299435],"category_scores_gemma":[0.00047127047,0.00011150389,0.000029465347,0.00006313102,0.00006284466,0.0006385546,0.000047682053,0.0001572808,2.1945992e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003672183,0.0002995598,0.045518592,0.0004199415,0.0002534152,0.0009158557,0.0040602772,0.00044630465,0.024716908,0.18029273,0.015713701,0.7269955],"study_design_scores_gemma":[0.0071865637,0.00077841216,0.58839846,0.0005235057,0.000085751686,0.001316277,0.00035807083,0.25197572,0.009717119,0.06432715,0.07325159,0.0020813737],"about_ca_topic_score_codex":0.05898476,"about_ca_topic_score_gemma":0.16885689,"teacher_disagreement_score":0.72491413,"about_ca_system_score_codex":0.0002713967,"about_ca_system_score_gemma":0.0026820623,"threshold_uncertainty_score":0.9996392},"labels":[],"label_agreement":null},{"id":"W2674585767","doi":"10.6033/tokkyou.52.75","title":"Discourse-Pragmatics in Children With Autism Spectrum Disorders: Argument Omission and Lexicalization","year":2014,"lang":"en","type":"article","venue":"The Japanese Journal of Special Education","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Lexicalization; Pragmatics; Argument (complex analysis); Autism; Linguistics; Psychology; Cognitive psychology; Philosophy; Developmental psychology; Medicine","score_opus":0.005833707176588233,"score_gpt":0.24848910629447044,"score_spread":0.2426553991178822,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2674585767","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93074524,0.00002981062,0.050328463,0.018317223,0.00015736462,0.00015181731,8.823795e-8,0.0000075154253,0.00026246125],"genre_scores_gemma":[0.99745625,0.000031907333,0.0020573828,0.000075556345,0.0003520344,0.0000028367685,0.0000012336922,0.000003600475,0.000019169336],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99917024,0.00012298394,0.00026892882,0.00010705642,0.00022986853,0.000100916914],"domain_scores_gemma":[0.9994103,0.000063449035,0.00023003109,0.00020948151,0.000025553623,0.00006121108],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006512872,0.00007383259,0.00010498857,0.00009486696,0.0001076955,0.000095307434,0.00027728154,0.00002631695,0.000009442677],"category_scores_gemma":[0.00006154043,0.000043818854,0.000020109192,0.00024341632,0.00006493134,0.0005182996,0.00002554613,0.00011342319,0.0000022630934],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000091714224,0.0010394496,0.15259896,0.000016517048,0.000026786203,1.7519598e-7,0.038650744,0.0017823365,0.0005079823,0.47920355,0.0001517277,0.32593006],"study_design_scores_gemma":[0.00035673566,0.0001727903,0.90554374,0.000039137736,0.000011388468,0.000080053615,0.00094220304,0.0037002186,0.00016710993,0.08861352,0.00028738665,0.00008568999],"about_ca_topic_score_codex":0.000055355093,"about_ca_topic_score_gemma":0.00005980922,"teacher_disagreement_score":0.7529448,"about_ca_system_score_codex":0.00006137078,"about_ca_system_score_gemma":0.00009859514,"threshold_uncertainty_score":0.17868811},"labels":[],"label_agreement":null},{"id":"W2734121241","doi":"10.1093/geroni/igx004.3494","title":"ADD A LANGUAGE! ADD A PICTURE!—IMPROVING PRESCRIPTION MEDICATION LABELS FOR ELDERLY SINGAPOREANS","year":2017,"lang":"en","type":"article","venue":"Innovation in Aging","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Children's Hospital of Eastern Ontario","funders":"","keywords":"Pictogram; Medical prescription; Literacy; Medicine; Health literacy; Malay; Reading (process); Family medicine; Psychology; Medical education; Linguistics; Nursing; Health care; Political science; Pedagogy","score_opus":0.03165806490031054,"score_gpt":0.3106842302414928,"score_spread":0.27902616534118224,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2734121241","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2580227,0.000028505801,0.7377291,0.0027844047,0.0003589699,0.0003983107,0.000005162722,0.00013531085,0.00053758273],"genre_scores_gemma":[0.9731959,0.0000010866788,0.026021453,0.00030559328,0.00013676871,0.0001221487,0.00005292723,0.000008891615,0.00015520399],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99868387,0.000040070383,0.00045840896,0.00038164028,0.0002206272,0.00021537462],"domain_scores_gemma":[0.99833906,0.00009360832,0.00046419338,0.00083531346,0.00024242386,0.00002538],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011597051,0.000109700544,0.000121212746,0.00028607796,0.00038368642,0.00044418787,0.00068377086,0.000088985646,0.000009085243],"category_scores_gemma":[0.0010399222,0.00011234499,0.000026088392,0.00037287304,0.00004802098,0.0013530736,0.00008881888,0.0001502295,0.000004997908],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010300538,0.000072724775,0.0057847695,0.000098387354,0.000007814896,0.0000015798863,0.007850717,0.000061212886,0.04964105,0.13244167,0.0006053901,0.8034244],"study_design_scores_gemma":[0.0041491967,0.00032530676,0.47579622,0.00061942154,0.000030909017,0.000026483516,0.0018096486,0.3343195,0.058476727,0.10164255,0.021549365,0.0012546874],"about_ca_topic_score_codex":0.00019574078,"about_ca_topic_score_gemma":0.00019230571,"teacher_disagreement_score":0.8021697,"about_ca_system_score_codex":0.00011051658,"about_ca_system_score_gemma":0.00008898165,"threshold_uncertainty_score":0.45812958},"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,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_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","score_opus":0.041035925270454,"score_gpt":0.3862038974468522,"score_spread":0.34516797217639816,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2738478726","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9964399,0.00010710691,0.0011637362,0.0017663523,0.000381958,0.000054503427,0.000007750203,8.8676705e-7,0.00007783034],"genre_scores_gemma":[0.99859744,0.00003854193,0.0012570877,0.0000149582,0.000013567045,1.3586073e-7,7.563376e-7,9.72918e-7,0.00007651167],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99886984,0.000080352576,0.0003505306,0.00009043459,0.0005666425,0.00004218473],"domain_scores_gemma":[0.99752545,0.00006969705,0.0016006805,0.00024094246,0.0005320531,0.00003119831],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00071119115,0.00004023706,0.00016884947,0.00019795845,0.000103359576,0.00003547521,0.0015475948,0.000020911428,0.000014887078],"category_scores_gemma":[0.000060825823,0.00003162305,0.00007663659,0.00017026541,0.00021083235,0.00031545822,0.00017383006,0.000046697063,1.4505505e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023127193,0.0005933786,0.9836538,0.000022804481,0.00033012457,0.0000010545782,0.004105144,0.00016916693,0.00013110765,0.00805754,0.00009017567,0.002822566],"study_design_scores_gemma":[0.0002278286,0.00007387206,0.99734557,0.000073435105,0.00006092432,0.000010382212,0.00086315355,0.00019571083,0.00017983968,0.00081295235,0.00013111616,0.000025219993],"about_ca_topic_score_codex":0.0007214411,"about_ca_topic_score_gemma":0.00014633372,"teacher_disagreement_score":0.013691755,"about_ca_system_score_codex":0.000053675976,"about_ca_system_score_gemma":0.00025040397,"threshold_uncertainty_score":0.2875842},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.02459756427332719,"score_gpt":0.28483828905968006,"score_spread":0.26024072478635285,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2753133191","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.69655144,0.00019188788,0.29650193,0.0057685487,0.0001386229,0.00006194425,0.000005022169,0.000009380039,0.00077119377],"genre_scores_gemma":[0.99691564,0.00006254755,0.0027847195,0.000060205435,0.00014561912,2.555838e-7,1.7426505e-7,0.0000036025917,0.000027212063],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99862874,0.00018963902,0.00054872036,0.00008821282,0.00039945086,0.00014523728],"domain_scores_gemma":[0.9965936,0.0011036656,0.0011834517,0.0006755666,0.00040389303,0.000039813163],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004051672,0.00008142799,0.00018969613,0.00004336427,0.0006051685,0.00022514668,0.0015568368,0.000026847787,0.0000030616752],"category_scores_gemma":[0.0010418354,0.00004361938,0.00010953036,0.00010050294,0.00026838292,0.0005077301,0.00023382566,0.00028997904,0.0000010049487],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000652897,0.001363857,0.19053221,0.00051473756,0.0021180569,0.00017072355,0.15397361,0.31758085,0.021897493,0.15124114,0.0025263855,0.15742806],"study_design_scores_gemma":[0.0005135771,0.00039484765,0.17317943,0.0006558712,0.00019714625,0.00031094553,0.022987925,0.78758633,0.0040602917,0.009705863,0.00018541355,0.00022237598],"about_ca_topic_score_codex":0.00006268072,"about_ca_topic_score_gemma":0.0000122752745,"teacher_disagreement_score":0.47000548,"about_ca_system_score_codex":0.000026738058,"about_ca_system_score_gemma":0.000082401806,"threshold_uncertainty_score":0.46545282},"labels":[],"label_agreement":null},{"id":"W2759448304","doi":"10.5539/elt.v10n10p159","title":"Detection of Common Errors in Turkish EFL Students’ Writing through a Corpus Analytic Approach","year":2017,"lang":"en","type":"article","venue":"English Language Teaching","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Turkish; Linguistics; Verb; Error analysis; Context (archaeology); Psychology; Noun; Academic writing; Grammar; Natural language processing; Computer science; Mathematics education; History","score_opus":0.02029820752825017,"score_gpt":0.3065248043780481,"score_spread":0.2862265968497979,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2759448304","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9204478,0.00010583,0.074425325,0.000028906137,0.00018653035,0.00018773829,0.0000017419628,0.00013005479,0.0044860593],"genre_scores_gemma":[0.9922015,0.000002146998,0.007610119,0.00002670384,0.0000977332,0.00001311193,0.0000052079095,0.000009715887,0.000033773893],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.99844056,0.0002448556,0.00036109134,0.00038385682,0.00033673455,0.00023288421],"domain_scores_gemma":[0.9983295,0.00013188113,0.00031161477,0.001153979,0.000033036264,0.000039948485],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015742606,0.00013012312,0.00025234264,0.00010021579,0.0003313008,0.00035020724,0.0014217772,0.0000857076,0.0000015816139],"category_scores_gemma":[0.00088026305,0.00013011119,0.00007383773,0.00011933969,0.000061068255,0.0011209011,0.0003336438,0.000500757,0.0000016368108],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021585462,0.0009018902,0.19256134,0.00020078923,0.00004943779,0.00003969162,0.5281063,0.0006970908,0.012484429,0.010272686,0.000009459909,0.25465533],"study_design_scores_gemma":[0.003225409,0.0002918912,0.7446163,0.0004833387,0.000071103896,0.000044668406,0.094166234,0.12503216,0.027367864,0.0030456441,0.00035836635,0.0012969782],"about_ca_topic_score_codex":0.0020898127,"about_ca_topic_score_gemma":0.00046367204,"teacher_disagreement_score":0.552055,"about_ca_system_score_codex":0.000096275595,"about_ca_system_score_gemma":0.000017027383,"threshold_uncertainty_score":0.530578},"labels":[],"label_agreement":null},{"id":"W2767393219","doi":"","title":"Using Coh-Metrix to Access Cohesion and Difficulty in High-School Textbooks","year":2006,"lang":"en","type":"article","venue":"eScholarship (California Digital Library)","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Cohesion (chemistry); Comprehension; Linguistics; Argument (complex analysis); Memphis; Computer science; Psychology; Philosophy; Chemistry","score_opus":0.025010056484805532,"score_gpt":0.25094336069461987,"score_spread":0.22593330420981433,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2767393219","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96905386,0.00007493876,0.02676047,0.0010259922,0.00007939625,0.0004337104,0.00024558706,0.00030986342,0.0020161793],"genre_scores_gemma":[0.990235,0.0000023012085,0.008842904,0.00046444812,0.00007828474,0.000017368538,0.00010589948,0.00002610239,0.00022771294],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9978846,0.00009357995,0.000502238,0.00072044175,0.00036776942,0.0004313845],"domain_scores_gemma":[0.99876076,0.00018498767,0.00010999907,0.0005839043,0.000039732804,0.00032063093],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.00022021882,0.00026021735,0.0002703236,0.00037912387,0.0001634548,0.0040668375,0.0010212193,0.00015340412,0.000033172568],"category_scores_gemma":[0.00021812606,0.00023779646,0.00006258331,0.0011060616,0.00006356903,0.008118334,0.0007582799,0.0003184522,0.0002952982],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007439005,0.0004177249,0.947288,0.000068423775,0.000009203254,0.000039285835,0.000036011952,0.0004466601,0.003668652,0.0199638,0.001750183,0.026237715],"study_design_scores_gemma":[0.0007179708,0.000079182755,0.92478716,0.000104373496,0.00000610688,0.00001933714,0.000008991783,0.0029301536,0.0075562466,0.042054333,0.021096038,0.0006401219],"about_ca_topic_score_codex":0.00009846073,"about_ca_topic_score_gemma":0.000015930016,"teacher_disagreement_score":0.025597595,"about_ca_system_score_codex":0.00008620151,"about_ca_system_score_gemma":0.000097780685,"threshold_uncertainty_score":0.996967},"labels":[],"label_agreement":null},{"id":"W2781187670","doi":"","title":"Variations in Textualization: A Cross-generic and Cross-disciplinary Study, Implications for Readability of the Academic Discourse","year":2018,"lang":"en","type":"article","venue":"DOAJ (DOAJ: Directory of Open Access Journals)","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Algonquin College","funders":"","keywords":"Readability; Cross disciplinary; Discipline; Linguistics; Genre analysis; Literature; Sociology; Computer science; Art; Philosophy; Social science; Data science","score_opus":0.34009982350384155,"score_gpt":0.6156297992036794,"score_spread":0.2755299756998379,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2781187670","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93313587,0.0008952727,0.06230568,0.0015801974,0.00025190582,0.0015340388,0.00008227419,0.00002591031,0.0001888226],"genre_scores_gemma":[0.99817777,0.00021019613,0.0011401778,0.00007126671,0.00008895911,0.00021126239,0.0000063421885,0.000014374711,0.000079664795],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99733406,0.000334344,0.0011040305,0.00060617446,0.00035781474,0.00026358172],"domain_scores_gemma":[0.99645495,0.00059915724,0.00087452756,0.0012513042,0.00070532435,0.00011471212],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024187607,0.00019438086,0.0004069574,0.00030793238,0.0006585777,0.00085836666,0.003930602,0.000118088465,0.00009830432],"category_scores_gemma":[0.0007678677,0.00015047511,0.00010586646,0.0018687986,0.0006553064,0.0029793198,0.001702581,0.0002461084,0.0000011550167],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004380963,0.00047243582,0.9739923,0.000046260968,0.000026303742,1.4123056e-7,0.001631544,0.00018568306,0.0074781845,0.006693282,0.0003686251,0.009061466],"study_design_scores_gemma":[0.0002512275,0.00002459244,0.93256885,0.00006105454,0.000021850019,0.000004334881,0.00007679154,0.0015866973,0.0019880729,0.06309744,0.00016259296,0.00015648476],"about_ca_topic_score_codex":0.0002529264,"about_ca_topic_score_gemma":0.0002410358,"teacher_disagreement_score":0.06504186,"about_ca_system_score_codex":0.00010248332,"about_ca_system_score_gemma":0.00029779595,"threshold_uncertainty_score":0.82772493},"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,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology; Reading (process); Critical reading; Linguistics; Mathematics education; Error analysis","score_opus":0.007723869247560229,"score_gpt":0.2972760731860103,"score_spread":0.28955220393845005,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2789586388","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8823821,0.00014467307,0.11522868,0.0001828416,0.00013916344,0.000188596,0.0000028349507,0.00013094145,0.0016002004],"genre_scores_gemma":[0.9788564,0.000004028391,0.020960173,0.000042911415,0.00011552302,0.00000485052,0.0000023901769,0.000007338926,0.0000064006103],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.9985607,0.00032373235,0.00027972457,0.00037246573,0.00027822872,0.00018510185],"domain_scores_gemma":[0.9982856,0.0010593934,0.0000753163,0.0004340806,0.00006429321,0.00008132639],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016306589,0.00011751954,0.00019612553,0.000076138014,0.00017611888,0.00021250355,0.0002513431,0.00006802574,0.000009720579],"category_scores_gemma":[0.0028368195,0.000108643464,0.00002774872,0.00010164379,0.00015646021,0.00094378414,0.000112231945,0.00022785446,0.0000017741698],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010598599,0.0005134783,0.023952462,0.0004279261,0.000037196725,0.000010153234,0.70921814,0.000002099251,0.02272459,0.07052519,0.000010053797,0.1725681],"study_design_scores_gemma":[0.004090469,0.0016907639,0.7244074,0.0017799344,0.00039246544,0.00023509395,0.093666814,0.058788564,0.05428081,0.057758015,0.0004955916,0.0024141113],"about_ca_topic_score_codex":0.0000830484,"about_ca_topic_score_gemma":0.000029222801,"teacher_disagreement_score":0.7004549,"about_ca_system_score_codex":0.000029701376,"about_ca_system_score_gemma":0.000016811386,"threshold_uncertainty_score":0.4430352},"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,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_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","score_opus":0.034709532721056736,"score_gpt":0.3604011198138306,"score_spread":0.32569158709277385,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2791769113","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17188497,0.000016877306,0.8130813,0.0032588642,0.00021358716,0.0003046884,7.1260473e-7,0.00011285545,0.0111260945],"genre_scores_gemma":[0.9727356,0.000009219592,0.02577335,0.0012793439,0.00014536576,0.00003463461,0.0000050938033,0.000003906708,0.000013484189],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9958535,0.00016828137,0.0009030704,0.00014682037,0.0026583397,0.00026998285],"domain_scores_gemma":[0.9979508,0.00041651487,0.00027653665,0.0009423653,0.00018457901,0.00022919207],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0043846625,0.00011847713,0.00021897366,0.00005479217,0.00019375978,0.00022906446,0.0022215017,0.00024336796,0.00014707039],"category_scores_gemma":[0.00096595555,0.0000703901,0.000074162526,0.00050267915,0.00080428325,0.0012625124,0.000540338,0.0004163831,0.000031397783],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007919911,0.00048095657,0.0018832515,0.00040103987,0.00004191608,0.000001672544,0.036195714,0.0000024181131,0.00001291792,0.09305896,0.0029289145,0.86498433],"study_design_scores_gemma":[0.0005737546,0.00016077426,0.009211279,0.00028383164,0.00001580192,0.00011918647,0.00518316,0.94836175,0.0007363188,0.011886505,0.023139104,0.0003285312],"about_ca_topic_score_codex":0.000033034674,"about_ca_topic_score_gemma":0.0000049869263,"teacher_disagreement_score":0.9483593,"about_ca_system_score_codex":0.000048751866,"about_ca_system_score_gemma":0.0004441749,"threshold_uncertainty_score":0.41281396},"labels":[],"label_agreement":null},{"id":"W2793382933","doi":"10.1007/978-3-319-75477-2_46","title":"Classification of Textual Genres Using Discourse Information","year":2018,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science; Task (project management); Variety (cybernetics); Linguistics; Natural language processing; Artificial intelligence; Discourse analysis; Discourse marker; Philosophy","score_opus":0.033788664726766955,"score_gpt":0.28669100035671935,"score_spread":0.2529023356299524,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2793382933","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004734752,0.000050373415,0.9926146,0.00027806012,0.0005670076,0.00030937922,0.000009641455,0.00006931052,0.0013668636],"genre_scores_gemma":[0.7319191,0.0000096041995,0.26756874,0.00019750232,0.00022814404,0.000003910493,0.000016615795,0.000010639195,0.000045733672],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975677,0.000031971253,0.00065319345,0.0006407806,0.00079308747,0.00031327025],"domain_scores_gemma":[0.9974169,0.00019877264,0.00055800343,0.0012838822,0.00045720892,0.00008521906],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0008255369,0.0002777486,0.00031314316,0.0006865926,0.00016993395,0.0002955586,0.001985263,0.00025726107,0.00002129419],"category_scores_gemma":[0.000114971066,0.00025185212,0.00008638334,0.0004950434,0.001055846,0.0018614928,0.0005007715,0.00030304215,0.000038633087],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007357384,0.000032035343,0.0001390619,0.00006258998,0.0000073773076,0.0000012558548,0.0024512452,0.0075958353,0.0012713439,0.0819053,0.00001599357,0.9065106],"study_design_scores_gemma":[0.00014979187,0.0001391617,0.0022834141,0.00021350368,0.000009994585,0.000024999477,0.0000032751307,0.9175976,0.002417038,0.07602378,0.0007048541,0.0004326149],"about_ca_topic_score_codex":0.000030796833,"about_ca_topic_score_gemma":0.000037143393,"teacher_disagreement_score":0.91000175,"about_ca_system_score_codex":0.0002528343,"about_ca_system_score_gemma":0.00059346616,"threshold_uncertainty_score":0.9999934},"labels":[],"label_agreement":null},{"id":"W2795042751","doi":"","title":"Collocation and collocation error processing in the context of second language learning","year":2018,"lang":"en","type":"dissertation","venue":"TDX (Tesis Doctorals en Xarxa)","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Humanities; Philosophy; Artificial intelligence; Computer science","score_opus":0.020180182956088873,"score_gpt":0.31041990531926467,"score_spread":0.2902397223631758,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2795042751","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9951953,0.0011056202,0.0012962716,0.00029986087,0.00016418658,0.0006701897,0.0000074546065,0.00007030464,0.0011907822],"genre_scores_gemma":[0.9966398,0.000026834856,0.0013539178,0.00008671856,0.00006979335,0.0001040938,0.00024554227,0.000017658816,0.0014556532],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99795896,0.00039214757,0.0005484761,0.0004996713,0.00038579662,0.00021493463],"domain_scores_gemma":[0.9983444,0.00028609348,0.00055727613,0.0004890722,0.00028150814,0.000041620457],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012281084,0.00023283415,0.00035067828,0.00023295151,0.00018072748,0.00022815574,0.0006731221,0.00027216424,0.0000390701],"category_scores_gemma":[0.00035146598,0.00019697928,0.00005708129,0.00065781665,0.00007495315,0.0005310742,0.000039460443,0.0002984311,0.000013108086],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016482345,0.0004668106,0.012379451,0.0026297204,0.000059967348,0.000006941108,0.35976332,0.000041520594,0.059286036,0.010559344,0.0012227002,0.55341935],"study_design_scores_gemma":[0.001689948,0.0006694939,0.80368876,0.0013743785,0.0001802253,0.00002837596,0.086763576,0.025149327,0.06377283,0.0022563539,0.012860127,0.0015666249],"about_ca_topic_score_codex":0.00024935743,"about_ca_topic_score_gemma":0.0027971826,"teacher_disagreement_score":0.7913093,"about_ca_system_score_codex":0.0000969895,"about_ca_system_score_gemma":0.00022412046,"threshold_uncertainty_score":0.8032582},"labels":[],"label_agreement":null},{"id":"W2795073795","doi":"10.1177/1468017318767091","title":"Readability, suitability, and writing for clients with limited literacy skills","year":2018,"lang":"en","type":"article","venue":"Journal of Social Work","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"McGill University","keywords":"Readability; Literacy; Psychology; Reading (process); Computer science; Pedagogy; Linguistics","score_opus":0.016843800256583233,"score_gpt":0.3015515451048925,"score_spread":0.2847077448483093,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2795073795","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9281347,0.000034365086,0.06853457,0.0027720982,0.00017601279,0.00017909026,0.0000023538764,0.000021879558,0.00014493689],"genre_scores_gemma":[0.958891,0.00000268183,0.04041442,0.00015435304,0.00048618147,0.000003663248,7.867116e-7,0.000006354724,0.000040580388],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9987573,0.00009515273,0.00045143598,0.00020778827,0.00027576467,0.00021257985],"domain_scores_gemma":[0.99805474,0.00046707471,0.00035590865,0.00020051414,0.00082879583,0.00009298789],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012390671,0.000098730634,0.00022082673,0.00006777598,0.0003994953,0.00025494036,0.0003735799,0.000075010605,0.0000067003693],"category_scores_gemma":[0.00024991247,0.000076869655,0.00008293577,0.00049644284,0.0002033747,0.00067485863,0.000091971364,0.00015014996,0.0000023360224],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00049650343,0.00094063557,0.40019566,0.00011489377,0.00010337846,0.0000058682263,0.026074994,0.0000032499606,0.00068592944,0.019587034,0.0013246139,0.55046725],"study_design_scores_gemma":[0.00067545054,0.00081763946,0.97016084,0.00011644088,0.000028583185,0.000037870606,0.00023026581,0.00013660126,0.0005791005,0.022491805,0.0045263837,0.00019901631],"about_ca_topic_score_codex":0.0000020253367,"about_ca_topic_score_gemma":0.0000039788147,"teacher_disagreement_score":0.5699652,"about_ca_system_score_codex":0.00007196428,"about_ca_system_score_gemma":0.00007665838,"threshold_uncertainty_score":0.31346536},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.02853277318405379,"score_gpt":0.33424594013566167,"score_spread":0.3057131669516079,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2883325825","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9485372,0.00008716964,0.049884237,0.00087355915,0.0002108096,0.00010009435,0.0000093996205,0.000013326499,0.00028422257],"genre_scores_gemma":[0.9982645,0.000042741874,0.0011310017,0.00035996546,0.00012931584,0.000005014258,0.000003651955,0.00000485406,0.00005893896],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9989937,0.00013954756,0.00039182452,0.00019864038,0.00013629878,0.0001399952],"domain_scores_gemma":[0.99918526,0.00005562108,0.0003344742,0.00012495802,0.00019558816,0.00010412396],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00042242795,0.00009577395,0.0001903615,0.00013278815,0.00018344058,0.000040549763,0.0001278056,0.000070717666,0.000031779655],"category_scores_gemma":[0.00009359732,0.000091630456,0.00003521312,0.00009338789,0.00012000216,0.00026682316,0.00006524591,0.00019076651,0.0000053248273],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021715288,0.00024322039,0.006738011,0.000020139127,0.00004386174,0.000011798456,0.0047647413,0.0000010760756,0.966077,0.00064112816,0.00006228135,0.021179534],"study_design_scores_gemma":[0.0013894264,0.001890061,0.57334363,0.00017274669,0.000027014808,0.0002243911,0.001702481,0.00011215117,0.4200414,0.0006186355,0.00030237608,0.0001756826],"about_ca_topic_score_codex":0.0000028554282,"about_ca_topic_score_gemma":6.0588803e-7,"teacher_disagreement_score":0.5666056,"about_ca_system_score_codex":0.000027787268,"about_ca_system_score_gemma":0.000013413344,"threshold_uncertainty_score":0.37365815},"labels":[],"label_agreement":null},{"id":"W2902840231","doi":"10.5539/ells.v8n4p8","title":"Impact of Language Input on Comprehensiveness of Reading Material among Students in Saudi Arabia","year":2018,"lang":"en","type":"article","venue":"English Language and Literature Studies","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Vocabulary; Reading (process); Meaning (existential); Comprehension; Reading comprehension; Computer science; Mathematics education; Field (mathematics); Linguistics; Psychology; Mathematics","score_opus":0.009735983842126796,"score_gpt":0.30488962381910895,"score_spread":0.29515363997698213,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2902840231","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9981079,0.0011558278,0.000052627962,0.000011104847,0.0002504746,0.00014576186,0.0000331128,0.000031884236,0.00021128135],"genre_scores_gemma":[0.99943274,0.00004121906,0.00028277206,0.000016047637,0.00017077591,0.0000053947956,0.000011711675,0.0000053243352,0.000034012166],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.99901974,0.000113813236,0.00025834102,0.0002655648,0.0001871198,0.0001554053],"domain_scores_gemma":[0.99912614,0.00012939634,0.0001239566,0.0003479872,0.00024121082,0.000031328193],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025858494,0.00014054387,0.00032477468,0.00014526036,0.000046987658,0.000075203956,0.0002833824,0.00006807965,0.000004262928],"category_scores_gemma":[0.00023610222,0.000103807026,0.0000540061,0.00034238605,0.00015836263,0.00027654303,0.00017758812,0.00010939529,4.6884466e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000109212335,0.00016898187,0.119064465,0.00018834094,0.0001183255,0.00003947202,0.86350936,0.000007568748,0.010634541,0.0010839633,0.00011932024,0.0049564694],"study_design_scores_gemma":[0.0007443076,0.00064587034,0.9569243,0.00085039216,0.000014390117,0.00000386741,0.022154778,0.000055533208,0.018154347,0.00018218774,0.000037327452,0.00023268725],"about_ca_topic_score_codex":0.000105081126,"about_ca_topic_score_gemma":0.000048944712,"teacher_disagreement_score":0.84135455,"about_ca_system_score_codex":0.000029239656,"about_ca_system_score_gemma":0.000011124114,"threshold_uncertainty_score":0.42331275},"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,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_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","score_opus":0.021454837210007724,"score_gpt":0.3203907298057573,"score_spread":0.29893589259574954,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2905305848","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98013556,0.000052110896,0.014942948,0.00015482304,0.00014779942,0.00017837695,0.000001876317,0.00021010914,0.004176373],"genre_scores_gemma":[0.9960437,0.0000032562562,0.0035485292,0.00014697056,0.00019811548,0.000009468869,0.0000073037577,0.000009029908,0.000033650158],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99869555,0.00021720525,0.00022543101,0.00043421224,0.0001907557,0.0002368717],"domain_scores_gemma":[0.9990451,0.00021205434,0.000071673676,0.0005616142,0.00003114192,0.000078467696],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007318433,0.00012522878,0.00013575824,0.00016337942,0.00027427907,0.000295396,0.00047689633,0.0000647063,0.000003903576],"category_scores_gemma":[0.00024149119,0.000121652374,0.000024123841,0.00020486633,0.000048769467,0.0004804849,0.00014712576,0.00032613444,0.000009528488],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026293337,0.0004274742,0.069807924,0.000035717945,0.000020418222,0.000021857817,0.29368523,0.00015371451,0.020700628,0.10489251,0.00015404052,0.5100742],"study_design_scores_gemma":[0.0017564294,0.00053941447,0.93832767,0.00041776765,0.00001883245,0.00003177349,0.029587418,0.014797478,0.005625428,0.0062777363,0.0016438519,0.0009761988],"about_ca_topic_score_codex":0.0001952708,"about_ca_topic_score_gemma":0.000118102005,"teacher_disagreement_score":0.8685197,"about_ca_system_score_codex":0.00007162956,"about_ca_system_score_gemma":0.000016310118,"threshold_uncertainty_score":0.49608397},"labels":[],"label_agreement":null},{"id":"W2940642754","doi":"","title":"Méthodes d’enseignement de la lecture pour les personnes ayant une déficience intellectuelle moyenne à sévère","year":2019,"lang":"fr","type":"article","venue":"Canadian Journal of Education / Revue canadienne de l éducation","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université Laval; Université du Québec à Rimouski","funders":"","keywords":"Humanities; Art","score_opus":0.03776281913377554,"score_gpt":0.2715780684212553,"score_spread":0.23381524928747976,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2940642754","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.88084525,0.0057176994,0.057571754,0.047166876,0.006313253,0.00036978116,0.000022647215,0.000013681618,0.0019790672],"genre_scores_gemma":[0.97361773,0.00020821713,0.016288584,0.00080581266,0.0009970806,0.000019917648,0.00002001097,0.000034116736,0.008008534],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.99660665,0.0009033236,0.00076576014,0.0005126299,0.0001640022,0.0010476512],"domain_scores_gemma":[0.9949446,0.00067709293,0.0007105822,0.00070472335,0.0013560321,0.001607001],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0029734904,0.0003292887,0.00038075613,0.00076242303,0.00049948896,0.00051299547,0.0010706306,0.00035431393,0.00073863013],"category_scores_gemma":[0.0022212095,0.0003782285,0.00019385785,0.0012532803,0.00030454135,0.00073566166,0.000023131714,0.00071522617,0.000073742245],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.000035771238,0.0006373479,0.019907573,0.00079832604,0.00011696624,0.00004533333,0.5453779,0.0121837305,0.0045183245,0.159803,0.043914244,0.21266145],"study_design_scores_gemma":[0.0010467399,0.0011008873,0.18382177,0.002646977,0.00035142511,0.009087396,0.21633859,0.03845724,0.0023321908,0.06296164,0.48011193,0.0017432179],"about_ca_topic_score_codex":0.13189697,"about_ca_topic_score_gemma":0.5172271,"teacher_disagreement_score":0.4361977,"about_ca_system_score_codex":0.008410253,"about_ca_system_score_gemma":0.030693483,"threshold_uncertainty_score":0.99986696},"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,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.02486016120334763,"score_gpt":0.286088772061162,"score_spread":0.2612286108578144,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2945464291","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9935371,0.0019543073,0.0026159973,0.0004984849,0.00036119952,0.00008597109,0.0000015879255,0.000019683972,0.0009256232],"genre_scores_gemma":[0.99817157,0.00006624055,0.0011870381,0.0004485623,0.000059634727,0.000003815764,0.0000058812016,0.0000045956267,0.00005264713],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.998838,0.0002539744,0.00033363776,0.00026455594,0.00017109633,0.00013873925],"domain_scores_gemma":[0.99934494,0.00010558456,0.00029053068,0.00014422907,0.000057090903,0.00005760812],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00039764305,0.000102393344,0.0002102154,0.00012716491,0.000065019856,0.00005603299,0.00022215852,0.00013586681,0.00008399916],"category_scores_gemma":[0.000041379866,0.000093963135,0.000050043116,0.000096732525,0.00006911239,0.0005008074,0.0000573779,0.00039196791,0.000028063776],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009769533,0.0014019953,0.0843483,0.0000174409,0.00008311948,0.00026251853,0.0053645424,0.0006344243,0.853909,0.0029808562,0.00028410822,0.049736723],"study_design_scores_gemma":[0.0044116094,0.0016435755,0.9227944,0.00017803845,0.000019209154,0.0012457484,0.0053215805,0.00058067794,0.051542807,0.011613028,0.0002743217,0.00037502655],"about_ca_topic_score_codex":0.0000066410385,"about_ca_topic_score_gemma":0.000002255625,"teacher_disagreement_score":0.8384461,"about_ca_system_score_codex":0.000028204899,"about_ca_system_score_gemma":0.000012070643,"threshold_uncertainty_score":0.38317055},"labels":[],"label_agreement":null},{"id":"W2958762673","doi":"10.1017/s1366728919000312","title":"The English disease in Finnish compound processing: Backward transfer effects in Finnish–English bilinguals","year":2019,"lang":"en","type":"article","venue":"Bilingualism Language and Cognition","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Spelling; Linguistics; Reading (process); Transfer (computing); Computer science; Line (geometry); History; Psychology; Mathematics; Parallel computing; Philosophy","score_opus":0.007664252920006852,"score_gpt":0.24128225543429307,"score_spread":0.23361800251428622,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2958762673","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99430037,0.0025215226,0.0011084005,0.00024074347,0.00031541105,0.0008719042,0.000009885643,0.00015632095,0.00047545222],"genre_scores_gemma":[0.99892056,0.00008246938,0.0002105781,0.00041645407,0.00015019922,0.000083591505,0.00005360366,0.000015581334,0.00006695422],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9979749,0.00027259337,0.00043075436,0.00062889076,0.00031124314,0.0003816664],"domain_scores_gemma":[0.998433,0.00068120897,0.00006490636,0.00048966915,0.00021523412,0.000115981085],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00088213006,0.0002176478,0.00024866036,0.00015302972,0.00014503051,0.00043000106,0.0004003781,0.00012499781,0.000009026515],"category_scores_gemma":[0.0007091276,0.00017603097,0.00006664227,0.00055817916,0.000099842524,0.0005808371,0.00007330388,0.0002872506,0.000012151942],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004376526,0.0015419922,0.0908676,0.0021233996,0.0000432022,0.0005030166,0.31776765,0.00022119515,0.0069772676,0.02462748,0.00012934994,0.55476016],"study_design_scores_gemma":[0.017713947,0.0010227673,0.78100044,0.0034519853,0.0002087959,0.000045931127,0.03338644,0.057675377,0.020232469,0.06338994,0.01757256,0.0042993724],"about_ca_topic_score_codex":0.00012295807,"about_ca_topic_score_gemma":0.00035899234,"teacher_disagreement_score":0.6901328,"about_ca_system_score_codex":0.000044797853,"about_ca_system_score_gemma":0.00015297731,"threshold_uncertainty_score":0.71783346},"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,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","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)","score_opus":0.02387598674403773,"score_gpt":0.3108783492838626,"score_spread":0.28700236253982486,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2962734277","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98997146,0.0007801121,0.007261865,0.00022863255,0.00028154117,0.00009836672,9.154518e-8,0.00001406349,0.001363893],"genre_scores_gemma":[0.9969238,0.000044435947,0.0027842168,0.0001711829,0.000043821034,0.0000013547346,9.077675e-7,0.0000049734035,0.000025288315],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99901724,0.00019137097,0.00032410215,0.00021842934,0.000114713024,0.00013413616],"domain_scores_gemma":[0.9994303,0.00013461125,0.000247854,0.00009473365,0.00003697076,0.000055538287],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00064386346,0.000093035414,0.0001784892,0.00017239763,0.00008561249,0.000068788664,0.00012406125,0.00007296728,0.000026315085],"category_scores_gemma":[0.000027078775,0.000090970985,0.00003254907,0.00012631615,0.00006808259,0.0005186088,0.000041469008,0.00039958674,0.0000150497335],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00044266472,0.00048067968,0.04118721,0.000045955294,0.00004814046,0.00008348192,0.012960977,0.00042076083,0.87253684,0.0008386442,0.00002402786,0.070930615],"study_design_scores_gemma":[0.026200853,0.010613479,0.46226728,0.0013964986,0.00011102212,0.019218065,0.055214435,0.050369058,0.33251128,0.036364853,0.003244021,0.0024891691],"about_ca_topic_score_codex":0.0000032960081,"about_ca_topic_score_gemma":0.0000014725617,"teacher_disagreement_score":0.5400256,"about_ca_system_score_codex":0.000023723951,"about_ca_system_score_gemma":0.000011796324,"threshold_uncertainty_score":0.37096894},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.022921391967392204,"score_gpt":0.25207139055509037,"score_spread":0.22914999858769816,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2962986840","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027285373,0.00005516679,0.9663415,0.0024607736,0.0006230277,0.00066684495,0.0000038937114,0.0006326734,0.0019307618],"genre_scores_gemma":[0.97029006,0.00001571899,0.028288528,0.00051933527,0.0002289458,0.00010588447,0.000090124144,0.000017608147,0.00044377515],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99751776,0.00013639258,0.00040839027,0.0011516899,0.0004180004,0.00036777483],"domain_scores_gemma":[0.99670637,0.0000908014,0.00031316414,0.0023580065,0.0003870326,0.00014463662],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00039191687,0.00032696227,0.00027979384,0.000103100865,0.0001684659,0.00045218982,0.0017798891,0.00026436843,0.000043913802],"category_scores_gemma":[0.000032037922,0.00025581362,0.00008803624,0.00034291807,0.00016713217,0.00037104407,0.0009372996,0.00047963124,0.00005138487],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028495907,0.0014021654,0.01144325,0.00060998707,0.0004247792,0.000044431603,0.0035678085,0.28689927,0.00087008846,0.07766847,0.021664616,0.5951202],"study_design_scores_gemma":[0.0001563093,0.00008737137,0.010036111,0.000037830072,0.000016404694,0.00001882849,0.00003189522,0.9859364,0.0004542019,0.0024504988,0.0004054406,0.00036871497],"about_ca_topic_score_codex":0.00016634875,"about_ca_topic_score_gemma":0.00007810709,"teacher_disagreement_score":0.9430047,"about_ca_system_score_codex":0.00011184612,"about_ca_system_score_gemma":0.000115533905,"threshold_uncertainty_score":0.9999894},"labels":[],"label_agreement":null},{"id":"W2964145186","doi":"10.26615/978-954-452-049-6_027","title":"Automatic Identification of AltLexes using Monolingual Parallel Corpora","year":2017,"lang":"en","type":"article","venue":"","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Natural language processing; WordNet; Leverage (statistics); Artificial intelligence; Parsing; Text simplification; Identification (biology); Task (project management); Natural language; Parallel corpora; Relation (database); Simple (philosophy); Sentence; Machine translation; Database","score_opus":0.05978571800230753,"score_gpt":0.3233308221855031,"score_spread":0.26354510418319554,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2964145186","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5078298,0.000012960854,0.49146223,0.00019744565,0.000095979405,0.00007794139,6.6149255e-7,0.000055741744,0.00026724467],"genre_scores_gemma":[0.93247515,0.0000020378964,0.06739137,0.000013513904,0.000014992171,0.0000028592306,0.0000010071119,0.000002488618,0.00009655205],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992248,0.000026569718,0.00030488815,0.00019546806,0.00015233966,0.00009594052],"domain_scores_gemma":[0.99824667,0.000034766195,0.0004144141,0.0011842952,0.000087959976,0.000031905645],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034876892,0.000058307724,0.000107813285,0.000042959702,0.00022430751,0.00021809916,0.000872886,0.000038189202,0.000013123243],"category_scores_gemma":[0.00012419866,0.000052638705,0.00003836868,0.0000487564,0.00007930816,0.0006590664,0.0001177504,0.000034843582,0.00002068712],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000063065513,0.00029327022,0.013942813,0.00014722376,0.00004096948,0.000002942574,0.0039719287,0.0011067168,0.123569235,0.5411617,0.00013785585,0.31561902],"study_design_scores_gemma":[0.00010679471,0.000013178536,0.12414181,0.0000109084995,0.0000067993064,0.000004272134,0.000035075533,0.82355887,0.020507371,0.03148712,0.00003825493,0.000089531735],"about_ca_topic_score_codex":0.00019927174,"about_ca_topic_score_gemma":0.000012949193,"teacher_disagreement_score":0.8224522,"about_ca_system_score_codex":0.000016758771,"about_ca_system_score_gemma":0.0000582437,"threshold_uncertainty_score":0.21465442},"labels":[],"label_agreement":null},{"id":"W2966658317","doi":"","title":"The Effects of Noun-Labelling by Others and the Self in the Domain of Mental Disorders","year":2018,"lang":"en","type":"article","venue":"Student Research Proceedings","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"MacEwan University","funders":"","keywords":"Noun; Psychology; Noun phrase; Linguistics; Determiner phrase; Identity (music); Phrase; Social psychology; Developmental psychology; Cognitive psychology","score_opus":0.017906094600222133,"score_gpt":0.3481998471781147,"score_spread":0.33029375257789256,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2966658317","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99119276,0.00039290194,0.0002893701,0.005216867,0.00003777541,0.0011658991,4.9622616e-7,0.000010741602,0.0016932063],"genre_scores_gemma":[0.99925,0.00038798706,0.00017256511,0.0000324227,0.000019045117,0.00009336964,1.4471574e-7,0.0000033690283,0.00004108838],"study_design_codex":"qualitative","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9983292,0.00016968376,0.00019081992,0.00020820837,0.0008439474,0.0002581437],"domain_scores_gemma":[0.9984084,0.0011262132,0.000070977716,0.00021436182,0.00015627636,0.000023772398],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0056381905,0.000067207,0.00009705032,0.000048985126,0.00040550614,0.00016346709,0.0013868305,0.000027597294,5.945624e-7],"category_scores_gemma":[0.00018906395,0.000030622887,0.0000261094,0.00053459423,0.0010761949,0.0001584241,0.0003020352,0.0001997547,0.0000013827885],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016864514,0.0006315642,0.021400318,0.0002968719,0.00008154031,2.3619536e-7,0.4846979,1.7667494e-7,0.022881892,0.435037,0.0035673724,0.03123648],"study_design_scores_gemma":[0.015193779,0.0065275235,0.2645288,0.0007318083,0.00004715045,0.000015894888,0.22114839,0.009496924,0.06838245,0.34230977,0.070748426,0.00086906867],"about_ca_topic_score_codex":0.00018906248,"about_ca_topic_score_gemma":0.00007397121,"teacher_disagreement_score":0.26354954,"about_ca_system_score_codex":0.00003322421,"about_ca_system_score_gemma":0.000029485778,"threshold_uncertainty_score":0.39652848},"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,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.10622571949909959,"score_gpt":0.3005297298892182,"score_spread":0.19430401039011863,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2977455214","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.016414853,0.0067482735,0.020484746,0.0014490013,0.0007384604,0.0086677885,0.00042837448,0.00039435894,0.94467413],"genre_scores_gemma":[0.4341006,0.00021168789,0.004792223,0.00063275057,0.00040834988,0.000018922363,0.00013421947,0.000068345194,0.5596329],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985678,0.00010984657,0.00021142185,0.0004886197,0.00044960206,0.00017271472],"domain_scores_gemma":[0.99815834,0.00044485758,0.00036490115,0.00067026063,0.0003082071,0.000053412346],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00094077154,0.00021840284,0.00025317766,0.000084041596,0.00021368726,0.000117335614,0.0009312379,0.0003199595,0.00001265819],"category_scores_gemma":[0.00012194958,0.00017932178,0.000105860476,0.000018048715,0.00020387665,0.00040741859,0.00027347603,0.00032716972,0.000002651768],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008164559,0.00001446884,0.0000027567507,0.00038364882,0.00008097608,0.0000025605768,0.005443378,0.000004057017,0.00021790453,0.50412065,0.0029487768,0.4866992],"study_design_scores_gemma":[0.002232176,0.0006111331,0.00046881332,0.0024806578,0.0009968693,0.000031939464,0.0015119644,0.03612586,0.00885375,0.04259567,0.90232,0.0017711172],"about_ca_topic_score_codex":0.000046741145,"about_ca_topic_score_gemma":0.000016883007,"teacher_disagreement_score":0.89937127,"about_ca_system_score_codex":0.00015466615,"about_ca_system_score_gemma":0.0001632373,"threshold_uncertainty_score":0.73125297},"labels":[],"label_agreement":null},{"id":"W3009120927","doi":"10.1017/s1351324920000133","title":"Nonuniform language in technical writing: Detection and correction","year":2020,"lang":"en","type":"article","venue":"Natural Language Engineering","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Computer science; Natural language processing; Readability; Paraphrase; Artificial intelligence; Task (project management); Sentence; Context (archaeology); Synonym (taxonomy); Similarity (geometry); Programming language","score_opus":0.004691055894078967,"score_gpt":0.21110933476405405,"score_spread":0.20641827886997507,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3009120927","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8255678,0.00086731976,0.17213686,0.00044623762,0.00025300754,0.00013107664,6.7677917e-7,0.000468295,0.00012873362],"genre_scores_gemma":[0.99494344,0.0000033649617,0.004870839,0.00008187423,0.00007522048,0.00000644305,0.0000023862428,0.0000055327737,0.000010895639],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9994424,0.000010700511,0.00012308657,0.00020021267,0.000093918636,0.00012969499],"domain_scores_gemma":[0.9997369,0.00005830625,0.000020436684,0.00012137087,0.000011490248,0.000051465828],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000107146385,0.00007709993,0.000083081526,0.00006598786,0.000024766265,0.000054686287,0.0001405825,0.00006208062,0.0000020521836],"category_scores_gemma":[0.00018870708,0.00007528801,0.000020383279,0.00032497026,0.0000068934587,0.00029153613,0.000060222097,0.00029329574,0.000004227846],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009665435,0.000015362128,0.00041074844,0.000056956185,0.000003329809,0.000035476736,0.0055369847,0.0014662223,0.6029116,0.0007825176,0.000012809805,0.38875833],"study_design_scores_gemma":[0.00017870724,0.000037672064,0.029663427,0.000019460535,0.0000018074221,0.00004793501,0.00034305194,0.93769574,0.031722534,0.0000046799987,0.00013420204,0.00015077596],"about_ca_topic_score_codex":0.00004671875,"about_ca_topic_score_gemma":0.000054675365,"teacher_disagreement_score":0.9362295,"about_ca_system_score_codex":0.000049641407,"about_ca_system_score_gemma":0.0000055341857,"threshold_uncertainty_score":0.30701557},"labels":[],"label_agreement":null},{"id":"W3009935877","doi":"10.1162/qss_a_00125","title":"Textual analysis of artificial intelligence manuscripts reveals features associated with peer review outcome","year":2021,"lang":"en","type":"preprint","venue":"Quantitative Science Studies","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; University of Ottawa","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Readability; Artificial intelligence; Natural language processing; Jargon; Computer science; Outcome (game theory); Similarity (geometry); Semantic similarity; Linguistics; Psychology; Mathematics; Philosophy","score_opus":0.2643686269816425,"score_gpt":0.4440727271641647,"score_spread":0.1797041001825222,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3009935877","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21422301,0.0680223,0.6842102,0.026403828,0.0015288985,0.00265485,0.00038429312,0.0003966359,0.0021760222],"genre_scores_gemma":[0.96013963,0.0017344352,0.037243795,0.00040374353,0.000013363935,0.000079506084,0.00006184094,0.000008649093,0.00031503587],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9938902,0.000464197,0.0011427851,0.0015264633,0.0025067958,0.00046951522],"domain_scores_gemma":[0.9884618,0.0010277485,0.0011784625,0.0014394044,0.0077875047,0.000105059575],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0067820232,0.00040504322,0.001630142,0.0007699656,0.00043909688,0.0003328612,0.0023057305,0.00011411609,0.000011306276],"category_scores_gemma":[0.015965195,0.00030076999,0.00036682986,0.0074866796,0.0024291505,0.00067346665,0.0017400685,0.0005347144,0.0000054411616],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000042478827,0.0010598375,0.020734364,0.0034776225,0.008788848,0.00006090114,0.046119552,0.0066214786,0.0019762819,0.87111473,0.0018487063,0.038155187],"study_design_scores_gemma":[0.00011910241,0.00085969374,0.8834671,0.009225428,0.0051554767,0.0000074348663,0.038189135,0.018969482,0.0036320842,0.03794063,0.00009657412,0.0023378883],"about_ca_topic_score_codex":0.000096044314,"about_ca_topic_score_gemma":0.00071960647,"teacher_disagreement_score":0.8627327,"about_ca_system_score_codex":0.00028072318,"about_ca_system_score_gemma":0.000531237,"threshold_uncertainty_score":0.99994445},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.16513473083563346,"score_gpt":0.3264333420404734,"score_spread":0.16129861120483996,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3032992654","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.58365273,0.00007805778,0.41258824,0.003413222,0.00013321884,0.000047599213,5.6378167e-7,0.000028647297,0.000057712088],"genre_scores_gemma":[0.9886992,0.0000040286027,0.009656615,0.0014949766,0.00013564632,6.82114e-7,5.7550443e-7,0.000004070794,0.000004222175],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991488,0.00011080341,0.00022973637,0.00017753812,0.00015913723,0.00017400479],"domain_scores_gemma":[0.9994325,0.00001992862,0.00007663201,0.00017970984,0.000056843954,0.00023440186],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030586566,0.00006809727,0.00010824736,0.000046079556,0.00009468855,0.00024127524,0.0004871165,0.000045919187,0.000018117564],"category_scores_gemma":[0.00007234377,0.00006238228,0.000043594875,0.0002532226,0.000032558324,0.00066043297,0.00004568983,0.0002627361,0.000014903252],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000091106405,0.00039049174,0.08956924,0.000047610018,0.00003115198,0.00031001522,0.03585348,0.0037543585,0.0781275,0.0730485,0.0017455639,0.717031],"study_design_scores_gemma":[0.0015650499,0.00036299133,0.051611066,0.00004950975,0.000011410313,0.00056957675,0.0015980663,0.89916986,0.005708541,0.010103376,0.028696045,0.0005545152],"about_ca_topic_score_codex":0.000020150677,"about_ca_topic_score_gemma":0.000015855541,"teacher_disagreement_score":0.8954155,"about_ca_system_score_codex":0.000073367686,"about_ca_system_score_gemma":0.00010421779,"threshold_uncertainty_score":0.25438756},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.03701943317026513,"score_gpt":0.246221930022016,"score_spread":0.20920249685175088,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3034886066","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008027425,0.000010913878,0.9518311,0.0378824,0.00008882419,0.00018559604,0.000002960778,0.00035393413,0.0016168718],"genre_scores_gemma":[0.9594853,0.0000011880999,0.034447867,0.005896446,0.0000818295,0.000019459789,0.000014789689,0.0000040795303,0.0000490311],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99894077,0.000071056165,0.00019895282,0.00042124538,0.00021640072,0.00015156221],"domain_scores_gemma":[0.99911886,0.00010991231,0.000051058116,0.0004445766,0.00013597286,0.0001396069],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012229684,0.00010003244,0.000098429664,0.000030416693,0.00009648412,0.00015449413,0.0006024976,0.000043900687,0.000062726016],"category_scores_gemma":[0.00010989899,0.00008690063,0.00004698514,0.0004474459,0.000037131653,0.0005053443,0.000057097765,0.00008576327,0.000250587],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006811465,0.0004874137,0.006694167,0.00013319946,0.000031881398,0.000011268873,0.011453825,0.0021400203,0.16307056,0.6025634,0.017402513,0.19594364],"study_design_scores_gemma":[0.00038546405,0.00013713905,0.011438331,0.0000067729243,0.0000041388216,0.0000014754429,0.0001329573,0.9174316,0.054075148,0.002194467,0.013927418,0.00026510784],"about_ca_topic_score_codex":0.000013918695,"about_ca_topic_score_gemma":0.000002932726,"teacher_disagreement_score":0.95145786,"about_ca_system_score_codex":0.000025950714,"about_ca_system_score_gemma":0.00007910819,"threshold_uncertainty_score":0.3543705},"labels":[],"label_agreement":null},{"id":"W3036182276","doi":"10.48550/arxiv.2006.09639","title":"Iterative Edit-Based Unsupervised Sentence Simplification","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Sentence; Computer science; Phrase; Simplicity; Artificial intelligence; Fluency; Natural language processing; Set (abstract data type); Word (group theory); Function (biology); Machine learning; Mathematics","score_opus":0.10680871208108451,"score_gpt":0.20094781286612134,"score_spread":0.09413910078503683,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3036182276","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06136396,0.000023291794,0.93401694,0.0024311114,0.00048384196,0.00048621077,0.000041857053,0.00048733596,0.00066542905],"genre_scores_gemma":[0.99492836,0.000022648232,0.004116056,0.0005038104,0.00012311556,0.0000041426642,0.00012863801,0.000015100384,0.0001580996],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973773,0.00027102677,0.00028662896,0.0016038893,0.00015507289,0.00030613053],"domain_scores_gemma":[0.9972086,0.00020234557,0.00029067823,0.0017183719,0.00033935497,0.00024066542],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0002302774,0.00034464034,0.00032894875,0.00017817198,0.00020440598,0.00024353615,0.002164864,0.0003011434,0.00002877496],"category_scores_gemma":[0.000106453415,0.00040104496,0.00022160876,0.0008161443,0.0001402313,0.0005234692,0.0008242921,0.00060453144,0.00020304353],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001422214,0.00056675065,0.005168611,0.00046283845,0.0001625008,0.00022093074,0.0024175202,0.29364404,0.0028823693,0.6859924,0.002032662,0.0063071223],"study_design_scores_gemma":[0.00035890652,0.000057971472,0.0047545917,0.000055421926,0.00004172814,0.0000012029781,0.00008219216,0.9463455,0.0011342755,0.04555733,0.001144339,0.00046652736],"about_ca_topic_score_codex":0.0000929113,"about_ca_topic_score_gemma":0.000019653158,"teacher_disagreement_score":0.9335644,"about_ca_system_score_codex":0.00026962816,"about_ca_system_score_gemma":0.00042563578,"threshold_uncertainty_score":0.99984413},"labels":[],"label_agreement":null},{"id":"W3040990147","doi":"10.1007/s11881-020-00200-2","title":"Correction to: Predicting Arabic word reading: A cross-classified generalized random-effects analysis showing the critical role of morphology","year":2020,"lang":"en","type":"erratum","venue":"Annals of Dyslexia","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Psycholinguistics; Arabic; Linguistics; Morphology (biology); Reading (process); Psychology; Word (group theory); Dyslexia; Natural language processing; Cognitive psychology; Computer science; Cognition; Philosophy; Biology; Neuroscience","score_opus":0.050013384576298656,"score_gpt":0.34407205301740956,"score_spread":0.2940586684411109,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3040990147","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12775648,0.004811745,0.7484102,0.035049696,0.062213145,0.0035360137,0.00013993039,0.0008879758,0.017194768],"genre_scores_gemma":[0.99276125,0.00009085715,0.0019270591,0.0009865724,0.0006469063,0.00011274896,0.00010504865,0.000030452615,0.003339083],"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9963289,0.0006604997,0.0010088147,0.0008974,0.00063484296,0.00046957834],"domain_scores_gemma":[0.99529403,0.0020624546,0.0005619069,0.0012449708,0.00064476166,0.00019185767],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0013120999,0.0003478713,0.0011693621,0.00043263938,0.00022489106,0.00019351354,0.0014609096,0.0004279872,0.000022461187],"category_scores_gemma":[0.005138038,0.0002818821,0.000704503,0.0020821856,0.00027959814,0.000314468,0.0003490818,0.000826038,0.00001077905],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016925322,0.00084948883,0.010777962,0.001379512,0.004719173,0.000049499435,0.013196257,0.007033164,0.03599916,0.030374313,0.81288034,0.08104862],"study_design_scores_gemma":[0.0020871407,0.001471617,0.09589989,0.0010641511,0.002314914,0.000045856155,0.00036551777,0.7755203,0.04973751,0.021068735,0.048745774,0.0016785392],"about_ca_topic_score_codex":0.00034326498,"about_ca_topic_score_gemma":0.000053092383,"teacher_disagreement_score":0.8650048,"about_ca_system_score_codex":0.00003781723,"about_ca_system_score_gemma":0.00022424846,"threshold_uncertainty_score":0.99996334},"labels":[],"label_agreement":null},{"id":"W3048273900","doi":"10.5539/ijel.v10n6p30","title":"An Evaluation of China’s Automated Scoring System Bingo English","year":2020,"lang":"en","type":"article","venue":"International Journal of English Linguistics","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Fluency; China; Quality (philosophy); Test (biology); Scoring system; Psychology; Natural language processing; Artificial intelligence; Linguistics; Computer science; Mathematics education; Medicine; Political science","score_opus":0.03625590267231639,"score_gpt":0.3134911558562807,"score_spread":0.2772352531839643,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3048273900","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.66162163,0.0003226543,0.25187463,0.00028620564,0.05900208,0.00049297325,0.000061864426,0.0010929126,0.02524506],"genre_scores_gemma":[0.9828075,0.000005218713,0.010674466,0.000041224837,0.006453181,0.0000014061744,0.000007548336,0.000008655684,7.9564495e-7],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9974134,0.00018161019,0.00077334524,0.0001881672,0.0013313779,0.000112123256],"domain_scores_gemma":[0.9584313,0.00011149552,0.0007398301,0.00023667901,0.040341448,0.000139226],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.00157133,0.00010756902,0.00020828257,0.00016036806,0.00003799871,0.00016946153,0.0012758002,0.00006634608,0.000007533293],"category_scores_gemma":[0.059930347,0.000104612795,0.0000935649,0.00022293911,0.000031901374,0.0003299476,0.00008161459,0.00020405602,0.0000017159799],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00035076457,0.0013260156,0.016161727,0.00042652962,0.0009085001,0.000097160664,0.08394739,0.29293394,0.0033862083,0.54503864,0.0047947387,0.050628364],"study_design_scores_gemma":[0.001069322,0.00029337744,0.010927574,0.00017472377,0.00008198751,0.0000045979177,0.0008504698,0.9724058,0.004737935,0.00068592106,0.00857961,0.00018867443],"about_ca_topic_score_codex":0.000011795584,"about_ca_topic_score_gemma":0.0000014141731,"teacher_disagreement_score":0.67947185,"about_ca_system_score_codex":0.00019882325,"about_ca_system_score_gemma":0.00031923671,"threshold_uncertainty_score":0.9479883},"labels":[],"label_agreement":null},{"id":"W3060766412","doi":"10.48550/arxiv.2008.08612","title":"A Survey on Text Simplification","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lakehead University","funders":"","keywords":"Computer science; Field (mathematics); Natural language processing; Focus (optics); Artificial intelligence; Text simplification; Similarity (geometry); Semantic similarity; Information retrieval; Data science; Sentence","score_opus":0.1624201718261306,"score_gpt":0.21252101699547102,"score_spread":0.05010084516934041,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3060766412","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13798662,0.000019130655,0.85751426,0.001035502,0.00039007902,0.00042188208,0.00006969341,0.00046297224,0.002099846],"genre_scores_gemma":[0.9985988,0.000039856925,0.00045311046,0.00027972524,0.000053308042,0.000001395117,0.00014294218,0.000013956247,0.000416871],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975938,0.00036512452,0.00022344971,0.001446241,0.00011909784,0.0002522641],"domain_scores_gemma":[0.99718344,0.0003066442,0.00025340967,0.0018767773,0.00018441725,0.00019533273],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00041349075,0.0002743859,0.00028223966,0.00015719343,0.00014526644,0.00017108314,0.0020969617,0.00029022977,0.000020470421],"category_scores_gemma":[0.00018986319,0.0003195747,0.00015512163,0.000726861,0.00007709496,0.00024902503,0.000955223,0.0005812609,0.0006004074],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011729399,0.00041064646,0.011260183,0.0001222556,0.00011410257,0.0000760185,0.0007039997,0.090075806,0.00019706768,0.87985027,0.004230445,0.012841922],"study_design_scores_gemma":[0.000320514,0.000118079,0.32939267,0.00004468177,0.000032391905,0.0000010204773,0.00002582117,0.5701264,0.00025505925,0.097038865,0.001983116,0.0006613653],"about_ca_topic_score_codex":0.00038091434,"about_ca_topic_score_gemma":0.00012144306,"teacher_disagreement_score":0.8606122,"about_ca_system_score_codex":0.00023030327,"about_ca_system_score_gemma":0.00021982548,"threshold_uncertainty_score":0.9999256},"labels":[],"label_agreement":null},{"id":"W3080107039","doi":"10.20944/preprints202008.0560.v1","title":"Social Media Platform: Measuring Readability and Socio-Economic Status","year":2020,"lang":"en","type":"preprint","venue":"Preprints.org","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Readability; Crowdsourcing; Socioeconomic status; Social media; Public relations; Political science; Sociology; Computer science; World Wide Web; Demography","score_opus":0.25424752382207333,"score_gpt":0.34385184990458667,"score_spread":0.08960432608251334,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3080107039","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98552597,0.000092397146,0.0073687504,0.0033504167,0.000635828,0.0005606586,0.000045274435,0.0005496613,0.0018710273],"genre_scores_gemma":[0.9975948,0.000096223266,0.0016988501,0.00009085275,0.00032197914,0.00010160766,0.0000446211,0.000025771806,0.000025326955],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99620754,0.00021174218,0.00073340244,0.0018974899,0.0004145235,0.0005353228],"domain_scores_gemma":[0.9972258,0.00033327338,0.00041156725,0.001594388,0.00011009284,0.00032484776],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0012794513,0.0004159841,0.00061586,0.00009711034,0.00029939224,0.00016968927,0.0015083291,0.0004863703,0.00009262031],"category_scores_gemma":[0.00057718356,0.0004636626,0.00022047093,0.000102987484,0.00025776043,0.0004942733,0.0049304096,0.0011332129,0.0005197178],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000109831904,0.00024364302,0.81035143,0.0009240627,0.00027510378,0.000012962111,0.07014193,0.00031721572,0.0034049628,0.046340853,0.00018384896,0.06769419],"study_design_scores_gemma":[0.00021703618,0.000009113341,0.8633146,0.000031000538,0.000031205465,0.0000043771906,0.0002186881,0.0029725723,0.0043740654,0.12632272,0.0019361658,0.00056845666],"about_ca_topic_score_codex":0.00037089916,"about_ca_topic_score_gemma":0.00008046405,"teacher_disagreement_score":0.07998187,"about_ca_system_score_codex":0.0006463637,"about_ca_system_score_gemma":0.0006003638,"threshold_uncertainty_score":0.9997815},"labels":[],"label_agreement":null},{"id":"W3080863676","doi":"10.31468/cjsdwr.789","title":"A Tutor-Led Collaborative Modelling Approach to Teaching Paraphrasing to International Graduate Students","year":2020,"lang":"en","type":"article","venue":"Discourse and Writing/Rédactologie","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Paraphrase; Writing center; TUTOR; CLARITY; Academic writing; Graduate students; Academic integrity; Citation; Mathematics education; Computer science; Legal writing; Plagiarism detection; Pedagogy; Psychology; Medical education; Library science; Medicine; Political science","score_opus":0.1823103370101203,"score_gpt":0.4233136540277681,"score_spread":0.2410033170176478,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3080863676","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.49071416,0.00003198876,0.499518,0.0084039755,0.0000789327,0.00026516803,0.0000094337165,0.00012457103,0.0008537721],"genre_scores_gemma":[0.93324804,0.000014142604,0.0650501,0.0014844926,0.00011532104,0.000048496295,0.000013554367,0.000009879939,0.00001594188],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9981004,0.00012655201,0.00031614868,0.0007040242,0.00043442714,0.0003184571],"domain_scores_gemma":[0.999098,0.00013550387,0.000088970584,0.00027954634,0.0001237796,0.00027420558],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00051018,0.00019365866,0.0002472166,0.00010102058,0.00027098053,0.00063495623,0.0009238538,0.00006105787,0.0000013088224],"category_scores_gemma":[0.00021867662,0.00017799184,0.000049122697,0.0003518152,0.00004763392,0.0005596714,0.0004255006,0.00026852867,0.000017033673],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00042716172,0.0021777668,0.095457464,0.00020720957,0.00047231393,0.00010569203,0.2061164,0.09570334,0.008198918,0.28783926,0.0045964,0.29869807],"study_design_scores_gemma":[0.0020056504,0.0006903326,0.047764063,0.0002708414,0.00008016329,0.000037902282,0.037845924,0.89608413,0.0029876528,0.0057457173,0.0045055775,0.0019820454],"about_ca_topic_score_codex":0.00002597071,"about_ca_topic_score_gemma":0.0000018888155,"teacher_disagreement_score":0.80038077,"about_ca_system_score_codex":0.00005209219,"about_ca_system_score_gemma":0.000061094164,"threshold_uncertainty_score":0.72582966},"labels":[],"label_agreement":null},{"id":"W3089382419","doi":"","title":"Analysis of Compositions by B1 Level (Threshold) Francophone Learners of Catalan: Typology of Errors and Correspondences","year":2020,"lang":"en","type":"article","venue":"Revista Internacional de Catalanística = Journal of Catalan Studies","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université TÉLUQ","funders":"","keywords":"Catalan; Typology; Linguistics; Natural language processing; Agreement; Focus (optics); Computer science; Error analysis; Artificial intelligence; Psychology; Mathematics; History","score_opus":0.0513775033841889,"score_gpt":0.31392978093471297,"score_spread":0.26255227755052407,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3089382419","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9561622,0.007535936,0.033428863,0.002116469,0.0001261654,0.00009830427,0.00048739754,0.000009365335,0.000035297013],"genre_scores_gemma":[0.9974326,0.0008590528,0.0015166043,0.00008281473,0.000031011496,0.000002331112,0.000049614417,0.0000064831693,0.0000194894],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9979003,0.00012254894,0.0010844581,0.00025922133,0.00045729225,0.00017619925],"domain_scores_gemma":[0.99727505,0.00065811735,0.0010643494,0.0002920312,0.00055791606,0.00015253562],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005357182,0.0001794412,0.0009938674,0.00031885965,0.0000533015,0.000021173657,0.00074303435,0.000066950975,0.000011941681],"category_scores_gemma":[0.000572413,0.00014991849,0.00025744786,0.00079043175,0.0007026557,0.00022514837,0.00024861193,0.0002230222,0.0000018700357],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0022873841,0.0015316161,0.52743036,0.0034302343,0.019324506,0.00019196962,0.08327951,0.0025446413,0.26004237,0.07609051,0.011313627,0.012533294],"study_design_scores_gemma":[0.00538734,0.0074367975,0.79074836,0.0029595324,0.007238981,0.0015434336,0.038386896,0.028986149,0.10569905,0.0032670614,0.006159589,0.0021868413],"about_ca_topic_score_codex":0.00005596927,"about_ca_topic_score_gemma":0.000015895666,"teacher_disagreement_score":0.26331797,"about_ca_system_score_codex":0.000048344813,"about_ca_system_score_gemma":0.00014383747,"threshold_uncertainty_score":0.6113499},"labels":[],"label_agreement":null},{"id":"W3091726675","doi":"10.5539/elt.v13n10p139","title":"Prediction Skills, Reading Comprehension and Learning Achievement in Vihiga County Kenya. Addressing Constraints and Prospects","year":2020,"lang":"en","type":"article","venue":"English Language Teaching","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Reading comprehension; Mathematics education; Psychology; Comprehension; Reading (process); Grammar; Control (management); Curriculum; Pedagogy; Computer science; Linguistics; Artificial intelligence","score_opus":0.0163929330620629,"score_gpt":0.24433727355153528,"score_spread":0.22794434048947237,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3091726675","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9599143,0.00023691735,0.038198248,0.00030540102,0.000092224866,0.00022753952,0.000004137444,0.0003126504,0.00070853904],"genre_scores_gemma":[0.99085486,0.000013204323,0.008786499,0.00019371956,0.00011151252,0.0000064032306,0.000015521897,0.000009249716,0.000009047001],"study_design_codex":"qualitative","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99860996,0.00028103578,0.00023957726,0.00045969663,0.00020095149,0.00020879404],"domain_scores_gemma":[0.9994188,0.00019068184,0.00009132299,0.00016527296,0.00002208222,0.00011182852],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008288733,0.00013390556,0.00016990963,0.000069764035,0.00027895367,0.0002623049,0.00015054985,0.0000684126,0.0000031260702],"category_scores_gemma":[0.00074660045,0.00013373898,0.000017280927,0.00012896078,0.00006758325,0.0006431817,0.00018266882,0.0006861546,8.5445686e-7],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018940322,0.00015943492,0.09716357,0.00021068526,0.000017292,0.000052898213,0.5690276,0.0005956162,0.030751018,0.009875851,0.00003623288,0.29209083],"study_design_scores_gemma":[0.0044110655,0.0006299019,0.43270954,0.0013892861,0.00004776243,0.00009018752,0.083513916,0.46611187,0.0055123367,0.0006703518,0.003527101,0.0013866769],"about_ca_topic_score_codex":0.000055955843,"about_ca_topic_score_gemma":0.000009555212,"teacher_disagreement_score":0.48551372,"about_ca_system_score_codex":0.0000599814,"about_ca_system_score_gemma":0.000019025125,"threshold_uncertainty_score":0.5453717},"labels":[],"label_agreement":null},{"id":"W3116307283","doi":"","title":"Prose and cons of scholarly articles: How readability tests expose poor knowledge mobilization in academic publications","year":2021,"lang":"en","type":"article","venue":"Journal of Professional Communication","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Readability; Reading (process); Comprehension; Meaning (existential); Index (typography); Psychology; Reading comprehension; Social science; Sociology; Political science; Computer science; World Wide Web","score_opus":0.08257423262281025,"score_gpt":0.3646460487182441,"score_spread":0.28207181609543386,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3116307283","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95404935,0.0030190975,0.014824647,0.027596261,0.000095739735,0.00027383328,0.0000040353584,0.000021004389,0.00011600529],"genre_scores_gemma":[0.9770694,0.00036725344,0.022274131,0.00007149104,0.000017265113,0.00002186055,0.000011314317,0.000005351843,0.00016194876],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99754363,0.0010080441,0.0007705336,0.00020651298,0.00034116782,0.00013013072],"domain_scores_gemma":[0.9955346,0.0008701768,0.00071147346,0.0008579147,0.0019258308,0.000100031924],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026273907,0.00009674793,0.00022465285,0.0002376987,0.00015219404,0.00014897609,0.0008190804,0.000155145,0.0000060192583],"category_scores_gemma":[0.0031277079,0.000085238295,0.000052468586,0.00094497896,0.00015629356,0.0034934042,0.0003854983,0.00071347196,0.000001432474],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010936002,0.0040936684,0.2929322,0.00033347844,0.000046639747,0.000002085977,0.019198805,0.00008353814,0.37909326,0.17845947,0.0013140441,0.12433343],"study_design_scores_gemma":[0.00070087734,0.000116038595,0.90964496,0.0004887687,0.00001532102,0.00008237397,0.0020520184,0.004345209,0.033268966,0.047720235,0.0013998286,0.00016542153],"about_ca_topic_score_codex":0.00000654815,"about_ca_topic_score_gemma":0.00006958114,"teacher_disagreement_score":0.61671275,"about_ca_system_score_codex":0.00012718627,"about_ca_system_score_gemma":0.0007580188,"threshold_uncertainty_score":0.37443846},"labels":[],"label_agreement":null},{"id":"W3119809947","doi":"10.1108/s1569-375920200000105007","title":"Readability Analysis of Laws Related to Public Financial Responsibility and State Budget: A Comparison of Selected Countries","year":2021,"lang":"en","type":"book-chapter","venue":"","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Readability; Audit; Political science; Turkish; Accountability; Accounting; Business; Law; Linguistics","score_opus":0.02204958258895439,"score_gpt":0.27746280220051506,"score_spread":0.25541321961156066,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3119809947","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.78458077,0.001317501,0.15988854,0.0042760693,0.00029435466,0.0023941593,0.0010109971,0.0004817666,0.045755863],"genre_scores_gemma":[0.9673647,0.000044952998,0.0072478927,0.000075916,0.000006171446,0.000011600728,0.00016507975,0.000015877522,0.025067799],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9963528,0.00024127615,0.0014762804,0.0010590656,0.00061526627,0.00025534615],"domain_scores_gemma":[0.99462706,0.00076305197,0.0006431465,0.0018133691,0.0019885118,0.00016488758],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001489348,0.00031179853,0.0014134703,0.000645406,0.0000927894,0.00009495567,0.00061635417,0.00037358428,0.00017255891],"category_scores_gemma":[0.0011226296,0.0002971148,0.00023548226,0.0014555146,0.00034188913,0.000250901,0.00039065437,0.0003341418,0.0000042748643],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027807459,0.0003760725,0.037324518,0.00034180642,0.0011055011,0.000003894486,0.0043007396,0.00018975849,0.0006342757,0.924818,0.0005004467,0.03012694],"study_design_scores_gemma":[0.000675164,0.0011436007,0.8064332,0.00020882941,0.0015942544,0.000007688059,0.00011029421,0.029454691,0.008272082,0.10771484,0.042549778,0.0018355555],"about_ca_topic_score_codex":0.00028438773,"about_ca_topic_score_gemma":0.0041951467,"teacher_disagreement_score":0.81710315,"about_ca_system_score_codex":0.00015173672,"about_ca_system_score_gemma":0.00093741383,"threshold_uncertainty_score":0.9999481},"labels":[],"label_agreement":null},{"id":"W3127970288","doi":"10.1037/cep0000222","title":"The effect of speaker age on the perception of ironic insults.","year":2021,"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":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Psychology; Insult; Interpretation (philosophy); Sentence; Context (archaeology); Sarcasm; Perception; Comprehension; Linguistics; Statement (logic); Utterance; Reading (process); Politeness; Social psychology; Cognitive psychology; Irony","score_opus":0.028484652904156003,"score_gpt":0.2945398781174392,"score_spread":0.2660552252132832,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3127970288","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9884907,0.0019662548,0.00047167853,0.0039401175,0.0015640422,0.00027528562,0.00001910155,0.000008968823,0.0032638698],"genre_scores_gemma":[0.9983235,0.00004797871,0.00061227777,0.00075580965,0.00009822099,0.000020414464,0.0000059565286,0.000016144964,0.00011969243],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9974679,0.0005887873,0.000734806,0.00041851378,0.00013826636,0.0006517725],"domain_scores_gemma":[0.9972187,0.00042451045,0.00051584345,0.001246279,0.00013354335,0.0004610971],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001571536,0.00023278603,0.00037222152,0.00018268224,0.00028134862,0.00006547739,0.0016660944,0.00015636433,0.00012742844],"category_scores_gemma":[0.00029108734,0.00016105051,0.00027281424,0.00046696726,0.00065893016,0.00017870568,0.000051944102,0.00042976774,0.000014934322],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00046638027,0.0005683749,0.016844584,0.000047884118,0.00034953115,0.0009109509,0.022751126,0.00009631173,0.8658351,0.028579546,0.023002079,0.040548176],"study_design_scores_gemma":[0.0056684143,0.010062733,0.31222993,0.00041271807,0.00009396804,0.0040321606,0.022703376,0.0001774234,0.6123808,0.005172408,0.02611422,0.000951839],"about_ca_topic_score_codex":0.0011852098,"about_ca_topic_score_gemma":0.008373413,"teacher_disagreement_score":0.29538536,"about_ca_system_score_codex":0.00064529275,"about_ca_system_score_gemma":0.00035003902,"threshold_uncertainty_score":0.6567449},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.03865048356363132,"score_gpt":0.39953929186046555,"score_spread":0.36088880829683423,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3162983511","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9808636,0.0022355986,0.015399812,0.00023384145,0.00077418756,0.0000620938,0.0000029635073,0.000011534174,0.00041640006],"genre_scores_gemma":[0.96948737,0.00005368694,0.029910622,0.00019776881,0.00013501364,0.00000236336,9.5246804e-7,0.000006382783,0.00020585002],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99873817,0.00017093813,0.00040233284,0.00023990954,0.00022218663,0.00022647106],"domain_scores_gemma":[0.9990091,0.000047220034,0.00034927495,0.00040302743,0.00010753475,0.00008389523],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005118773,0.00010315012,0.00021537565,0.000056863206,0.00006974651,0.00003213798,0.00051529106,0.00008596205,0.000054958957],"category_scores_gemma":[0.00003641892,0.000096049975,0.00013889582,0.00017490714,0.000091515925,0.00033300923,0.00010308263,0.00021366589,0.0000062228446],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022079117,0.00041618312,0.012020701,0.00001501949,0.000018020452,0.00013483269,0.0027677943,0.000040389274,0.97948307,0.0011308576,0.00027527788,0.0036757488],"study_design_scores_gemma":[0.0005707073,0.00030590114,0.07646808,0.00003104017,0.000011932735,0.0010977896,0.0006094924,0.00018697331,0.92032623,0.00011006484,0.00016131974,0.0001204941],"about_ca_topic_score_codex":0.000003816054,"about_ca_topic_score_gemma":0.000001140589,"teacher_disagreement_score":0.06444738,"about_ca_system_score_codex":0.000047879705,"about_ca_system_score_gemma":0.0000464843,"threshold_uncertainty_score":0.39168045},"labels":[],"label_agreement":null},{"id":"W3164248983","doi":"10.17045/sthlmuni.13067432.v1","title":"Deepening source criticism in higher education to avoid plagiarism","year":2020,"lang":"en","type":"article","venue":"Figshare","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Presentation (obstetrics); Criticism; Class (philosophy); Cheating; Constructive; Mathematics education; Psychology; Pedagogy; Test (biology); Sociology; Computer science; Political science; Social psychology","score_opus":0.08998237246836117,"score_gpt":0.2808323116461741,"score_spread":0.19084993917781296,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3164248983","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.093411,0.0023319994,0.15316473,0.6142617,0.0030093358,0.0067741205,0.031868305,0.005199982,0.08997884],"genre_scores_gemma":[0.9846128,1.1786448e-7,0.0037766492,0.008770441,0.0001729924,0.00014086637,0.0019432439,0.000008512481,0.0005743727],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992172,0.000040009072,0.00014338257,0.00030688112,0.00013799811,0.00015454297],"domain_scores_gemma":[0.9994196,0.000094356095,0.000028961495,0.0002630604,0.000059522183,0.00013446288],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.000040725372,0.00007516198,0.000079749065,0.00004928621,0.000048915346,0.00012806512,0.0005049204,0.00007271647,0.012160173],"category_scores_gemma":[0.00047027858,0.00008163279,0.000023985294,0.0003666408,0.0000018331139,0.00031188046,0.00015928679,0.00016584038,0.0025019273],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014112213,0.00022941854,0.0005420128,0.00048399437,0.000006986262,0.000012435864,0.015177907,0.0011635607,0.0022416846,0.0142287975,0.68071693,0.28518215],"study_design_scores_gemma":[0.00015311984,0.000054761356,0.0562229,0.0004326682,0.0000014007255,0.0000037668708,0.00007765477,0.008837339,0.0023855683,0.0013375803,0.9301749,0.00031835743],"about_ca_topic_score_codex":0.000014430772,"about_ca_topic_score_gemma":0.000007193096,"teacher_disagreement_score":0.8912018,"about_ca_system_score_codex":0.000046163415,"about_ca_system_score_gemma":0.000081972066,"threshold_uncertainty_score":0.99827474},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":["research_integrity"],"domain":null,"study_design":"theoretical_or_conceptual","genre":"other","about_ca_system":false,"about_ca_topic":false,"confidence":"low"}],"label_agreement":"split"},{"id":"W3164815944","doi":"10.17239/l1esll-2021.21.01.07","title":"The revision of syntactic errors related to complex sentences in French L1: strategies of secondary school advanced writers","year":2021,"lang":"en","type":"article","venue":"L1 Educational Studies in Language and Literature","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Grammaticality; Syntax; Context (archaeology); Linguistics; Computer science; Think aloud protocol; Salient; Psychology; Cognition; Natural language processing; Artificial intelligence; Grammar; History; Philosophy","score_opus":0.015840453870229722,"score_gpt":0.33489663422044136,"score_spread":0.31905618035021166,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3164815944","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95922446,0.03441499,0.00005798136,0.0054597813,0.00020581833,0.00014870579,0.000016309754,0.0000063579296,0.00046561158],"genre_scores_gemma":[0.99521923,0.00059802126,0.0038206954,0.00010802358,0.000015980484,0.000010661555,0.000025242376,0.000002097543,0.00020007009],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.99908257,0.00011799792,0.00031774864,0.00023027677,0.00014452577,0.00010686333],"domain_scores_gemma":[0.998962,0.0004732471,0.00009294482,0.0002523204,0.0001903597,0.000029172055],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025402827,0.00008349655,0.00016870332,0.00007841126,0.00007617192,0.00006323486,0.00020442375,0.000040162497,0.000017638795],"category_scores_gemma":[0.00042395454,0.00005998272,0.000026866932,0.0007135419,0.00009572965,0.0003298365,0.000099072546,0.0001677802,5.794589e-7],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000078208126,0.0006724663,0.038191285,0.0015308345,0.00017556058,0.000059713984,0.5974099,0.0005216412,0.018012501,0.20567025,0.003629058,0.13404855],"study_design_scores_gemma":[0.00043704722,0.00010667636,0.76331633,0.0014711769,0.000009058119,0.000047531765,0.21131478,0.00022940495,0.0009115676,0.018916901,0.003007101,0.00023239301],"about_ca_topic_score_codex":0.000044330664,"about_ca_topic_score_gemma":0.00019386815,"teacher_disagreement_score":0.7251251,"about_ca_system_score_codex":0.00003601357,"about_ca_system_score_gemma":0.00014450232,"threshold_uncertainty_score":0.24460244},"labels":[],"label_agreement":null},{"id":"W3179000338","doi":"10.48550/arxiv.2107.04268","title":"Learning Syntactic Dense Embedding with Correlation Graph for Automatic Readability Assessment","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Readability; Computer science; Complement (music); Artificial intelligence; Natural language processing; Embedding; Graph; Correlation; Task (project management); Artificial neural network; Deep learning; Machine learning; Theoretical computer science; Mathematics","score_opus":0.050591787988661215,"score_gpt":0.22447759298153833,"score_spread":0.17388580499287712,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3179000338","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.44849995,0.00000845838,0.55050033,0.000072324,0.00015798988,0.00041128154,0.0000030873432,0.00023064142,0.000115907525],"genre_scores_gemma":[0.9599889,0.00001740617,0.039620027,0.000020405216,0.000022896047,0.000010426732,0.00007037625,0.000017393184,0.0002321737],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99752635,0.00038015016,0.00029113053,0.0013289459,0.00015412677,0.00031932845],"domain_scores_gemma":[0.99705994,0.00067345775,0.00044839428,0.0012928759,0.00039306463,0.00013223718],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0007176981,0.00029762092,0.00037973665,0.00019529703,0.00037695144,0.00033173081,0.00078021426,0.00026579574,0.000016464408],"category_scores_gemma":[0.00018479957,0.00032068283,0.00021093553,0.00058798306,0.00008993462,0.00071745773,0.0005356339,0.00069249707,0.00000531951],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003946485,0.0002660565,0.034977265,0.00059276546,0.0001689665,0.000065924396,0.0011602442,0.9082915,0.00009007484,0.0487086,0.000012972604,0.005626162],"study_design_scores_gemma":[0.00025127988,0.0001307305,0.023039158,0.00017663483,0.00013217279,0.0000104337405,0.0005486824,0.9630063,0.000080770405,0.012214283,0.000036395668,0.0003731432],"about_ca_topic_score_codex":0.00010205458,"about_ca_topic_score_gemma":0.0001144212,"teacher_disagreement_score":0.511489,"about_ca_system_score_codex":0.0005819801,"about_ca_system_score_gemma":0.0005266994,"threshold_uncertainty_score":0.99992454},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Readability; Data science; Computer science; Information retrieval; Programming language","score_opus":0.17077772098894595,"score_gpt":0.4425319273195456,"score_spread":0.27175420633059966,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3183940262","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7075609,0.000022503873,0.28322002,0.0016235784,0.0008134408,0.0003227408,0.000011814177,0.00023899009,0.006186032],"genre_scores_gemma":[0.9877316,0.0000012515228,0.011344174,0.000042800006,0.00013110969,0.00021202456,0.00026732215,0.000009718215,0.00026004922],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9973254,0.0007806126,0.00042352665,0.0008069366,0.0003813357,0.00028217805],"domain_scores_gemma":[0.99870926,0.00016442646,0.00010318177,0.0008267282,0.000108824286,0.0000875973],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0015203395,0.00014267657,0.00016244613,0.0009788101,0.0015568176,0.00047138348,0.0006447487,0.000047118883,0.00016885735],"category_scores_gemma":[0.000010145822,0.00015157397,0.000058840706,0.0010805667,0.00011700802,0.0017818951,0.0013165461,0.0006750158,0.0000072049847],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000042228887,0.0021183651,0.002106907,0.000026795457,0.000021389335,0.0000076336255,0.014346167,0.004562465,0.0003008122,0.15567446,0.0013298453,0.81946295],"study_design_scores_gemma":[0.0006081894,0.0012426686,0.22815184,0.000021451098,0.0000097834745,0.00022094938,0.0028152012,0.6702983,0.00008047822,0.07744272,0.018549146,0.0005593075],"about_ca_topic_score_codex":0.0003165599,"about_ca_topic_score_gemma":0.00024925725,"teacher_disagreement_score":0.8189036,"about_ca_system_score_codex":0.0003991872,"about_ca_system_score_gemma":0.000029110353,"threshold_uncertainty_score":0.99974304},"labels":[],"label_agreement":null},{"id":"W3186632741","doi":"10.18653/v1/2021.semeval-1.83","title":"UNBNLP at SemEval-2021 Task 1: Predicting lexical complexity with masked language models and character-level encoders","year":2021,"lang":"en","type":"article","venue":"","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Character (mathematics); Encoder; SemEval; Artificial intelligence; Natural language processing; Task (project management); Context (archaeology); Security token; Language model; Mathematics","score_opus":0.06418587855620984,"score_gpt":0.2623062474996264,"score_spread":0.19812036894341656,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3186632741","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4980029,0.00004854447,0.4973125,0.0019503619,0.000045619767,0.0001128271,0.000015682546,0.00011052505,0.002401068],"genre_scores_gemma":[0.9500029,0.000007969009,0.048310056,0.0003511323,0.000039156643,0.000010345828,0.000039528895,0.000007718598,0.001231206],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99850726,0.0001096352,0.00021744399,0.000589249,0.00030629232,0.00027009044],"domain_scores_gemma":[0.9989438,0.00012460607,0.00006593222,0.0006140868,0.00010664796,0.0001449118],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002524891,0.00014819117,0.00018874939,0.000036208094,0.00020884736,0.00016983872,0.00027792796,0.00007298221,0.00009251101],"category_scores_gemma":[0.00003533231,0.00012045941,0.00003902128,0.0002451887,0.00012372599,0.0005962526,0.0003472941,0.0001447508,0.000016490023],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015373,0.0011697812,0.08685852,0.00040307018,0.00029413338,0.00037753195,0.052786823,0.0016667908,0.102917805,0.5787813,0.00083598227,0.17375454],"study_design_scores_gemma":[0.001118148,0.00012026684,0.17067474,0.00006237122,0.000028612678,0.00023553822,0.0014261679,0.79855084,0.016232247,0.01017383,0.0007725113,0.00060469814],"about_ca_topic_score_codex":0.0001245694,"about_ca_topic_score_gemma":0.0005276133,"teacher_disagreement_score":0.79688406,"about_ca_system_score_codex":0.000066514556,"about_ca_system_score_gemma":0.00010009608,"threshold_uncertainty_score":0.4912192},"labels":[],"label_agreement":null},{"id":"W3196454181","doi":"10.7820/vli.v08.1.pinchbeck","title":"Validating the construct of readability in EFL contexts: A proposal for criteria","year":2019,"lang":"en","type":"article","venue":"Vocabulary Learning and Instruction","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Readability; Construct (python library); Computer science; Psychology; Linguistics; Natural language processing; Programming language; Philosophy","score_opus":0.010968339778973272,"score_gpt":0.2677708520025041,"score_spread":0.25680251222353084,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3196454181","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9726133,0.000054296124,0.02587471,0.00057230575,0.00022700032,0.000425799,0.00000157932,0.000045650257,0.00018537557],"genre_scores_gemma":[0.98488545,0.000007630169,0.015004669,0.000019226036,0.00002307624,0.000018377063,0.000005134618,0.0000042966926,0.000032129243],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9989827,0.00020688915,0.0002846964,0.00028643684,0.00011057111,0.00012867239],"domain_scores_gemma":[0.9993056,0.00019926133,0.00014544398,0.0002452183,0.00008314913,0.000021327574],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00087309344,0.00008139833,0.0001532625,0.00006202902,0.00011324434,0.00006416417,0.00016112215,0.00006256993,0.000006995807],"category_scores_gemma":[0.00020280416,0.00006216134,0.00003585212,0.00019057067,0.00011473893,0.0003671627,0.000056085722,0.00016727533,0.0000016341836],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009996798,0.0000501394,0.21367478,0.0002859572,0.000015604417,3.2759488e-7,0.0032903343,0.00021099983,0.028788997,0.08789759,0.00001531674,0.66567],"study_design_scores_gemma":[0.00374984,0.0017775983,0.4428148,0.00041193428,0.000036002777,0.00028729343,0.005585026,0.39471325,0.04423135,0.09644406,0.009118739,0.00083008985],"about_ca_topic_score_codex":0.000082103616,"about_ca_topic_score_gemma":0.000011388315,"teacher_disagreement_score":0.66483986,"about_ca_system_score_codex":0.000028145178,"about_ca_system_score_gemma":0.00007213332,"threshold_uncertainty_score":0.2534866},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Need to know; Profiling (computer programming); Psychology; Linguistics; Natural language processing; Computer science","score_opus":0.06034828346412041,"score_gpt":0.3346003613303287,"score_spread":0.2742520778662083,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3205584125","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9512384,0.025467291,0.010005035,0.011672617,0.00019469323,0.00062134594,0.0000030977635,0.00014801686,0.000649484],"genre_scores_gemma":[0.97431105,0.010771379,0.013308279,0.0007914037,0.00013399114,0.00008003152,0.000029158415,0.000028762166,0.00054591877],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.996866,0.00051564176,0.0004509295,0.000887383,0.00059018016,0.0006898949],"domain_scores_gemma":[0.9974606,0.0011393942,0.000070360846,0.000786179,0.00013793478,0.00040555163],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001877123,0.00025485904,0.00037511528,0.00042079916,0.00027051545,0.0041541816,0.00049378123,0.00023356728,0.000017984688],"category_scores_gemma":[0.0007546196,0.00024374733,0.00005320631,0.0014695296,0.00025526786,0.00507138,0.0007473055,0.00061477337,0.000011788199],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029958494,0.00014164779,0.0014117453,0.0003287179,0.00001847162,0.00019413853,0.046332795,0.000045499,0.038335223,0.18121329,0.00012552219,0.73182297],"study_design_scores_gemma":[0.0033151656,0.0012550864,0.007512805,0.013475492,0.000048362843,0.0009105065,0.49964753,0.094902806,0.26040575,0.09547354,0.020494485,0.0025584777],"about_ca_topic_score_codex":0.000077640296,"about_ca_topic_score_gemma":0.00012412008,"teacher_disagreement_score":0.7292645,"about_ca_system_score_codex":0.00017728527,"about_ca_system_score_gemma":0.00018357633,"threshold_uncertainty_score":0.9968796},"labels":[],"label_agreement":null},{"id":"W4205266265","doi":"10.46451/ijts.2021.12.01","title":"TESOL in the New Era: Introduction to the 2021 Global English Education China Assembly Special Issue","year":2021,"lang":"en","type":"article","venue":"International Journal of TESOL Studies","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Thompson Rivers University","funders":"Shenzhen University; Beijing Language and Culture University; Soochow University; Guangdong University of Foreign Studies; Tongji University; Loyola University Chicago; Beijing Normal University; University of South Australia; Northeast Normal University","keywords":"China; Political science; Engineering ethics; Mathematics education; Library science; History; Engineering; Computer science; Psychology; Law","score_opus":0.013780956982584391,"score_gpt":0.31731800734391247,"score_spread":0.30353705036132805,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4205266265","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.069281965,0.003693474,0.029307446,0.8665724,0.027136637,0.0003434689,0.000010537813,0.000021760048,0.0036323469],"genre_scores_gemma":[0.8645951,0.00072198344,0.011492827,0.003601498,0.118637,0.000022652339,0.000008428688,0.000007928815,0.000912536],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983286,0.00018652939,0.00045047284,0.00021660408,0.00068684376,0.00013094448],"domain_scores_gemma":[0.99783915,0.00018963907,0.00023462546,0.0002968931,0.001394682,0.000045023535],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007833424,0.000107824635,0.00015818595,0.00008005495,0.00011440211,0.00031890383,0.0012434713,0.000031206637,0.00003847117],"category_scores_gemma":[0.0023570226,0.00006693582,0.00009599944,0.00050904386,0.00003382508,0.0005269152,0.00021800605,0.00023673137,0.000027054104],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030447667,0.00033591638,0.0022616365,0.000004145995,0.00015236149,0.000019611993,0.016234273,0.00071141066,0.00014019516,0.01819733,0.5205253,0.4413874],"study_design_scores_gemma":[0.0003432715,0.00011613261,0.14546493,0.00006350777,0.00002346304,0.00031849716,0.0056159627,0.00015495601,0.00068750436,0.014833108,0.8322335,0.00014518636],"about_ca_topic_score_codex":0.000051839772,"about_ca_topic_score_gemma":0.0003515,"teacher_disagreement_score":0.8629709,"about_ca_system_score_codex":0.00032608354,"about_ca_system_score_gemma":0.0004677951,"threshold_uncertainty_score":0.3075197},"labels":[],"label_agreement":null},{"id":"W4211253469","doi":"10.1108/jet-04-2021-0020","title":"Editing assistance tool validation for English language learners","year":2022,"lang":"en","type":"article","venue":"Journal of Enabling Technologies","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Spelling; Computer science; Grammar; Punctuation; Ell; Natural language processing; Artificial intelligence; Teaching method; Psychology; Mathematics education; Linguistics; Vocabulary development","score_opus":0.02279043390278417,"score_gpt":0.26912191857950185,"score_spread":0.24633148467671767,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4211253469","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.49411175,0.00062814803,0.4997583,0.0037961104,0.00090122735,0.00015375229,0.0000046075197,0.00055399875,0.000092106166],"genre_scores_gemma":[0.9354956,0.000018529225,0.06429796,0.000023369124,0.00009993296,0.00001871162,0.0000014433859,0.000004481348,0.000039958366],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.999113,0.00003835688,0.00030535716,0.00013953044,0.00025905046,0.00014469265],"domain_scores_gemma":[0.9988818,0.00022146321,0.0004145707,0.0002874558,0.00018406901,0.000010619096],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012215364,0.0000620819,0.00012355394,0.00021339049,0.00023500893,0.000114429255,0.0008814638,0.00004457361,0.0000030045696],"category_scores_gemma":[0.0025558195,0.000056836427,0.00007925169,0.00038567098,0.00003067537,0.0005125911,0.0001951352,0.0002958802,3.3745738e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007238754,0.0002458568,0.0023969486,0.00010497316,0.00007130235,0.000032269636,0.011532328,0.00939285,0.037969638,0.12165056,0.005300755,0.8112301],"study_design_scores_gemma":[0.0023532182,0.0018970289,0.0011350511,0.00014653022,0.0000697951,0.00024294815,0.18219943,0.020285325,0.3624755,0.13858794,0.28965273,0.0009544923],"about_ca_topic_score_codex":0.0000016071278,"about_ca_topic_score_gemma":5.1843745e-7,"teacher_disagreement_score":0.8102756,"about_ca_system_score_codex":0.00012583783,"about_ca_system_score_gemma":0.00006043755,"threshold_uncertainty_score":0.30597395},"labels":[],"label_agreement":null},{"id":"W4213010795","doi":"10.1352/1944-7558-126.1.75","title":"Résumés en Français","year":2020,"lang":"fr","type":"article","venue":"American Journal on Intellectual and Developmental Disabilities","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Icon; Citation; Computer science; Information retrieval; Download; World Wide Web; Programming language","score_opus":0.047592453534489626,"score_gpt":0.2646375348734983,"score_spread":0.21704508133900866,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4213010795","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8510705,0.0017157714,0.04710985,0.0774095,0.0012343668,0.0002775644,0.00004026557,0.00012651064,0.02101563],"genre_scores_gemma":[0.98156524,0.0008233889,0.007769083,0.006065475,0.0003854021,0.000009560551,0.000003407553,0.000021475782,0.0033569424],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99742776,0.0004224993,0.0006368067,0.0005600519,0.00045422555,0.00049863226],"domain_scores_gemma":[0.995831,0.0031470754,0.00010337843,0.00016376897,0.00011643704,0.00063832774],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00035444958,0.00035632856,0.00046265646,0.00008164131,0.00044922307,0.00053805986,0.00054223114,0.000079323305,0.0035794126],"category_scores_gemma":[0.0033135696,0.00031651664,0.00014933546,0.0005675127,0.0019067118,0.0006496587,0.00026332468,0.00070083665,0.0032521382],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020437237,0.00020417155,0.0029213908,0.000065202694,0.00009237497,0.000010446894,0.3185837,0.000022043372,0.000090729496,0.014842867,0.024041314,0.6389214],"study_design_scores_gemma":[0.0006278149,0.005477328,0.014539586,0.00026443324,0.000038072263,0.0014123607,0.16580577,0.0038299414,0.0012444973,0.007738788,0.79786164,0.0011597611],"about_ca_topic_score_codex":0.00019461456,"about_ca_topic_score_gemma":0.000014589192,"teacher_disagreement_score":0.77382034,"about_ca_system_score_codex":0.00022756703,"about_ca_system_score_gemma":0.00032091912,"threshold_uncertainty_score":0.9999287},"labels":[],"label_agreement":null},{"id":"W4224272003","doi":"10.1352/1944-7558-127.3.264","title":"Résumés en Français","year":2022,"lang":"fr","type":"article","venue":"American Journal on Intellectual and Developmental Disabilities","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Icon; Citation; Computer science; Download; Information retrieval; World Wide Web; Programming language","score_opus":0.03253244248008126,"score_gpt":0.2609031443318721,"score_spread":0.22837070185179087,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4224272003","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9499124,0.001719269,0.009844736,0.016101,0.002421558,0.00025279584,0.000071103794,0.00008088446,0.01959625],"genre_scores_gemma":[0.9756961,0.00042239262,0.0038496112,0.0020485092,0.00017880023,0.000044985616,0.0000064231863,0.000021709968,0.017731495],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99676704,0.000863889,0.00062099507,0.0005345748,0.00067231664,0.0005411977],"domain_scores_gemma":[0.9955171,0.0037236987,0.00011997031,0.00023373733,0.000084490646,0.00032104808],"candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00085077656,0.00032247385,0.00040349,0.00018454755,0.0014657974,0.0004062619,0.00066735846,0.000041333606,0.011774195],"category_scores_gemma":[0.0013409567,0.00031167959,0.00015330421,0.00066827267,0.0016621448,0.00048512517,0.0006335591,0.000985514,0.00094300666],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021882723,0.0005492428,0.0032804972,0.000031272757,0.000098725206,0.000014578032,0.2580995,0.000118428994,0.00004746205,0.026726015,0.029222004,0.6815934],"study_design_scores_gemma":[0.000355567,0.003563141,0.009032539,0.00006074205,0.000019056957,0.0034304545,0.20370254,0.0011751708,0.0001925723,0.011693911,0.76610994,0.0006643744],"about_ca_topic_score_codex":0.00046667128,"about_ca_topic_score_gemma":0.000023895838,"teacher_disagreement_score":0.73688793,"about_ca_system_score_codex":0.0007319941,"about_ca_system_score_gemma":0.00043612983,"threshold_uncertainty_score":0.99993354},"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,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Morpheme; Priming (agriculture); Psychology; Character (mathematics); Linguistics; Lexical decision task; Repetition priming; Communication; Mathematics; Cognition; Biology; Neuroscience; Philosophy","score_opus":0.020197376580676007,"score_gpt":0.31514183035548443,"score_spread":0.29494445377480843,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4226024717","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.996065,0.00013561189,0.0029022465,0.00020300347,0.00023712426,0.000122012796,0.0000013015919,0.0000057667735,0.00032793524],"genre_scores_gemma":[0.9996675,0.000007000255,0.00017219865,0.00010653888,0.000021650763,0.0000067026417,0.0000023910352,0.000003882801,0.000012138582],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9986989,0.0006034152,0.00030863652,0.00013154147,0.00017557753,0.00008191297],"domain_scores_gemma":[0.99907905,0.00015569873,0.0005459184,0.00013202388,0.00006259665,0.000024694651],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005907336,0.00007261278,0.00016857234,0.00012832541,0.00013715315,0.0000065472977,0.00021935864,0.00004359776,0.000032461743],"category_scores_gemma":[0.000047607966,0.000054322685,0.0001234267,0.00015108052,0.00009492072,0.00016186255,0.000036459587,0.00033230303,4.1780743e-7],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00036807515,0.00050688256,0.0012028345,0.000011034642,0.000035977177,0.0000051850957,0.0034450828,0.00030278802,0.973571,0.00023934993,0.000015419366,0.02029634],"study_design_scores_gemma":[0.0022136734,0.0070324237,0.5484211,0.00006230732,0.000031386793,0.00058180257,0.0007332634,0.0006829134,0.4391907,0.0009115061,0.000026631747,0.000112337155],"about_ca_topic_score_codex":0.000003127627,"about_ca_topic_score_gemma":6.308178e-8,"teacher_disagreement_score":0.5472182,"about_ca_system_score_codex":0.000040006646,"about_ca_system_score_gemma":0.000025959129,"threshold_uncertainty_score":0.22152148},"labels":[],"label_agreement":null},{"id":"W4229722991","doi":"10.1352/1944-7558-122.4.354","title":"Résumés en Français","year":2017,"lang":"fr","type":"article","venue":"American Journal on Intellectual and Developmental Disabilities","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Icon; Citation; Computer science; Download; Information retrieval; World Wide Web; Programming language","score_opus":0.0464597806764474,"score_gpt":0.2915915235032005,"score_spread":0.2451317428267531,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4229722991","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91707695,0.00084920163,0.011891429,0.020789389,0.002320129,0.00020032648,0.00002782175,0.000055700282,0.046789065],"genre_scores_gemma":[0.97400427,0.0010242452,0.005933802,0.0008061487,0.00032106636,0.00001150663,0.0000019417969,0.000019154599,0.01787787],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9975727,0.00031241114,0.00057712686,0.0005365565,0.00044923986,0.00055192783],"domain_scores_gemma":[0.9960448,0.002675311,0.0002143251,0.00051890453,0.00014268908,0.0004039583],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["sts","insufficient_payload"],"category_scores_codex":[0.0006665321,0.0003605583,0.00045703602,0.00010984928,0.0019891039,0.0018490455,0.0010762566,0.00009227952,0.0023695612],"category_scores_gemma":[0.005016123,0.0003145766,0.00015510665,0.0001368129,0.0041636196,0.0012118537,0.00045192786,0.0006490187,0.0022762758],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012609294,0.00026071453,0.01022268,0.000038907692,0.000091054426,0.000010768964,0.11238311,0.0000043850687,0.000040384028,0.023706045,0.010929266,0.84218657],"study_design_scores_gemma":[0.00083421724,0.003547395,0.20904012,0.00062787347,0.000046839086,0.0028535991,0.089843854,0.0013472972,0.0012357912,0.03255455,0.6566171,0.0014513398],"about_ca_topic_score_codex":0.0008645926,"about_ca_topic_score_gemma":0.00009715828,"teacher_disagreement_score":0.84073526,"about_ca_system_score_codex":0.0003028153,"about_ca_system_score_gemma":0.00032286794,"threshold_uncertainty_score":0.9999306},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Period (music); Library science; Geography; History; Computer science; Art","score_opus":0.04848193635037118,"score_gpt":0.27505699262660915,"score_spread":0.22657505627623797,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4229836027","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000019815248,0.001056655,0.5640147,0.0012112969,0.002680676,0.00032448955,0.00001581688,0.00030294008,0.4303736],"genre_scores_gemma":[0.006249857,0.0007186929,0.008402592,0.00038845025,0.0017172017,0.000025813859,0.000086782944,0.000046346093,0.98236424],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99813163,0.000020316475,0.0003714329,0.0007232635,0.00048199497,0.0002713868],"domain_scores_gemma":[0.99799454,0.00006623903,0.0002173862,0.0014601551,0.00012652343,0.00013517617],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00023687225,0.00028860715,0.00028449192,0.00013444072,0.000140343,0.00018520051,0.0015887056,0.00021658165,0.000074399206],"category_scores_gemma":[0.000048843678,0.00027403515,0.00015365392,0.00006389225,0.00012216276,0.00017923898,0.00035757694,0.00040331672,0.00051931076],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[2.1532678e-7,0.000008976948,0.0000068021623,0.000025226263,0.000002113571,6.16034e-7,0.00004572994,0.0000015024171,0.000002191102,0.5590856,0.0024631885,0.4383578],"study_design_scores_gemma":[0.00006186031,0.00003523019,0.00031362672,0.000068436006,0.000009062733,0.000005444441,5.8185555e-7,0.0015581973,0.000022776798,0.06264572,0.9349764,0.00030264593],"about_ca_topic_score_codex":0.0000026010932,"about_ca_topic_score_gemma":0.000012904231,"teacher_disagreement_score":0.93251324,"about_ca_system_score_codex":0.00009978002,"about_ca_system_score_gemma":0.00014533127,"threshold_uncertainty_score":0.9999712},"labels":[],"label_agreement":null},{"id":"W4229961377","doi":"10.1352/1944-7558-123.2.189","title":"Résumés en Français","year":2018,"lang":"fr","type":"article","venue":"American Journal on Intellectual and Developmental Disabilities","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Icon; Citation; Computer science; Download; Information retrieval; World Wide Web; Programming language","score_opus":0.03532833154366792,"score_gpt":0.2766916632806961,"score_spread":0.24136333173702818,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4229961377","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9184605,0.00077991874,0.028530387,0.0104774255,0.0022904417,0.00019235791,0.000021845193,0.00008098168,0.03916617],"genre_scores_gemma":[0.97331977,0.00053107983,0.009651364,0.0017640415,0.00066158717,0.000010098016,0.0000024028839,0.00002075212,0.014038915],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9973408,0.00043671392,0.00063058053,0.00054803933,0.00045577396,0.0005880972],"domain_scores_gemma":[0.99580145,0.0031999294,0.00010864269,0.00025629075,0.00023310466,0.00040057316],"candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0006277,0.00035844522,0.00041355763,0.00015941451,0.0007482564,0.0005752416,0.00054641376,0.00009093309,0.0054375706],"category_scores_gemma":[0.0024497123,0.0003110124,0.00012862401,0.00055875804,0.0049273386,0.0006868765,0.0002573801,0.0005417274,0.005280012],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017020917,0.00028150895,0.003156554,0.000028674795,0.0000854053,0.000004674699,0.2107771,0.0000017622405,0.00007413872,0.020702627,0.022638958,0.74207836],"study_design_scores_gemma":[0.000519829,0.0070343404,0.029914288,0.00038539412,0.000032897802,0.002728678,0.10865251,0.0012838828,0.002305752,0.021751897,0.82429487,0.0010956585],"about_ca_topic_score_codex":0.00041069573,"about_ca_topic_score_gemma":0.00008395264,"teacher_disagreement_score":0.8016559,"about_ca_system_score_codex":0.0003439231,"about_ca_system_score_gemma":0.00034776388,"threshold_uncertainty_score":0.9999342},"labels":[],"label_agreement":null},{"id":"W4230188865","doi":"10.1352/1944-7558-123.3.300","title":"Résumés en Français","year":2018,"lang":"fr","type":"article","venue":"American Journal on Intellectual and Developmental Disabilities","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Icon; Citation; Computer science; Download; World Wide Web; Information retrieval; Programming language","score_opus":0.03532833154366792,"score_gpt":0.2766916632806961,"score_spread":0.24136333173702818,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4230188865","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9184605,0.00077991874,0.028530387,0.0104774255,0.0022904417,0.00019235791,0.000021845193,0.00008098168,0.03916617],"genre_scores_gemma":[0.97331977,0.00053107983,0.009651364,0.0017640415,0.00066158717,0.000010098016,0.0000024028839,0.00002075212,0.014038915],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9973408,0.00043671392,0.00063058053,0.00054803933,0.00045577396,0.0005880972],"domain_scores_gemma":[0.99580145,0.0031999294,0.00010864269,0.00025629075,0.00023310466,0.00040057316],"candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0006277,0.00035844522,0.00041355763,0.00015941451,0.0007482564,0.0005752416,0.00054641376,0.00009093309,0.0054375706],"category_scores_gemma":[0.0024497123,0.0003110124,0.00012862401,0.00055875804,0.0049273386,0.0006868765,0.0002573801,0.0005417274,0.005280012],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017020917,0.00028150895,0.003156554,0.000028674795,0.0000854053,0.000004674699,0.2107771,0.0000017622405,0.00007413872,0.020702627,0.022638958,0.74207836],"study_design_scores_gemma":[0.000519829,0.0070343404,0.029914288,0.00038539412,0.000032897802,0.002728678,0.10865251,0.0012838828,0.002305752,0.021751897,0.82429487,0.0010956585],"about_ca_topic_score_codex":0.00041069573,"about_ca_topic_score_gemma":0.00008395264,"teacher_disagreement_score":0.8016559,"about_ca_system_score_codex":0.0003439231,"about_ca_system_score_gemma":0.00034776388,"threshold_uncertainty_score":0.9999342},"labels":[],"label_agreement":null},{"id":"W4230430983","doi":"10.1352/1944-7558-120.3.269","title":"Résumés en Français","year":2015,"lang":"fr","type":"article","venue":"American Journal on Intellectual and Developmental Disabilities","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Icon; Citation; Computer science; Download; Information retrieval; World Wide Web; Programming language","score_opus":0.061060970991956474,"score_gpt":0.2826934995018871,"score_spread":0.22163252850993062,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4230430983","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91487396,0.0020378465,0.026114592,0.014950391,0.0024381732,0.00022749392,0.000024086947,0.000093678165,0.039239783],"genre_scores_gemma":[0.9728053,0.0005015339,0.010183538,0.0013933771,0.0003199244,0.00001287884,0.000003832863,0.00002142794,0.01475816],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9972207,0.00052883703,0.0006325637,0.0004948498,0.0005801986,0.00054287264],"domain_scores_gemma":[0.99580896,0.002911811,0.00010726655,0.00023578598,0.00022891277,0.0007072707],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0008865163,0.00035574083,0.00044358708,0.00015313253,0.00035830427,0.00058140507,0.00051956257,0.00008914672,0.0012776308],"category_scores_gemma":[0.0039566206,0.0003085063,0.00012106462,0.0005122463,0.0022359977,0.0007863705,0.0002561762,0.00060922065,0.0030923507],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020565308,0.00036697357,0.0046170363,0.000029998579,0.000084651,0.000010510719,0.28633434,0.000028238766,0.000018346082,0.02049844,0.041505277,0.64630055],"study_design_scores_gemma":[0.00073028647,0.004304727,0.0105463015,0.0002662881,0.000029392831,0.0031602108,0.2261044,0.0014452534,0.00053015276,0.028232576,0.72366875,0.0009816556],"about_ca_topic_score_codex":0.000552922,"about_ca_topic_score_gemma":0.00004911855,"teacher_disagreement_score":0.6821635,"about_ca_system_score_codex":0.00054055796,"about_ca_system_score_gemma":0.000635389,"threshold_uncertainty_score":0.9999367},"labels":[],"label_agreement":null},{"id":"W4231287158","doi":"10.1352/1944-7558-117.5.435","title":"Résumés en Français","year":2012,"lang":"fr","type":"article","venue":"American Journal on Intellectual and Developmental Disabilities","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Icon; Citation; Computer science; Information retrieval; Download; World Wide Web; Programming language","score_opus":0.03992681201984083,"score_gpt":0.2749049892730803,"score_spread":0.2349781772532395,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4231287158","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9431666,0.003187336,0.018590175,0.0071290676,0.0025176986,0.00018900039,0.000020410602,0.00007015138,0.02512952],"genre_scores_gemma":[0.9793179,0.000862494,0.008087828,0.0012710221,0.00051793584,0.000013484486,0.0000031341285,0.000020717078,0.009905497],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9972731,0.0004982657,0.00061032915,0.0003719477,0.00045751632,0.0007888275],"domain_scores_gemma":[0.99498826,0.0039741485,0.00010663987,0.00022133072,0.00010474773,0.0006049003],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00084448693,0.0003622165,0.00041936373,0.00014588979,0.00053742283,0.00040385273,0.00043285938,0.00009134626,0.0037241206],"category_scores_gemma":[0.0022160376,0.0003127266,0.00014359162,0.00045958775,0.0020110935,0.0012216743,0.00023209468,0.0006314287,0.003554696],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010102719,0.0005312332,0.019154573,0.00004194398,0.00009016871,0.000002075305,0.26533803,0.0000044192457,0.000049750717,0.030043937,0.015082883,0.66955996],"study_design_scores_gemma":[0.00041730082,0.002021667,0.08169227,0.0002710955,0.000038945553,0.0030749883,0.13976958,0.000375486,0.0010889132,0.0066616395,0.7635215,0.0010666492],"about_ca_topic_score_codex":0.00029259102,"about_ca_topic_score_gemma":0.00001688892,"teacher_disagreement_score":0.7484386,"about_ca_system_score_codex":0.00039870542,"about_ca_system_score_gemma":0.00021770543,"threshold_uncertainty_score":0.99993247},"labels":[],"label_agreement":null},{"id":"W4231939881","doi":"10.1352/1934-9556-53.6.441","title":"Résumés en Français","year":2015,"lang":"fr","type":"article","venue":"Intellectual and developmental disabilities","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Icon; Citation; Download; Computer science; World Wide Web; Information retrieval","score_opus":0.09478286869654018,"score_gpt":0.2827716178574192,"score_spread":0.18798874916087904,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4231939881","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.67077893,0.009731039,0.05334058,0.01346716,0.003731926,0.00065164326,0.00006712935,0.0003437347,0.24788786],"genre_scores_gemma":[0.8933431,0.00021063676,0.010254884,0.0004656541,0.00017480148,0.000038093054,0.000014754391,0.00001709368,0.095480986],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.997912,0.00022950159,0.00045676396,0.00058524736,0.00037185987,0.00044461773],"domain_scores_gemma":[0.9970323,0.0021483358,0.000023176715,0.00026904955,0.00015981476,0.0003673482],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0005621926,0.00029553444,0.00028349255,0.00007512801,0.00019384845,0.00036563183,0.0004197046,0.00019088962,0.0027699894],"category_scores_gemma":[0.004153178,0.00028213972,0.000070682305,0.00031613378,0.0010922124,0.00088699226,0.00049884256,0.0002371413,0.01101127],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006661903,0.0003491809,0.007820163,0.00017927206,0.00005557155,0.0000038105145,0.5582873,0.000008883572,0.00006544535,0.086658485,0.13310155,0.21340372],"study_design_scores_gemma":[0.00042746076,0.0003089737,0.006617517,0.00010091677,0.000014536654,0.00027314623,0.054462288,0.0026552037,0.0014547793,0.05151842,0.88154256,0.00062419206],"about_ca_topic_score_codex":0.0012969788,"about_ca_topic_score_gemma":0.00026111846,"teacher_disagreement_score":0.74844104,"about_ca_system_score_codex":0.00030060275,"about_ca_system_score_gemma":0.00044415178,"threshold_uncertainty_score":0.9999631},"labels":[],"label_agreement":null},{"id":"W4233949603","doi":"10.26522/ti.v2i1.741","title":"Braille 1","year":2013,"lang":"en","type":"article","venue":"ti<","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Braille; Computer science; Operating system","score_opus":0.008663149444903994,"score_gpt":0.1970102448804729,"score_spread":0.1883470954355689,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4233949603","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.26908737,0.000061675884,0.609534,0.0138039375,0.0002660583,0.00025120671,4.4737638e-7,0.00044410527,0.1065512],"genre_scores_gemma":[0.98869395,7.3898775e-7,0.008576041,0.00032125716,0.000018783605,0.000010448045,5.0061027e-7,0.0000011650025,0.002377132],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99972457,0.000010158272,0.000047300855,0.00009465683,0.000054874417,0.00006845809],"domain_scores_gemma":[0.99963254,0.000020892378,0.000010809682,0.000286503,0.000021761987,0.000027474176],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00004594279,0.00002362552,0.000026737534,0.00001219623,0.00002999136,0.00005781097,0.00024752086,0.00001490536,0.00020172866],"category_scores_gemma":[0.000012707645,0.000019719118,0.000012219922,0.00007278544,0.000010389115,0.00026380483,0.00004078426,0.000023947925,0.0028370665],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[2.700957e-7,0.00004439709,0.0010776892,0.0000049047367,0.000002525446,4.1734353e-7,0.0006758782,0.0000073437577,0.004239439,0.36139113,0.029546386,0.6030096],"study_design_scores_gemma":[0.00024052104,0.00007145077,0.40158752,0.000006145303,0.0000017660012,0.000013645,0.000048853864,0.04557548,0.008298056,0.16421805,0.3796324,0.00030609674],"about_ca_topic_score_codex":0.00006271704,"about_ca_topic_score_gemma":0.0000024088704,"teacher_disagreement_score":0.7196066,"about_ca_system_score_codex":0.000006939955,"about_ca_system_score_gemma":0.000008703661,"threshold_uncertainty_score":0.99793935},"labels":[],"label_agreement":null},{"id":"W4234480813","doi":"10.26522/ti.v2i1.742","title":"Braille 2","year":2013,"lang":"en","type":"article","venue":"ti<","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Braille; Computer science; Operating system","score_opus":0.008135870919932427,"score_gpt":0.19622989942085445,"score_spread":0.18809402850092202,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4234480813","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27090403,0.00006422024,0.60214597,0.013922373,0.0002728471,0.00025466617,4.3948995e-7,0.00045127387,0.111984156],"genre_scores_gemma":[0.988929,7.712069e-7,0.008320264,0.00032230277,0.00001926814,0.000010177858,5.054346e-7,0.0000011662186,0.002396593],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9997247,0.000010153044,0.000047333,0.000094549185,0.00005485357,0.000068419795],"domain_scores_gemma":[0.9996339,0.000020446103,0.000010832637,0.0002856692,0.000021688626,0.000027468075],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00004556288,0.000023614126,0.000026747466,0.00001218412,0.000029994693,0.00005800139,0.00024731198,0.000014905491,0.00019599222],"category_scores_gemma":[0.000012475714,0.00001970934,0.0000122163365,0.00007269964,0.000010388897,0.00026407905,0.000040775558,0.000023939561,0.002791408],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[2.5976217e-7,0.00004303228,0.0009952303,0.0000048218544,0.0000024490575,4.2163356e-7,0.0006562643,0.000007173508,0.0038973088,0.35928804,0.027934086,0.60717094],"study_design_scores_gemma":[0.00023979897,0.00007052051,0.38692915,0.000005950626,0.0000017330015,0.000013509254,0.00004746114,0.04451687,0.008110845,0.16396365,0.39579946,0.00030107345],"about_ca_topic_score_codex":0.000063678155,"about_ca_topic_score_gemma":0.000002430529,"teacher_disagreement_score":0.7180249,"about_ca_system_score_codex":0.0000069429707,"about_ca_system_score_gemma":0.000008644974,"threshold_uncertainty_score":0.997985},"labels":[],"label_agreement":null},{"id":"W4237644368","doi":"10.1352/1944-7558-121.6.564","title":"Résumés en Français","year":2016,"lang":"fr","type":"article","venue":"American Journal on Intellectual and Developmental Disabilities","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Icon; Citation; Computer science; Download; Information retrieval; World Wide Web; Programming language","score_opus":0.03248268548073877,"score_gpt":0.26266051393124573,"score_spread":0.23017782845050697,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4237644368","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8898196,0.0010027905,0.05928487,0.030964736,0.0017101432,0.0002001638,0.000040144307,0.000086629574,0.016890893],"genre_scores_gemma":[0.9680405,0.0014633016,0.0053220913,0.0010581209,0.00026516672,0.000013711495,0.0000010924474,0.000020509087,0.023815453],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9973386,0.00045752796,0.0006352144,0.00053964794,0.00045112945,0.0005778982],"domain_scores_gemma":[0.9927609,0.006331447,0.00010923205,0.00024877494,0.00013998908,0.00040964494],"candidate_categories":["sts","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00058894034,0.00035508556,0.00041549478,0.00014914299,0.00044666664,0.000365565,0.000515193,0.000086332475,0.0047243214],"category_scores_gemma":[0.0031693827,0.00023615512,0.00014501986,0.00037892224,0.002815134,0.0008269477,0.0002304339,0.00036184807,0.00387916],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012753751,0.0002112659,0.0042409026,0.000021933209,0.00006933046,0.0000054387524,0.06766085,0.0000011107837,0.00022201237,0.022674615,0.012409251,0.89235574],"study_design_scores_gemma":[0.00095239835,0.004298736,0.042002276,0.00090042886,0.000033958084,0.0030296785,0.061445598,0.00018979181,0.0030386029,0.03593961,0.8468363,0.0013325708],"about_ca_topic_score_codex":0.00020722713,"about_ca_topic_score_gemma":0.000036516958,"teacher_disagreement_score":0.89102316,"about_ca_system_score_codex":0.00045354306,"about_ca_system_score_gemma":0.0003198947,"threshold_uncertainty_score":0.9998986},"labels":[],"label_agreement":null},{"id":"W4237746967","doi":"10.1352/1944-7558-123.6.585","title":"Résumés en Français","year":2018,"lang":"fr","type":"article","venue":"American Journal on Intellectual and Developmental Disabilities","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Icon; Citation; Computer science; Download; World Wide Web; Information retrieval; Programming language","score_opus":0.03532833154366792,"score_gpt":0.2766916632806961,"score_spread":0.24136333173702818,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4237746967","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9184605,0.00077991874,0.028530387,0.0104774255,0.0022904417,0.00019235791,0.000021845193,0.00008098168,0.03916617],"genre_scores_gemma":[0.97331977,0.00053107983,0.009651364,0.0017640415,0.00066158717,0.000010098016,0.0000024028839,0.00002075212,0.014038915],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9973408,0.00043671392,0.00063058053,0.00054803933,0.00045577396,0.0005880972],"domain_scores_gemma":[0.99580145,0.0031999294,0.00010864269,0.00025629075,0.00023310466,0.00040057316],"candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0006277,0.00035844522,0.00041355763,0.00015941451,0.0007482564,0.0005752416,0.00054641376,0.00009093309,0.0054375706],"category_scores_gemma":[0.0024497123,0.0003110124,0.00012862401,0.00055875804,0.0049273386,0.0006868765,0.0002573801,0.0005417274,0.005280012],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017020917,0.00028150895,0.003156554,0.000028674795,0.0000854053,0.000004674699,0.2107771,0.0000017622405,0.00007413872,0.020702627,0.022638958,0.74207836],"study_design_scores_gemma":[0.000519829,0.0070343404,0.029914288,0.00038539412,0.000032897802,0.002728678,0.10865251,0.0012838828,0.002305752,0.021751897,0.82429487,0.0010956585],"about_ca_topic_score_codex":0.00041069573,"about_ca_topic_score_gemma":0.00008395264,"teacher_disagreement_score":0.8016559,"about_ca_system_score_codex":0.0003439231,"about_ca_system_score_gemma":0.00034776388,"threshold_uncertainty_score":0.9999342},"labels":[],"label_agreement":null},{"id":"W4238761088","doi":"10.1017/s0142716412000628","title":"Fixed-choice word-association tasks as second-language lexical tests: What native-speaker performance reveals about their potential weaknesses—CORRIGENDUM","year":2012,"lang":"en","type":"erratum","venue":"Applied Psycholinguistics","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Syntagmatic analysis; Psychology; Word Association; Regret; Association (psychology); Linguistics; Sentence; Word (group theory); Transposition (logic); Computer science","score_opus":0.02111943383475751,"score_gpt":0.2827225891372971,"score_spread":0.2616031553025396,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4238761088","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.054241233,0.016894681,0.09685409,0.0021370691,0.36287674,0.0057241376,0.0009443548,0.0029088752,0.45741883],"genre_scores_gemma":[0.8289934,0.0021065115,0.0052750623,0.0029442047,0.021628842,0.00038522482,0.0019936077,0.00023921616,0.13643396],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99441624,0.0002071175,0.0012340487,0.0015626544,0.0012806163,0.001299304],"domain_scores_gemma":[0.99445885,0.00058284815,0.0014494775,0.002364555,0.0007341533,0.0004100835],"candidate_categories":["metaepi_narrow","scholarly_communication","research_integrity","insufficient_payload"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.0013980692,0.00094234134,0.00095402566,0.0003056521,0.0005959728,0.0012893201,0.002390263,0.0016214082,0.00040531956],"category_scores_gemma":[0.00086404197,0.00091808115,0.00029465256,0.0008218361,0.00015378013,0.00068371516,0.0003781234,0.00267225,0.0009317248],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011411911,0.0012237262,0.0006563582,0.00097057293,0.0004457349,0.00002430269,0.015040536,0.000049635553,0.00090076425,0.029747577,0.78429943,0.16652721],"study_design_scores_gemma":[0.00066606235,0.00008361347,0.026963226,0.00038001788,0.00013630318,0.00003254052,0.00043695347,0.0011381567,0.00029476255,0.005042969,0.9632853,0.0015400662],"about_ca_topic_score_codex":0.000052610965,"about_ca_topic_score_gemma":0.000077251905,"teacher_disagreement_score":0.77475214,"about_ca_system_score_codex":0.00070249295,"about_ca_system_score_gemma":0.00040431748,"threshold_uncertainty_score":0.99984616},"labels":[],"label_agreement":null},{"id":"W4239261758","doi":"10.1352/1944-7558-124.3.286","title":"Résumés en Français","year":2019,"lang":"fr","type":"article","venue":"American Journal on Intellectual and Developmental Disabilities","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Icon; Citation; Computer science; Information retrieval; Download; World Wide Web; Programming language","score_opus":0.024980033049128787,"score_gpt":0.25661534380090545,"score_spread":0.23163531075177665,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4239261758","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95333254,0.00085998,0.0056969225,0.006590141,0.0018125117,0.00023596686,0.000016589996,0.000054753436,0.03140058],"genre_scores_gemma":[0.9643634,0.00066422776,0.004861786,0.0013424867,0.00018067966,0.000009416711,0.0000033881045,0.000020992138,0.028553613],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99737144,0.00040812435,0.0006196991,0.0005613784,0.000484128,0.0005552549],"domain_scores_gemma":[0.9951147,0.0040292004,0.00011047414,0.00027537355,0.0001268826,0.0003433622],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00057760667,0.0003605169,0.0004779224,0.0001543849,0.00033600174,0.00052895024,0.0005277126,0.00009209981,0.0075681657],"category_scores_gemma":[0.0012923306,0.00031390353,0.00015350616,0.00046988906,0.0014617131,0.0007512815,0.00024119826,0.00066155166,0.00935526],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020572949,0.00038659637,0.01825754,0.000087683526,0.00012333061,0.000005811264,0.18915,0.000029765302,0.000140554,0.033201694,0.011616052,0.74679524],"study_design_scores_gemma":[0.00084946526,0.005431806,0.058391724,0.00057545485,0.00003326988,0.0027178046,0.16247779,0.0021533354,0.0011564075,0.016668566,0.7481156,0.0014287616],"about_ca_topic_score_codex":0.00033523754,"about_ca_topic_score_gemma":0.000025566822,"teacher_disagreement_score":0.74536645,"about_ca_system_score_codex":0.00036853526,"about_ca_system_score_gemma":0.00033058846,"threshold_uncertainty_score":0.9999313},"labels":[],"label_agreement":null},{"id":"W4241482399","doi":"10.1249/01.mss.0000433712.56493.55","title":"E-15 Thematic Poster - Neuroscience","year":2013,"lang":"en","type":"article","venue":"Medicine & Science in Sports & Exercise","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Neuroscience; Thematic map; Psychology; Cartography; Geography","score_opus":0.021244762373427855,"score_gpt":0.26994404415573403,"score_spread":0.2486992817823062,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4241482399","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9793058,0.000028032617,0.009668047,0.005837199,0.0007959091,0.00065007026,1.7595502e-7,0.00013205172,0.0035827153],"genre_scores_gemma":[0.9964671,0.000027751936,0.0018958657,0.0010339628,0.000035533565,0.00007273044,5.2388583e-7,0.000005750353,0.0004607559],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9966055,0.000031439482,0.0005375671,0.00087320554,0.0013370861,0.0006152021],"domain_scores_gemma":[0.99795365,0.00007480179,0.000158084,0.0013341721,0.00019440449,0.00028490133],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020347924,0.00018954826,0.00029937917,0.0004598346,0.00025079865,0.00020198106,0.0024174347,0.000043144493,0.00023065637],"category_scores_gemma":[0.0003836532,0.0001335167,0.000033965174,0.0028029634,0.0013967226,0.0027049368,0.00030890777,0.0001893773,0.00012494701],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000042003453,0.00029143906,0.33330148,0.000055796976,7.227302e-8,0.00006270032,0.010887698,0.00008826899,0.008584102,0.0017777608,0.0017708833,0.6431756],"study_design_scores_gemma":[0.00014999964,0.0000619719,0.97699976,0.00015257209,0.000002749649,0.000035885732,0.00030014085,0.012116879,0.00012426541,0.009522638,0.00035120556,0.00018193899],"about_ca_topic_score_codex":0.00029444558,"about_ca_topic_score_gemma":0.000010322729,"teacher_disagreement_score":0.6436983,"about_ca_system_score_codex":0.0000819338,"about_ca_system_score_gemma":0.00020553998,"threshold_uncertainty_score":0.5444653},"labels":[],"label_agreement":null},{"id":"W4241656786","doi":"10.1352/1944-7558-120.4.371","title":"Résumés en Français","year":2015,"lang":"fr","type":"article","venue":"American Journal on Intellectual and Developmental Disabilities","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Icon; Citation; Computer science; Information retrieval; Download; World Wide Web; Programming language","score_opus":0.061060970991956474,"score_gpt":0.2826934995018871,"score_spread":0.22163252850993062,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4241656786","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91487396,0.0020378465,0.026114592,0.014950391,0.0024381732,0.00022749392,0.000024086947,0.000093678165,0.039239783],"genre_scores_gemma":[0.9728053,0.0005015339,0.010183538,0.0013933771,0.0003199244,0.00001287884,0.000003832863,0.00002142794,0.01475816],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9972207,0.00052883703,0.0006325637,0.0004948498,0.0005801986,0.00054287264],"domain_scores_gemma":[0.99580896,0.002911811,0.00010726655,0.00023578598,0.00022891277,0.0007072707],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0008865163,0.00035574083,0.00044358708,0.00015313253,0.00035830427,0.00058140507,0.00051956257,0.00008914672,0.0012776308],"category_scores_gemma":[0.0039566206,0.0003085063,0.00012106462,0.0005122463,0.0022359977,0.0007863705,0.0002561762,0.00060922065,0.0030923507],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020565308,0.00036697357,0.0046170363,0.000029998579,0.000084651,0.000010510719,0.28633434,0.000028238766,0.000018346082,0.02049844,0.041505277,0.64630055],"study_design_scores_gemma":[0.00073028647,0.004304727,0.0105463015,0.0002662881,0.000029392831,0.0031602108,0.2261044,0.0014452534,0.00053015276,0.028232576,0.72366875,0.0009816556],"about_ca_topic_score_codex":0.000552922,"about_ca_topic_score_gemma":0.00004911855,"teacher_disagreement_score":0.6821635,"about_ca_system_score_codex":0.00054055796,"about_ca_system_score_gemma":0.000635389,"threshold_uncertainty_score":0.9999367},"labels":[],"label_agreement":null},{"id":"W4242069306","doi":"10.1352/1944-7558-123.1.83","title":"Résumés en Français","year":2017,"lang":"fr","type":"article","venue":"American Journal on Intellectual and Developmental Disabilities","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Icon; Citation; Computer science; Download; Information retrieval; World Wide Web; Programming language","score_opus":0.0464597806764474,"score_gpt":0.2915915235032005,"score_spread":0.2451317428267531,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4242069306","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91707695,0.00084920163,0.011891429,0.020789389,0.002320129,0.00020032648,0.00002782175,0.000055700282,0.046789065],"genre_scores_gemma":[0.97400427,0.0010242452,0.005933802,0.0008061487,0.00032106636,0.00001150663,0.0000019417969,0.000019154599,0.01787787],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9975727,0.00031241114,0.00057712686,0.0005365565,0.00044923986,0.00055192783],"domain_scores_gemma":[0.9960448,0.002675311,0.0002143251,0.00051890453,0.00014268908,0.0004039583],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["sts","insufficient_payload"],"category_scores_codex":[0.0006665321,0.0003605583,0.00045703602,0.00010984928,0.0019891039,0.0018490455,0.0010762566,0.00009227952,0.0023695612],"category_scores_gemma":[0.005016123,0.0003145766,0.00015510665,0.0001368129,0.0041636196,0.0012118537,0.00045192786,0.0006490187,0.0022762758],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012609294,0.00026071453,0.01022268,0.000038907692,0.000091054426,0.000010768964,0.11238311,0.0000043850687,0.000040384028,0.023706045,0.010929266,0.84218657],"study_design_scores_gemma":[0.00083421724,0.003547395,0.20904012,0.00062787347,0.000046839086,0.0028535991,0.089843854,0.0013472972,0.0012357912,0.03255455,0.6566171,0.0014513398],"about_ca_topic_score_codex":0.0008645926,"about_ca_topic_score_gemma":0.00009715828,"teacher_disagreement_score":0.84073526,"about_ca_system_score_codex":0.0003028153,"about_ca_system_score_gemma":0.00032286794,"threshold_uncertainty_score":0.9999306},"labels":[],"label_agreement":null},{"id":"W4242224582","doi":"10.1352/1934-9556-53.5.377","title":"Résumés en Français","year":2015,"lang":"fr","type":"article","venue":"Intellectual and developmental disabilities","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Icon; Citation; Computer science; Download; Information retrieval; World Wide Web; Programming language","score_opus":0.09478286869654018,"score_gpt":0.2827716178574192,"score_spread":0.18798874916087904,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4242224582","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.67077893,0.009731039,0.05334058,0.01346716,0.003731926,0.00065164326,0.00006712935,0.0003437347,0.24788786],"genre_scores_gemma":[0.8933431,0.00021063676,0.010254884,0.0004656541,0.00017480148,0.000038093054,0.000014754391,0.00001709368,0.095480986],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.997912,0.00022950159,0.00045676396,0.00058524736,0.00037185987,0.00044461773],"domain_scores_gemma":[0.9970323,0.0021483358,0.000023176715,0.00026904955,0.00015981476,0.0003673482],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0005621926,0.00029553444,0.00028349255,0.00007512801,0.00019384845,0.00036563183,0.0004197046,0.00019088962,0.0027699894],"category_scores_gemma":[0.004153178,0.00028213972,0.000070682305,0.00031613378,0.0010922124,0.00088699226,0.00049884256,0.0002371413,0.01101127],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006661903,0.0003491809,0.007820163,0.00017927206,0.00005557155,0.0000038105145,0.5582873,0.000008883572,0.00006544535,0.086658485,0.13310155,0.21340372],"study_design_scores_gemma":[0.00042746076,0.0003089737,0.006617517,0.00010091677,0.000014536654,0.00027314623,0.054462288,0.0026552037,0.0014547793,0.05151842,0.88154256,0.00062419206],"about_ca_topic_score_codex":0.0012969788,"about_ca_topic_score_gemma":0.00026111846,"teacher_disagreement_score":0.74844104,"about_ca_system_score_codex":0.00030060275,"about_ca_system_score_gemma":0.00044415178,"threshold_uncertainty_score":0.9999631},"labels":[],"label_agreement":null},{"id":"W4242568833","doi":"10.1352/1944-7558-123.5.495","title":"Résumés en Français","year":2018,"lang":"fr","type":"article","venue":"American Journal on Intellectual and Developmental Disabilities","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Icon; Citation; Computer science; Information retrieval; Download; World Wide Web; Programming language","score_opus":0.03532833154366792,"score_gpt":0.2766916632806961,"score_spread":0.24136333173702818,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4242568833","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9184605,0.00077991874,0.028530387,0.0104774255,0.0022904417,0.00019235791,0.000021845193,0.00008098168,0.03916617],"genre_scores_gemma":[0.97331977,0.00053107983,0.009651364,0.0017640415,0.00066158717,0.000010098016,0.0000024028839,0.00002075212,0.014038915],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9973408,0.00043671392,0.00063058053,0.00054803933,0.00045577396,0.0005880972],"domain_scores_gemma":[0.99580145,0.0031999294,0.00010864269,0.00025629075,0.00023310466,0.00040057316],"candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0006277,0.00035844522,0.00041355763,0.00015941451,0.0007482564,0.0005752416,0.00054641376,0.00009093309,0.0054375706],"category_scores_gemma":[0.0024497123,0.0003110124,0.00012862401,0.00055875804,0.0049273386,0.0006868765,0.0002573801,0.0005417274,0.005280012],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017020917,0.00028150895,0.003156554,0.000028674795,0.0000854053,0.000004674699,0.2107771,0.0000017622405,0.00007413872,0.020702627,0.022638958,0.74207836],"study_design_scores_gemma":[0.000519829,0.0070343404,0.029914288,0.00038539412,0.000032897802,0.002728678,0.10865251,0.0012838828,0.002305752,0.021751897,0.82429487,0.0010956585],"about_ca_topic_score_codex":0.00041069573,"about_ca_topic_score_gemma":0.00008395264,"teacher_disagreement_score":0.8016559,"about_ca_system_score_codex":0.0003439231,"about_ca_system_score_gemma":0.00034776388,"threshold_uncertainty_score":0.9999342},"labels":[],"label_agreement":null},{"id":"W4244221259","doi":"10.1352/1944-7558-120.2.189","title":"Résumés en Français","year":2015,"lang":"fr","type":"article","venue":"American Journal on Intellectual and Developmental Disabilities","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Icon; Citation; Computer science; Download; Information retrieval; World Wide Web; Programming language","score_opus":0.061060970991956474,"score_gpt":0.2826934995018871,"score_spread":0.22163252850993062,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4244221259","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91487396,0.0020378465,0.026114592,0.014950391,0.0024381732,0.00022749392,0.000024086947,0.000093678165,0.039239783],"genre_scores_gemma":[0.9728053,0.0005015339,0.010183538,0.0013933771,0.0003199244,0.00001287884,0.000003832863,0.00002142794,0.01475816],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9972207,0.00052883703,0.0006325637,0.0004948498,0.0005801986,0.00054287264],"domain_scores_gemma":[0.99580896,0.002911811,0.00010726655,0.00023578598,0.00022891277,0.0007072707],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0008865163,0.00035574083,0.00044358708,0.00015313253,0.00035830427,0.00058140507,0.00051956257,0.00008914672,0.0012776308],"category_scores_gemma":[0.0039566206,0.0003085063,0.00012106462,0.0005122463,0.0022359977,0.0007863705,0.0002561762,0.00060922065,0.0030923507],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020565308,0.00036697357,0.0046170363,0.000029998579,0.000084651,0.000010510719,0.28633434,0.000028238766,0.000018346082,0.02049844,0.041505277,0.64630055],"study_design_scores_gemma":[0.00073028647,0.004304727,0.0105463015,0.0002662881,0.000029392831,0.0031602108,0.2261044,0.0014452534,0.00053015276,0.028232576,0.72366875,0.0009816556],"about_ca_topic_score_codex":0.000552922,"about_ca_topic_score_gemma":0.00004911855,"teacher_disagreement_score":0.6821635,"about_ca_system_score_codex":0.00054055796,"about_ca_system_score_gemma":0.000635389,"threshold_uncertainty_score":0.9999367},"labels":[],"label_agreement":null},{"id":"W4247282175","doi":"10.1352/1944-7558-115.6.524","title":"Résumés en Français","year":2010,"lang":"fr","type":"article","venue":"American Journal on Intellectual and Developmental Disabilities","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Icon; Citation; Computer science; Information retrieval; Download; World Wide Web; Programming language","score_opus":0.02520750867445705,"score_gpt":0.26460478443402835,"score_spread":0.23939727575957132,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4247282175","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9578135,0.00034195554,0.008458492,0.009966756,0.0027652562,0.00016131617,0.000019975063,0.000065257664,0.02040748],"genre_scores_gemma":[0.9744401,0.00040275988,0.012788062,0.0011549997,0.00039191314,0.000013142426,0.000003143044,0.000021282605,0.010784588],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9975306,0.00030107697,0.0006247596,0.00052861363,0.00045382298,0.0005611202],"domain_scores_gemma":[0.9948061,0.004188906,0.00010852913,0.00028302247,0.00015376965,0.00045964256],"candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00068935513,0.0003660307,0.00041560043,0.0001568779,0.00059743936,0.0006474114,0.0005921692,0.000120791614,0.0053445604],"category_scores_gemma":[0.0032914127,0.0003177531,0.00014643175,0.00045149773,0.0030093295,0.0007098664,0.00023204088,0.0012767366,0.0025722403],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010707471,0.00036287555,0.005346754,0.000033908113,0.000071122995,0.000006968118,0.13831905,0.000003927026,0.00052596576,0.04135339,0.011092347,0.80277663],"study_design_scores_gemma":[0.00054493925,0.0026849248,0.046970922,0.0002037303,0.00003242623,0.0043683746,0.07746862,0.0011307964,0.0023903872,0.025043923,0.83796066,0.001200294],"about_ca_topic_score_codex":0.0004306712,"about_ca_topic_score_gemma":0.00017068579,"teacher_disagreement_score":0.8268683,"about_ca_system_score_codex":0.00016630505,"about_ca_system_score_gemma":0.00037311664,"threshold_uncertainty_score":0.99992746},"labels":[],"label_agreement":null},{"id":"W4247675585","doi":"10.1352/1944-7558-114.6","title":"Résumés en Français","year":2009,"lang":"fr","type":"article","venue":"American Journal on Intellectual and Developmental Disabilities","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Icon; Citation; Computer science; Download; World Wide Web; Information retrieval; Programming language","score_opus":0.030274512467821476,"score_gpt":0.2697937082398396,"score_spread":0.23951919577201813,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4247675585","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.90788007,0.0017492026,0.024416748,0.028879544,0.0013227282,0.00023551089,0.000019194007,0.00010165285,0.035395373],"genre_scores_gemma":[0.97730136,0.0009832544,0.008403465,0.0030361363,0.0002634965,0.0000055233872,0.000003068096,0.000012958002,0.009990717],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99739915,0.0003909637,0.0006521115,0.0005179319,0.00046491445,0.0005749218],"domain_scores_gemma":[0.99640507,0.0027171539,0.00010588065,0.0002346091,0.00012843464,0.00040885486],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0005470947,0.0003722055,0.00045105696,0.00016079754,0.0005396752,0.0005894442,0.0005132218,0.00009048593,0.0021418089],"category_scores_gemma":[0.001938799,0.00032561994,0.00015187259,0.00051843125,0.0015627027,0.0007366581,0.0001124683,0.0006520655,0.0017627672],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012343051,0.00035936377,0.0010660909,0.000016021273,0.00004360392,0.0000073948663,0.11654273,0.000011283173,0.00006925202,0.027169662,0.012261106,0.84233004],"study_design_scores_gemma":[0.0009269,0.0110361865,0.10677272,0.00061477016,0.00005234726,0.0049418076,0.12857264,0.0017898785,0.0017056623,0.07780811,0.6639065,0.0018724732],"about_ca_topic_score_codex":0.00017326693,"about_ca_topic_score_gemma":0.00001890158,"teacher_disagreement_score":0.8404576,"about_ca_system_score_codex":0.00035708866,"about_ca_system_score_gemma":0.00028958337,"threshold_uncertainty_score":0.9999196},"labels":[],"label_agreement":null},{"id":"W4248192047","doi":"10.1213/ane.0000000000002035","title":"In Response","year":2017,"lang":"en","type":"letter","venue":"Anesthesia & Analgesia","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"St. Paul's Hospital; University of Toronto; University of British Columbia","funders":"","keywords":"Medicine; The Internet; Service (business); Internet privacy; Public relations; Medical education; World Wide Web; Marketing; Political science; Computer science","score_opus":0.022249977290122406,"score_gpt":0.2663142338826563,"score_spread":0.2440642565925339,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4248192047","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005377444,0.00015948158,0.0022716124,0.99127245,0.00009336367,0.00023254498,8.881052e-7,0.00012315382,0.00046903337],"genre_scores_gemma":[0.03993467,0.00004103424,0.0030168968,0.94388103,0.0012230449,0.00009722175,0.000045641926,0.000056035817,0.011704426],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99731725,0.0005465891,0.00037719286,0.00083034683,0.00044680675,0.00048179209],"domain_scores_gemma":[0.99636847,0.00034098516,0.00029039435,0.0028706437,0.000070379334,0.000059126076],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0010632579,0.00031832117,0.00042918592,0.00035588862,0.00017257218,0.00043113544,0.0029749516,0.00076528644,0.000031892196],"category_scores_gemma":[0.00010746146,0.00030927442,0.00016340739,0.00023306212,0.0001157511,0.0006726992,0.00008974741,0.0011149548,0.00046552022],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030051022,0.000028805798,0.00031003144,0.000035999048,0.000008999701,0.008245186,0.00025110683,0.0000017729571,0.000028828763,0.0019934345,0.98635346,0.0027123005],"study_design_scores_gemma":[0.00011592822,0.000049842354,0.036513112,0.000046607143,0.0000073789743,0.00056050235,0.000002330448,0.0002803957,0.00004190109,0.0044896444,0.9575385,0.0003538732],"about_ca_topic_score_codex":0.00022870336,"about_ca_topic_score_gemma":0.00001703561,"teacher_disagreement_score":0.04739145,"about_ca_system_score_codex":0.00013210776,"about_ca_system_score_gemma":0.000282689,"threshold_uncertainty_score":0.9999359},"labels":[],"label_agreement":null},{"id":"W4248432020","doi":"10.1352/1944-7558-118.3.244","title":"Résumés en Français","year":2013,"lang":"fr","type":"article","venue":"American Journal on Intellectual and Developmental Disabilities","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Icon; Citation; Computer science; Information retrieval; Download; World Wide Web; Programming language","score_opus":0.028588327779737924,"score_gpt":0.2543272179324839,"score_spread":0.225738890152746,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4248432020","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9430592,0.0010057818,0.014315112,0.016208341,0.0012833717,0.00030967605,0.000012911578,0.00007322524,0.023732351],"genre_scores_gemma":[0.9700173,0.0007580533,0.00929735,0.001779656,0.00023874959,0.000035932608,0.0000030345377,0.000021360183,0.017848546],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99732995,0.00043260475,0.00067288236,0.00051275716,0.00045052063,0.00060126197],"domain_scores_gemma":[0.9950393,0.003952203,0.00010849876,0.00024324619,0.00019420958,0.00046252937],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00042644414,0.00037405774,0.00043725126,0.00015271874,0.0005260183,0.0008888847,0.00053169625,0.000091321956,0.010477966],"category_scores_gemma":[0.0020402921,0.000316786,0.00014212572,0.00046291194,0.0023045305,0.0011182557,0.00023863695,0.00063943927,0.009186754],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004456506,0.00029145778,0.003946109,0.000037810696,0.000079479476,0.0000031171398,0.13108833,0.000008105335,0.000085160806,0.013218143,0.033213563,0.81798416],"study_design_scores_gemma":[0.0007967802,0.005138225,0.115407325,0.0005560149,0.000043067896,0.003631956,0.24168189,0.0032367252,0.0013898985,0.054947883,0.5712794,0.0018908469],"about_ca_topic_score_codex":0.0013174646,"about_ca_topic_score_gemma":0.000035021003,"teacher_disagreement_score":0.8160933,"about_ca_system_score_codex":0.00034097352,"about_ca_system_score_gemma":0.0002706031,"threshold_uncertainty_score":0.9999284},"labels":[],"label_agreement":null},{"id":"W4248761357","doi":"10.1352/1944-7558-119.3.287","title":"Résumés en Français","year":2014,"lang":"fr","type":"article","venue":"American Journal on Intellectual and Developmental Disabilities","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Icon; Citation; Computer science; Information retrieval; Download; World Wide Web; Programming language","score_opus":0.027124249413381492,"score_gpt":0.25782087402685094,"score_spread":0.23069662461346946,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4248761357","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.86030024,0.0007433134,0.08208672,0.013467157,0.0018663787,0.00019614497,0.000015453528,0.00009184851,0.041232757],"genre_scores_gemma":[0.9772359,0.0005133071,0.009337351,0.0018056182,0.0003446982,0.000011595238,0.0000030511987,0.00002094072,0.010727531],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99714833,0.0006685949,0.0006389081,0.0005300065,0.00045935236,0.00055478455],"domain_scores_gemma":[0.9934653,0.0056185396,0.00011282218,0.00025849984,0.00013225977,0.00041255623],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00087443285,0.00036331255,0.00046290792,0.00014950732,0.00056092854,0.00056953385,0.0005285821,0.00008947845,0.0023758353],"category_scores_gemma":[0.003760455,0.00031564958,0.000143677,0.00042995223,0.0022488113,0.0006060984,0.00021853708,0.000620703,0.0026737824],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009246776,0.00024413806,0.0031212973,0.000040642888,0.00006039234,0.0000020430755,0.10870999,0.000016503649,0.000043122964,0.043721046,0.010688319,0.83326006],"study_design_scores_gemma":[0.00053783145,0.003962043,0.028755125,0.00034195697,0.000030393545,0.0018170287,0.058915503,0.0036224327,0.00078580866,0.030382404,0.8698164,0.0010330433],"about_ca_topic_score_codex":0.00034151567,"about_ca_topic_score_gemma":0.00004387284,"teacher_disagreement_score":0.8591281,"about_ca_system_score_codex":0.00028726918,"about_ca_system_score_gemma":0.0002148369,"threshold_uncertainty_score":0.99992955},"labels":[],"label_agreement":null},{"id":"W4250007667","doi":"10.1352/1944-7558-118.6.496","title":"Résumés en Français","year":2013,"lang":"fr","type":"article","venue":"American Journal on Intellectual and Developmental Disabilities","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Icon; Citation; Computer science; Download; Information retrieval; World Wide Web; Programming language","score_opus":0.028588327779737924,"score_gpt":0.2543272179324839,"score_spread":0.225738890152746,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4250007667","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9430592,0.0010057818,0.014315112,0.016208341,0.0012833717,0.00030967605,0.000012911578,0.00007322524,0.023732351],"genre_scores_gemma":[0.9700173,0.0007580533,0.00929735,0.001779656,0.00023874959,0.000035932608,0.0000030345377,0.000021360183,0.017848546],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99732995,0.00043260475,0.00067288236,0.00051275716,0.00045052063,0.00060126197],"domain_scores_gemma":[0.9950393,0.003952203,0.00010849876,0.00024324619,0.00019420958,0.00046252937],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00042644414,0.00037405774,0.00043725126,0.00015271874,0.0005260183,0.0008888847,0.00053169625,0.000091321956,0.010477966],"category_scores_gemma":[0.0020402921,0.000316786,0.00014212572,0.00046291194,0.0023045305,0.0011182557,0.00023863695,0.00063943927,0.009186754],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004456506,0.00029145778,0.003946109,0.000037810696,0.000079479476,0.0000031171398,0.13108833,0.000008105335,0.000085160806,0.013218143,0.033213563,0.81798416],"study_design_scores_gemma":[0.0007967802,0.005138225,0.115407325,0.0005560149,0.000043067896,0.003631956,0.24168189,0.0032367252,0.0013898985,0.054947883,0.5712794,0.0018908469],"about_ca_topic_score_codex":0.0013174646,"about_ca_topic_score_gemma":0.000035021003,"teacher_disagreement_score":0.8160933,"about_ca_system_score_codex":0.00034097352,"about_ca_system_score_gemma":0.0002706031,"threshold_uncertainty_score":0.9999284},"labels":[],"label_agreement":null},{"id":"W4251591461","doi":"10.1352/1934-9556-53.4.319","title":"Résumés en Français","year":2015,"lang":"fr","type":"article","venue":"Intellectual and developmental disabilities","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Icon; Citation; Download; Computer science; Information retrieval; World Wide Web; Programming language","score_opus":0.09478286869654018,"score_gpt":0.2827716178574192,"score_spread":0.18798874916087904,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4251591461","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.67077893,0.009731039,0.05334058,0.01346716,0.003731926,0.00065164326,0.00006712935,0.0003437347,0.24788786],"genre_scores_gemma":[0.8933431,0.00021063676,0.010254884,0.0004656541,0.00017480148,0.000038093054,0.000014754391,0.00001709368,0.095480986],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.997912,0.00022950159,0.00045676396,0.00058524736,0.00037185987,0.00044461773],"domain_scores_gemma":[0.9970323,0.0021483358,0.000023176715,0.00026904955,0.00015981476,0.0003673482],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0005621926,0.00029553444,0.00028349255,0.00007512801,0.00019384845,0.00036563183,0.0004197046,0.00019088962,0.0027699894],"category_scores_gemma":[0.004153178,0.00028213972,0.000070682305,0.00031613378,0.0010922124,0.00088699226,0.00049884256,0.0002371413,0.01101127],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006661903,0.0003491809,0.007820163,0.00017927206,0.00005557155,0.0000038105145,0.5582873,0.000008883572,0.00006544535,0.086658485,0.13310155,0.21340372],"study_design_scores_gemma":[0.00042746076,0.0003089737,0.006617517,0.00010091677,0.000014536654,0.00027314623,0.054462288,0.0026552037,0.0014547793,0.05151842,0.88154256,0.00062419206],"about_ca_topic_score_codex":0.0012969788,"about_ca_topic_score_gemma":0.00026111846,"teacher_disagreement_score":0.74844104,"about_ca_system_score_codex":0.00030060275,"about_ca_system_score_gemma":0.00044415178,"threshold_uncertainty_score":0.9999631},"labels":[],"label_agreement":null},{"id":"W4253230338","doi":"10.1352/1944-7558-125.5.408","title":"Résumés en Français","year":2020,"lang":"fr","type":"article","venue":"American Journal on Intellectual and Developmental Disabilities","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Icon; Citation; Computer science; Download; Information retrieval; World Wide Web; Programming language","score_opus":0.047592453534489626,"score_gpt":0.2646375348734983,"score_spread":0.21704508133900866,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4253230338","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8510705,0.0017157714,0.04710985,0.0774095,0.0012343668,0.0002775644,0.00004026557,0.00012651064,0.02101563],"genre_scores_gemma":[0.98156524,0.0008233889,0.007769083,0.006065475,0.0003854021,0.000009560551,0.000003407553,0.000021475782,0.0033569424],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99742776,0.0004224993,0.0006368067,0.0005600519,0.00045422555,0.00049863226],"domain_scores_gemma":[0.995831,0.0031470754,0.00010337843,0.00016376897,0.00011643704,0.00063832774],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00035444958,0.00035632856,0.00046265646,0.00008164131,0.00044922307,0.00053805986,0.00054223114,0.000079323305,0.0035794126],"category_scores_gemma":[0.0033135696,0.00031651664,0.00014933546,0.0005675127,0.0019067118,0.0006496587,0.00026332468,0.00070083665,0.0032521382],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020437237,0.00020417155,0.0029213908,0.000065202694,0.00009237497,0.000010446894,0.3185837,0.000022043372,0.000090729496,0.014842867,0.024041314,0.6389214],"study_design_scores_gemma":[0.0006278149,0.005477328,0.014539586,0.00026443324,0.000038072263,0.0014123607,0.16580577,0.0038299414,0.0012444973,0.007738788,0.79786164,0.0011597611],"about_ca_topic_score_codex":0.00019461456,"about_ca_topic_score_gemma":0.000014589192,"teacher_disagreement_score":0.77382034,"about_ca_system_score_codex":0.00022756703,"about_ca_system_score_gemma":0.00032091912,"threshold_uncertainty_score":0.9999287},"labels":[],"label_agreement":null},{"id":"W4253508568","doi":"10.1352/1944-7558-118.2.177","title":"Résumés en Français","year":2013,"lang":"fr","type":"article","venue":"American Journal on Intellectual and Developmental Disabilities","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Icon; Citation; Computer science; Information retrieval; Download; World Wide Web; Programming language","score_opus":0.028588327779737924,"score_gpt":0.2543272179324839,"score_spread":0.225738890152746,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4253508568","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9430592,0.0010057818,0.014315112,0.016208341,0.0012833717,0.00030967605,0.000012911578,0.00007322524,0.023732351],"genre_scores_gemma":[0.9700173,0.0007580533,0.00929735,0.001779656,0.00023874959,0.000035932608,0.0000030345377,0.000021360183,0.017848546],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99732995,0.00043260475,0.00067288236,0.00051275716,0.00045052063,0.00060126197],"domain_scores_gemma":[0.9950393,0.003952203,0.00010849876,0.00024324619,0.00019420958,0.00046252937],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00042644414,0.00037405774,0.00043725126,0.00015271874,0.0005260183,0.0008888847,0.00053169625,0.000091321956,0.010477966],"category_scores_gemma":[0.0020402921,0.000316786,0.00014212572,0.00046291194,0.0023045305,0.0011182557,0.00023863695,0.00063943927,0.009186754],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004456506,0.00029145778,0.003946109,0.000037810696,0.000079479476,0.0000031171398,0.13108833,0.000008105335,0.000085160806,0.013218143,0.033213563,0.81798416],"study_design_scores_gemma":[0.0007967802,0.005138225,0.115407325,0.0005560149,0.000043067896,0.003631956,0.24168189,0.0032367252,0.0013898985,0.054947883,0.5712794,0.0018908469],"about_ca_topic_score_codex":0.0013174646,"about_ca_topic_score_gemma":0.000035021003,"teacher_disagreement_score":0.8160933,"about_ca_system_score_codex":0.00034097352,"about_ca_system_score_gemma":0.0002706031,"threshold_uncertainty_score":0.9999284},"labels":[],"label_agreement":null},{"id":"W4253921612","doi":"10.1352/1944-7558-124.6.583","title":"Résumés en Français","year":2019,"lang":"fr","type":"article","venue":"American Journal on Intellectual and Developmental Disabilities","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Icon; Citation; Computer science; Information retrieval; Download; World Wide Web; Programming language","score_opus":0.024980033049128787,"score_gpt":0.25661534380090545,"score_spread":0.23163531075177665,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4253921612","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95333254,0.00085998,0.0056969225,0.006590141,0.0018125117,0.00023596686,0.000016589996,0.000054753436,0.03140058],"genre_scores_gemma":[0.9643634,0.00066422776,0.004861786,0.0013424867,0.00018067966,0.000009416711,0.0000033881045,0.000020992138,0.028553613],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99737144,0.00040812435,0.0006196991,0.0005613784,0.000484128,0.0005552549],"domain_scores_gemma":[0.9951147,0.0040292004,0.00011047414,0.00027537355,0.0001268826,0.0003433622],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00057760667,0.0003605169,0.0004779224,0.0001543849,0.00033600174,0.00052895024,0.0005277126,0.00009209981,0.0075681657],"category_scores_gemma":[0.0012923306,0.00031390353,0.00015350616,0.00046988906,0.0014617131,0.0007512815,0.00024119826,0.00066155166,0.00935526],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020572949,0.00038659637,0.01825754,0.000087683526,0.00012333061,0.000005811264,0.18915,0.000029765302,0.000140554,0.033201694,0.011616052,0.74679524],"study_design_scores_gemma":[0.00084946526,0.005431806,0.058391724,0.00057545485,0.00003326988,0.0027178046,0.16247779,0.0021533354,0.0011564075,0.016668566,0.7481156,0.0014287616],"about_ca_topic_score_codex":0.00033523754,"about_ca_topic_score_gemma":0.000025566822,"teacher_disagreement_score":0.74536645,"about_ca_system_score_codex":0.00036853526,"about_ca_system_score_gemma":0.00033058846,"threshold_uncertainty_score":0.9999313},"labels":[],"label_agreement":null},{"id":"W4254058603","doi":"10.1352/1944-7558-124.4.391","title":"Résumés en Français","year":2019,"lang":"fr","type":"article","venue":"American Journal on Intellectual and Developmental Disabilities","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Icon; Citation; Computer science; Download; Information retrieval; World Wide Web; Programming language","score_opus":0.024980033049128787,"score_gpt":0.25661534380090545,"score_spread":0.23163531075177665,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4254058603","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95333254,0.00085998,0.0056969225,0.006590141,0.0018125117,0.00023596686,0.000016589996,0.000054753436,0.03140058],"genre_scores_gemma":[0.9643634,0.00066422776,0.004861786,0.0013424867,0.00018067966,0.000009416711,0.0000033881045,0.000020992138,0.028553613],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99737144,0.00040812435,0.0006196991,0.0005613784,0.000484128,0.0005552549],"domain_scores_gemma":[0.9951147,0.0040292004,0.00011047414,0.00027537355,0.0001268826,0.0003433622],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00057760667,0.0003605169,0.0004779224,0.0001543849,0.00033600174,0.00052895024,0.0005277126,0.00009209981,0.0075681657],"category_scores_gemma":[0.0012923306,0.00031390353,0.00015350616,0.00046988906,0.0014617131,0.0007512815,0.00024119826,0.00066155166,0.00935526],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020572949,0.00038659637,0.01825754,0.000087683526,0.00012333061,0.000005811264,0.18915,0.000029765302,0.000140554,0.033201694,0.011616052,0.74679524],"study_design_scores_gemma":[0.00084946526,0.005431806,0.058391724,0.00057545485,0.00003326988,0.0027178046,0.16247779,0.0021533354,0.0011564075,0.016668566,0.7481156,0.0014287616],"about_ca_topic_score_codex":0.00033523754,"about_ca_topic_score_gemma":0.000025566822,"teacher_disagreement_score":0.74536645,"about_ca_system_score_codex":0.00036853526,"about_ca_system_score_gemma":0.00033058846,"threshold_uncertainty_score":0.9999313},"labels":[],"label_agreement":null},{"id":"W4254390547","doi":"10.1352/1944-7558-121.1.74","title":"Résumés en Français","year":2015,"lang":"fr","type":"article","venue":"American Journal on Intellectual and Developmental Disabilities","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Icon; Citation; Computer science; Download; Information retrieval; World Wide Web; Programming language","score_opus":0.061060970991956474,"score_gpt":0.2826934995018871,"score_spread":0.22163252850993062,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4254390547","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91487396,0.0020378465,0.026114592,0.014950391,0.0024381732,0.00022749392,0.000024086947,0.000093678165,0.039239783],"genre_scores_gemma":[0.9728053,0.0005015339,0.010183538,0.0013933771,0.0003199244,0.00001287884,0.000003832863,0.00002142794,0.01475816],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9972207,0.00052883703,0.0006325637,0.0004948498,0.0005801986,0.00054287264],"domain_scores_gemma":[0.99580896,0.002911811,0.00010726655,0.00023578598,0.00022891277,0.0007072707],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0008865163,0.00035574083,0.00044358708,0.00015313253,0.00035830427,0.00058140507,0.00051956257,0.00008914672,0.0012776308],"category_scores_gemma":[0.0039566206,0.0003085063,0.00012106462,0.0005122463,0.0022359977,0.0007863705,0.0002561762,0.00060922065,0.0030923507],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020565308,0.00036697357,0.0046170363,0.000029998579,0.000084651,0.000010510719,0.28633434,0.000028238766,0.000018346082,0.02049844,0.041505277,0.64630055],"study_design_scores_gemma":[0.00073028647,0.004304727,0.0105463015,0.0002662881,0.000029392831,0.0031602108,0.2261044,0.0014452534,0.00053015276,0.028232576,0.72366875,0.0009816556],"about_ca_topic_score_codex":0.000552922,"about_ca_topic_score_gemma":0.00004911855,"teacher_disagreement_score":0.6821635,"about_ca_system_score_codex":0.00054055796,"about_ca_system_score_gemma":0.000635389,"threshold_uncertainty_score":0.9999367},"labels":[],"label_agreement":null},{"id":"W4254490885","doi":"10.1352/1944-7558-122.5.453","title":"Résumés en Français","year":2017,"lang":"fr","type":"article","venue":"American Journal on Intellectual and Developmental Disabilities","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Icon; Citation; Computer science; Download; World Wide Web; Information retrieval; Programming language","score_opus":0.0464597806764474,"score_gpt":0.2915915235032005,"score_spread":0.2451317428267531,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4254490885","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91707695,0.00084920163,0.011891429,0.020789389,0.002320129,0.00020032648,0.00002782175,0.000055700282,0.046789065],"genre_scores_gemma":[0.97400427,0.0010242452,0.005933802,0.0008061487,0.00032106636,0.00001150663,0.0000019417969,0.000019154599,0.01787787],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9975727,0.00031241114,0.00057712686,0.0005365565,0.00044923986,0.00055192783],"domain_scores_gemma":[0.9960448,0.002675311,0.0002143251,0.00051890453,0.00014268908,0.0004039583],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["sts","insufficient_payload"],"category_scores_codex":[0.0006665321,0.0003605583,0.00045703602,0.00010984928,0.0019891039,0.0018490455,0.0010762566,0.00009227952,0.0023695612],"category_scores_gemma":[0.005016123,0.0003145766,0.00015510665,0.0001368129,0.0041636196,0.0012118537,0.00045192786,0.0006490187,0.0022762758],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012609294,0.00026071453,0.01022268,0.000038907692,0.000091054426,0.000010768964,0.11238311,0.0000043850687,0.000040384028,0.023706045,0.010929266,0.84218657],"study_design_scores_gemma":[0.00083421724,0.003547395,0.20904012,0.00062787347,0.000046839086,0.0028535991,0.089843854,0.0013472972,0.0012357912,0.03255455,0.6566171,0.0014513398],"about_ca_topic_score_codex":0.0008645926,"about_ca_topic_score_gemma":0.00009715828,"teacher_disagreement_score":0.84073526,"about_ca_system_score_codex":0.0003028153,"about_ca_system_score_gemma":0.00032286794,"threshold_uncertainty_score":0.9999306},"labels":[],"label_agreement":null},{"id":"W4254531792","doi":"10.1352/1944-7558-115.3.263","title":"Résumés en Français","year":2010,"lang":"fr","type":"article","venue":"American Journal on Intellectual and Developmental Disabilities","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Icon; Citation; Computer science; Information retrieval; Download; World Wide Web; Programming language","score_opus":0.02520750867445705,"score_gpt":0.26460478443402835,"score_spread":0.23939727575957132,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4254531792","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9578135,0.00034195554,0.008458492,0.009966756,0.0027652562,0.00016131617,0.000019975063,0.000065257664,0.02040748],"genre_scores_gemma":[0.9744401,0.00040275988,0.012788062,0.0011549997,0.00039191314,0.000013142426,0.000003143044,0.000021282605,0.010784588],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9975306,0.00030107697,0.0006247596,0.00052861363,0.00045382298,0.0005611202],"domain_scores_gemma":[0.9948061,0.004188906,0.00010852913,0.00028302247,0.00015376965,0.00045964256],"candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00068935513,0.0003660307,0.00041560043,0.0001568779,0.00059743936,0.0006474114,0.0005921692,0.000120791614,0.0053445604],"category_scores_gemma":[0.0032914127,0.0003177531,0.00014643175,0.00045149773,0.0030093295,0.0007098664,0.00023204088,0.0012767366,0.0025722403],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010707471,0.00036287555,0.005346754,0.000033908113,0.000071122995,0.000006968118,0.13831905,0.000003927026,0.00052596576,0.04135339,0.011092347,0.80277663],"study_design_scores_gemma":[0.00054493925,0.0026849248,0.046970922,0.0002037303,0.00003242623,0.0043683746,0.07746862,0.0011307964,0.0023903872,0.025043923,0.83796066,0.001200294],"about_ca_topic_score_codex":0.0004306712,"about_ca_topic_score_gemma":0.00017068579,"teacher_disagreement_score":0.8268683,"about_ca_system_score_codex":0.00016630505,"about_ca_system_score_gemma":0.00037311664,"threshold_uncertainty_score":0.99992746},"labels":[],"label_agreement":null},{"id":"W4255180076","doi":"10.2196/preprints.33335","title":"A Virtual Community for Disability Advocacy: Development of a Searchable Artificial Intelligence–Supported Platform (Preprint)","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Women's and Gender Studies et Recherches Féministes; York University","funders":"","keywords":"Upload; World Wide Web; Computer science; International Classification of Functioning, Disability and Health; Internet privacy; Psychology","score_opus":0.12819739944544545,"score_gpt":0.33898675826110564,"score_spread":0.2107893588156602,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4255180076","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.42802826,0.0000067162046,0.57029307,0.00024451315,0.00018947296,0.00091843493,0.000012368014,0.000120433906,0.00018670484],"genre_scores_gemma":[0.78741854,0.0000030351455,0.21196312,0.000030059437,0.000023023233,0.00031059267,0.00019769795,0.00001091178,0.000042994252],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9964692,0.00030032842,0.001386701,0.0008745339,0.0005386276,0.00043060214],"domain_scores_gemma":[0.99506986,0.0009069882,0.00036075275,0.002866233,0.00062377227,0.00017237471],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0038229714,0.00033119813,0.0006217505,0.00009569988,0.00038874766,0.00026486852,0.0023878543,0.00036101977,0.00013002167],"category_scores_gemma":[0.00065077416,0.00032324388,0.00029638156,0.0003378552,0.00032266648,0.00032673994,0.004291204,0.0009918949,0.000012311674],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009322515,0.00246688,0.0006313791,0.0008815528,0.00013464077,7.8768437e-7,0.04075756,0.002078214,0.0014365317,0.061006635,0.00002515248,0.89048743],"study_design_scores_gemma":[0.00025437048,0.00040618572,0.01904067,0.0003715984,0.000043020034,0.00000808463,0.021678425,0.25402707,0.40803126,0.29411373,0.00067218376,0.001353433],"about_ca_topic_score_codex":0.0008822869,"about_ca_topic_score_gemma":0.0019045838,"teacher_disagreement_score":0.889134,"about_ca_system_score_codex":0.00039426264,"about_ca_system_score_gemma":0.0023669922,"threshold_uncertainty_score":0.999922},"labels":[],"label_agreement":null},{"id":"W4255464461","doi":"10.1352/1944-7558-119.2.199","title":"Résumés en Français","year":2014,"lang":"fr","type":"article","venue":"American Journal on Intellectual and Developmental Disabilities","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Icon; Citation; Computer science; Information retrieval; Download; World Wide Web; Programming language","score_opus":0.027124249413381492,"score_gpt":0.25782087402685094,"score_spread":0.23069662461346946,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4255464461","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.86030024,0.0007433134,0.08208672,0.013467157,0.0018663787,0.00019614497,0.000015453528,0.00009184851,0.041232757],"genre_scores_gemma":[0.9772359,0.0005133071,0.009337351,0.0018056182,0.0003446982,0.000011595238,0.0000030511987,0.00002094072,0.010727531],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99714833,0.0006685949,0.0006389081,0.0005300065,0.00045935236,0.00055478455],"domain_scores_gemma":[0.9934653,0.0056185396,0.00011282218,0.00025849984,0.00013225977,0.00041255623],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00087443285,0.00036331255,0.00046290792,0.00014950732,0.00056092854,0.00056953385,0.0005285821,0.00008947845,0.0023758353],"category_scores_gemma":[0.003760455,0.00031564958,0.000143677,0.00042995223,0.0022488113,0.0006060984,0.00021853708,0.000620703,0.0026737824],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009246776,0.00024413806,0.0031212973,0.000040642888,0.00006039234,0.0000020430755,0.10870999,0.000016503649,0.000043122964,0.043721046,0.010688319,0.83326006],"study_design_scores_gemma":[0.00053783145,0.003962043,0.028755125,0.00034195697,0.000030393545,0.0018170287,0.058915503,0.0036224327,0.00078580866,0.030382404,0.8698164,0.0010330433],"about_ca_topic_score_codex":0.00034151567,"about_ca_topic_score_gemma":0.00004387284,"teacher_disagreement_score":0.8591281,"about_ca_system_score_codex":0.00028726918,"about_ca_system_score_gemma":0.0002148369,"threshold_uncertainty_score":0.99992955},"labels":[],"label_agreement":null},{"id":"W4256075605","doi":"10.1352/1944-7558-122.3.282","title":"Résumés en Français","year":2017,"lang":"fr","type":"article","venue":"American Journal on Intellectual and Developmental Disabilities","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Icon; Citation; Computer science; Download; World Wide Web; Information retrieval; Programming language","score_opus":0.0464597806764474,"score_gpt":0.2915915235032005,"score_spread":0.2451317428267531,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4256075605","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91707695,0.00084920163,0.011891429,0.020789389,0.002320129,0.00020032648,0.00002782175,0.000055700282,0.046789065],"genre_scores_gemma":[0.97400427,0.0010242452,0.005933802,0.0008061487,0.00032106636,0.00001150663,0.0000019417969,0.000019154599,0.01787787],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9975727,0.00031241114,0.00057712686,0.0005365565,0.00044923986,0.00055192783],"domain_scores_gemma":[0.9960448,0.002675311,0.0002143251,0.00051890453,0.00014268908,0.0004039583],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["sts","insufficient_payload"],"category_scores_codex":[0.0006665321,0.0003605583,0.00045703602,0.00010984928,0.0019891039,0.0018490455,0.0010762566,0.00009227952,0.0023695612],"category_scores_gemma":[0.005016123,0.0003145766,0.00015510665,0.0001368129,0.0041636196,0.0012118537,0.00045192786,0.0006490187,0.0022762758],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012609294,0.00026071453,0.01022268,0.000038907692,0.000091054426,0.000010768964,0.11238311,0.0000043850687,0.000040384028,0.023706045,0.010929266,0.84218657],"study_design_scores_gemma":[0.00083421724,0.003547395,0.20904012,0.00062787347,0.000046839086,0.0028535991,0.089843854,0.0013472972,0.0012357912,0.03255455,0.6566171,0.0014513398],"about_ca_topic_score_codex":0.0008645926,"about_ca_topic_score_gemma":0.00009715828,"teacher_disagreement_score":0.84073526,"about_ca_system_score_codex":0.0003028153,"about_ca_system_score_gemma":0.00032286794,"threshold_uncertainty_score":0.9999306},"labels":[],"label_agreement":null},{"id":"W4256502487","doi":"10.1352/1944-7558-125.3.243","title":"Résumés en Français","year":2020,"lang":"fr","type":"article","venue":"American Journal on Intellectual and Developmental Disabilities","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Icon; Citation; Computer science; Download; Information retrieval; World Wide Web; Programming language","score_opus":0.047592453534489626,"score_gpt":0.2646375348734983,"score_spread":0.21704508133900866,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4256502487","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8510705,0.0017157714,0.04710985,0.0774095,0.0012343668,0.0002775644,0.00004026557,0.00012651064,0.02101563],"genre_scores_gemma":[0.98156524,0.0008233889,0.007769083,0.006065475,0.0003854021,0.000009560551,0.000003407553,0.000021475782,0.0033569424],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99742776,0.0004224993,0.0006368067,0.0005600519,0.00045422555,0.00049863226],"domain_scores_gemma":[0.995831,0.0031470754,0.00010337843,0.00016376897,0.00011643704,0.00063832774],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00035444958,0.00035632856,0.00046265646,0.00008164131,0.00044922307,0.00053805986,0.00054223114,0.000079323305,0.0035794126],"category_scores_gemma":[0.0033135696,0.00031651664,0.00014933546,0.0005675127,0.0019067118,0.0006496587,0.00026332468,0.00070083665,0.0032521382],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020437237,0.00020417155,0.0029213908,0.000065202694,0.00009237497,0.000010446894,0.3185837,0.000022043372,0.000090729496,0.014842867,0.024041314,0.6389214],"study_design_scores_gemma":[0.0006278149,0.005477328,0.014539586,0.00026443324,0.000038072263,0.0014123607,0.16580577,0.0038299414,0.0012444973,0.007738788,0.79786164,0.0011597611],"about_ca_topic_score_codex":0.00019461456,"about_ca_topic_score_gemma":0.000014589192,"teacher_disagreement_score":0.77382034,"about_ca_system_score_codex":0.00022756703,"about_ca_system_score_gemma":0.00032091912,"threshold_uncertainty_score":0.9999287},"labels":[],"label_agreement":null},{"id":"W4281926114","doi":"10.4018/978-1-7998-4736-6.ch009","title":"Implementing UN CRDP Through Human Interface Equivalencies (HIEs) With Semantic Interoperability","year":2022,"lang":"en","type":"book-chapter","venue":"Advances in educational technologies and instructional design book series","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"EnGlobe (Canada)","funders":"","keywords":"Interoperability; Semantic interoperability; Computer science; Interface (matter); Context (archaeology); Software engineering; Knowledge management; World Wide Web; Geography","score_opus":0.025571319730915865,"score_gpt":0.28002045834929856,"score_spread":0.2544491386183827,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4281926114","genre_codex":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023738965,0.14000757,0.38214558,0.054165766,0.0042924085,0.006987286,0.00042000183,0.0047334586,0.38350898],"genre_scores_gemma":[0.38839674,0.04882799,0.5013818,0.00041022198,0.00026026682,0.001416017,0.00026812652,0.00015582032,0.058883023],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9975955,0.000052335145,0.0006102805,0.0009353812,0.0004365777,0.00036995736],"domain_scores_gemma":[0.9984938,0.0002453722,0.0003752882,0.0006865164,0.00017082843,0.000028206541],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00032835343,0.00041425906,0.00039322895,0.0002556249,0.0007513674,0.00015013175,0.00093995564,0.00017772274,0.00040652798],"category_scores_gemma":[0.00007754824,0.00037537588,0.00006486439,0.00017651237,0.0011137818,0.0040774103,0.00087373203,0.0006180853,0.00000483276],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029672663,0.000039545404,0.00017245577,0.00009915166,0.000034174718,0.0000017039063,0.00037185557,0.000129409,0.00011630376,0.9523567,0.000086001826,0.04656305],"study_design_scores_gemma":[0.00013546768,0.00030418424,0.00044774165,0.00011336764,0.000011962624,0.00017132972,0.0011893329,0.000023394305,0.00066683296,0.6917666,0.30477417,0.00039558695],"about_ca_topic_score_codex":0.000023896142,"about_ca_topic_score_gemma":0.000089405796,"teacher_disagreement_score":0.3646578,"about_ca_system_score_codex":0.0003437223,"about_ca_system_score_gemma":0.00023520782,"threshold_uncertainty_score":0.9998698},"labels":[],"label_agreement":null},{"id":"W4284885746","doi":"10.1037/cep0000287","title":"Constituent processing in compound and pseudocompound words.","year":2022,"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":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Priming (agriculture); Seabird; Compound; PsycINFO; Word (group theory); Semantics (computer science); Psychology; Computer science; Natural language processing; Linguistics; Chemistry; Biology; Ecology; MEDLINE; Biochemistry","score_opus":0.03691423754906093,"score_gpt":0.29734344383234684,"score_spread":0.2604292062832859,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4284885746","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9851542,0.0054174787,0.002159142,0.0029455163,0.0014331379,0.00031733426,0.000019244477,0.000023160845,0.0025307918],"genre_scores_gemma":[0.99238586,0.00001322871,0.0052649453,0.0021414754,0.00006783059,0.000056412566,0.000006694297,0.000018106119,0.000045466863],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99742925,0.00026952886,0.0006834213,0.0006098511,0.00011581043,0.0008921265],"domain_scores_gemma":[0.99809724,0.000051778632,0.0003447884,0.0005417478,0.000052453106,0.0009120015],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011544216,0.00024593784,0.0003687371,0.0007108059,0.00046575133,0.0001403929,0.0013631359,0.00009684299,0.00015668938],"category_scores_gemma":[0.000037197577,0.00028888008,0.000091219255,0.0005823515,0.00042533528,0.00047338262,0.000118930766,0.00062631845,0.000004535071],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007478135,0.0040223524,0.2934594,0.00012707796,0.00024255946,0.015225258,0.15772359,0.0013675137,0.32850608,0.06641972,0.029441081,0.10271758],"study_design_scores_gemma":[0.024089327,0.008928721,0.49429426,0.0005202268,0.00009516244,0.10921276,0.10980644,0.0047864877,0.015528176,0.04736066,0.18044516,0.004932626],"about_ca_topic_score_codex":0.0033996669,"about_ca_topic_score_gemma":0.015277019,"teacher_disagreement_score":0.3129779,"about_ca_system_score_codex":0.0017519903,"about_ca_system_score_gemma":0.000666361,"threshold_uncertainty_score":0.9999563},"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,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.07035566898821673,"score_gpt":0.3433580144822387,"score_spread":0.27300234549402197,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285793742","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98899275,0.0010897631,0.0027610606,0.0043673594,0.0000530876,0.0003953821,0.0000052084465,0.000035791454,0.002299572],"genre_scores_gemma":[0.9987834,0.000014118334,0.0002451121,0.0007540997,0.000028175558,0.00009432803,0.000016749307,0.00000164206,0.00006233972],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983601,0.000660178,0.00012548204,0.00021719046,0.00052795786,0.00010909271],"domain_scores_gemma":[0.9993416,0.00024300048,0.00006161502,0.00029482273,0.000022373837,0.000036573434],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023728167,0.000055348548,0.00006367545,0.000046011228,0.00024427916,0.0001566095,0.00042841383,0.00002048951,0.00008311733],"category_scores_gemma":[0.00017805184,0.000039969444,0.0000162361,0.00020023751,0.000027204742,0.00011885684,0.00011969925,0.00010854483,0.0000018225094],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000044009466,0.00022049202,0.008580747,0.0000722308,0.000013159212,0.00002467424,0.40206158,0.0058054356,0.0009459436,0.02996774,0.0012337456,0.5510303],"study_design_scores_gemma":[0.0015810891,0.00032104342,0.18366334,0.000012172772,0.000038780774,0.00015403844,0.07491803,0.47305793,0.00032817308,0.01562825,0.24985869,0.00043844982],"about_ca_topic_score_codex":0.0014163691,"about_ca_topic_score_gemma":0.00048282038,"teacher_disagreement_score":0.5505918,"about_ca_system_score_codex":0.00005352507,"about_ca_system_score_gemma":0.000077206016,"threshold_uncertainty_score":0.21411358},"labels":[],"label_agreement":null},{"id":"W4293055821","doi":"10.1352/1944-7558-127.4.345","title":"Résumés en Français","year":2022,"lang":"fr","type":"article","venue":"American Journal on Intellectual and Developmental Disabilities","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Icon; Citation; Computer science; Download; Information retrieval; World Wide Web; Programming language","score_opus":0.03253244248008126,"score_gpt":0.2609031443318721,"score_spread":0.22837070185179087,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4293055821","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9499124,0.001719269,0.009844736,0.016101,0.002421558,0.00025279584,0.000071103794,0.00008088446,0.01959625],"genre_scores_gemma":[0.9756961,0.00042239262,0.0038496112,0.0020485092,0.00017880023,0.000044985616,0.0000064231863,0.000021709968,0.017731495],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99676704,0.000863889,0.00062099507,0.0005345748,0.00067231664,0.0005411977],"domain_scores_gemma":[0.9955171,0.0037236987,0.00011997031,0.00023373733,0.000084490646,0.00032104808],"candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00085077656,0.00032247385,0.00040349,0.00018454755,0.0014657974,0.0004062619,0.00066735846,0.000041333606,0.011774195],"category_scores_gemma":[0.0013409567,0.00031167959,0.00015330421,0.00066827267,0.0016621448,0.00048512517,0.0006335591,0.000985514,0.00094300666],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021882723,0.0005492428,0.0032804972,0.000031272757,0.000098725206,0.000014578032,0.2580995,0.000118428994,0.00004746205,0.026726015,0.029222004,0.6815934],"study_design_scores_gemma":[0.000355567,0.003563141,0.009032539,0.00006074205,0.000019056957,0.0034304545,0.20370254,0.0011751708,0.0001925723,0.011693911,0.76610994,0.0006643744],"about_ca_topic_score_codex":0.00046667128,"about_ca_topic_score_gemma":0.000023895838,"teacher_disagreement_score":0.73688793,"about_ca_system_score_codex":0.0007319941,"about_ca_system_score_gemma":0.00043612983,"threshold_uncertainty_score":0.99993354},"labels":[],"label_agreement":null},{"id":"W4293797358","doi":"10.48550/arxiv.2208.12924","title":"Quantifying French Document Complexity","year":2022,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science; Contrast (vision); Task (project management); Natural language processing; Range (aeronautics); Linguistic sequence complexity; Measure (data warehouse); Artificial intelligence; Information retrieval; Linguistics; Data mining","score_opus":0.22118086501807158,"score_gpt":0.23909837313316293,"score_spread":0.017917508115091352,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4293797358","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27846524,0.000056425477,0.71558976,0.0003846307,0.00082910823,0.00035987844,0.000022686503,0.00040490515,0.0038873388],"genre_scores_gemma":[0.99425054,0.000050290942,0.0046264185,0.000089414156,0.000036133675,0.0000027210508,0.000052151136,0.000009858536,0.000882491],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99771714,0.00028902176,0.00023654387,0.0012758268,0.00015784976,0.00032359647],"domain_scores_gemma":[0.99743414,0.00011909319,0.00025348234,0.0019608212,0.00009424497,0.00013820377],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00047549163,0.00025683682,0.0002903471,0.00019442427,0.0003959594,0.0001915915,0.0026279562,0.00015657753,0.00035462214],"category_scores_gemma":[0.000028355069,0.00031725518,0.00021736941,0.000561317,0.0001299168,0.00037640703,0.0038719967,0.000729159,0.000089864785],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007805931,0.0001449412,0.0062671867,0.00009264826,0.000053354433,0.000085769476,0.0005844794,0.06947617,0.000035948062,0.92140627,0.000415513,0.0014299079],"study_design_scores_gemma":[0.00048268208,0.000091930015,0.040274393,0.000047798578,0.00006507084,0.000007866683,0.00019698849,0.41423073,0.0001938649,0.53247714,0.010924963,0.001006601],"about_ca_topic_score_codex":0.0010501775,"about_ca_topic_score_gemma":0.0001480943,"teacher_disagreement_score":0.71578526,"about_ca_system_score_codex":0.0004963443,"about_ca_system_score_gemma":0.00021840185,"threshold_uncertainty_score":0.99992794},"labels":[],"label_agreement":null},{"id":"W4294300070","doi":"10.21428/594757db.8b7cd94b","title":"Quantifying French Document Complexity","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université Laval","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Contrast (vision); Task (project management); Natural language processing; Range (aeronautics); Linguistic sequence complexity; Artificial intelligence; Measure (data warehouse); Information retrieval; Linguistics; Data mining","score_opus":0.15225465829946824,"score_gpt":0.346716417992687,"score_spread":0.19446175969321874,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4294300070","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018504648,0.00013797975,0.957716,0.0043043187,0.0014631638,0.00046124175,0.000012089639,0.00061929575,0.016781284],"genre_scores_gemma":[0.83355504,0.000017633301,0.16491039,0.00031472716,0.000050816714,0.000119620454,0.000074710755,0.0000075403473,0.0009495021],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9979788,0.00017737164,0.0003468821,0.00080530485,0.0004619423,0.00022971697],"domain_scores_gemma":[0.99778914,0.000092668204,0.00015627626,0.0018275992,0.00005775957,0.00007655302],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0006487063,0.00018517647,0.00023295748,0.000095374,0.00023909684,0.00038783086,0.002116781,0.00010044327,0.0012394895],"category_scores_gemma":[0.00002882905,0.00017962218,0.00013622464,0.00018191487,0.000052672447,0.00017952385,0.0045784544,0.0005959143,0.000075965516],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000011501687,0.00011877154,0.0017652288,0.0001142807,0.0000256712,0.0000043944465,0.0011418998,0.001118364,0.00005641644,0.96561897,0.0028654211,0.027169455],"study_design_scores_gemma":[0.00023046667,0.00007788025,0.102385364,0.000035345533,0.000017591592,0.000011977506,0.00013758818,0.07842498,0.0006457153,0.72390145,0.093118876,0.0010127833],"about_ca_topic_score_codex":0.0016364331,"about_ca_topic_score_gemma":0.0002297001,"teacher_disagreement_score":0.8150504,"about_ca_system_score_codex":0.00022221348,"about_ca_system_score_gemma":0.00017617851,"threshold_uncertainty_score":0.9996735},"labels":[],"label_agreement":null},{"id":"W4297831600","doi":"10.31234/osf.io/h3neu","title":"Contextual Dynamics in Lexical Encoding across the Aging Spectrum: A Simulation Study","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Word lists by frequency; Psycholinguistics; Psychology; Word recognition; Optimal distinctiveness theory; Operationalization; Word (group theory); Cognition; Cognitive psychology; Computer science; Linguistics; Natural language processing; Social psychology; Sentence","score_opus":0.05102747469442191,"score_gpt":0.35470628393747244,"score_spread":0.3036788092430505,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4297831600","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5371472,0.000019803594,0.45796785,0.0023004187,0.00040595638,0.0008865434,0.00000736623,0.00016445611,0.0011003859],"genre_scores_gemma":[0.9989112,0.0000025664237,0.0005927723,0.00012851116,0.000054197335,0.000101360856,0.000019171397,0.0000088654515,0.00018133741],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9975368,0.00042240648,0.00048740723,0.00077429466,0.00046755135,0.00031155878],"domain_scores_gemma":[0.997886,0.000627877,0.00016227966,0.0012468621,0.00003652297,0.00004045828],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018764911,0.00019981938,0.00025168265,0.00008624256,0.00035761387,0.0005134451,0.0017135232,0.00010088486,0.000046273723],"category_scores_gemma":[0.00011825979,0.00015764064,0.00009494462,0.00038086472,0.000054910583,0.00022267833,0.0030898906,0.0010274391,0.000008125379],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021089865,0.00089981814,0.1026003,0.0000399839,0.000037802536,0.000025710548,0.04266103,0.6512163,0.0000058895034,0.15638198,0.000012928291,0.04609712],"study_design_scores_gemma":[0.00018610788,0.00004642515,0.06870793,0.000008561415,0.0000037022157,0.0000018299637,0.00705153,0.9123054,0.0000043802343,0.011405792,0.00009672053,0.00018159069],"about_ca_topic_score_codex":0.001370531,"about_ca_topic_score_gemma":0.0062262127,"teacher_disagreement_score":0.46176398,"about_ca_system_score_codex":0.0008368156,"about_ca_system_score_gemma":0.00012363173,"threshold_uncertainty_score":0.64283985},"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,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Readability; Computer science; Natural language processing; Linguistics; Artificial intelligence; Set (abstract data type); Sentence; Vocabulary","score_opus":0.2309234669878421,"score_gpt":0.3783169797667931,"score_spread":0.14739351277895102,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4303437283","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7926846,0.052440476,0.14935465,0.004594233,0.00033241743,0.00045452846,0.000011849501,0.000087019536,0.000040206316],"genre_scores_gemma":[0.97876775,0.0017971457,0.019071182,0.00011143354,0.000111165034,0.00009629436,0.00001827877,0.000014049022,0.00001268461],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99367666,0.0034570107,0.00080849556,0.00061878096,0.0010719429,0.00036710553],"domain_scores_gemma":[0.9967119,0.0017237545,0.0002577466,0.00076974224,0.00040969026,0.00012717754],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005677468,0.00017378542,0.00039194073,0.00047076406,0.001148846,0.00024730884,0.0010678458,0.00004883869,0.00004459025],"category_scores_gemma":[0.0007047323,0.0001550102,0.00018458389,0.0018617683,0.00020033163,0.0008999239,0.000092286224,0.0010610261,0.000006649544],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009659707,0.00036532694,0.0036174906,0.00006136671,0.00017856088,0.000035647874,0.0044545033,0.005876519,0.015558919,0.010004977,0.00007119563,0.9596789],"study_design_scores_gemma":[0.0012108786,0.000509745,0.16975155,0.000094404924,0.00021020473,0.000094886615,0.0014764138,0.049606465,0.007966699,0.71816945,0.05018804,0.0007212292],"about_ca_topic_score_codex":0.00013387424,"about_ca_topic_score_gemma":0.00006530516,"teacher_disagreement_score":0.9589577,"about_ca_system_score_codex":0.0006582049,"about_ca_system_score_gemma":0.00022341321,"threshold_uncertainty_score":0.883611},"labels":[],"label_agreement":null},{"id":"W4303437868","doi":"10.7202/1092189ar","title":"La traduction automatique des textes faciles à lire et à comprendre (FALC) : une étude comparative","year":2022,"lang":"fr","type":"article","venue":"Meta Journal des traducteurs","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Humanities; Art; Philosophy","score_opus":0.09756364640311707,"score_gpt":0.31695197860302293,"score_spread":0.21938833219990586,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4303437868","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.45433262,0.08627144,0.442331,0.013880561,0.0017918693,0.00045280872,0.00016647397,0.00023133185,0.00054191373],"genre_scores_gemma":[0.9585366,0.007056008,0.031724535,0.00022656852,0.0002166052,0.0000875764,0.000030500183,0.00004024945,0.002081321],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9924704,0.0041618217,0.0010017464,0.0007321197,0.0009276994,0.0007062384],"domain_scores_gemma":[0.99732214,0.00073229655,0.000602165,0.0006189894,0.00033511128,0.00038930448],"candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0029702955,0.00054260157,0.0008683277,0.0003267958,0.0022121398,0.0010916673,0.0013863655,0.00014322103,0.0004226493],"category_scores_gemma":[0.000132897,0.0005201018,0.0006537521,0.0015972717,0.001317322,0.0025664368,0.00023435145,0.0019538982,0.000031764444],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000088531146,0.0024334192,0.0009037997,0.00027327315,0.0018403628,0.00014819275,0.089120276,0.04462461,0.0074808365,0.23534143,0.0024011277,0.61534417],"study_design_scores_gemma":[0.0014238216,0.001476301,0.23004065,0.00022336132,0.0015055579,0.023223445,0.005960763,0.034298968,0.003548813,0.22786719,0.4690453,0.0013858274],"about_ca_topic_score_codex":0.0004279985,"about_ca_topic_score_gemma":0.0006284814,"teacher_disagreement_score":0.6139583,"about_ca_system_score_codex":0.0004627925,"about_ca_system_score_gemma":0.00041370746,"threshold_uncertainty_score":0.9999453},"labels":[],"label_agreement":null},{"id":"W4308183710","doi":"10.3233/shti220992","title":"What Can We Learn from Quality Requirements in ISO/TS 82304-2 for Evaluating Conversational Agents in Healthcare?","year":2022,"lang":"en","type":"article","venue":"Studies in health technology and informatics","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung; National Science Foundation","keywords":"Usability; Readability; Computer science; Quality (philosophy); Set (abstract data type); Relevance (law); Health care; Work (physics); Process management; Risk analysis (engineering); Knowledge management; Human–computer interaction; Engineering; Business","score_opus":0.2701706356446133,"score_gpt":0.46908263442580905,"score_spread":0.19891199878119575,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4308183710","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.90775365,0.0037832882,0.003200308,0.08304021,0.0007979406,0.001299388,0.000035738474,0.00007932014,0.000010178438],"genre_scores_gemma":[0.984824,0.002625089,0.009912023,0.0022045097,0.000005839408,0.00038996653,0.000025869147,0.000003291006,0.000009416927],"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99778533,0.00023449965,0.0011538678,0.00022021554,0.0002570038,0.00034908653],"domain_scores_gemma":[0.9987971,0.00039912332,0.00038704096,0.0003122229,0.000072904455,0.00003156088],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025675136,0.00010889973,0.00032191642,0.0004684226,0.000356008,0.000024001785,0.00036500854,0.00008626964,0.000002214889],"category_scores_gemma":[0.00050204044,0.00011710732,0.000016873526,0.00077982637,0.00015258328,0.0005573936,0.0005192548,0.00039912463,8.403721e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006562939,0.00018267086,0.39947766,0.0013168337,0.00002929048,0.0000014140078,0.121274464,0.0010865398,0.000002717267,0.12120777,0.00020666503,0.35514835],"study_design_scores_gemma":[0.003509954,0.000994645,0.21392463,0.00048283744,0.0000033319686,0.000005980664,0.1616187,0.17468916,0.000023363948,0.44025013,0.0040780683,0.00041923072],"about_ca_topic_score_codex":0.0005813625,"about_ca_topic_score_gemma":0.0017001234,"teacher_disagreement_score":0.35472912,"about_ca_system_score_codex":0.0007383869,"about_ca_system_score_gemma":0.00025557436,"threshold_uncertainty_score":0.47754982},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_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","score_opus":0.02522489423537592,"score_gpt":0.28554218481581917,"score_spread":0.26031729058044323,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4309376528","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.028895972,0.00006400915,0.9653757,0.0014044278,0.00023599801,0.00082910137,0.0000018738674,0.00059837394,0.0025945054],"genre_scores_gemma":[0.9815225,0.000018295294,0.01537146,0.0019506128,0.00013138955,0.000428726,0.0003674202,0.00003067453,0.0001789275],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9924575,0.0005305547,0.0017080697,0.0004938526,0.0040859953,0.0007240352],"domain_scores_gemma":[0.9966801,0.0005236838,0.00085604476,0.0010539595,0.00023916033,0.0006470571],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.0034573718,0.00036193142,0.00042617158,0.0003766144,0.0013587794,0.0002845875,0.0022309145,0.00036369442,0.00090855133],"category_scores_gemma":[0.0011737881,0.0003547733,0.00018087395,0.0014091429,0.00025584296,0.00095938926,0.0008346532,0.0019942212,0.00014282805],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008345672,0.0012164109,0.0017586123,0.0006418399,0.000087506596,0.000012909917,0.023943147,0.42463517,0.00024017603,0.053569198,0.0013427668,0.4924688],"study_design_scores_gemma":[0.00071151,0.00020191884,0.0006082261,0.000029003464,0.000014686304,0.00007339813,0.0026959968,0.94210184,0.00007286251,0.00022448078,0.052878056,0.00038804841],"about_ca_topic_score_codex":0.000034469955,"about_ca_topic_score_gemma":0.0000021499216,"teacher_disagreement_score":0.9526265,"about_ca_system_score_codex":0.0005865489,"about_ca_system_score_gemma":0.0008554881,"threshold_uncertainty_score":0.9999413},"labels":[],"label_agreement":null},{"id":"W4310243183","doi":"10.5430/wjel.v13n1p131","title":"Use of Google Translate for Translating Scientific Texts: An Investigation with Saudi English-Major Students","year":2022,"lang":"en","type":"article","venue":"World Journal of English Language","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Arabic; Syntax; Computer science; Meaning (existential); Mathematics education; Sample (material); Dependency (UML); Psychology; Linguistics; Natural language processing; Artificial intelligence","score_opus":0.024816574279460404,"score_gpt":0.2755410390846637,"score_spread":0.25072446480520333,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4310243183","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98059064,0.00028669773,0.017708572,0.0001674485,0.00073032535,0.00035184118,0.000042596068,0.00005146534,0.000070415306],"genre_scores_gemma":[0.9699108,0.0000010311253,0.02963221,0.00006098613,0.00016535581,0.000015729183,0.000018140312,0.0000145011545,0.00018121846],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.99789727,0.00022899818,0.0005933127,0.0002839516,0.0007765483,0.00021994543],"domain_scores_gemma":[0.99791664,0.00022940707,0.00052603794,0.00044016732,0.0007578515,0.00012989277],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001813647,0.00013052073,0.00025463133,0.0003890229,0.00030515296,0.00033409047,0.0009467177,0.000026386087,0.000023432374],"category_scores_gemma":[0.00028846163,0.00011429021,0.00011998683,0.00093408115,0.0001126453,0.0017237131,0.000051442174,0.00029277868,1.6922714e-7],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00047369982,0.0012067289,0.02427601,0.000254663,0.00020611462,0.000041218773,0.82192916,0.014826719,0.035828315,0.0070585515,0.00083795004,0.093060896],"study_design_scores_gemma":[0.042336464,0.018672356,0.12430931,0.0024487204,0.001837379,0.00030787964,0.17394033,0.069498464,0.22481976,0.016504295,0.318751,0.006574038],"about_ca_topic_score_codex":0.000028037792,"about_ca_topic_score_gemma":0.0003449693,"teacher_disagreement_score":0.6479888,"about_ca_system_score_codex":0.00007649296,"about_ca_system_score_gemma":0.00017470258,"threshold_uncertainty_score":0.46606195},"labels":[],"label_agreement":null},{"id":"W4312190272","doi":"10.1352/1944-7558-128.1.96","title":"Résumés en Français","year":2022,"lang":"fr","type":"article","venue":"American Journal on Intellectual and Developmental Disabilities","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Icon; Citation; Download; Computer science; Information retrieval; World Wide Web; Programming language","score_opus":0.03253244248008126,"score_gpt":0.2609031443318721,"score_spread":0.22837070185179087,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312190272","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9499124,0.001719269,0.009844736,0.016101,0.002421558,0.00025279584,0.000071103794,0.00008088446,0.01959625],"genre_scores_gemma":[0.9756961,0.00042239262,0.0038496112,0.0020485092,0.00017880023,0.000044985616,0.0000064231863,0.000021709968,0.017731495],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99676704,0.000863889,0.00062099507,0.0005345748,0.00067231664,0.0005411977],"domain_scores_gemma":[0.9955171,0.0037236987,0.00011997031,0.00023373733,0.000084490646,0.00032104808],"candidate_categories":["metaepi_narrow","sts","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00085077656,0.00032247385,0.00040349,0.00018454755,0.0014657974,0.0004062619,0.00066735846,0.000041333606,0.011774195],"category_scores_gemma":[0.0013409567,0.00031167959,0.00015330421,0.00066827267,0.0016621448,0.00048512517,0.0006335591,0.000985514,0.00094300666],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021882723,0.0005492428,0.0032804972,0.000031272757,0.000098725206,0.000014578032,0.2580995,0.000118428994,0.00004746205,0.026726015,0.029222004,0.6815934],"study_design_scores_gemma":[0.000355567,0.003563141,0.009032539,0.00006074205,0.000019056957,0.0034304545,0.20370254,0.0011751708,0.0001925723,0.011693911,0.76610994,0.0006643744],"about_ca_topic_score_codex":0.00046667128,"about_ca_topic_score_gemma":0.000023895838,"teacher_disagreement_score":0.73688793,"about_ca_system_score_codex":0.0007319941,"about_ca_system_score_gemma":0.00043612983,"threshold_uncertainty_score":0.99993354},"labels":[],"label_agreement":null},{"id":"W4313469559","doi":"10.5539/ass.v19n1p1","title":"Readability and Simplicity of Arabic Political Discourse","year":2023,"lang":"en","type":"article","venue":"Asian Social Science","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Readability; Simplicity; Presidency; Arabic; Politics; Political science; Media studies; Linguistics; Law; Sociology; Epistemology; Philosophy","score_opus":0.022896580321759057,"score_gpt":0.32486401840779416,"score_spread":0.3019674380860351,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313469559","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91582066,0.000004778747,0.019233359,0.015555215,0.0001411692,0.00020356386,0.000010624846,0.00022624365,0.04880438],"genre_scores_gemma":[0.9990927,8.2909077e-7,0.0007621332,0.000071795315,0.00003506798,0.000005193984,7.6324915e-7,0.0000019880379,0.000029553756],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99851716,0.000057010373,0.0001816919,0.00041260698,0.00042770462,0.00040383238],"domain_scores_gemma":[0.9992447,0.00009225869,0.00005570031,0.0003578531,0.00009723228,0.00015225848],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010726355,0.00007064518,0.00012694584,0.0000854584,0.00036774058,0.000085964835,0.00070693064,0.00004577007,0.0000028659822],"category_scores_gemma":[0.00030245533,0.000063044936,0.000036491114,0.0015869753,0.001736019,0.0005878538,0.00029359516,0.00008245501,0.00001399147],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000011491104,0.000028981787,0.004735489,0.000008681194,8.5637606e-7,5.271061e-7,0.0014537147,1.0151856e-7,0.0025478278,0.8206002,0.000037153866,0.17058527],"study_design_scores_gemma":[0.000037734106,0.000025471541,0.87817246,0.000002677842,0.0000018023579,0.0000019598979,0.0006755476,0.0005391806,0.0018079154,0.11853689,0.00011803817,0.000080303784],"about_ca_topic_score_codex":0.00009606832,"about_ca_topic_score_gemma":0.000011980187,"teacher_disagreement_score":0.873437,"about_ca_system_score_codex":0.000065733264,"about_ca_system_score_gemma":0.00018475729,"threshold_uncertainty_score":0.63964343},"labels":[],"label_agreement":null},{"id":"W4313589266","doi":"10.21203/rs.3.rs-2410184/v1","title":"Biomedical Text Readability and Cognitive Burden after Hypernym Substitution with Fine-Tuned Large Language Models","year":2023,"lang":"en","type":"preprint","venue":"Research Square","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Readability; Substitution (logic); Computer science; Cognition; Natural language processing; Linguistics; Artificial intelligence; Psychology; Programming language; Philosophy","score_opus":0.0669732686738143,"score_gpt":0.3703418086020396,"score_spread":0.30336853992822527,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313589266","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7620103,0.0007667225,0.23135304,0.0029733991,0.000114763396,0.0016359132,0.00049224147,0.00040534444,0.00024828027],"genre_scores_gemma":[0.9966163,0.000075146156,0.0017655619,0.000019943054,0.00017297387,0.0006084368,0.00036075735,0.000026795926,0.00035408864],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99504316,0.00075126323,0.00036145118,0.0014585081,0.001620821,0.00076479214],"domain_scores_gemma":[0.99653333,0.000896086,0.00008564238,0.0013666706,0.00077969814,0.00033857572],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0030724057,0.0002933561,0.00037884974,0.00043480148,0.00028937514,0.00044749692,0.0008410093,0.0004428913,0.000033601573],"category_scores_gemma":[0.0007815672,0.00023437859,0.0000894602,0.000826004,0.0006444464,0.00042967967,0.0021753095,0.0014088207,0.0001230877],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0049671093,0.005938077,0.06989794,0.022728818,0.0013463739,0.0041457796,0.15640731,0.0016161025,0.00393288,0.13006134,0.0025953567,0.5963629],"study_design_scores_gemma":[0.003652783,0.0019859392,0.35749248,0.006725347,0.00016551516,0.00012363477,0.011433686,0.47240517,0.002554248,0.13730712,0.003074584,0.0030794996],"about_ca_topic_score_codex":0.0011740461,"about_ca_topic_score_gemma":0.00065582496,"teacher_disagreement_score":0.5932834,"about_ca_system_score_codex":0.00021352948,"about_ca_system_score_gemma":0.0006505768,"threshold_uncertainty_score":0.9557681},"labels":[],"label_agreement":null},{"id":"W4318929966","doi":"10.1037/cep0000303","title":"Text validation: Overlooking discrepancies in question constructions.","year":2023,"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":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Interrogative; Interrogative word; Consistency (knowledge bases); Linguistics; Construct (python library); Verb; Psychology; Sentence; PsycINFO; Natural language processing; Computer science; Cognitive psychology; Artificial intelligence; Philosophy; MEDLINE","score_opus":0.039592660537402666,"score_gpt":0.31976434062296377,"score_spread":0.2801716800855611,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4318929966","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9856873,0.00069550483,0.0024544504,0.0049839546,0.0030249252,0.00025169385,0.00002007074,0.00007671217,0.002805381],"genre_scores_gemma":[0.9947348,0.000038332528,0.0042493166,0.0006372302,0.00015429506,0.000035451994,0.000019789171,0.000019728363,0.00011102992],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.9974285,0.0002389931,0.00073535397,0.0005579593,0.000106815445,0.0009324141],"domain_scores_gemma":[0.99801826,0.000094816234,0.00032749728,0.0007034017,0.000098533776,0.0007575137],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001292567,0.00023715157,0.0003222502,0.0010773153,0.00023654562,0.00013782406,0.0011301767,0.00019697324,0.00011443373],"category_scores_gemma":[0.0001649997,0.0002655936,0.00014147368,0.0012073086,0.0003280461,0.0007773079,0.00004653487,0.00038884662,0.000069901624],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020055528,0.0008376741,0.22337604,0.00006199806,0.00022737909,0.003813033,0.045757186,0.0010649542,0.39433706,0.2611026,0.033392742,0.035828803],"study_design_scores_gemma":[0.0072060307,0.0023738972,0.75126994,0.0006149802,0.00004791196,0.010566203,0.03667096,0.0014884799,0.079676904,0.05654851,0.05120215,0.002334042],"about_ca_topic_score_codex":0.005792045,"about_ca_topic_score_gemma":0.025072603,"teacher_disagreement_score":0.5278939,"about_ca_system_score_codex":0.0012702909,"about_ca_system_score_gemma":0.00046069466,"threshold_uncertainty_score":0.9999796},"labels":[],"label_agreement":null},{"id":"W4319082003","doi":"10.5489/cuaj.8169","title":"Difficult to read: An analysis of urology publications using readability tools","year":2023,"lang":"en","type":"article","venue":"Canadian Urological Association Journal","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Ottawa; Queen's University","funders":"","keywords":"Readability; Computer science; Urology; Medicine; Programming language","score_opus":0.056154078180344576,"score_gpt":0.2875564630730842,"score_spread":0.23140238489273962,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4319082003","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8926316,0.000007567829,0.0681527,0.038431533,0.0001697888,0.00016028194,0.00008535039,0.0001169541,0.00024421455],"genre_scores_gemma":[0.99558365,0.000004152152,0.0030131214,0.0011725639,0.00006457481,0.000009186644,0.00006351317,0.000004005273,0.00008523837],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99776614,0.0004957789,0.000528995,0.0003715699,0.00036704808,0.00047046307],"domain_scores_gemma":[0.99718374,0.00047411755,0.00032508117,0.0004994318,0.00081403437,0.00070356845],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021795009,0.00010590205,0.00029496197,0.0009994806,0.0003446682,0.0002801083,0.00079333683,0.00022088061,0.00013253823],"category_scores_gemma":[0.0034603754,0.00009596983,0.0001461947,0.0050546303,0.000046554418,0.00057551195,0.000058173602,0.00027383462,0.000033109194],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012921377,0.0001762368,0.844231,0.0000029576013,0.00040279672,0.000008223751,0.0015297816,0.068043515,0.0009601466,0.0522875,0.002254244,0.030090645],"study_design_scores_gemma":[0.000046924597,0.0000870002,0.9138392,4.6937643e-7,0.00008229621,0.000006851454,0.00007042134,0.07567997,0.000007769014,0.0023689982,0.00770987,0.000100182086],"about_ca_topic_score_codex":0.0024767136,"about_ca_topic_score_gemma":0.006920145,"teacher_disagreement_score":0.10295203,"about_ca_system_score_codex":0.0007830159,"about_ca_system_score_gemma":0.0004762147,"threshold_uncertainty_score":0.41426426},"labels":[],"label_agreement":null},{"id":"W4320161966","doi":"10.7202/1095682ar","title":"ILSA: an automated language complexity analysis tool for French","year":2021,"lang":"fr","type":"article","venue":"Mesure et évaluation en éducation","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Computer science; Vocabulary; Natural language processing; Sentence; Artificial intelligence; Variance (accounting); Spectrum analyzer; Linguistics","score_opus":0.1296194640007061,"score_gpt":0.4205212441199161,"score_spread":0.29090178011921,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4320161966","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.30416945,0.00058790576,0.6691763,0.023261113,0.0014363779,0.00057428825,0.00012837614,0.0003472499,0.00031897912],"genre_scores_gemma":[0.8858213,0.00002914762,0.10473993,0.00048992777,0.00025772094,0.00013461141,0.004299121,0.000018468258,0.0042097755],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.9924983,0.0050086407,0.00066944864,0.0008807857,0.0006042984,0.00033857598],"domain_scores_gemma":[0.9959956,0.00084872806,0.00033510572,0.0012408874,0.0014691554,0.00011055206],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.010818418,0.00024556907,0.0003751138,0.00024159724,0.0002993394,0.00055335124,0.00040925207,0.00026581803,0.00055922254],"category_scores_gemma":[0.0018241777,0.00028794768,0.00025451975,0.0020352828,0.000085426975,0.0015335421,0.00006744912,0.00019280681,0.000085415544],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002896882,0.0030246025,0.0126714725,0.00045386632,0.0010327358,0.0000058029063,0.45928887,0.017749632,0.008569868,0.25436178,0.012166343,0.23064606],"study_design_scores_gemma":[0.00025984348,0.000057998695,0.51237637,0.000016608023,0.00042969355,0.0000064662677,0.0005859878,0.47566715,0.0010148868,0.006900573,0.0024605256,0.00022389666],"about_ca_topic_score_codex":0.0008905339,"about_ca_topic_score_gemma":0.0045560966,"teacher_disagreement_score":0.58165187,"about_ca_system_score_codex":0.0004649633,"about_ca_system_score_gemma":0.0017844859,"threshold_uncertainty_score":0.99995726},"labels":[],"label_agreement":null},{"id":"W4321370343","doi":"10.1352/1944-7558-128.2.181","title":"Résumés en Français","year":2023,"lang":"fr","type":"article","venue":"American Journal on Intellectual and Developmental Disabilities","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Icon; Citation; Computer science; Download; World Wide Web; Information retrieval; Programming language","score_opus":0.04369313419022415,"score_gpt":0.28091875655433335,"score_spread":0.2372256223641092,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4321370343","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95795184,0.0006123251,0.006888155,0.01636479,0.0018937946,0.00019810819,0.000032423377,0.00019384112,0.015864717],"genre_scores_gemma":[0.9666041,0.0017576937,0.0030228598,0.0010814129,0.00028587607,0.000020272397,0.000008292611,0.00002599364,0.027193462],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9972544,0.00043189607,0.0006226985,0.00053199043,0.0005085307,0.00065053336],"domain_scores_gemma":[0.99393183,0.0052439813,0.00009135724,0.00023334431,0.000118650176,0.00038083308],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0007932572,0.0003452127,0.00042242152,0.00026247822,0.0006203754,0.0005497073,0.00051843526,0.000087646695,0.0023704174],"category_scores_gemma":[0.002823795,0.00030627564,0.00014965961,0.0011693022,0.002046432,0.0006172272,0.0003021886,0.0005985046,0.009119959],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000098739096,0.00018439988,0.0037077968,0.000052337535,0.00008853137,0.000015422123,0.19130144,0.000032611406,0.00006134367,0.017864054,0.04665688,0.7399365],"study_design_scores_gemma":[0.0005297132,0.0029299743,0.06423072,0.00040570652,0.000029950215,0.0018936096,0.19152686,0.0035195455,0.0007414338,0.027598783,0.7054396,0.0011540542],"about_ca_topic_score_codex":0.0003138797,"about_ca_topic_score_gemma":0.00003717608,"teacher_disagreement_score":0.7387824,"about_ca_system_score_codex":0.00030488268,"about_ca_system_score_gemma":0.0003116555,"threshold_uncertainty_score":0.9999389},"labels":[],"label_agreement":null},{"id":"W4322210710","doi":"10.31234/osf.io/hy2dj","title":"More than Words: Speech production in first episode psychosis predicts later social and vocational functioning.","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Douglas Mental Health University Institute; Lawson Health Research Institute; Western University","funders":"Fonds de Recherche du Québec - Santé; Canadian Institutes of Health Research; Academic Medical Organization of Southwestern Ontario; McGill University; Chrysalis","keywords":"Psychology; Psychosis; Socioeconomic status; Schizophrenia (object-oriented programming); Vocational education; Psychosocial; Developmental psychology; Antipsychotic; Clinical psychology; Cognitive psychology; Psychiatry; Medicine","score_opus":0.04941969443484621,"score_gpt":0.28871508670116547,"score_spread":0.23929539226631927,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4322210710","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.72721887,0.00011168397,0.13585354,0.12748566,0.0050320695,0.0017707666,0.000033636912,0.0013347813,0.0011589653],"genre_scores_gemma":[0.9863832,0.00005417129,0.01036692,0.00010902925,0.00053243,0.000293045,0.00011626367,0.000018615465,0.0021263186],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9978587,0.000072421804,0.00038823497,0.0010593991,0.0003844201,0.00023681833],"domain_scores_gemma":[0.99899095,0.00007216297,0.00014632593,0.00061301107,0.00012228638,0.000055276334],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006064233,0.00021462816,0.00021546203,0.0002577467,0.00021237967,0.00027081312,0.00047181238,0.0003014777,0.000019146824],"category_scores_gemma":[0.00010849714,0.00021040335,0.00006654761,0.00042447358,0.00009390158,0.00035817476,0.0005369763,0.00043695112,0.00004550752],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008878763,0.00071760203,0.7284422,0.0009523986,0.00015816175,0.0000075545204,0.021931238,0.0037893173,0.00008338836,0.011032302,0.038347427,0.19444963],"study_design_scores_gemma":[0.00013923453,0.000017361617,0.96480703,0.000081987695,0.000009430299,0.0000068984377,0.00009522979,0.011364468,0.00017259717,0.021901613,0.001143757,0.00026038807],"about_ca_topic_score_codex":0.0010715888,"about_ca_topic_score_gemma":0.004782463,"teacher_disagreement_score":0.25916433,"about_ca_system_score_codex":0.00014465694,"about_ca_system_score_gemma":0.000058614543,"threshold_uncertainty_score":0.858},"labels":[],"label_agreement":null},{"id":"W4361281563","doi":"10.31730/osf.io/cmb7x","title":"Individual Differences in Leveraging Regularity in Emergent L2 Readers in Rural Côte d’Ivoire","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Orthography; Reading (process); Psychology; Literacy; Consistency (knowledge bases); Linguistics; Leverage (statistics); Contrast (vision); Cognitive psychology; Computer science; Artificial intelligence","score_opus":0.11367268561229299,"score_gpt":0.29261490160200937,"score_spread":0.17894221598971638,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4361281563","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.970815,0.00007720598,0.020258632,0.007204119,0.0006856438,0.00054056454,0.000008601722,0.00020995962,0.00020028112],"genre_scores_gemma":[0.9952176,0.00007378212,0.004162901,0.00008907565,0.000031449275,0.000120282,0.00005188667,0.0000109919565,0.00024202693],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9968428,0.00037429229,0.00079921354,0.00096403714,0.0005272946,0.00049237185],"domain_scores_gemma":[0.998553,0.00016557511,0.00015782367,0.0010102512,0.000035852067,0.000077509714],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001535061,0.0002972563,0.00047140376,0.00070506224,0.00004919473,0.00023808243,0.001812141,0.00036168122,0.000021330306],"category_scores_gemma":[0.00013768623,0.00029049767,0.00009078481,0.0008719955,0.0000769895,0.00033000723,0.0018962843,0.0010713249,0.000021267955],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010833536,0.00028775074,0.9039403,0.00020390033,0.00001929973,0.000041796353,0.03536022,0.0021251822,0.000033561148,0.010154773,0.00023172598,0.047590666],"study_design_scores_gemma":[0.0002037153,0.0000117309055,0.9164143,0.00023884271,0.0000022696017,0.0000012671348,0.0017849512,0.036487654,0.00006173506,0.04445036,0.000021897938,0.00032126714],"about_ca_topic_score_codex":0.012022065,"about_ca_topic_score_gemma":0.01963238,"teacher_disagreement_score":0.047269396,"about_ca_system_score_codex":0.00030377618,"about_ca_system_score_gemma":0.00027040328,"threshold_uncertainty_score":0.9999547},"labels":[],"label_agreement":null},{"id":"W4365139124","doi":"10.15398/jlm.v10i2.263","title":"Simplicity and learning to distinguish arguments from modifiers","year":2022,"lang":"en","type":"article","venue":"Journal of Language Modelling","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; Canadian Institute for Advanced Research","funders":"","keywords":"Argument (complex analysis); Lexicon; Simplicity; Learnability; Computer science; Simple (philosophy); Argument map; Artificial intelligence; Natural language processing; Linguistics; Epistemology; Philosophy","score_opus":0.020543879023698513,"score_gpt":0.2515011090621402,"score_spread":0.23095723003844168,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4365139124","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5141183,0.00011706129,0.48544425,0.00017250754,0.000066807486,0.000026202853,0.0000016752006,0.000010781462,0.00004239912],"genre_scores_gemma":[0.9545731,0.000003196811,0.045133784,0.00016810032,0.00006813731,0.0000017760691,0.0000013596707,0.0000045880206,0.00004596101],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990609,0.00012182719,0.00024638075,0.0001535834,0.00029410177,0.00012318157],"domain_scores_gemma":[0.99938136,0.0001311383,0.00018048885,0.00015513087,0.000051995306,0.00009986571],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006415008,0.0000636029,0.00012818204,0.00008305127,0.00025859187,0.00009580403,0.00036782518,0.000015920403,0.000012654994],"category_scores_gemma":[0.000088958506,0.00006139026,0.000042714808,0.00014568023,0.000008208283,0.00018731895,0.00019412873,0.00035349457,0.0000011493853],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020634354,0.000044648194,0.00093923515,0.0000047394014,0.000016970413,0.000038168502,0.03336633,0.916955,0.0031614779,0.0004968457,0.000036336995,0.044919636],"study_design_scores_gemma":[0.00021473276,0.0001233124,0.0005963829,0.000013032547,0.000009897899,0.000048351623,0.002791848,0.99166274,0.0004613942,0.0028124948,0.0011466254,0.00011920562],"about_ca_topic_score_codex":0.0001996812,"about_ca_topic_score_gemma":0.0000022610106,"teacher_disagreement_score":0.44045478,"about_ca_system_score_codex":0.000073428375,"about_ca_system_score_gemma":0.000026182284,"threshold_uncertainty_score":0.25034222},"labels":[],"label_agreement":null},{"id":"W4367173206","doi":"10.1352/1944-7558-128.3.269","title":"Résumés en Français","year":2023,"lang":"fr","type":"article","venue":"American Journal on Intellectual and Developmental Disabilities","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Icon; Citation; Computer science; Download; World Wide Web; Information retrieval; Programming language","score_opus":0.04369313419022415,"score_gpt":0.28091875655433335,"score_spread":0.2372256223641092,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367173206","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95795184,0.0006123251,0.006888155,0.01636479,0.0018937946,0.00019810819,0.000032423377,0.00019384112,0.015864717],"genre_scores_gemma":[0.9666041,0.0017576937,0.0030228598,0.0010814129,0.00028587607,0.000020272397,0.000008292611,0.00002599364,0.027193462],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9972544,0.00043189607,0.0006226985,0.00053199043,0.0005085307,0.00065053336],"domain_scores_gemma":[0.99393183,0.0052439813,0.00009135724,0.00023334431,0.000118650176,0.00038083308],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0007932572,0.0003452127,0.00042242152,0.00026247822,0.0006203754,0.0005497073,0.00051843526,0.000087646695,0.0023704174],"category_scores_gemma":[0.002823795,0.00030627564,0.00014965961,0.0011693022,0.002046432,0.0006172272,0.0003021886,0.0005985046,0.009119959],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000098739096,0.00018439988,0.0037077968,0.000052337535,0.00008853137,0.000015422123,0.19130144,0.000032611406,0.00006134367,0.017864054,0.04665688,0.7399365],"study_design_scores_gemma":[0.0005297132,0.0029299743,0.06423072,0.00040570652,0.000029950215,0.0018936096,0.19152686,0.0035195455,0.0007414338,0.027598783,0.7054396,0.0011540542],"about_ca_topic_score_codex":0.0003138797,"about_ca_topic_score_gemma":0.00003717608,"teacher_disagreement_score":0.7387824,"about_ca_system_score_codex":0.00030488268,"about_ca_system_score_gemma":0.0003116555,"threshold_uncertainty_score":0.9999389},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.08187653957215646,"score_gpt":0.30157016578413276,"score_spread":0.2196936262119763,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4367558144","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16890243,0.0000070155957,0.8233212,0.0039170156,0.00017185089,0.00044306807,0.000010074408,0.0008074846,0.0024198666],"genre_scores_gemma":[0.87539834,0.000005007154,0.12320055,0.00016259213,0.000060024613,0.000067390916,0.000010000421,0.0000150315645,0.0010810675],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9985428,0.00004574579,0.00037870943,0.00041772187,0.0003403291,0.0002746807],"domain_scores_gemma":[0.9978534,0.00031735317,0.00008213331,0.0015202691,0.000105205894,0.00012162747],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0009028498,0.00012704136,0.00016789061,0.00014035664,0.00013051774,0.0001713447,0.0008365552,0.00006554354,0.000037691698],"category_scores_gemma":[0.00025566132,0.00011691595,0.000057526868,0.0011140842,0.000033347987,0.00024748011,0.00020068715,0.00008540606,0.0039103376],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000039826355,0.000397732,0.0003601767,0.00021376772,0.000014717716,0.0000045992606,0.014503522,0.00043157072,0.026181988,0.6935411,0.022426223,0.24192059],"study_design_scores_gemma":[0.00020207395,0.0001244659,0.09633032,0.00006451621,0.000009831244,0.000021491607,0.0007967006,0.08836628,0.02622128,0.6960785,0.09098529,0.00079924124],"about_ca_topic_score_codex":0.0000049098867,"about_ca_topic_score_gemma":0.000003929351,"teacher_disagreement_score":0.7064959,"about_ca_system_score_codex":0.00008071404,"about_ca_system_score_gemma":0.000034917368,"threshold_uncertainty_score":0.9968652},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.057294112566049486,"score_gpt":0.33096322800508265,"score_spread":0.27366911543903316,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4380318953","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97722375,0.0001616031,0.0211401,0.0008078182,0.00047747383,0.00006031355,3.4584832e-7,0.000028716682,0.00009984684],"genre_scores_gemma":[0.9978884,0.000020458125,0.001843784,0.00015181591,0.000069916765,0.0000010057645,0.0000019498539,0.0000054544853,0.00001722696],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99897707,0.00014373475,0.00031459323,0.00022190045,0.0001687754,0.00017392598],"domain_scores_gemma":[0.9995033,0.00004947465,0.00013411751,0.00017806316,0.00005919197,0.00007581566],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00038421166,0.00009390267,0.000206958,0.00021194541,0.00024365653,0.000041445393,0.00043181144,0.00006433496,0.000011970207],"category_scores_gemma":[0.000033816614,0.00008790506,0.000035269575,0.000565901,0.00009755332,0.00035231214,0.0005089386,0.00018399172,0.000011466593],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025387702,0.00026714682,0.92351884,0.0000079194215,0.000021527654,0.00010468785,0.0037431696,0.00012624136,0.06503154,0.00615506,0.0002103692,0.0007881058],"study_design_scores_gemma":[0.0007353719,0.00010605116,0.98887175,0.000014685165,0.000004177322,0.00024300045,0.00018176205,0.0027462402,0.0035246767,0.0034536605,0.000013732255,0.000104905805],"about_ca_topic_score_codex":0.000034518733,"about_ca_topic_score_gemma":0.000011290667,"teacher_disagreement_score":0.065352894,"about_ca_system_score_codex":0.00006289817,"about_ca_system_score_gemma":0.000020436946,"threshold_uncertainty_score":0.35846642},"labels":[],"label_agreement":null},{"id":"W4381856832","doi":"10.13001/jtilt.v2i1.7663","title":"Writing Effective Alt-text for Online Instructional Materials","year":2023,"lang":"en","type":"article","venue":"Journal of Technology-Integrated Lessons and Teaching","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Checklist; Context (archaeology); Space (punctuation); Multimedia; Psychology; Cognitive psychology","score_opus":0.01831035615465189,"score_gpt":0.3061146976422623,"score_spread":0.2878043414876104,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4381856832","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.849281,0.00006700781,0.13845025,0.011512033,0.00028954906,0.00015631055,0.000026551026,0.00019862143,0.000018635406],"genre_scores_gemma":[0.92290676,0.000029970644,0.07687959,0.00003859729,0.000094587645,0.00001251222,0.000009692759,0.000008272635,0.000020005438],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.998921,0.00007242001,0.00044329264,0.0002179164,0.00013134093,0.00021407728],"domain_scores_gemma":[0.99894154,0.00026472344,0.00034407104,0.00019134548,0.00021095357,0.000047389345],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013292003,0.00012397309,0.0002796138,0.00063449406,0.00030866923,0.00013107454,0.0004207208,0.00017349492,0.0000021580925],"category_scores_gemma":[0.0006289819,0.000096142874,0.00007060624,0.00036245244,0.00008030855,0.0003903762,0.00010494575,0.00053083285,0.0000021018895],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018952092,0.00005680545,0.00033620463,0.000022916793,0.000042668657,0.0000075894,0.00013109414,0.000021091451,0.062858865,0.1918583,0.00015477721,0.74449074],"study_design_scores_gemma":[0.006316391,0.002890054,0.09808263,0.0020305621,0.00022099623,0.005815588,0.010445177,0.058030408,0.2125014,0.5120641,0.09002342,0.0015792891],"about_ca_topic_score_codex":0.000014263373,"about_ca_topic_score_gemma":0.0000068788727,"teacher_disagreement_score":0.74291146,"about_ca_system_score_codex":0.00006791118,"about_ca_system_score_gemma":0.00006566718,"threshold_uncertainty_score":0.39205924},"labels":[],"label_agreement":null},{"id":"W4384937799","doi":"10.1352/1944-7558-128.4.344","title":"Résumés en Français","year":2023,"lang":"fr","type":"article","venue":"American Journal on Intellectual and Developmental Disabilities","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Icon; Citation; Computer science; Download; World Wide Web; Information retrieval; Programming language","score_opus":0.04369313419022415,"score_gpt":0.28091875655433335,"score_spread":0.2372256223641092,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384937799","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95795184,0.0006123251,0.006888155,0.01636479,0.0018937946,0.00019810819,0.000032423377,0.00019384112,0.015864717],"genre_scores_gemma":[0.9666041,0.0017576937,0.0030228598,0.0010814129,0.00028587607,0.000020272397,0.000008292611,0.00002599364,0.027193462],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9972544,0.00043189607,0.0006226985,0.00053199043,0.0005085307,0.00065053336],"domain_scores_gemma":[0.99393183,0.0052439813,0.00009135724,0.00023334431,0.000118650176,0.00038083308],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0007932572,0.0003452127,0.00042242152,0.00026247822,0.0006203754,0.0005497073,0.00051843526,0.000087646695,0.0023704174],"category_scores_gemma":[0.002823795,0.00030627564,0.00014965961,0.0011693022,0.002046432,0.0006172272,0.0003021886,0.0005985046,0.009119959],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000098739096,0.00018439988,0.0037077968,0.000052337535,0.00008853137,0.000015422123,0.19130144,0.000032611406,0.00006134367,0.017864054,0.04665688,0.7399365],"study_design_scores_gemma":[0.0005297132,0.0029299743,0.06423072,0.00040570652,0.000029950215,0.0018936096,0.19152686,0.0035195455,0.0007414338,0.027598783,0.7054396,0.0011540542],"about_ca_topic_score_codex":0.0003138797,"about_ca_topic_score_gemma":0.00003717608,"teacher_disagreement_score":0.7387824,"about_ca_system_score_codex":0.00030488268,"about_ca_system_score_gemma":0.0003116555,"threshold_uncertainty_score":0.9999389},"labels":[],"label_agreement":null},{"id":"W4385572402","doi":"10.18653/v1/2023.bea-1.43","title":"CEFR-based Contextual Lexical Complexity Classifier in English and French","year":2023,"lang":"en","type":"article","venue":"","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"CBC (Canada)","funders":"","keywords":"Computer science; Natural language processing; Artificial intelligence; Classifier (UML); Perspective (graphical); Lexical choice; Lexical item; Linguistics","score_opus":0.07541358480765059,"score_gpt":0.28329778466675754,"score_spread":0.20788419985910694,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385572402","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.774377,0.000021883812,0.20789807,0.0074377935,0.00027534697,0.0002623179,0.00000950897,0.00083241554,0.008885704],"genre_scores_gemma":[0.99567634,0.000001590524,0.0036640696,0.00031648495,0.000028900713,0.0000123873915,0.000009267393,0.0000026546954,0.0002882945],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.999066,0.000076991026,0.0001783355,0.00032421923,0.00015570385,0.00019872849],"domain_scores_gemma":[0.9992643,0.00024609792,0.000022024005,0.0003305604,0.00006127716,0.000075714546],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00037396638,0.000076706965,0.00011731102,0.00009817025,0.000059222835,0.000097864526,0.00028733202,0.000067029854,0.000035102923],"category_scores_gemma":[0.00015597403,0.00006749146,0.000024695406,0.00047223218,0.0001871866,0.0002155948,0.000104866594,0.000119918666,0.000051773208],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008387072,0.0001668264,0.041285932,0.000025502595,0.0000043166456,0.000010616245,0.002183046,0.000050565195,0.00043866786,0.8937038,0.007599333,0.05452297],"study_design_scores_gemma":[0.00059891376,0.00006558084,0.7480597,0.000008557352,0.0000011693434,0.0000012141246,0.00019707278,0.21525294,0.00062327867,0.025658723,0.009349587,0.00018330713],"about_ca_topic_score_codex":0.00030368395,"about_ca_topic_score_gemma":0.00084931956,"teacher_disagreement_score":0.8680451,"about_ca_system_score_codex":0.000029496243,"about_ca_system_score_gemma":0.000057413712,"threshold_uncertainty_score":0.27522218},"labels":[],"label_agreement":null},{"id":"W4385572792","doi":"10.18653/v1/2022.emnlp-demos.24","title":"Arabic Word-level Readability Visualization for Assisted Text Simplification","year":2022,"lang":"en","type":"article","venue":"","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"York University; New York University Abu Dhabi","keywords":"Computer science; Readability; WordNet; Natural language processing; Lemmatisation; Visualization; Artificial intelligence; Lexicon; Task (project management); Arabic; Reading (process); Word (group theory); Component (thermodynamics); Information retrieval; Programming language; Linguistics","score_opus":0.07738544741331606,"score_gpt":0.31193981962727757,"score_spread":0.23455437221396153,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385572792","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022439402,0.000018153556,0.9727703,0.0025679488,0.0002428372,0.00079477864,0.00003160697,0.00038528803,0.0007497041],"genre_scores_gemma":[0.96853393,0.0000014625541,0.028519703,0.0004356351,0.000034185185,0.000605931,0.00016865213,0.000011467602,0.0016890593],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99809384,0.00021853791,0.00041759378,0.0006449238,0.0003766939,0.00024840856],"domain_scores_gemma":[0.99820787,0.00032973904,0.0001702532,0.0010002297,0.00021695894,0.00007497837],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011192292,0.00013180925,0.00015325654,0.000118992735,0.00064266974,0.00013654391,0.0008002904,0.00005148821,0.00013183749],"category_scores_gemma":[0.00024885894,0.00013238848,0.00009539735,0.0007986127,0.000038899343,0.00049265183,0.0002093469,0.0001046684,0.000020334866],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000043512417,0.00059296546,0.0018071001,0.00004297882,0.000014774184,2.6953023e-7,0.00077952456,0.00047295584,0.008089422,0.51666826,0.0037135007,0.46777475],"study_design_scores_gemma":[0.0008979193,0.000456222,0.39124933,0.000006717038,0.000030433732,0.000033864726,0.00068139436,0.34999192,0.011514224,0.083680876,0.16055028,0.00090682873],"about_ca_topic_score_codex":0.000056176574,"about_ca_topic_score_gemma":0.000033253615,"teacher_disagreement_score":0.9460945,"about_ca_system_score_codex":0.00028151492,"about_ca_system_score_gemma":0.00013761074,"threshold_uncertainty_score":0.53986454},"labels":[],"label_agreement":null},{"id":"W4386241845","doi":"10.1352/1944-7558-128.5.393","title":"Résumés en Français","year":2023,"lang":"fr","type":"article","venue":"American Journal on Intellectual and Developmental Disabilities","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Icon; Citation; Computer science; Download; World Wide Web; Information retrieval; Programming language","score_opus":0.04369313419022415,"score_gpt":0.28091875655433335,"score_spread":0.2372256223641092,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386241845","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95795184,0.0006123251,0.006888155,0.01636479,0.0018937946,0.00019810819,0.000032423377,0.00019384112,0.015864717],"genre_scores_gemma":[0.9666041,0.0017576937,0.0030228598,0.0010814129,0.00028587607,0.000020272397,0.000008292611,0.00002599364,0.027193462],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9972544,0.00043189607,0.0006226985,0.00053199043,0.0005085307,0.00065053336],"domain_scores_gemma":[0.99393183,0.0052439813,0.00009135724,0.00023334431,0.000118650176,0.00038083308],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0007932572,0.0003452127,0.00042242152,0.00026247822,0.0006203754,0.0005497073,0.00051843526,0.000087646695,0.0023704174],"category_scores_gemma":[0.002823795,0.00030627564,0.00014965961,0.0011693022,0.002046432,0.0006172272,0.0003021886,0.0005985046,0.009119959],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000098739096,0.00018439988,0.0037077968,0.000052337535,0.00008853137,0.000015422123,0.19130144,0.000032611406,0.00006134367,0.017864054,0.04665688,0.7399365],"study_design_scores_gemma":[0.0005297132,0.0029299743,0.06423072,0.00040570652,0.000029950215,0.0018936096,0.19152686,0.0035195455,0.0007414338,0.027598783,0.7054396,0.0011540542],"about_ca_topic_score_codex":0.0003138797,"about_ca_topic_score_gemma":0.00003717608,"teacher_disagreement_score":0.7387824,"about_ca_system_score_codex":0.00030488268,"about_ca_system_score_gemma":0.0003116555,"threshold_uncertainty_score":0.9999389},"labels":[],"label_agreement":null},{"id":"W4386339136","doi":"10.18653/v1/2022.tsar-1.29","title":"RCML at TSAR-2022 Shared Task: Lexical Simplification With Modular Substitution Candidate Ranking","year":2022,"lang":"en","type":"article","venue":"","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"CBC (Canada)","funders":"","keywords":"Substitution (logic); Computer science; Natural language processing; Task (project management); Ranking (information retrieval); Modular design; Artificial intelligence; Simplicity; Similarity (geometry); Word (group theory); Semantic similarity; Information retrieval; Linguistics; Programming language; Engineering","score_opus":0.013976155098637671,"score_gpt":0.22354935231361558,"score_spread":0.2095731972149779,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386339136","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.36976054,0.000056515175,0.6265242,0.0020686819,0.0001527478,0.00035617375,0.00002048249,0.0003164841,0.0007441752],"genre_scores_gemma":[0.99415195,0.0000042551173,0.004442242,0.0003383794,0.000031470503,0.00015891452,0.00020666259,0.000009658635,0.000656475],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979826,0.00017520734,0.00027649026,0.00065740035,0.0006096776,0.00029862806],"domain_scores_gemma":[0.9987297,0.00006434123,0.00012329376,0.00090639025,0.00007784311,0.00009842546],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00055966596,0.0001517591,0.00015335435,0.000112632966,0.00095465325,0.00015038428,0.0007766532,0.00004375633,0.00034910726],"category_scores_gemma":[0.000025774474,0.0001334715,0.000056758854,0.0006722228,0.000066061424,0.00059525867,0.00039394674,0.00020321163,0.000050716244],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00035500646,0.00064447476,0.012721487,0.000060583618,0.00008426898,0.000044299875,0.0042858794,0.034475986,0.12194049,0.77960366,0.0029425258,0.042841326],"study_design_scores_gemma":[0.0022033069,0.00057078135,0.12048054,0.000017530092,0.000052702133,0.00032778195,0.00029945138,0.7025131,0.020749262,0.013145404,0.13837259,0.0012675355],"about_ca_topic_score_codex":0.00018819483,"about_ca_topic_score_gemma":0.000092661525,"teacher_disagreement_score":0.7664583,"about_ca_system_score_codex":0.00047157178,"about_ca_system_score_gemma":0.00012251436,"threshold_uncertainty_score":0.73425174},"labels":[],"label_agreement":null},{"id":"W4386950453","doi":"10.3389/frai.2023.1223924","title":"MeaningBERT: assessing meaning preservation between sentences","year":2023,"lang":"en","type":"article","venue":"Frontiers in Artificial Intelligence","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"Fonds de recherche du Québec – Nature et technologies; Natural Sciences and Engineering Research Council of Canada","keywords":"Meaning (existential); Linguistics; Psychology; Natural language processing; Computer science; Philosophy; Epistemology","score_opus":0.10614501263648841,"score_gpt":0.3312490320625678,"score_spread":0.22510401942607938,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386950453","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06238858,0.000040275874,0.93330276,0.0016262305,0.0010266155,0.00018188062,0.0000014664814,0.0003609842,0.0010711937],"genre_scores_gemma":[0.93625385,0.000022359043,0.06342807,0.000049916234,0.00011767119,0.000021478114,0.000013085523,0.0000089597615,0.00008460409],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9979867,0.00015542544,0.00053607684,0.00053097034,0.00039396048,0.00039690075],"domain_scores_gemma":[0.9989889,0.00023297509,0.0001333581,0.00047780343,0.00009368157,0.00007323921],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012376228,0.00014026862,0.0002060196,0.00037707583,0.00021417259,0.00040365866,0.00095950597,0.00009800686,0.0000061506657],"category_scores_gemma":[0.00047848708,0.00014561578,0.00005521524,0.0021132992,0.0000958253,0.0017674322,0.0001879052,0.00021620591,0.00010712782],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000049399137,0.000039347986,0.07829952,0.000023958655,0.000011791477,0.000009382814,0.004961381,0.004007511,0.0006961918,0.09958517,0.0008716471,0.81148916],"study_design_scores_gemma":[0.000015344809,0.000025331898,0.02140249,0.000055716064,0.0000042842307,9.084752e-7,0.0018315277,0.51077694,0.011620402,0.45315135,0.00088486937,0.00023081481],"about_ca_topic_score_codex":0.00013194961,"about_ca_topic_score_gemma":0.000063287276,"teacher_disagreement_score":0.8738653,"about_ca_system_score_codex":0.00010187897,"about_ca_system_score_gemma":0.00006987787,"threshold_uncertainty_score":0.59380394},"labels":[],"label_agreement":null},{"id":"W4387376139","doi":"10.5430/wjel.v13n8p299","title":"Unveiling the Role of Explicit Metadiscourse Instruction, Language Proficiency, and Content Familiarity in EFL Reading Comprehension: A Comprehensive Review","year":2023,"lang":"en","type":"review","venue":"World Journal of English Language","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Metadiscourse; Comprehension; Reading comprehension; Context (archaeology); Psychology; Computer science; Reading (process); Linguistics","score_opus":0.05873227492118983,"score_gpt":0.32814316039857183,"score_spread":0.269410885477382,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387376139","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0037775328,0.99447715,0.00014412454,0.00008027587,0.00043846804,0.0008255078,0.000015235676,0.00004087767,0.00020084488],"genre_scores_gemma":[0.0033115249,0.9953123,0.00095338514,0.00007460559,0.00022100881,0.0000261333,0.00001017884,0.000024489953,0.00006639675],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9964802,0.000664419,0.0016606085,0.00039399767,0.0005181836,0.00028258192],"domain_scores_gemma":[0.99613565,0.000818027,0.0015594546,0.00079299347,0.00058501156,0.00010884736],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016924632,0.00033959825,0.0018571572,0.0005406082,0.00009506117,0.000089228015,0.0011114886,0.00010868655,0.000007884709],"category_scores_gemma":[0.00090022746,0.00021891875,0.0004323585,0.0017439357,0.00012868276,0.00041269383,0.00030316922,0.0009238555,0.0000034058603],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008158481,0.000090417765,0.00004572864,0.014205912,0.00012642654,0.000068046604,0.0101435,0.000007726344,0.00004696369,0.004975208,0.000109720466,0.97017217],"study_design_scores_gemma":[0.0011252728,0.00024889936,0.0007232046,0.1389893,0.0012585131,0.00055090064,0.03918614,0.0005213519,0.00011924834,0.00041929955,0.81581676,0.0010411437],"about_ca_topic_score_codex":0.00011493586,"about_ca_topic_score_gemma":0.00008421396,"teacher_disagreement_score":0.96913105,"about_ca_system_score_codex":0.00011835806,"about_ca_system_score_gemma":0.00021838042,"threshold_uncertainty_score":0.89272475},"labels":[],"label_agreement":null},{"id":"W4387860315","doi":"10.1002/pra2.817","title":"Spontaneous Learning Environments: Manipulating Readability &amp; Cohesion in Support of Searching as Learning","year":2023,"lang":"en","type":"article","venue":"Proceedings of the Association for Information Science and Technology","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Cohesion (chemistry); Computer science; Readability; Social connectedness; Natural language processing; Ranking (information retrieval); Set (abstract data type); Artificial intelligence; Psychology","score_opus":0.01487362154818951,"score_gpt":0.261656599823897,"score_spread":0.2467829782757075,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387860315","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9955618,0.0000015096201,0.00084958726,0.001934694,0.000036166795,0.0002928071,0.0000010946438,0.00009142884,0.0012309565],"genre_scores_gemma":[0.9986223,0.000012356593,0.0011700917,0.00002333164,0.0000025514107,0.000019955023,0.0000026782475,0.0000019132524,0.00014484853],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9986271,0.000010575352,0.0004154506,0.00017456428,0.0005564334,0.00021586074],"domain_scores_gemma":[0.9986549,0.0001737204,0.0006467888,0.000110460685,0.00039336097,0.000020744586],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004707412,0.000061421146,0.00012827676,0.00058814016,0.00031264705,0.00007618075,0.00054544123,0.000096042895,6.752813e-7],"category_scores_gemma":[0.007643051,0.000052929423,0.000025194095,0.0022767228,0.00015007459,0.0020005559,0.00034041502,0.00019556198,0.000006656913],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020991594,0.000043363503,0.62994087,0.000189203,0.000009474597,1.2542918e-7,0.008898664,0.0011087848,0.08881647,0.1738156,0.000071866925,0.09708462],"study_design_scores_gemma":[0.0011897143,0.0007037343,0.57711804,0.00015184784,0.000023449544,0.00009063539,0.00894313,0.11200297,0.16441077,0.08457347,0.050219025,0.00057318923],"about_ca_topic_score_codex":0.000018322322,"about_ca_topic_score_gemma":0.0000030293995,"teacher_disagreement_score":0.11089418,"about_ca_system_score_codex":0.00022905483,"about_ca_system_score_gemma":0.00007401713,"threshold_uncertainty_score":0.9149998},"labels":[],"label_agreement":null},{"id":"W4387898649","doi":"10.1352/1944-7558-128.6.494","title":"Résumés en Français","year":2023,"lang":"fr","type":"article","venue":"American Journal on Intellectual and Developmental Disabilities","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Icon; Citation; Computer science; Download; Information retrieval; World Wide Web; Programming language","score_opus":0.04369313419022415,"score_gpt":0.28091875655433335,"score_spread":0.2372256223641092,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387898649","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95795184,0.0006123251,0.006888155,0.01636479,0.0018937946,0.00019810819,0.000032423377,0.00019384112,0.015864717],"genre_scores_gemma":[0.9666041,0.0017576937,0.0030228598,0.0010814129,0.00028587607,0.000020272397,0.000008292611,0.00002599364,0.027193462],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9972544,0.00043189607,0.0006226985,0.00053199043,0.0005085307,0.00065053336],"domain_scores_gemma":[0.99393183,0.0052439813,0.00009135724,0.00023334431,0.000118650176,0.00038083308],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0007932572,0.0003452127,0.00042242152,0.00026247822,0.0006203754,0.0005497073,0.00051843526,0.000087646695,0.0023704174],"category_scores_gemma":[0.002823795,0.00030627564,0.00014965961,0.0011693022,0.002046432,0.0006172272,0.0003021886,0.0005985046,0.009119959],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000098739096,0.00018439988,0.0037077968,0.000052337535,0.00008853137,0.000015422123,0.19130144,0.000032611406,0.00006134367,0.017864054,0.04665688,0.7399365],"study_design_scores_gemma":[0.0005297132,0.0029299743,0.06423072,0.00040570652,0.000029950215,0.0018936096,0.19152686,0.0035195455,0.0007414338,0.027598783,0.7054396,0.0011540542],"about_ca_topic_score_codex":0.0003138797,"about_ca_topic_score_gemma":0.00003717608,"teacher_disagreement_score":0.7387824,"about_ca_system_score_codex":0.00030488268,"about_ca_system_score_gemma":0.0003116555,"threshold_uncertainty_score":0.9999389},"labels":[],"label_agreement":null},{"id":"W4389005017","doi":"10.5430/jct.v12n6p347","title":"Content Words and Readability in Students’ Thesis Findings","year":2023,"lang":"en","type":"article","venue":"Journal of Curriculum and Teaching","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Readability; Bachelor; Computer science; Reading (process); Content (measure theory); Content analysis; Natural language processing; Linguistics; Lexical density; Mathematics education; Psychology; Lexical item; Mathematics","score_opus":0.031129943626759474,"score_gpt":0.2941948043226865,"score_spread":0.26306486069592705,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389005017","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99319506,0.00012415297,0.005005322,0.0014062584,0.00010573293,0.00006266069,3.8057547e-7,0.000020733107,0.00007973138],"genre_scores_gemma":[0.9983832,0.00006609342,0.0014481619,0.00004256356,0.000029648603,0.000001430198,1.7615213e-7,0.0000023617445,0.000026323753],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99896383,0.00015349126,0.00033382923,0.00015065863,0.00026290503,0.00013529998],"domain_scores_gemma":[0.999431,0.00020054955,0.00012177537,0.00013465417,0.000037150818,0.00007487667],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002649822,0.000072371324,0.00017539161,0.00016391472,0.0001005732,0.00017071028,0.00029342328,0.000037281392,0.0000010000301],"category_scores_gemma":[0.00033965372,0.00005283334,0.00003969051,0.00013875232,0.00003137868,0.00052388565,0.00013848643,0.0002837504,0.000001132881],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004411194,0.00011310337,0.89139,0.000020505733,0.000009855169,0.000015258853,0.004813182,0.000006368746,0.0004943187,0.0073746494,0.00005041566,0.095707916],"study_design_scores_gemma":[0.00024567905,0.000081852995,0.99136555,0.00007744615,0.0000065298645,0.00006426854,0.0015516997,0.0020063317,0.000080495236,0.004087649,0.00035125835,0.000081241575],"about_ca_topic_score_codex":0.00008603215,"about_ca_topic_score_gemma":0.000018106037,"teacher_disagreement_score":0.09997553,"about_ca_system_score_codex":0.00003728285,"about_ca_system_score_gemma":0.000017542925,"threshold_uncertainty_score":0.21544811},"labels":[],"label_agreement":null},{"id":"W4389048524","doi":"10.5539/elt.v16n12p1","title":"Readability of Reading Texts for EFL Students at Al-Baha University","year":2023,"lang":"en","type":"article","venue":"English Language Teaching","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Readability; Reading (process); Set (abstract data type); Psychology; Mathematics education; Index (typography); Computer science; Linguistics; Pedagogy; World Wide Web","score_opus":0.01310576124463612,"score_gpt":0.2848362922160709,"score_spread":0.27173053097143474,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389048524","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9672614,0.000020274812,0.029980998,0.00017929476,0.00023213463,0.0003004113,0.00002275187,0.0005250366,0.0014777374],"genre_scores_gemma":[0.9926264,0.000002621946,0.0060154465,0.00004272353,0.000057756937,0.0000044051326,0.00003424246,0.000009262371,0.0012070843],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.9985735,0.0002179148,0.00021069973,0.00043112016,0.0003052517,0.00026151937],"domain_scores_gemma":[0.9984031,0.0005953637,0.000117432595,0.0007436866,0.000063094085,0.00007733179],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019645311,0.000112875714,0.00018489241,0.00013317514,0.0002684729,0.000053953285,0.0009428589,0.000068353496,0.0000074062027],"category_scores_gemma":[0.0011353496,0.000117013806,0.00010055315,0.00031844497,0.000042283362,0.00043684285,0.00045532623,0.00018546438,0.000012913098],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012527406,0.00058228074,0.10029012,0.00041836867,0.00012791931,0.00005428671,0.5423203,0.00057819433,0.03611623,0.04564291,0.0065266034,0.26721752],"study_design_scores_gemma":[0.0060119973,0.0012531023,0.4163273,0.00079035875,0.00026608375,0.000031474585,0.17009617,0.098441154,0.12819797,0.010120945,0.16428404,0.004179402],"about_ca_topic_score_codex":0.00014832147,"about_ca_topic_score_gemma":0.000056896806,"teacher_disagreement_score":0.37222412,"about_ca_system_score_codex":0.00019178311,"about_ca_system_score_gemma":0.000028210627,"threshold_uncertainty_score":0.47716844},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.0296680655231284,"score_gpt":0.359881211422216,"score_spread":0.3302131458990876,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389294437","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7880567,0.0000082329,0.21014544,0.000118065574,0.00021573852,0.00041297945,0.000019947405,0.00081962656,0.00020327186],"genre_scores_gemma":[0.9802725,9.708205e-7,0.019339617,0.000026061021,0.000052083265,0.00011176667,0.00004693149,0.000011963748,0.00013811055],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9982348,0.000121939825,0.00042179416,0.00039788726,0.0004916967,0.00033186068],"domain_scores_gemma":[0.99897623,0.00022959757,0.00018459039,0.00045338183,0.0000901913,0.00006602624],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011132472,0.00013931212,0.0002202543,0.0001334027,0.00013037985,0.00021621247,0.0007928991,0.000058463575,0.000006747511],"category_scores_gemma":[0.00002646708,0.0001383288,0.0000959745,0.00046959732,0.000021383024,0.00051827735,0.00006507311,0.0000880709,0.000014305362],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000033116816,0.0014770799,0.15367603,0.0010317528,0.00025305885,0.00007972993,0.093690924,0.0002957399,0.19971862,0.033600073,0.0010069781,0.5151369],"study_design_scores_gemma":[0.0011157865,0.0006074037,0.8524105,0.00010034975,0.00002777803,0.0000062145377,0.0050720507,0.13514766,0.0036421674,0.00149702,0.00004980215,0.00032325735],"about_ca_topic_score_codex":0.00006737553,"about_ca_topic_score_gemma":0.000034188684,"teacher_disagreement_score":0.69873446,"about_ca_system_score_codex":0.00009068496,"about_ca_system_score_gemma":0.00007510196,"threshold_uncertainty_score":0.56408846},"labels":[],"label_agreement":null},{"id":"W4390246740","doi":"10.1352/1944-7558-129.1.86","title":"Résumés en Français","year":2023,"lang":"fr","type":"article","venue":"American Journal on Intellectual and Developmental Disabilities","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Icon; Citation; Computer science; Download; World Wide Web; Information retrieval; Programming language","score_opus":0.04369313419022415,"score_gpt":0.28091875655433335,"score_spread":0.2372256223641092,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390246740","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95795184,0.0006123251,0.006888155,0.01636479,0.0018937946,0.00019810819,0.000032423377,0.00019384112,0.015864717],"genre_scores_gemma":[0.9666041,0.0017576937,0.0030228598,0.0010814129,0.00028587607,0.000020272397,0.000008292611,0.00002599364,0.027193462],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9972544,0.00043189607,0.0006226985,0.00053199043,0.0005085307,0.00065053336],"domain_scores_gemma":[0.99393183,0.0052439813,0.00009135724,0.00023334431,0.000118650176,0.00038083308],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0007932572,0.0003452127,0.00042242152,0.00026247822,0.0006203754,0.0005497073,0.00051843526,0.000087646695,0.0023704174],"category_scores_gemma":[0.002823795,0.00030627564,0.00014965961,0.0011693022,0.002046432,0.0006172272,0.0003021886,0.0005985046,0.009119959],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000098739096,0.00018439988,0.0037077968,0.000052337535,0.00008853137,0.000015422123,0.19130144,0.000032611406,0.00006134367,0.017864054,0.04665688,0.7399365],"study_design_scores_gemma":[0.0005297132,0.0029299743,0.06423072,0.00040570652,0.000029950215,0.0018936096,0.19152686,0.0035195455,0.0007414338,0.027598783,0.7054396,0.0011540542],"about_ca_topic_score_codex":0.0003138797,"about_ca_topic_score_gemma":0.00003717608,"teacher_disagreement_score":0.7387824,"about_ca_system_score_codex":0.00030488268,"about_ca_system_score_gemma":0.0003116555,"threshold_uncertainty_score":0.9999389},"labels":[],"label_agreement":null},{"id":"W4390787184","doi":"10.20380/gi2016.21","title":"Assessing the Readability of Stacked Graphs","year":2016,"lang":"en","type":"article","venue":"","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Readability; Computer science; Programming language","score_opus":0.0384153603042611,"score_gpt":0.3077049804550657,"score_spread":0.2692896201508046,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390787184","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.39839715,0.000007893098,0.5934035,0.005096357,0.00005407774,0.00007563175,5.829574e-7,0.00006309546,0.0029016966],"genre_scores_gemma":[0.9909574,0.0000024355545,0.008831311,0.00006727019,0.0000055346013,0.000003938423,1.4050983e-7,0.00000137118,0.00013063652],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9992763,0.00010564793,0.00017541261,0.00018341246,0.00015929385,0.00009998088],"domain_scores_gemma":[0.998549,0.0004311125,0.000064604115,0.000840604,0.00008980348,0.00002488231],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006684555,0.00004640761,0.00006887945,0.000020980164,0.00006373768,0.000058697293,0.0005560183,0.000025051213,0.000027506321],"category_scores_gemma":[0.000139748,0.000019284827,0.00004356714,0.00019956812,0.00013016474,0.00062576076,0.000084431544,0.000028864986,0.000010761219],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000013199702,0.000055640558,0.014931247,0.0000068318727,0.0000045961206,1.1763727e-7,0.00023866117,6.875548e-7,0.021132383,0.49412417,0.00019495781,0.4693094],"study_design_scores_gemma":[0.00010630982,0.000048322207,0.5457423,0.000018761544,0.000004355106,0.0000035511887,0.00014532756,0.0011505537,0.11659506,0.33322105,0.002823847,0.00014061971],"about_ca_topic_score_codex":0.00004497398,"about_ca_topic_score_gemma":0.000013860352,"teacher_disagreement_score":0.59256023,"about_ca_system_score_codex":0.000017208242,"about_ca_system_score_gemma":0.00004498289,"threshold_uncertainty_score":0.10332297},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Reading comprehension; Comprehension; Reading (process); Sentence; Computer science; Cognition; Natural language processing; Artificial intelligence; Sample (material); Psychology; Cognitive psychology; Linguistics","score_opus":0.2292006550062576,"score_gpt":0.41553136314358546,"score_spread":0.18633070813732786,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391227797","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04994125,0.022070535,0.53300875,0.38089556,0.005057779,0.0010359164,0.000006668714,0.00028316394,0.0077003767],"genre_scores_gemma":[0.84331477,0.00013806619,0.15415604,0.0013171277,0.00053977396,0.000025844269,0.0000061792794,0.00001019621,0.00049201725],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99852574,0.0002062378,0.00019857587,0.0004062213,0.0005169924,0.0001462632],"domain_scores_gemma":[0.9987654,0.00042835355,0.000047767862,0.00028118337,0.00036336394,0.000113902315],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017046565,0.000104796316,0.00009004534,0.000095324816,0.00022265218,0.00077487703,0.00020566647,0.000032653,0.000029603489],"category_scores_gemma":[0.0006401949,0.00009690991,0.000021618347,0.00032869435,0.000015692593,0.0012716807,0.00008151884,0.00009931235,0.00010675185],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000070128626,0.0004982131,0.00039348673,0.00026869884,0.00014614686,0.000009297942,0.013742962,0.0017002141,0.1939696,0.63599116,0.035572145,0.11763793],"study_design_scores_gemma":[0.00007562586,0.000066307824,0.003512979,0.00020373781,0.00003635377,0.00013311022,0.0002806189,0.026795179,0.0027491401,0.005684999,0.9601875,0.00027447607],"about_ca_topic_score_codex":0.0003025889,"about_ca_topic_score_gemma":0.0000057273255,"teacher_disagreement_score":0.9246153,"about_ca_system_score_codex":0.00014149577,"about_ca_system_score_gemma":0.0002199734,"threshold_uncertainty_score":0.7472157},"labels":[],"label_agreement":null},{"id":"W4391296597","doi":"10.1352/1934-9556-61.2.82","title":"Résumés en Français","year":2024,"lang":"fr","type":"article","venue":"Intellectual and developmental disabilities","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Psychology","score_opus":0.0482418427436531,"score_gpt":0.27701672487887474,"score_spread":0.22877488213522165,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391296597","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4920795,0.06986557,0.124865316,0.028958367,0.009526083,0.00093831134,0.00018622009,0.0011507531,0.27242988],"genre_scores_gemma":[0.85440665,0.00089351705,0.0045678504,0.00027880122,0.00021301444,0.000042991778,0.000014208386,0.000020711926,0.13956222],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99798614,0.00015436056,0.0004367167,0.0007169622,0.00028164888,0.00042416743],"domain_scores_gemma":[0.9953914,0.004155618,0.000009137933,0.00021954783,0.00005628571,0.00016796293],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00039251643,0.00030057595,0.00024031448,0.00010905344,0.00023100758,0.0008991368,0.00034339694,0.00018823161,0.009664374],"category_scores_gemma":[0.0013980141,0.00027681552,0.00010502014,0.00043073605,0.0009909282,0.0009795908,0.00038643787,0.0003119275,0.017178578],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015766158,0.00012160163,0.00071875233,0.000700491,0.00007242605,0.000007808254,0.29820257,0.0000023768519,0.00017311856,0.20192702,0.07218173,0.42587635],"study_design_scores_gemma":[0.000087457636,0.00013526552,0.0029165288,0.00033960777,0.000017404045,0.00030550157,0.013555728,0.0075933216,0.001464574,0.042252854,0.93085927,0.00047251373],"about_ca_topic_score_codex":0.000674831,"about_ca_topic_score_gemma":0.00015842234,"teacher_disagreement_score":0.8586775,"about_ca_system_score_codex":0.00023842274,"about_ca_system_score_gemma":0.0003182006,"threshold_uncertainty_score":0.9999684},"labels":[],"label_agreement":null},{"id":"W4391652633","doi":"10.1075/lab.22013.whi","title":"Pronoun interpretation in Italian","year":2024,"lang":"en","type":"article","venue":"Linguistic Approaches to Bilingualism","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University; Université Laval; McGill University","funders":"","keywords":"Interpretation (philosophy); Pronoun; Linguistics; Psychology; Natural language processing; Computer science; Philosophy","score_opus":0.09952524450511449,"score_gpt":0.28389726005120736,"score_spread":0.18437201554609287,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391652633","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.057909496,0.00044769226,0.9252649,0.0025251699,0.0013109838,0.0006985105,0.000005567868,0.000637788,0.011199891],"genre_scores_gemma":[0.94630873,0.0000013479222,0.052894894,0.00015275806,0.00021482515,0.00008246234,0.000012872113,0.000013919063,0.00031820324],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99836886,0.000080291735,0.0003799586,0.00068663567,0.0002134364,0.00027078888],"domain_scores_gemma":[0.999054,0.0002114077,0.000031403313,0.00056157593,0.00004039316,0.0001012248],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00074161927,0.0001568151,0.00016253437,0.00027638333,0.000047218888,0.0003791435,0.00056677737,0.00008718309,0.000006373078],"category_scores_gemma":[0.0008739968,0.00014599177,0.000059625687,0.0007504378,0.000038138973,0.00016784035,0.00013608011,0.00020160555,0.0001474379],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010266431,0.00010355456,0.00020514161,0.00018995465,0.000012219196,0.00004501015,0.06560269,0.0005539064,0.00011952438,0.7356333,0.000050514544,0.19747393],"study_design_scores_gemma":[0.00015046612,0.00011659054,0.0019641502,0.00026429218,0.000013128352,0.000032126532,0.00044653966,0.81237036,0.0010346292,0.1574279,0.02564671,0.0005331191],"about_ca_topic_score_codex":0.00009022047,"about_ca_topic_score_gemma":0.00006732272,"teacher_disagreement_score":0.88839924,"about_ca_system_score_codex":0.00014265206,"about_ca_system_score_gemma":0.00014565131,"threshold_uncertainty_score":0.59533715},"labels":[],"label_agreement":null},{"id":"W4393672517","doi":"10.5281/zenodo.7674560","title":"DEplain-APA","year":2023,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science","score_opus":0.045894029508618026,"score_gpt":0.2616816573578845,"score_spread":0.21578762784926647,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393672517","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000021864806,0.00004451244,0.019820012,0.0013446831,0.00045632757,0.00053863594,0.9707377,0.0024941296,0.0045421193],"genre_scores_gemma":[0.00016146041,0.00015201065,0.00035511047,0.00017111216,0.00019186304,7.220988e-8,0.997671,0.00074074505,0.0005566034],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9973518,0.00042788486,0.00034743274,0.00082313444,0.0005990628,0.00045065559],"domain_scores_gemma":[0.99725294,0.0000706609,0.00017859403,0.001835055,0.00045751454,0.0002052408],"candidate_categories":["sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0010025395,0.00022444515,0.000219147,0.00039648457,0.0020683678,0.0019031723,0.0046632965,0.00019682622,0.0016909738],"category_scores_gemma":[0.000946794,0.00024041846,0.00008721136,0.0010716335,0.00013324988,0.00037468996,0.0032120147,0.00053463166,0.11943829],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005525446,0.000072724906,4.113781e-8,0.0000814664,0.000021436776,0.000016552141,0.00010749531,0.000011535495,0.000038548264,0.0021687362,0.95467466,0.042801302],"study_design_scores_gemma":[0.00014445571,0.00010563674,0.00008660206,0.000029345256,0.000010374351,0.00007047611,0.00002373102,0.00029863813,0.00002187343,0.00054526713,0.9984146,0.0002490386],"about_ca_topic_score_codex":0.0000857916,"about_ca_topic_score_gemma":0.0000025912193,"teacher_disagreement_score":0.117747314,"about_ca_system_score_codex":0.00019986092,"about_ca_system_score_gemma":0.000009712425,"threshold_uncertainty_score":0.9992308},"labels":[],"label_agreement":null},{"id":"W4393791440","doi":"10.5281/zenodo.8304430","title":"DEplain-APA","year":2023,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science","score_opus":0.045894029508618026,"score_gpt":0.2616816573578845,"score_spread":0.21578762784926647,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393791440","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000021864806,0.00004451244,0.019820012,0.0013446831,0.00045632757,0.00053863594,0.9707377,0.0024941296,0.0045421193],"genre_scores_gemma":[0.00016146041,0.00015201065,0.00035511047,0.00017111216,0.00019186304,7.220988e-8,0.997671,0.00074074505,0.0005566034],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9973518,0.00042788486,0.00034743274,0.00082313444,0.0005990628,0.00045065559],"domain_scores_gemma":[0.99725294,0.0000706609,0.00017859403,0.001835055,0.00045751454,0.0002052408],"candidate_categories":["sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0010025395,0.00022444515,0.000219147,0.00039648457,0.0020683678,0.0019031723,0.0046632965,0.00019682622,0.0016909738],"category_scores_gemma":[0.000946794,0.00024041846,0.00008721136,0.0010716335,0.00013324988,0.00037468996,0.0032120147,0.00053463166,0.11943829],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005525446,0.000072724906,4.113781e-8,0.0000814664,0.000021436776,0.000016552141,0.00010749531,0.000011535495,0.000038548264,0.0021687362,0.95467466,0.042801302],"study_design_scores_gemma":[0.00014445571,0.00010563674,0.00008660206,0.000029345256,0.000010374351,0.00007047611,0.00002373102,0.00029863813,0.00002187343,0.00054526713,0.9984146,0.0002490386],"about_ca_topic_score_codex":0.0000857916,"about_ca_topic_score_gemma":0.0000025912193,"teacher_disagreement_score":0.117747314,"about_ca_system_score_codex":0.00019986092,"about_ca_system_score_gemma":0.000009712425,"threshold_uncertainty_score":0.9992308},"labels":[],"label_agreement":null},{"id":"W4393791968","doi":"10.5281/zenodo.7674559","title":"DEplain-APA","year":2024,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Computer science","score_opus":0.0326686651163991,"score_gpt":0.2553250948946891,"score_spread":0.22265642977828998,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393791968","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000015963815,0.0001901706,0.015137851,0.0015736371,0.0005111987,0.0004746607,0.96968174,0.0017562711,0.010658511],"genre_scores_gemma":[0.00045358847,0.00015851852,0.0004534447,0.00021187987,0.00023913398,6.436024e-8,0.9973812,0.00067860796,0.00042356717],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9974824,0.0003475383,0.00033747128,0.0008801702,0.0005513407,0.00040106408],"domain_scores_gemma":[0.9975516,0.000043726395,0.00012278654,0.0017075015,0.00037790686,0.00019645659],"candidate_categories":["sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0008405009,0.00023567847,0.0002077395,0.00038392906,0.0015009315,0.0029701872,0.0041694324,0.00019503041,0.004744579],"category_scores_gemma":[0.00049177976,0.00024006661,0.0000965081,0.00086218154,0.00013414008,0.00037652854,0.0032159376,0.00066839834,0.13809754],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004893763,0.000073114476,2.1720545e-8,0.00015749183,0.000026460497,0.000022295533,0.00014811775,0.000005606128,0.000044479002,0.003948191,0.9418057,0.053763628],"study_design_scores_gemma":[0.00009656314,0.00010877075,0.000015688624,0.000048504717,0.00001819356,0.00014891256,0.000020931959,0.00035798363,0.000031940304,0.0010261694,0.9978754,0.00025093395],"about_ca_topic_score_codex":0.000027082908,"about_ca_topic_score_gemma":0.0000012293074,"teacher_disagreement_score":0.13335297,"about_ca_system_score_codex":0.00022173014,"about_ca_system_score_gemma":0.000011144601,"threshold_uncertainty_score":0.99979895},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.019835033893093094,"score_gpt":0.2663777210944307,"score_spread":0.2465426872013376,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4394844693","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.59100205,0.0009287627,0.40073594,0.0048047677,0.0001424793,0.00043862165,0.0001971538,0.00074064935,0.0010095632],"genre_scores_gemma":[0.9973135,0.000008754238,0.0020001864,0.00028005967,0.00007307357,0.00005389552,0.00009636773,0.00001271681,0.00016144152],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9980803,0.000055165943,0.00032356696,0.0006247238,0.0004835719,0.00043263924],"domain_scores_gemma":[0.9988393,0.00012295281,0.000044333032,0.0006739081,0.000057625035,0.00026184518],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033216504,0.00016576232,0.00020603315,0.00010595292,0.00010437593,0.0004408233,0.00034387194,0.00007791587,0.000016549875],"category_scores_gemma":[0.00004680593,0.00012218427,0.000059715625,0.00053998583,0.00011423131,0.0017260626,0.00010655693,0.00020709253,0.00016819932],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030088593,0.004384396,0.005970475,0.0031198424,0.00013370893,0.0002955072,0.01775353,0.0000763016,0.0003998879,0.31925324,0.0013175496,0.6469947],"study_design_scores_gemma":[0.0017647293,0.0031027705,0.03283994,0.001914306,0.00005655324,0.00042377136,0.0011076295,0.8333518,0.002294075,0.07830669,0.042465713,0.0023720283],"about_ca_topic_score_codex":0.00006525447,"about_ca_topic_score_gemma":0.000091655966,"teacher_disagreement_score":0.8332755,"about_ca_system_score_codex":0.00022665974,"about_ca_system_score_gemma":0.0004803689,"threshold_uncertainty_score":0.49825302},"labels":[],"label_agreement":null},{"id":"W4396590733","doi":"10.1007/s00146-024-01945-9","title":"GPT-4-Trinis: assessing GPT-4’s communicative competence in the English-speaking majority world","year":2024,"lang":"en","type":"article","venue":"AI & Society","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria; McMaster University; University of Toronto","funders":"Social Sciences and Humanities Research Council","keywords":"Communicative competence; Psychology; Communicative language teaching; Competence (human resources); Linguistics; Communication; Pedagogy; Philosophy; Social psychology","score_opus":0.033409473284503534,"score_gpt":0.3192342277502775,"score_spread":0.28582475446577393,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396590733","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20426063,0.008059261,0.6623964,0.06874395,0.0026398897,0.0016774423,0.000024569144,0.0023168589,0.049881056],"genre_scores_gemma":[0.9825852,0.00008291362,0.015134126,0.0019939474,0.00011078555,0.00003533787,0.0000064804526,0.000008269106,0.000042940716],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99812806,0.00040617833,0.00031793793,0.00046804766,0.00036479483,0.00031499227],"domain_scores_gemma":[0.99734133,0.0012206655,0.00007121793,0.0012061347,0.00011719477,0.000043450556],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0019580498,0.00015899501,0.00017453,0.000042816075,0.00036198203,0.0011066766,0.0019346104,0.000077914556,0.000009605842],"category_scores_gemma":[0.00008812852,0.00012062033,0.00018933293,0.001387461,0.00020557766,0.0013178193,0.00041452344,0.000892983,0.000030055546],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000026839978,0.00030547983,0.0075253984,0.00015611005,0.00006118338,0.000014608884,0.39034587,0.00008540352,0.0005248991,0.5001387,0.005491166,0.095348515],"study_design_scores_gemma":[0.0005866589,0.000083894236,0.28374952,0.0007296066,0.000051982857,0.000030685733,0.025894895,0.28894842,0.00086128264,0.054584306,0.3433882,0.0010905535],"about_ca_topic_score_codex":0.00024402003,"about_ca_topic_score_gemma":0.00030737196,"teacher_disagreement_score":0.77832454,"about_ca_system_score_codex":0.00018801485,"about_ca_system_score_gemma":0.00015429308,"threshold_uncertainty_score":0.99993026},"labels":[],"label_agreement":null},{"id":"W4396928327","doi":"10.31235/osf.io/wqeg7","title":"Does Readability in MOOC Attract Potential Learners?","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Athabasca University; National Research Council Canada","funders":"","keywords":"Readability; Computer science; Mathematics education; Psychology","score_opus":0.01871363278137474,"score_gpt":0.27420816565635064,"score_spread":0.2554945328749759,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396928327","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7236031,0.0002538583,0.2345577,0.02311555,0.00490374,0.0011233079,0.000029805522,0.0013597208,0.011053164],"genre_scores_gemma":[0.9871727,0.000028712233,0.01065307,0.00007831556,0.00012905136,0.000054865322,0.000019725456,0.000012395452,0.0018511226],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99722016,0.00018858345,0.00052844157,0.0013647745,0.00038361148,0.00031445542],"domain_scores_gemma":[0.9977422,0.00010491126,0.00009562998,0.0018962796,0.00006846406,0.00009254679],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009830432,0.00027068093,0.00032659675,0.00019676138,0.000044817756,0.00054251147,0.0014166232,0.00040460765,0.00009674176],"category_scores_gemma":[0.00009713246,0.0001685543,0.00020549966,0.00028887737,0.00008666085,0.00021637122,0.002582438,0.0012480825,0.00024533548],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000048892798,0.0011377604,0.007190769,0.0020883596,0.00011026342,0.00016791042,0.006129888,0.011012847,0.0017134366,0.1872617,0.002278427,0.78085977],"study_design_scores_gemma":[0.00010680813,0.000052121602,0.048196163,0.00014990105,0.000021510023,0.000009970546,0.00013796733,0.13946372,0.0019792905,0.8066832,0.002462831,0.0007365302],"about_ca_topic_score_codex":0.0019151961,"about_ca_topic_score_gemma":0.0008285439,"teacher_disagreement_score":0.78012323,"about_ca_system_score_codex":0.00023397172,"about_ca_system_score_gemma":0.0003092789,"threshold_uncertainty_score":0.68734443},"labels":[],"label_agreement":null},{"id":"W4398788073","doi":"10.5114/aic.2024.139632","title":"Clarification of misused terminology in the context of thebesian veins","year":2024,"lang":"en","type":"article","venue":"Advances in Interventional Cardiology","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Terminology; Context (archaeology); Medicine; Archaeology; History; Philosophy; Linguistics","score_opus":0.024138864953434907,"score_gpt":0.3246274678187292,"score_spread":0.3004886028652943,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4398788073","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5449309,0.01738503,0.42769676,0.0039001587,0.0012771054,0.00050952827,0.00003647303,0.0000512614,0.004212812],"genre_scores_gemma":[0.9990912,0.00011499812,0.0006662991,0.00003617805,0.000022178552,0.000042286807,0.000012408462,0.0000021304847,0.000012306587],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99877685,0.00037118548,0.00042702103,0.00022291871,0.00009940475,0.000102589285],"domain_scores_gemma":[0.99907804,0.00047197193,0.000083286686,0.00031346577,0.00004578549,0.000007481411],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00074296887,0.00006104039,0.00019117651,0.00016972475,0.000011504477,0.000008182579,0.0005595805,0.000074015625,0.000006628312],"category_scores_gemma":[0.00009341364,0.000045882058,0.00013296076,0.00027919398,0.0001856986,0.00026052626,0.000045056404,0.00014629586,0.000004461483],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016789416,0.00010892555,0.010683108,0.00011030899,0.000015048498,0.0000094355955,0.0010467852,0.00023619944,0.0006851471,0.899556,0.000029792773,0.087502494],"study_design_scores_gemma":[0.0006989256,0.0009797306,0.54980874,0.00035195655,0.000018045688,0.00020103576,0.0015791727,0.006996378,0.0032484422,0.4012289,0.034652073,0.00023660342],"about_ca_topic_score_codex":0.000034098983,"about_ca_topic_score_gemma":0.00016294318,"teacher_disagreement_score":0.5391256,"about_ca_system_score_codex":0.000033830453,"about_ca_system_score_gemma":0.000036423575,"threshold_uncertainty_score":0.1871016},"labels":[],"label_agreement":null},{"id":"W4399377830","doi":"10.1109/iciet60671.2024.10542803","title":"Breaking Language Barriers: The Power of Machine Translation in Online Learning","year":2024,"lang":"en","type":"article","venue":"","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Systems, Applications & Products in Data Processing (Canada)","funders":"","keywords":"Computer science; Artificial intelligence; Machine translation; Feature (linguistics); World Wide Web; Product (mathematics); Natural language processing; Machine learning; Linguistics; Mathematics","score_opus":0.013529347516024408,"score_gpt":0.27732357694348975,"score_spread":0.26379422942746533,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399377830","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4801248,0.0016334928,0.5112589,0.0041999365,0.00010256859,0.00011880182,0.000002990917,0.00016675456,0.002391734],"genre_scores_gemma":[0.996906,0.0000039303522,0.0029093549,0.000050568528,0.000008651947,0.0000015540832,0.0000039014585,0.0000025367394,0.00011354204],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99950975,0.000059774367,0.00013334036,0.00012962354,0.00009923929,0.000068264686],"domain_scores_gemma":[0.999612,0.00017487553,0.000015792466,0.0001719819,0.000010442767,0.000014920355],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034212708,0.000040101524,0.000050299845,0.000058034384,0.000025877927,0.000049780407,0.0002008648,0.000023261657,0.000058202124],"category_scores_gemma":[0.000043050244,0.000025627858,0.000027842074,0.0003179577,0.00001749754,0.00021333274,0.000021724387,0.00012469015,0.000004618539],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004592995,0.000040204755,0.004053341,0.000049976763,0.000010145936,0.0000063448056,0.06407142,0.0017022422,0.00937787,0.0605722,0.000022950155,0.8600887],"study_design_scores_gemma":[0.00012122116,0.00004531221,0.02690706,0.00005484129,0.0000037480713,0.000009183079,0.002588245,0.96299714,0.0019586247,0.0015017712,0.0037115833,0.00010124231],"about_ca_topic_score_codex":0.00022112929,"about_ca_topic_score_gemma":0.00027527715,"teacher_disagreement_score":0.96129495,"about_ca_system_score_codex":0.000012526975,"about_ca_system_score_gemma":0.00002231063,"threshold_uncertainty_score":0.10450737},"labels":[],"label_agreement":null},{"id":"W4399450555","doi":"10.7202/1111723ar","title":"Les facteurs influençant la profondeur de traitement de la rétroaction corrective écrite des apprenants de français langue étrangère","year":2024,"lang":"fr","type":"article","venue":"˜La œRevue de l'AQEFLS/Revue de l'AQEFLS","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Victoria; Université du Québec en Abitibi-Témiscamingue","funders":"","keywords":"Humanities; Philosophy; Art","score_opus":0.034947942020777445,"score_gpt":0.29077554171286235,"score_spread":0.2558275996920849,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399450555","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6559756,0.0069290632,0.32296675,0.004704181,0.0013439674,0.0013789448,0.00040817008,0.00086365285,0.005429698],"genre_scores_gemma":[0.9742106,0.00071201375,0.019292798,0.0005705327,0.0011270434,0.00059319724,0.00009263495,0.00019521522,0.0032059313],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9912473,0.0029420792,0.0012222135,0.0018190352,0.0005133002,0.0022560963],"domain_scores_gemma":[0.99426836,0.0027410504,0.00039142338,0.0013175805,0.00037900955,0.0009025585],"candidate_categories":["metaepi_narrow","scholarly_communication","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0040821214,0.001045882,0.0009517206,0.00059155945,0.00067484763,0.0017110612,0.0015789632,0.0014249334,0.00017333023],"category_scores_gemma":[0.00088819256,0.0011857077,0.0006810036,0.001449694,0.00086795946,0.0016823788,0.00031982968,0.0022879296,0.00020514363],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028222756,0.0016594955,0.08549509,0.005674063,0.0005748593,0.001869074,0.16583073,0.010159917,0.041168563,0.08021777,0.0030132507,0.604055],"study_design_scores_gemma":[0.0017845737,0.00061397656,0.61708266,0.0037736956,0.00081401056,0.0062436364,0.0042514517,0.15209661,0.020916775,0.027742263,0.16235226,0.0023280832],"about_ca_topic_score_codex":0.007852262,"about_ca_topic_score_gemma":0.0034374455,"teacher_disagreement_score":0.6017269,"about_ca_system_score_codex":0.0023178381,"about_ca_system_score_gemma":0.0012662538,"threshold_uncertainty_score":0.99987143},"labels":[],"label_agreement":null},{"id":"W4399612718","doi":"10.5539/elt.v17n7p38","title":"The Effectiveness of the Integration of ChatGPT into Flipped Classrooms from Teachers’ and Learners’ Perspectives","year":2024,"lang":"en","type":"article","venue":"English Language Teaching","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology; Flipped classroom; Class (philosophy); Mathematics education; Teaching method; Language acquisition; Language proficiency; Qualitative property; Multimethodology; Student engagement; Qualitative research; Pedagogy; Computer science","score_opus":0.007002628958308093,"score_gpt":0.2579146049192551,"score_spread":0.250911975960947,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399612718","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9297479,0.0028392158,0.06575515,0.00024247511,0.0003011869,0.00018480439,0.0000034483821,0.00009750792,0.0008283149],"genre_scores_gemma":[0.9986035,0.000012940664,0.00122784,0.0000059282474,0.00007501962,0.000010254157,0.0000027515684,0.0000069167495,0.00005484883],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9983753,0.00091960526,0.00016406034,0.00026211786,0.00018218489,0.00009673456],"domain_scores_gemma":[0.99786,0.0015394462,0.0000657387,0.00047998547,0.00003398402,0.000020847723],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0019462096,0.00009204547,0.00012045152,0.000042478314,0.00016628731,0.00016380052,0.00046298112,0.0000551112,0.0000020846219],"category_scores_gemma":[0.0014747197,0.000052100324,0.00007062127,0.00016428826,0.00013703939,0.00036791316,0.00014983947,0.00039802244,5.467022e-7],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000085538995,0.000024637144,0.0007287528,0.000034312292,0.00002784212,5.316735e-7,0.7080489,0.000014327165,0.045575425,0.08032098,0.000007156055,0.16520861],"study_design_scores_gemma":[0.00057460164,0.00018026136,0.09830448,0.0009846375,0.000076280056,0.000005002236,0.7657424,0.03275394,0.074707545,0.024523485,0.0017178386,0.00042953034],"about_ca_topic_score_codex":0.000822373,"about_ca_topic_score_gemma":0.00014317686,"teacher_disagreement_score":0.16477908,"about_ca_system_score_codex":0.00006426206,"about_ca_system_score_gemma":0.000034930756,"threshold_uncertainty_score":0.21245895},"labels":[],"label_agreement":null},{"id":"W4399991839","doi":"","title":"Organisation des fonctions lexicales pour un meilleur accès à l'information dans le dico","year":2006,"lang":"fr","type":"article","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Gynecology; Medicine","score_opus":0.014883632348303666,"score_gpt":0.21222545862650435,"score_spread":0.19734182627820068,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399991839","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09670963,0.0009195594,0.8191903,0.036916018,0.00035433256,0.0003950846,0.000054407927,0.00037750832,0.045083124],"genre_scores_gemma":[0.87810165,0.00027561912,0.10418407,0.00016078082,0.00007976375,0.000052555344,0.0004531523,0.0000305804,0.016661847],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9931853,0.00408149,0.00092446554,0.0006626525,0.0005695727,0.00057651364],"domain_scores_gemma":[0.9937931,0.0012368995,0.0005613897,0.0018805382,0.002296957,0.00023115227],"candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.004102532,0.00036285893,0.00030332015,0.00022717039,0.0016845284,0.0013082221,0.0013883257,0.00030799521,0.00027013087],"category_scores_gemma":[0.0011488028,0.00041567962,0.00021886022,0.0011123646,0.0007699624,0.0031536038,0.00046637384,0.00038647154,0.00051668327],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000060501056,0.0009521596,0.0038976017,0.000082766484,0.000027607837,0.0000015472145,0.0120891845,0.00027526284,0.007111063,0.7371019,0.0017024254,0.23675239],"study_design_scores_gemma":[0.0018909243,0.0000040793325,0.30379793,0.0007683534,0.00011946481,0.00013286578,0.0018764497,0.1847886,0.19593766,0.17939414,0.13004985,0.0012396789],"about_ca_topic_score_codex":0.01079174,"about_ca_topic_score_gemma":0.0055364817,"teacher_disagreement_score":0.781392,"about_ca_system_score_codex":0.00041199775,"about_ca_system_score_gemma":0.0006407016,"threshold_uncertainty_score":0.99982953},"labels":[],"label_agreement":null},{"id":"W4400352013","doi":"10.1109/smartnets61466.2024.10577676","title":"Towards a Reliable French Speech Recognition Tool for an Automated Diagnosis of Learning Disabilities","year":2024,"lang":"en","type":"article","venue":"","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal; Collège de Maisonneuve; Laboratoire Recherche Informatique Maisonneuve","funders":"","keywords":"Computer science; Speech recognition; Natural language processing; Artificial intelligence","score_opus":0.04460580678073276,"score_gpt":0.3071121234356765,"score_spread":0.2625063166549437,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400352013","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.72312564,0.00008911391,0.27096245,0.0009062392,0.00029464217,0.00047650415,0.00002214346,0.0020838669,0.002039397],"genre_scores_gemma":[0.9132504,0.000017837305,0.08596721,0.000022587401,0.000036361598,0.00018661619,0.00004517566,0.0000074907357,0.0004663577],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9990182,0.000052263316,0.00026348938,0.00035107005,0.00015688401,0.0001581148],"domain_scores_gemma":[0.9990799,0.00040179116,0.00003385534,0.00030863684,0.00013931683,0.00003650066],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00054425804,0.0000873017,0.00012635326,0.00007832613,0.00007500269,0.00020200091,0.0002565655,0.00006790245,0.000096467695],"category_scores_gemma":[0.00037676518,0.00007531495,0.00007132301,0.00032754836,0.00004323984,0.0009398053,0.000049626724,0.00007642651,0.00003016024],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006355108,0.00020575404,0.00428162,0.00049288356,0.000022216256,5.8951235e-7,0.0032838413,0.00018029984,0.0010487974,0.021733792,0.0054132924,0.96333057],"study_design_scores_gemma":[0.00017116882,0.00068752246,0.00655034,0.00013549985,0.000022231858,0.000008378489,0.00051355024,0.8548583,0.057484373,0.06813611,0.011124163,0.00030838404],"about_ca_topic_score_codex":0.00042474474,"about_ca_topic_score_gemma":0.000046419413,"teacher_disagreement_score":0.9630222,"about_ca_system_score_codex":0.000050242077,"about_ca_system_score_gemma":0.00008234474,"threshold_uncertainty_score":0.30712548},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Milton District Hospital","funders":"","keywords":"Psychology; Computer science; Linguistics; Philosophy","score_opus":0.042605813696583734,"score_gpt":0.3892562671185863,"score_spread":0.34665045342200257,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400663124","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[9.852523e-8,0.50883245,0.4907283,0.000023157196,0.000024664429,0.00032628668,0.0000069669386,0.000033706987,0.000024385316],"genre_scores_gemma":[0.000027515636,0.6650732,0.33457866,0.000024622123,0.000021178534,0.00018305493,0.000076226905,0.000011327688,0.000004206469],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989246,0.000033347973,0.0005071291,0.0003224487,0.00008643641,0.00012604443],"domain_scores_gemma":[0.99920136,0.00044719072,0.00012621925,0.00015863491,0.000041229312,0.000025352478],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00087907613,0.00017637447,0.000641937,0.00017942727,0.000019028354,0.000038079048,0.00021259197,0.00008207597,7.5675e-7],"category_scores_gemma":[0.00005175592,0.00015784102,0.0001061313,0.00034338215,0.0000057450943,0.000107823784,0.00009475322,0.000137171,0.0000012835164],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[1.5022518e-7,0.000009754374,5.7053042e-9,0.085184865,0.000017329481,1.367546e-7,0.00017623979,0.0037353935,0.0000010192028,0.20714095,0.000012430433,0.7037217],"study_design_scores_gemma":[0.000069432856,0.000007882169,8.8536706e-7,0.025666686,0.000073252006,0.0000051689176,0.000006380975,0.8287368,6.7368836e-7,0.006471451,0.13878375,0.00017763881],"about_ca_topic_score_codex":0.0000027492495,"about_ca_topic_score_gemma":3.2718046e-7,"teacher_disagreement_score":0.8250014,"about_ca_system_score_codex":0.000040949744,"about_ca_system_score_gemma":0.00006226378,"threshold_uncertainty_score":0.643657},"labels":[],"label_agreement":null},{"id":"W4401044086","doi":"10.18653/v1/2024.findings-naacl.274","title":"Fumbling in Babel: An Investigation into ChatGPT’s Language Identification Ability","year":2024,"lang":"en","type":"article","venue":"","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Alliance de recherche numérique du Canada; Social Sciences and Humanities Research Council of Canada; Natural Sciences and Engineering Research Council of Canada; Canada Research Chairs","keywords":"Identification (biology); Computer science; Natural language processing; Artificial intelligence; Linguistics; Computer vision; Philosophy","score_opus":0.021733055645058025,"score_gpt":0.301173562386556,"score_spread":0.279440506741498,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401044086","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.79311365,0.00016803817,0.2035147,0.002182957,0.00022479688,0.00016760678,6.405259e-7,0.00044814977,0.00017948388],"genre_scores_gemma":[0.99015474,0.0000054638085,0.009489093,0.00011044896,0.0000435894,0.000030800693,0.000023194312,0.000005484941,0.00013720713],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987313,0.00012509647,0.0003053057,0.00051445985,0.00018861513,0.00013519246],"domain_scores_gemma":[0.9991154,0.000087605746,0.000030450181,0.0006542277,0.000043585344,0.00006874477],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012126549,0.0000833172,0.00007913868,0.00018215326,0.000058845148,0.00043385784,0.00040827345,0.000067373454,0.000018949375],"category_scores_gemma":[0.00008049942,0.000078287245,0.000028291568,0.0007407744,0.000042984026,0.0018825702,0.000060090482,0.00012412986,0.000100455916],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000028567197,0.000104177314,0.0071098786,0.00021818488,0.0000049010264,0.000005411254,0.051637754,0.00019708,0.17411335,0.3392843,0.0000839256,0.4272382],"study_design_scores_gemma":[0.00010698234,0.000040240036,0.20651779,0.00005344623,0.0000038681223,0.000005295955,0.0010229532,0.6350267,0.044372376,0.11223589,0.0003531416,0.00026134425],"about_ca_topic_score_codex":0.0008791258,"about_ca_topic_score_gemma":0.0012255586,"teacher_disagreement_score":0.6348296,"about_ca_system_score_codex":0.0001297988,"about_ca_system_score_gemma":0.00008015319,"threshold_uncertainty_score":0.4183701},"labels":[],"label_agreement":null},{"id":"W4401457226","doi":"10.31234/osf.io/wqs3y","title":"Long-lag morphological priming and inflectional paradigm size effects in Estonian and Finnish text reading","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Social Sciences and Humanities Research Council of Canada; Eesti Teadusagentuur","keywords":"Estonian; Priming (agriculture); Reading (process); Context (archaeology); Sentence; Linguistics; Psychology; Computer science; History; Artificial intelligence; Biology","score_opus":0.017916838335177158,"score_gpt":0.2701940601135351,"score_spread":0.25227722177835793,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401457226","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9288208,0.0007843665,0.06487829,0.0030163813,0.00040086795,0.0005266576,0.000002452737,0.00026500184,0.001305196],"genre_scores_gemma":[0.97835606,0.000062623185,0.020998685,0.0002184211,0.000057128174,0.000073672985,0.000004445763,0.000009305514,0.00021963591],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99809587,0.00012016579,0.00031739872,0.0010111264,0.00019972412,0.0002556926],"domain_scores_gemma":[0.99846256,0.0008803627,0.000072485214,0.00045218476,0.000022665701,0.000109715824],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00052703574,0.00024267862,0.00030228082,0.00015509954,0.00009295087,0.0005529468,0.00034963322,0.00034386254,0.000008732034],"category_scores_gemma":[0.00026550388,0.00021282806,0.00004843543,0.00023219216,0.00012156026,0.00016333956,0.0015255946,0.00078578666,0.00001399106],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000055423217,0.0004051923,0.1530529,0.0028044262,0.00011674763,0.0007238227,0.0064524473,0.0011377512,0.002840523,0.5169672,0.0009571805,0.31448638],"study_design_scores_gemma":[0.00021007805,0.00007839325,0.74289864,0.00025173245,0.000016568894,0.00027296232,0.000011774272,0.03672603,0.0004117326,0.21842489,0.00028886483,0.0004083143],"about_ca_topic_score_codex":0.0002511451,"about_ca_topic_score_gemma":0.00012824479,"teacher_disagreement_score":0.5898458,"about_ca_system_score_codex":0.00011890381,"about_ca_system_score_gemma":0.00011573355,"threshold_uncertainty_score":0.8678877},"labels":[],"label_agreement":null},{"id":"W4401854735","doi":"10.5430/wjel.v15n1p9","title":"Gender Issues between Gemini and ChatGPT: The Case of English-Arabic Translation","year":2024,"lang":"en","type":"article","venue":"World Journal of English Language","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Arabic; Computer science; Translation (biology); Natural language processing; Test (biology); Artificial intelligence; Face (sociological concept); Machine translation; Suite; Linguistics; Political science","score_opus":0.024007042465658747,"score_gpt":0.2881520704045148,"score_spread":0.264145027938856,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401854735","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94286716,0.033517025,0.016178487,0.0011928874,0.0017137249,0.0002235949,0.000020597963,0.000106746724,0.0041797557],"genre_scores_gemma":[0.9960952,0.00007950553,0.0024978532,0.000029848985,0.0011941212,0.0000013879048,0.0000015472601,0.000007533133,0.000093041446],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989981,0.00011967133,0.00040167634,0.00015798052,0.00019445382,0.00012813452],"domain_scores_gemma":[0.99868375,0.00046397749,0.0001408465,0.00029183843,0.00035369286,0.000065916036],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010774684,0.00009889759,0.00018718136,0.00019783239,0.000060869,0.00017145237,0.0003341105,0.000043459826,0.00002197051],"category_scores_gemma":[0.00041973116,0.000065915614,0.00009581703,0.0004326795,0.00006767044,0.0006388469,0.000039161016,0.00028262375,0.0000010980117],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013279115,0.000052901818,0.0012099106,0.00021401292,0.00012504561,0.00043970378,0.48128006,0.000050455383,0.0004944819,0.022397032,0.0010971002,0.49262604],"study_design_scores_gemma":[0.0036359075,0.0010704924,0.04810535,0.0015275198,0.0010933344,0.0018941131,0.09622873,0.015378683,0.033731584,0.024508428,0.7708276,0.0019982904],"about_ca_topic_score_codex":0.000028930472,"about_ca_topic_score_gemma":0.000059853035,"teacher_disagreement_score":0.76973045,"about_ca_system_score_codex":0.000021339454,"about_ca_system_score_gemma":0.00004668435,"threshold_uncertainty_score":0.2687961},"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,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_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","score_opus":0.08136452976121444,"score_gpt":0.42053083430275,"score_spread":0.33916630454153557,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401873941","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9015629,0.03267819,0.032540932,0.029104374,0.00036858904,0.0026021036,0.00008572469,0.00006265972,0.0009944941],"genre_scores_gemma":[0.99129426,0.008280548,0.00016142115,0.0000570847,0.000013950271,0.000054908123,0.00006946726,0.0000046163445,0.00006375753],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9978771,0.00054418796,0.00059827545,0.0003678856,0.00044416977,0.00016834302],"domain_scores_gemma":[0.99832326,0.0008467408,0.00015363567,0.00027728584,0.0003536146,0.00004547739],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005202727,0.000092639486,0.00024722633,0.00022699442,0.000074971475,0.00031767203,0.00084351434,0.000048423975,0.000025923375],"category_scores_gemma":[0.0011524309,0.00005945785,0.00004485313,0.0006113759,0.00016680779,0.0005560881,0.000727306,0.00051369594,0.000002847124],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008115473,0.00030616968,0.060071994,0.0065363445,0.0000649825,0.0000057426982,0.0020002495,0.000042534448,0.007289488,0.20053343,0.00020522405,0.72286266],"study_design_scores_gemma":[0.0026721102,0.00069648115,0.3989647,0.097481824,0.000059366943,0.0000588364,0.00680567,0.29702538,0.007435258,0.15428081,0.03383131,0.0006882577],"about_ca_topic_score_codex":0.00078457675,"about_ca_topic_score_gemma":0.00011410174,"teacher_disagreement_score":0.7221744,"about_ca_system_score_codex":0.00010577214,"about_ca_system_score_gemma":0.000105390165,"threshold_uncertainty_score":0.30633187},"labels":[],"label_agreement":null},{"id":"W4402671017","doi":"10.18653/v1/2024.arabicnlp-1.5","title":"Strategies for Arabic Readability Modeling","year":2024,"lang":"en","type":"article","venue":"","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"York University; New York University Abu Dhabi","keywords":"Readability; Arabic; Computer science; Natural language processing; Artificial intelligence; Programming language; Linguistics","score_opus":0.050073713926361625,"score_gpt":0.3045772543765915,"score_spread":0.2545035404502299,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402671017","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015573293,0.00013344019,0.9767259,0.0021738664,0.00019536163,0.00018130933,0.0000018443695,0.0005615742,0.0044534206],"genre_scores_gemma":[0.94105715,0.0000027572444,0.058570947,0.0000612609,0.000037160535,0.000040927494,0.0000024689512,0.000003354591,0.00022397438],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9992677,0.000016947057,0.00014703172,0.00034074602,0.00009343471,0.00013414407],"domain_scores_gemma":[0.99936473,0.00012993942,0.0000074411987,0.00040618607,0.0000589305,0.000032782624],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00036982927,0.00006373905,0.00006611813,0.00003732732,0.00006383118,0.00047603593,0.00030945177,0.00003818469,0.0000097872635],"category_scores_gemma":[0.00002258437,0.00004950983,0.000059388574,0.0001614488,0.000017486305,0.00088598765,0.000038223865,0.000053156677,0.000027608363],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000013143946,0.000013527158,0.0000051278553,0.00005710525,0.000003387917,2.397513e-7,0.00032533595,0.0026486956,0.00041148235,0.94011605,0.00026181867,0.056155894],"study_design_scores_gemma":[0.0000110091005,0.000015112119,0.000018886987,0.0000045478596,0.0000013973232,0.0000014280184,0.000087727974,0.68922573,0.00027839883,0.3081891,0.0021173537,0.00004932716],"about_ca_topic_score_codex":0.000048387457,"about_ca_topic_score_gemma":0.000028216642,"teacher_disagreement_score":0.9254839,"about_ca_system_score_codex":0.000033234617,"about_ca_system_score_gemma":0.00013898747,"threshold_uncertainty_score":0.45904255},"labels":[],"label_agreement":null},{"id":"W4402683016","doi":"10.18653/v1/2024.textgraphs-1.8","title":"Semantic Graphs for Syntactic Simplification: A Revisit from the Age of LLM","year":2024,"lang":"en","type":"article","venue":"","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Natural language processing; Artificial intelligence","score_opus":0.03173685682643382,"score_gpt":0.28075379192165173,"score_spread":0.2490169350952179,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402683016","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015880326,0.00063235586,0.97222716,0.009829971,0.00021281876,0.000396695,0.000013074445,0.00017360094,0.0006340212],"genre_scores_gemma":[0.98946,0.000026055122,0.009921346,0.0002768771,0.000043138498,0.00004061997,0.000017183713,0.0000049364207,0.00020983719],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99916947,0.000045339173,0.00023177463,0.00030453768,0.00014190565,0.00010699551],"domain_scores_gemma":[0.9980031,0.0011000296,0.0000402038,0.00077566615,0.000057856378,0.000023134497],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035488457,0.00007374822,0.000107546395,0.00003549841,0.000077191355,0.00019474383,0.0006196031,0.000036981837,0.000027411521],"category_scores_gemma":[0.000100788704,0.000046552916,0.000104353756,0.0003668069,0.000043033917,0.00025985145,0.00005442799,0.00006162095,0.000037782174],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000036842325,0.000047527654,0.00025126274,0.00011072422,0.00003356095,0.0000012895541,0.0010492054,0.000007529922,0.004938311,0.93023694,0.0028963226,0.06042363],"study_design_scores_gemma":[0.00023990416,0.00017876303,0.052494217,0.00023749207,0.000114349474,0.000014183616,0.00026740873,0.1183722,0.010006491,0.6847013,0.13299029,0.00038339826],"about_ca_topic_score_codex":0.00012147987,"about_ca_topic_score_gemma":0.00003190225,"teacher_disagreement_score":0.9735797,"about_ca_system_score_codex":0.0000161929,"about_ca_system_score_gemma":0.000044269902,"threshold_uncertainty_score":0.18983728},"labels":[],"label_agreement":null},{"id":"W4402946729","doi":"10.1167/jov.24.10.1022","title":"A psychophysical approach for investigating format readability online","year":2024,"lang":"en","type":"article","venue":"Journal of Vision","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Readability; Computer science; Psychology; Programming language","score_opus":0.03949815641872762,"score_gpt":0.3442729548641129,"score_spread":0.3047747984453853,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402946729","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19027935,0.00016229096,0.8068806,0.0021697627,0.0002625846,0.00011468974,0.0000033493327,0.00004019365,0.000087209744],"genre_scores_gemma":[0.69380474,0.000007635459,0.30585903,0.00008840445,0.0002159062,0.0000021971891,0.0000032943265,0.0000042501165,0.0000145558015],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9989627,0.000051397757,0.00042654236,0.00017402989,0.00026784863,0.00011747238],"domain_scores_gemma":[0.99913394,0.00022933955,0.00013556848,0.00025422723,0.00015796864,0.0000889779],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008751054,0.00007525903,0.00014932976,0.00008510344,0.00006593555,0.00018755795,0.0003960354,0.000050802326,0.0000010312418],"category_scores_gemma":[0.00017746478,0.000052629275,0.00015686765,0.0002619018,0.00003629836,0.0009654044,0.00004910512,0.00020827292,0.0000021245528],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000040391682,0.00063210755,0.00013518846,0.00039141736,0.000027152002,0.0000028303457,0.0016827178,0.00047616652,0.02587851,0.030420454,0.005164536,0.93514854],"study_design_scores_gemma":[0.00020915693,0.00062620646,0.0066718766,0.00016607832,0.000014895082,0.00009613713,0.00006385056,0.9206571,0.001021929,0.061179932,0.009170739,0.00012212337],"about_ca_topic_score_codex":0.0000017348071,"about_ca_topic_score_gemma":4.126604e-7,"teacher_disagreement_score":0.9350264,"about_ca_system_score_codex":0.000060284707,"about_ca_system_score_gemma":0.000093550225,"threshold_uncertainty_score":0.21461596},"labels":[],"label_agreement":null},{"id":"W4402946852","doi":"10.1167/jov.24.10.1024","title":"The effects of variable fonts on sentence-level reading","year":2024,"lang":"en","type":"article","venue":"Journal of Vision","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Reading (process); Sentence; Variable (mathematics); Computer science; Natural language processing; Linguistics; Mathematics; Philosophy","score_opus":0.016848552346685045,"score_gpt":0.2872712614771783,"score_spread":0.27042270913049327,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402946852","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22529192,0.001245396,0.76518977,0.0033485675,0.0035617936,0.00016388133,0.0000011074211,0.000035955094,0.0011616392],"genre_scores_gemma":[0.993209,0.00010958701,0.0063844174,0.000042057996,0.00007490216,5.3890636e-7,8.647737e-8,0.0000029001963,0.0001765311],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.999175,0.000072326,0.00026044258,0.00009206587,0.0003125541,0.00008760814],"domain_scores_gemma":[0.9985273,0.00097416126,0.00013206704,0.00022102978,0.00010810669,0.000037333637],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009054723,0.000048896774,0.000092815186,0.000072718074,0.000080019156,0.00012535264,0.0003921264,0.000030935793,0.0000013648435],"category_scores_gemma":[0.00033318892,0.00002706589,0.000064699416,0.00023164565,0.000020144917,0.00034214059,0.000045765493,0.00014919094,0.000007863643],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000047811543,0.00015168589,0.00016259767,0.0002115169,0.00004268991,0.000035048015,0.0010287951,0.00014124837,0.14918683,0.16113989,0.0060642785,0.6817876],"study_design_scores_gemma":[0.0016155471,0.007819869,0.21132144,0.010652372,0.00011704813,0.0006647191,0.00026373166,0.22472739,0.18974736,0.26532653,0.08715241,0.0005915711],"about_ca_topic_score_codex":0.000005595137,"about_ca_topic_score_gemma":4.4379212e-7,"teacher_disagreement_score":0.76791704,"about_ca_system_score_codex":0.000045577737,"about_ca_system_score_gemma":0.00006809722,"threshold_uncertainty_score":0.12087785},"labels":[],"label_agreement":null},{"id":"W4403440036","doi":"10.5121/ijaia.2024.15504","title":"Transformer-Based Regression Models for Assessing Reading Passage Complexity: A Deep Learning Approach in Natural Language Processing","year":2024,"lang":"en","type":"article","venue":"International Journal of Artificial Intelligence & Applications","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Laurentian University","funders":"","keywords":"Computer science; Transformer; Artificial intelligence; Natural language processing; Deep learning; Regression; Machine learning; Statistics; Electrical engineering; Mathematics","score_opus":0.07330698097469918,"score_gpt":0.37530803584542255,"score_spread":0.3020010548707234,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403440036","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0037597492,0.0009898128,0.9925464,0.001639859,0.00025453806,0.00039950185,0.0000044052235,0.00008508869,0.0003206666],"genre_scores_gemma":[0.86072946,0.00001892605,0.1388113,0.000052770643,0.00020496333,0.00013278659,0.000024645455,0.000012687206,0.00001245308],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99807745,0.00007437984,0.00080099073,0.000342355,0.0004905021,0.0002142909],"domain_scores_gemma":[0.998689,0.00032520073,0.0002726462,0.00016906348,0.00047573133,0.00006834185],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009743232,0.00014972589,0.00019659397,0.0005123738,0.00017100024,0.0008454521,0.0009430897,0.00007822826,0.000005049443],"category_scores_gemma":[0.000077456796,0.00013078637,0.00016317205,0.00058403984,0.000091936905,0.0015975222,0.000031487438,0.00046710583,0.0000040783675],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025510371,0.00015184787,0.000020078392,0.00005074373,0.000015323865,0.0000052772903,0.0024413466,0.03758528,0.0060899407,0.12067479,0.000003587867,0.8329363],"study_design_scores_gemma":[0.000043937165,0.000026343567,0.000044372347,0.00021837316,0.000010643432,0.000038659335,0.0011051843,0.9240958,0.005317767,0.068299375,0.0006703184,0.00012923116],"about_ca_topic_score_codex":0.00001831921,"about_ca_topic_score_gemma":0.000021073609,"teacher_disagreement_score":0.8865105,"about_ca_system_score_codex":0.00025344384,"about_ca_system_score_gemma":0.000228648,"threshold_uncertainty_score":0.8152714},"labels":[],"label_agreement":null},{"id":"W4403444399","doi":"10.48550/arxiv.2410.08674","title":"Guidelines for Fine-grained Sentence-level Arabic Readability Annotation","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Zayed University; York University; New York University Abu Dhabi","keywords":"Readability; Annotation; Arabic; Sentence; Natural language processing; Computer science; Linguistics; Artificial intelligence; Programming language; Philosophy","score_opus":0.3015222385074146,"score_gpt":0.2694105302271697,"score_spread":0.0321117082802449,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403444399","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15477587,0.00008157733,0.83907557,0.0032116529,0.0009624332,0.00085155945,0.0001707102,0.0004949123,0.00037572766],"genre_scores_gemma":[0.9745617,0.000037007143,0.022041347,0.0001643096,0.0001732111,0.000013117523,0.00013958785,0.000020116246,0.0028496005],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99718386,0.00013032235,0.00047823848,0.0017129106,0.00014020709,0.00035449024],"domain_scores_gemma":[0.9962796,0.00029901907,0.0002654689,0.0017250779,0.0012878681,0.00014294423],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.000808752,0.0003604905,0.00037036536,0.00026170345,0.00017857697,0.0002235648,0.0015160999,0.00034671975,0.000010056308],"category_scores_gemma":[0.0006496498,0.00037742473,0.00037329344,0.0006991789,0.00012981339,0.00034483717,0.0012367349,0.00044553165,0.00007547957],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013784964,0.00025896842,0.0012717533,0.0014021285,0.0002031664,0.000062735766,0.0010250339,0.14202708,0.00054531,0.80607885,0.012240759,0.03474634],"study_design_scores_gemma":[0.00015262794,0.00004280461,0.0012902995,0.00008746966,0.000058920778,0.0000028216805,0.000060956878,0.60474205,0.00027748826,0.3915014,0.0014413182,0.00034180793],"about_ca_topic_score_codex":0.00029575048,"about_ca_topic_score_gemma":0.00026617182,"teacher_disagreement_score":0.81978583,"about_ca_system_score_codex":0.00041504842,"about_ca_system_score_gemma":0.00054234307,"threshold_uncertainty_score":0.9998678},"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,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"York University; New York University Abu Dhabi; National Science Foundation","keywords":"Top-down and bottom-up design; Dynamics (music); Reading (process); Computer science; Physics; Linguistics; Acoustics; Programming language","score_opus":0.01674059201527363,"score_gpt":0.2681636207854258,"score_spread":0.2514230287701522,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403510607","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9297909,0.0004229227,0.06582259,0.0031538084,0.0006799239,0.000049244376,9.797162e-7,0.000021031543,0.000058604324],"genre_scores_gemma":[0.99805194,0.00012238696,0.001560463,0.00003572853,0.000036679103,5.8698225e-7,4.8007234e-8,0.0000031867091,0.00018899862],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99892324,0.000045499128,0.00033966062,0.00019310319,0.00035103387,0.00014747183],"domain_scores_gemma":[0.9992687,0.00013362391,0.0002453082,0.00019885157,0.00009463859,0.00005886015],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00069787196,0.00006628731,0.000102730875,0.000080938546,0.0002870634,0.000349687,0.0005870006,0.00002348214,2.718417e-7],"category_scores_gemma":[0.00021054293,0.00004381631,0.00003864726,0.00044686315,0.0001847831,0.0009243603,0.0001407215,0.0001914057,4.1034795e-7],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000055704557,0.00006875517,0.020062331,0.00045214294,0.0000060585435,0.000108516724,0.00415374,0.00041461032,0.5370215,0.037997793,0.0001304453,0.3995284],"study_design_scores_gemma":[0.00018308176,0.00021618327,0.31662583,0.00032946654,0.0000095199,0.0013844834,0.000100142424,0.64840716,0.025312351,0.0050535784,0.0021951639,0.00018305311],"about_ca_topic_score_codex":0.0000038145427,"about_ca_topic_score_gemma":0.000006375689,"teacher_disagreement_score":0.64799255,"about_ca_system_score_codex":0.00007340019,"about_ca_system_score_gemma":0.0001281651,"threshold_uncertainty_score":0.33720398},"labels":[],"label_agreement":null},{"id":"W4404781595","doi":"10.18653/v1/2024.findings-emnlp.564","title":"Machine Translation Hallucination Detection for Low and High Resource Languages using Large Language Models","year":2024,"lang":"en","type":"article","venue":"","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Institute for Advanced Research","keywords":"Computer science; Machine translation; Artificial intelligence; Translation (biology); Resource (disambiguation); Natural language processing; Computer network","score_opus":0.02065377648243963,"score_gpt":0.2803603852179046,"score_spread":0.2597066087354649,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404781595","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03597916,0.0011789241,0.96154964,0.0004266871,0.000058305755,0.00023236204,0.000013628785,0.0002790416,0.0002822695],"genre_scores_gemma":[0.95590734,0.0000064037545,0.043829612,0.000053277232,0.00004422918,0.000012481096,0.000023585048,0.0000073061715,0.000115764415],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99935585,0.00003473747,0.00012251548,0.00027035092,0.000102219565,0.00011432035],"domain_scores_gemma":[0.9996545,0.00010333867,0.00002036758,0.00017009642,0.000024634921,0.000027064072],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033502936,0.000071969866,0.00006646504,0.00009877833,0.000100460675,0.00017835553,0.0000889879,0.000056683948,0.0000048873476],"category_scores_gemma":[0.000012725171,0.000063459,0.000027594295,0.00016902563,0.000009402155,0.00066198164,0.000018621527,0.00005454061,0.0000016619432],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009242615,0.000028890021,0.0000058578476,0.00016779384,0.000009205865,0.0000014307069,0.003551228,0.0022708664,0.018884292,0.090601884,0.000007895183,0.8844614],"study_design_scores_gemma":[0.00014233997,0.000024935456,0.00011723554,0.000018296736,0.000007963987,0.0000073133006,0.00009316834,0.9867954,0.0068839076,0.00532379,0.0005068663,0.00007876046],"about_ca_topic_score_codex":0.0001500517,"about_ca_topic_score_gemma":0.0001710763,"teacher_disagreement_score":0.98452455,"about_ca_system_score_codex":0.000034470126,"about_ca_system_score_gemma":0.0000123057125,"threshold_uncertainty_score":0.2587783},"labels":[],"label_agreement":null},{"id":"W4404914736","doi":"10.1109/vis55277.2024.00067","title":"From Graphs to Words: A Computer-Assisted Framework for the Production of Accessible Text Descriptions","year":2024,"lang":"en","type":"article","venue":"","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Computer science; Production (economics); Natural language processing; Artificial intelligence; Information retrieval","score_opus":0.053207467301638466,"score_gpt":0.3137622289964166,"score_spread":0.26055476169477815,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404914736","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020392416,0.00018940697,0.9636414,0.01303747,0.0019056,0.0005188311,0.000009201776,0.0002459961,0.000059668182],"genre_scores_gemma":[0.6398024,0.000005971911,0.35958615,0.00015151729,0.00017114486,0.00010815635,0.0000036629324,0.0000045719603,0.0001664187],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99905294,0.00003540968,0.00022628157,0.00040184107,0.00015300071,0.00013054897],"domain_scores_gemma":[0.9984776,0.00064219977,0.00003715485,0.000699151,0.00010035007,0.000043582484],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00026579286,0.000083602616,0.00010075235,0.00010368216,0.00014183673,0.0003272716,0.0006321301,0.000054850374,0.000022752693],"category_scores_gemma":[0.00011633687,0.000054655477,0.00008774162,0.00099309,0.000040176317,0.0004003446,0.00010485017,0.00009471142,0.000022879183],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008657108,0.00010247935,0.00010693164,0.000039069906,0.000041046624,1.8114433e-7,0.0031130186,0.0002681151,0.0022849273,0.47810817,0.008299221,0.5076282],"study_design_scores_gemma":[0.00011183325,0.0002515346,0.05389107,0.00043926496,0.00006890544,0.0000075194043,0.0007080471,0.21371682,0.011291198,0.68009967,0.03904062,0.00037352685],"about_ca_topic_score_codex":0.00017691201,"about_ca_topic_score_gemma":0.00007806669,"teacher_disagreement_score":0.61941,"about_ca_system_score_codex":0.000028860732,"about_ca_system_score_gemma":0.00005703253,"threshold_uncertainty_score":0.31558877},"labels":[],"label_agreement":null},{"id":"W4405576246","doi":"10.4995/eurocall2024.2024.19042","title":"Fostering equity, accessibility and academic integrity within an LMS module","year":2024,"lang":"en","type":"article","venue":"","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"Université du Québec à Montréal","keywords":"Academic integrity; Computer science; Learning Management; Asynchronous communication; Web accessibility; Comprehension; Presentation (obstetrics); Equity (law); Multimedia; Medical education; The Internet; World Wide Web; Telecommunications","score_opus":0.17842880774012973,"score_gpt":0.4075352660311423,"score_spread":0.2291064582910126,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405576246","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.546495,0.00013384395,0.44975194,0.0013388422,0.00023488396,0.000107334454,0.0000015572136,0.00043325333,0.0015033223],"genre_scores_gemma":[0.9838336,0.000008991375,0.015853493,0.0001424621,0.000042202417,0.000008756111,0.0000018306371,0.0000041573626,0.0001044908],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987891,0.00007174213,0.00022890174,0.00057080295,0.00017587024,0.00016358469],"domain_scores_gemma":[0.9992248,0.00008092153,0.000024369776,0.0005286056,0.000031459906,0.00010984842],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011571703,0.000096317985,0.0000996755,0.000054004464,0.00008240653,0.0005483914,0.0006932249,0.0001097557,0.000016171025],"category_scores_gemma":[0.00005845282,0.000074979755,0.000023950106,0.000229198,0.00006546138,0.002057462,0.0017749192,0.00046433278,0.000018367324],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000038548783,0.000033982073,0.0025085856,0.0001178045,0.0000053785934,0.0000024646024,0.002778332,0.000014806189,0.009393233,0.2207263,0.00006627667,0.764349],"study_design_scores_gemma":[0.000058500118,0.00006129287,0.052903652,0.00003589935,0.000004022708,0.000023085748,0.00007681122,0.5370726,0.009606608,0.39986357,0.00011498642,0.00017897396],"about_ca_topic_score_codex":0.00013665846,"about_ca_topic_score_gemma":0.00010113522,"teacher_disagreement_score":0.76417,"about_ca_system_score_codex":0.000053244985,"about_ca_system_score_gemma":0.000073110605,"threshold_uncertainty_score":0.52881515},"labels":[],"label_agreement":null},{"id":"W4405576871","doi":"10.4995/eurocall2024.2024.19026","title":"A semi-systematic review of research on generative artificial intelligence (GenAI) in second-language acquisition (SLA)","year":2024,"lang":"en","type":"review","venue":"","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Affordance; Computer science; Milestone; Language acquisition; Reading (process); Field (mathematics); Psychology; Mathematics education; Linguistics; Human–computer interaction","score_opus":0.1947316809011773,"score_gpt":0.4681658255788571,"score_spread":0.2734341446776798,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405576871","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000001238867,0.9770681,0.017861621,0.00020207565,0.00018031872,0.003146896,0.00002830853,0.0000763098,0.0014351023],"genre_scores_gemma":[0.00008786539,0.9974793,0.00089553284,0.00012743166,0.00007774997,0.0006621407,0.000047926536,0.000019895713,0.0006021536],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.9939488,0.0020373708,0.0018896908,0.0009392413,0.0008367153,0.00034818644],"domain_scores_gemma":[0.99663275,0.0010527088,0.0003730825,0.0016169024,0.00024444587,0.000080108715],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00560844,0.0003524863,0.0019771233,0.0008135118,0.000059162994,0.00017300462,0.0014607421,0.00026021103,0.00018915682],"category_scores_gemma":[0.00047401743,0.00023950968,0.00041229257,0.0028762375,0.00009952787,0.00020713753,0.0003200997,0.00080144685,0.0007818018],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[6.4309324e-7,0.00006320375,6.8463466e-9,0.8096423,0.00002468418,0.000013926515,0.00047775602,3.3716523e-7,0.0000020119287,0.0761384,0.00024192245,0.11339477],"study_design_scores_gemma":[0.000008640896,0.00012059574,1.12568436e-7,0.9887351,0.00014767513,0.00002779861,0.00014442649,0.0008909416,0.00014278734,0.005553871,0.003942282,0.00028581583],"about_ca_topic_score_codex":0.000023027846,"about_ca_topic_score_gemma":0.0000772795,"teacher_disagreement_score":0.1790927,"about_ca_system_score_codex":0.00038152438,"about_ca_system_score_gemma":0.00048772854,"threshold_uncertainty_score":0.9999962},"labels":[],"label_agreement":null},{"id":"W4405629337","doi":"10.70637/xvc8m613","title":"L’utilisation de ChatGPT 3.5 pour la rétroaction corrective écrite interactive en enseignement-apprentissage du français langue seconde : une étude exploratoire","year":2024,"lang":"en","type":"article","venue":"Actes des Journées de linguistique","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Corrective feedback; Affordance; Psychology; Quality (philosophy); Perception; Computer science; Affect (linguistics); Language acquisition; Mathematics education; Pedagogy; Communication; Cognitive psychology","score_opus":0.011614954208429179,"score_gpt":0.2669293219336712,"score_spread":0.255314367725242,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405629337","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5071609,0.0007444981,0.48721468,0.0012299244,0.000608666,0.0002112005,0.000014914638,0.00043144997,0.0023837835],"genre_scores_gemma":[0.988277,0.00017515806,0.010677098,0.00013652314,0.00046509595,0.00007378746,0.000029158447,0.000031019095,0.0001351418],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.9981004,0.0004902393,0.0003362086,0.00049830036,0.00020442439,0.00037043908],"domain_scores_gemma":[0.99797016,0.0010725441,0.00012682781,0.00036986527,0.00031593035,0.00014469356],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00081038463,0.00024707805,0.0002098517,0.00021667371,0.0002534029,0.00069506007,0.00040725697,0.00019484549,0.000066736706],"category_scores_gemma":[0.0012659613,0.0002472183,0.00013652268,0.00042745026,0.000088822424,0.00094174006,0.00010326803,0.0005949035,0.00005896186],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011212717,0.00052935706,0.011863105,0.00044597773,0.00040425867,0.0005213774,0.46076348,0.0006298487,0.062367186,0.037192136,0.0019619076,0.42320922],"study_design_scores_gemma":[0.0010026935,0.0003921706,0.4465648,0.0013795255,0.00019777962,0.001637138,0.018628696,0.29733312,0.09834058,0.0950274,0.038103644,0.0013924408],"about_ca_topic_score_codex":0.0006821954,"about_ca_topic_score_gemma":0.0005301574,"teacher_disagreement_score":0.48111615,"about_ca_system_score_codex":0.0005894363,"about_ca_system_score_gemma":0.00024601675,"threshold_uncertainty_score":0.99999803},"labels":[],"label_agreement":null},{"id":"W4405686922","doi":"10.1352/1944-7558-130.1.76","title":"Résumés en Français","year":2024,"lang":"fr","type":"article","venue":"American Journal on Intellectual and Developmental Disabilities","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Icon; Citation; Computer science; Download; Information retrieval; World Wide Web; Programming language","score_opus":0.03277075305047605,"score_gpt":0.2774935311091289,"score_spread":0.24472277805865283,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405686922","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.85515326,0.012061608,0.055689156,0.029440556,0.0056143487,0.0003120038,0.000059805596,0.00027570743,0.041393552],"genre_scores_gemma":[0.96858317,0.0019599597,0.0051848935,0.00092728104,0.0004046826,0.000015203892,0.0000039189354,0.000026970643,0.022893911],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9974566,0.0003694553,0.00060752244,0.00059477653,0.0004513307,0.0005202966],"domain_scores_gemma":[0.994036,0.0052844784,0.000046186193,0.00019606201,0.00008898407,0.00034829142],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0006404106,0.00036122513,0.00038199127,0.00021454164,0.0004198951,0.0013121117,0.00043327708,0.000088010675,0.0039720736],"category_scores_gemma":[0.0014773358,0.00030324308,0.00017324278,0.0006779047,0.002047359,0.00086002017,0.00020338349,0.00078073866,0.0046431357],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005648752,0.00014295921,0.00053853396,0.00010422665,0.00010886569,0.000020366686,0.1608529,0.000008673125,0.0000447518,0.04797624,0.023966588,0.7661794],"study_design_scores_gemma":[0.00017027915,0.0019990632,0.0049233665,0.0007822954,0.00003390564,0.0034255234,0.06573625,0.0036742513,0.0005228105,0.023147484,0.8948371,0.00074771367],"about_ca_topic_score_codex":0.00030602427,"about_ca_topic_score_gemma":0.000031250664,"teacher_disagreement_score":0.8708705,"about_ca_system_score_codex":0.00043836905,"about_ca_system_score_gemma":0.0004699459,"threshold_uncertainty_score":0.99994195},"labels":[],"label_agreement":null},{"id":"W4406074029","doi":"10.48550/arxiv.2407.16470","title":"Machine Translation Hallucination Detection for Low and High Resource Languages using Large Language Models","year":2024,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Institute for Advanced Research","keywords":"Computer science; Machine translation; Translation (biology); Natural language processing; Artificial intelligence; Resource (disambiguation); Linguistics; Psychology; Chemistry; Philosophy","score_opus":0.05613422021312714,"score_gpt":0.2141775388453185,"score_spread":0.15804331863219137,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406074029","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22604103,0.0004676464,0.772524,0.00008224684,0.00010752553,0.00036206743,0.00006507792,0.00020131287,0.00014907707],"genre_scores_gemma":[0.99394286,0.000031819796,0.0056763384,0.000025376059,0.000057555793,0.0000023075656,0.00007744081,0.00001602997,0.0001702855],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99874973,0.00009141598,0.00015105715,0.000755439,0.00006965043,0.00018271228],"domain_scores_gemma":[0.99917525,0.00009585793,0.000114118695,0.00048909703,0.00006828424,0.00005738309],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00034470152,0.0001809466,0.00017274755,0.00023502095,0.00015064047,0.0001438966,0.00031793484,0.0002326588,0.000002668389],"category_scores_gemma":[0.000016383176,0.00020571997,0.000088765315,0.0002681682,0.000029242177,0.00033851687,0.00030755403,0.00027766702,0.0000029466212],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009414552,0.00014363638,0.00005831377,0.0012747793,0.00010081279,0.000043295466,0.005273071,0.59291464,0.0027148894,0.28695923,0.000009604317,0.1104136],"study_design_scores_gemma":[0.0002719869,0.00002379756,0.00010069303,0.00006961664,0.000063724,0.0000032598457,0.00012690153,0.93427855,0.0006867455,0.06411773,0.00006279755,0.00019421324],"about_ca_topic_score_codex":0.0003431679,"about_ca_topic_score_gemma":0.00028509478,"teacher_disagreement_score":0.76790184,"about_ca_system_score_codex":0.00014955852,"about_ca_system_score_gemma":0.000045324516,"threshold_uncertainty_score":0.8389017},"labels":[],"label_agreement":null},{"id":"W4406749487","doi":"10.1016/b978-0-323-95504-1.00344-6","title":"CompLex: An Eye-Movement Data Resource for Research on Compound Word Reading","year":2025,"lang":"en","type":"book-chapter","venue":"Elsevier eBooks","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Reading (process); Word (group theory); Movement (music); Computer science; Resource (disambiguation); Eye movement; Linguistics; Natural language processing; Artificial intelligence; Art; Philosophy; Aesthetics","score_opus":0.22051508396738684,"score_gpt":0.4051230660394905,"score_spread":0.18460798207210366,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406749487","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000014832856,0.00011907425,0.006306262,0.0013894221,0.00025779466,0.0018758902,0.00028374494,0.00019297215,0.98956],"genre_scores_gemma":[0.0008090149,0.000015564394,0.014939058,0.0013087229,0.00037804464,0.000119287404,0.00094438955,0.000050796025,0.9814351],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9958003,0.0002161778,0.0006657055,0.0017902561,0.00093638024,0.0005911868],"domain_scores_gemma":[0.9924653,0.0009097257,0.00022731014,0.0058703534,0.00032316445,0.000204107],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0033453712,0.0004053356,0.0005363888,0.00045642475,0.00065949955,0.0005194045,0.0048609874,0.00031494725,0.000026148882],"category_scores_gemma":[0.00009816253,0.0004017474,0.00012917351,0.000069240305,0.00024321853,0.00021583233,0.001746806,0.0008102962,0.00006750105],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002772533,0.000030301937,0.0000010437965,0.000095500756,0.000032217547,0.000003758305,0.00018125733,0.000002259051,0.00002997029,0.30919123,0.0047428557,0.6856619],"study_design_scores_gemma":[0.00021838305,0.0001835229,0.00004414774,0.0004010189,0.000020037476,0.000001291591,0.000019841133,0.0027760155,0.000039689487,0.08789215,0.90806115,0.00034276035],"about_ca_topic_score_codex":0.000004701209,"about_ca_topic_score_gemma":0.000083511964,"teacher_disagreement_score":0.9033183,"about_ca_system_score_codex":0.00034239516,"about_ca_system_score_gemma":0.00035844167,"threshold_uncertainty_score":0.9998434},"labels":[],"label_agreement":null},{"id":"W4407002447","doi":"10.1007/978-3-031-79038-6_13","title":"Gender-Neutral English to Portuguese Machine Translator: Promoting Inclusive Language","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Portuguese; Computer science; Natural language processing; Linguistics; Artificial intelligence; Programming language; Philosophy","score_opus":0.012572199068466254,"score_gpt":0.26164184440604965,"score_spread":0.24906964533758338,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407002447","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00063116685,0.00063837046,0.9886715,0.001317581,0.0013645596,0.0008083854,0.000024754321,0.0003323403,0.006211382],"genre_scores_gemma":[0.6844524,0.000022934864,0.31097844,0.0031203863,0.00070828694,0.00003147971,0.000029935123,0.00004104675,0.0006150738],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9960105,0.00005735519,0.00061947666,0.0018340909,0.0007897965,0.00068882667],"domain_scores_gemma":[0.99710554,0.00039185438,0.00019678561,0.0017041585,0.000333497,0.0002681479],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0011202205,0.00052683835,0.0005366383,0.0008544505,0.0002799751,0.00039579484,0.003555511,0.0003289789,0.000014391756],"category_scores_gemma":[0.0002398379,0.00049919676,0.0001649159,0.0008873436,0.00027372883,0.00057535653,0.0013662191,0.00089356274,0.000020082758],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000060937655,0.00004605882,0.00004490023,0.000100018195,0.000011725243,0.00005949037,0.02054083,0.0036399716,0.00031437795,0.02639175,0.00002043795,0.94882435],"study_design_scores_gemma":[0.001177413,0.00071032287,0.002088701,0.0014943872,0.00006364353,0.00014431168,0.000008852695,0.68722486,0.022006951,0.2713313,0.009991277,0.0037579373],"about_ca_topic_score_codex":0.00006218064,"about_ca_topic_score_gemma":0.00033290748,"teacher_disagreement_score":0.9450664,"about_ca_system_score_codex":0.000378142,"about_ca_system_score_gemma":0.0008333897,"threshold_uncertainty_score":0.99974597},"labels":[],"label_agreement":null},{"id":"W4407793840","doi":"10.1098/rsos.241313","title":"Text understanding in GPT-4 versus humans","year":2025,"lang":"en","type":"article","venue":"Royal Society Open Science","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute; McGill University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Biology; Computer science; Computational biology","score_opus":0.06907462797592029,"score_gpt":0.34142323568442967,"score_spread":0.2723486077085094,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407793840","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.047127284,0.000052639407,0.8118092,0.006447358,0.000855453,0.0005647476,0.0000016194404,0.00011336735,0.13302834],"genre_scores_gemma":[0.98534083,0.0000054329807,0.013020104,0.00042052846,0.000008873777,0.000016301894,5.843347e-7,0.000002001249,0.0011853263],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9983948,0.000036959627,0.00019994556,0.0006467314,0.00035948656,0.0003620941],"domain_scores_gemma":[0.9989686,0.00017099957,0.000048777263,0.0006858686,0.000056874935,0.000068905945],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0018536481,0.000093040326,0.00012562046,0.00006285545,0.0006632937,0.001048769,0.004431127,0.000052439358,0.000019537518],"category_scores_gemma":[0.00012749048,0.00008948468,0.000059198406,0.002020803,0.00043173213,0.0010543396,0.0015224547,0.00015522,0.000026409522],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001102081,0.00007676239,0.003216755,0.000009890531,0.0000045541915,7.1071656e-7,0.0029413174,0.0005448775,0.00040095788,0.9806755,0.0021102605,0.010007372],"study_design_scores_gemma":[0.0034721314,0.00019602253,0.21711971,0.00016643982,0.000012077938,0.0000011447985,0.009016384,0.608738,0.0031378227,0.13922083,0.018011183,0.0009082771],"about_ca_topic_score_codex":0.00037884462,"about_ca_topic_score_gemma":0.00020828121,"teacher_disagreement_score":0.9382136,"about_ca_system_score_codex":0.0008016282,"about_ca_system_score_gemma":0.00056491,"threshold_uncertainty_score":0.99998826},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.04025664368284644,"score_gpt":0.3625063414730358,"score_spread":0.32224969779018936,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407842065","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.30913377,0.000023033273,0.68426675,0.0048697,0.00015887232,0.0005576698,9.550007e-7,0.00019710693,0.00079214433],"genre_scores_gemma":[0.93381304,0.0000032817088,0.0632712,0.0007734484,0.00004841194,0.00005785882,0.000002083024,0.000005662438,0.0020250361],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9984314,0.00009200467,0.0003652398,0.0005616749,0.00018356572,0.00036612272],"domain_scores_gemma":[0.9987295,0.00035919726,0.00009424445,0.00055385235,0.00016981347,0.00009335748],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010798578,0.00014625792,0.00018897917,0.00013322393,0.00039393897,0.00011898033,0.0007353565,0.00012518244,0.000011603424],"category_scores_gemma":[0.0007577018,0.00014007004,0.0000728043,0.0008880073,0.00004180536,0.00055973936,0.00039271018,0.00033959353,0.000022808328],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005250972,0.000116292314,0.009042855,0.00022932279,0.000025782141,5.378039e-7,0.00807568,0.004472625,0.07623139,0.06114043,0.0008819889,0.83973056],"study_design_scores_gemma":[0.00043191318,0.00029427392,0.018738495,0.00048251712,0.00004596161,0.00000676698,0.002876879,0.7200707,0.19034451,0.01984575,0.04579958,0.0010626371],"about_ca_topic_score_codex":0.00009701745,"about_ca_topic_score_gemma":0.000027467246,"teacher_disagreement_score":0.8386679,"about_ca_system_score_codex":0.00018284883,"about_ca_system_score_gemma":0.0001384518,"threshold_uncertainty_score":0.57118905},"labels":[],"label_agreement":null},{"id":"W4408863230","doi":"10.1109/icca62237.2024.10928130","title":"SmartCaption AI - Enhancing Web Accessibility with Context-Aware Image Descriptions Using Large Language Models","year":2024,"lang":"en","type":"article","venue":"","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Algoma University","funders":"","keywords":"Computer science; Context (archaeology); World Wide Web; Context model; Natural language processing; Artificial intelligence; Human–computer interaction; Information retrieval; Multimedia","score_opus":0.030489971609641994,"score_gpt":0.30176499911137444,"score_spread":0.27127502750173244,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408863230","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25745237,0.00013447841,0.7404082,0.0005025724,0.00012660632,0.00018413809,0.000014324322,0.0005309162,0.00064640073],"genre_scores_gemma":[0.9756901,0.0000032802213,0.02367398,0.00027279565,0.000046224613,0.0000187345,0.000013784025,0.000011594833,0.00026948005],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99852705,0.00009236888,0.0002630107,0.00058811955,0.0002400136,0.00028946353],"domain_scores_gemma":[0.9990569,0.00007050423,0.00003950683,0.00061746687,0.00012801347,0.00008764559],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005400329,0.00015099652,0.00014449889,0.00011664112,0.00021783702,0.00074954814,0.00038356148,0.000073320705,0.00008597699],"category_scores_gemma":[0.0000189473,0.00011699376,0.00006622336,0.00049522234,0.00005249118,0.0034711575,0.00013264369,0.00020202597,0.00004981705],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004278271,0.00060577627,0.0014326423,0.0006216241,0.00010687618,0.0000890969,0.020029033,0.0017198799,0.36322325,0.5423453,0.0008803404,0.06890338],"study_design_scores_gemma":[0.00014080545,0.00002623021,0.0006385855,0.000075887845,0.000014304314,0.000022330996,0.0007367982,0.98494613,0.008276117,0.0047461456,0.00019061059,0.00018605996],"about_ca_topic_score_codex":0.00027317012,"about_ca_topic_score_gemma":0.0015501806,"teacher_disagreement_score":0.98322624,"about_ca_system_score_codex":0.00016347459,"about_ca_system_score_gemma":0.00023488911,"threshold_uncertainty_score":0.722791},"labels":[],"label_agreement":null},{"id":"W4409068941","doi":"10.18260/1-2-1153-52784","title":"Evaluation of the Accessibility of Engineering Vocabulary","year":2025,"lang":"en","type":"article","venue":"","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Vocabulary; Computer science; Linguistics","score_opus":0.027480301984636742,"score_gpt":0.2964749120046319,"score_spread":0.26899461001999514,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409068941","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.54079765,0.000048181875,0.45581177,0.00040651552,0.000111831294,0.00013812048,2.933367e-7,0.000017438733,0.0026681838],"genre_scores_gemma":[0.99700767,4.203541e-7,0.0029380247,0.000015946584,0.0000018525192,0.0000044430085,1.3740662e-7,4.2636856e-7,0.000031052805],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99939317,0.00006821414,0.00014852214,0.00009804865,0.0002562392,0.000035812485],"domain_scores_gemma":[0.9991244,0.0000618268,0.00004190131,0.0005372417,0.00022912174,0.000005498223],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013793479,0.000025547593,0.000049758895,0.000026104068,0.000014620474,0.00000770597,0.0004332908,0.000019719066,0.000007728568],"category_scores_gemma":[0.00028349977,0.000016778955,0.0000306364,0.0003250173,0.000017544664,0.00012381555,0.00010465192,0.000026820213,3.3378325e-7],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000030642768,0.00019277501,0.035545178,0.00015452516,0.000034695673,1.537475e-8,0.00062323426,0.01073423,0.049717024,0.43617612,0.00012713484,0.466692],"study_design_scores_gemma":[0.000056275447,0.0000029748112,0.53044176,0.000010175511,0.000008837068,5.946563e-8,0.000005946623,0.36789578,0.09149467,0.010039608,0.00002857813,0.000015358231],"about_ca_topic_score_codex":0.000025007676,"about_ca_topic_score_gemma":0.00000723488,"teacher_disagreement_score":0.49489656,"about_ca_system_score_codex":0.000028058103,"about_ca_system_score_gemma":0.00012886761,"threshold_uncertainty_score":0.080516934},"labels":[],"label_agreement":null},{"id":"W4409148165","doi":"10.3758/s13428-025-02656-9","title":"VOC-ADO: A lexical database for French-speaking adolescents","year":2025,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre for Interdisciplinary Research in Rehabilitation","funders":"Agence Nationale de la Recherche","keywords":"Vocabulary; Computer science; Lemma (botany); Psychology; Linguistics; Lexical database; Mathematics education; Natural language processing","score_opus":0.3489859521934305,"score_gpt":0.6063080813811523,"score_spread":0.25732212918772185,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409148165","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019596986,0.00015510793,0.9772587,0.0009548031,0.00033036165,0.001092391,0.000019259885,0.00013432375,0.00045809336],"genre_scores_gemma":[0.28043914,0.000008863827,0.71796894,0.00008896134,0.000058680165,0.0006787309,0.000016464232,0.000009970508,0.00073025323],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99621236,0.0015070104,0.00033966987,0.00075230765,0.0005494244,0.00063923997],"domain_scores_gemma":[0.99688786,0.0010127848,0.000044604956,0.0014324251,0.00044816223,0.00017414507],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008318839,0.00013586243,0.0002083109,0.00038804114,0.00043393503,0.0003175162,0.001635245,0.00012089207,0.000017278471],"category_scores_gemma":[0.0018537225,0.00012584975,0.000117460186,0.0011351104,0.00019106717,0.0004250003,0.0007698452,0.0005228325,0.000019020992],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019557014,0.0004569297,0.007089455,0.00011880736,0.000005963148,0.000006530844,0.0002843317,0.0000012776056,0.0309151,0.04554972,0.0010717028,0.9144806],"study_design_scores_gemma":[0.0022729076,0.00045718392,0.62611103,0.00068707793,0.00006074126,0.000020592703,0.00029769712,0.041833926,0.10057174,0.042381253,0.18443063,0.00087525096],"about_ca_topic_score_codex":0.0002740931,"about_ca_topic_score_gemma":0.00005174779,"teacher_disagreement_score":0.9136054,"about_ca_system_score_codex":0.00016680136,"about_ca_system_score_gemma":0.00032782907,"threshold_uncertainty_score":0.51320034},"labels":[],"label_agreement":null},{"id":"W4409824787","doi":"10.5430/wjel.v15n6p11","title":"Shifting Roles: Employing AI-driven Translation Engines to Enhance the Writing Proficiency of EFL Learners","year":2025,"lang":"en","type":"article","venue":"World Journal of English Language","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Translation (biology); Natural language processing; Linguistics; Chemistry","score_opus":0.01018622541184751,"score_gpt":0.2909843998097799,"score_spread":0.2807981743979324,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409824787","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.69317615,0.0012141531,0.2998478,0.002591196,0.00043663784,0.00020570568,0.0000012547558,0.000051682306,0.0024753776],"genre_scores_gemma":[0.9881712,0.0000062578497,0.011353274,0.00020725655,0.00016414613,0.0000033085416,4.3066638e-7,0.00000481814,0.00008930735],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9987728,0.000113199734,0.00052418216,0.00015553221,0.00026436136,0.00016994371],"domain_scores_gemma":[0.9987313,0.00034042593,0.00024721934,0.0002879501,0.00035081993,0.000042278563],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010976867,0.00009029528,0.00017630143,0.0002788714,0.00010897084,0.00010355889,0.00069938385,0.000028351118,0.0000045314023],"category_scores_gemma":[0.0008072954,0.000067435976,0.000098983524,0.0009894058,0.000032824297,0.00043983362,0.000054021268,0.0002748046,8.629938e-7],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003894511,0.00013812733,0.009863543,0.00017459966,0.000055733628,0.000010718059,0.22143842,0.017302291,0.042307273,0.018757787,0.00022104321,0.68969154],"study_design_scores_gemma":[0.0034096816,0.0011207266,0.09068268,0.008224573,0.0003855998,0.00004964906,0.17582503,0.100050434,0.5711252,0.005279291,0.041537233,0.0023099056],"about_ca_topic_score_codex":0.000012547689,"about_ca_topic_score_gemma":0.00007005751,"teacher_disagreement_score":0.6873816,"about_ca_system_score_codex":0.000038273924,"about_ca_system_score_gemma":0.000081769496,"threshold_uncertainty_score":0.27499592},"labels":[],"label_agreement":null},{"id":"W4410447618","doi":"10.3233/shti250612","title":"Utilizing Large Language Models to Monitor Social Media for Disability: An Analysis of Sentiment and Disability Models in Tweets","year":2025,"lang":"en","type":"article","venue":"Studies in health technology and informatics","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"York University","keywords":"Sentiment analysis; Social media; Computer science; Social model of disability; Language model; Natural language processing; Artificial intelligence; Psychology; World Wide Web; Psychiatry","score_opus":0.0679866848074883,"score_gpt":0.39370301037434774,"score_spread":0.3257163255668594,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410447618","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91073835,0.0005877996,0.08498725,0.0029828507,0.000059810667,0.000535308,0.00003730463,0.000048898313,0.000022442118],"genre_scores_gemma":[0.9866387,0.0001554403,0.012946562,0.0001446228,0.0000035242645,0.00010208223,0.000006511764,0.000001603262,9.253145e-7],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9986115,0.00005658293,0.0007731867,0.00020252744,0.00009402832,0.00026214277],"domain_scores_gemma":[0.9990796,0.00033984217,0.0001287498,0.00035638723,0.000061777835,0.000033656368],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012824534,0.000103386556,0.00048266372,0.00040502936,0.0001608196,0.000012697992,0.00023054575,0.0001175887,1.469889e-7],"category_scores_gemma":[0.00019511048,0.00009534456,0.00002976324,0.0013771497,0.0003742098,0.000417756,0.00036490362,0.00012757497,4.095482e-8],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000038233855,0.00039747093,0.080758706,0.0017005663,0.00014048969,1.5264926e-7,0.20460011,0.0023694679,0.0000032499288,0.5234005,0.000012717012,0.18657832],"study_design_scores_gemma":[0.00040193542,0.00008583023,0.050255034,0.00006437418,0.000028867371,2.0293406e-7,0.08742935,0.7437407,0.000042115866,0.11781925,0.000022041704,0.00011034476],"about_ca_topic_score_codex":0.00006842069,"about_ca_topic_score_gemma":0.0016579964,"teacher_disagreement_score":0.7413712,"about_ca_system_score_codex":0.0001739509,"about_ca_system_score_gemma":0.000030933887,"threshold_uncertainty_score":0.38880384},"labels":[],"label_agreement":null},{"id":"W4410469786","doi":"10.21608/tjhss.2025.340427.1298","title":"Raising University Students’ Critical Awareness of the Linguistic Limitations and the Potential Invalid Knowledge of ChatGPT Responses to Academic Writing Prompts","year":2025,"lang":"en","type":"article","venue":"Transcultural Journal of Humanities and Social Sciences/Transcultural Journal of Humanities and Social Sciences ","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Prince Edward Island","funders":"","keywords":"Raising (metalworking); Psychology; Linguistics; Consciousness raising; Academic writing; Mathematics education; Pedagogy; Mathematics; Philosophy","score_opus":0.1438738242997092,"score_gpt":0.3649760790440655,"score_spread":0.22110225474435627,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410469786","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98803115,0.0018275824,0.0011143038,0.007951513,0.00045532934,0.00019441218,0.000010908415,0.000006288634,0.00040852025],"genre_scores_gemma":[0.9987631,0.0005598249,0.0002169717,0.00016082132,0.00020116221,7.423121e-7,1.8550082e-7,0.0000024958026,0.00009468455],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.9971626,0.00067063124,0.0008590071,0.00020245154,0.000815037,0.00029026714],"domain_scores_gemma":[0.99762124,0.0006901054,0.000566802,0.000056700166,0.0010262775,0.000038867027],"candidate_categories":["sts"],"consensus_categories":["sts"],"category_scores_codex":[0.002896125,0.00018137692,0.00052160263,0.00020250939,0.004349218,0.0005799318,0.0014066118,0.000092052025,0.0000029604314],"category_scores_gemma":[0.00021451827,0.000099563025,0.00029741172,0.0005007702,0.006315343,0.001123486,0.0001323059,0.0004092932,4.3780688e-8],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024392894,0.0001032605,0.0022602757,0.00022789084,0.000115612835,0.0000043778186,0.4929293,0.000029494091,0.0034389547,0.4956244,0.00005947326,0.004963038],"study_design_scores_gemma":[0.004064102,0.001572886,0.25643474,0.0012624401,0.0007855932,0.00036932612,0.68860525,0.0002371869,0.00082036137,0.04263791,0.0025428243,0.00066737155],"about_ca_topic_score_codex":0.00019499115,"about_ca_topic_score_gemma":0.00043549843,"teacher_disagreement_score":0.45298648,"about_ca_system_score_codex":0.00005427011,"about_ca_system_score_gemma":0.0003532258,"threshold_uncertainty_score":0.996947},"labels":[],"label_agreement":null},{"id":"W4410814295","doi":"10.2196/59054","title":"Evaluating the Readability of a Custom Generative Pre-Trained Transformer with Retrieval Augmentation for Pediatric Neurocutaneous Syndromes (Preprint)","year":2024,"lang":"en","type":"article","venue":"JMIR Dermatology","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Preprint; Readability; Transformer; Computer science; Medicine; Artificial intelligence; Engineering; World Wide Web; Programming language; Electrical engineering","score_opus":0.0419523948505979,"score_gpt":0.35976101347469847,"score_spread":0.3178086186241006,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410814295","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.68835026,0.00010131783,0.30734545,0.0026858603,0.00010386345,0.0012534631,0.000009021414,0.00010801651,0.000042753276],"genre_scores_gemma":[0.98973644,0.00000805006,0.009823103,0.00007690983,0.000029387465,0.00026518013,0.0000095236055,0.000009367097,0.000042044026],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99839324,0.00026134867,0.00040316567,0.00048390473,0.00024801787,0.0002103235],"domain_scores_gemma":[0.9982657,0.0009590964,0.00010976515,0.0004696905,0.00015811881,0.000037651625],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00044424387,0.00013607241,0.0002105778,0.0000882638,0.00013543299,0.000077939694,0.00039720943,0.00008508044,0.000009652177],"category_scores_gemma":[0.000106031184,0.000089108114,0.00008462473,0.00046390016,0.00011808012,0.00028390382,0.000023449922,0.00014780078,0.000005312469],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0036870895,0.0014186258,0.016958296,0.00801451,0.00061197666,0.00021479889,0.12730071,0.012441799,0.15597127,0.19191453,0.0011118347,0.48035455],"study_design_scores_gemma":[0.0010966157,0.002856896,0.036815014,0.00007645932,0.00026655733,0.0055645653,0.00058673107,0.8176857,0.09754643,0.0358798,0.00092143746,0.00070374587],"about_ca_topic_score_codex":0.000011429729,"about_ca_topic_score_gemma":0.000015987356,"teacher_disagreement_score":0.80524397,"about_ca_system_score_codex":0.00005018303,"about_ca_system_score_gemma":0.0002492035,"threshold_uncertainty_score":0.36337233},"labels":[],"label_agreement":null},{"id":"W4410903557","doi":"10.1111/bjet.13600","title":"Beyond verbal self‐explanations: Student annotations of a code‐tracing solution produced by <scp>ChatGPT</scp>","year":2025,"lang":"en","type":"article","venue":"British Journal of Educational Technology","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Tracing; Code (set theory); Computer science; Nonverbal communication; Programming language; Mathematics education; Psychology; Communication","score_opus":0.007584775305880134,"score_gpt":0.28101598039395104,"score_spread":0.2734312050880709,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410903557","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8580577,0.0063281804,0.09897238,0.034230273,0.001023228,0.00038580393,0.000051148552,0.00009451912,0.00085681496],"genre_scores_gemma":[0.9803109,0.00026163223,0.018997807,0.000114231494,0.000055654615,0.000034796838,0.000017167102,0.000005137651,0.00020263922],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9984311,0.00007819896,0.00070997456,0.0002629098,0.00032722056,0.00019060906],"domain_scores_gemma":[0.99769133,0.0004284846,0.0005199605,0.00028663105,0.0010241612,0.000049400238],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00055334135,0.00009875782,0.00021847205,0.00056432735,0.00022129176,0.00009490551,0.00083237217,0.00014221393,0.000007323381],"category_scores_gemma":[0.0012346474,0.00012429514,0.00007473838,0.0011713761,0.00012475741,0.00054343394,0.00009068161,0.000301698,0.0000043074833],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005910475,0.0039089406,0.016754316,0.00011239984,0.00032214413,0.000008599639,0.0022707544,0.00029152984,0.02807104,0.798221,0.089663774,0.06036961],"study_design_scores_gemma":[0.0024811141,0.00065989705,0.24400003,0.0009257604,0.00017008073,0.0026507836,0.0035423855,0.0026248302,0.049721632,0.65993375,0.032911684,0.00037804293],"about_ca_topic_score_codex":0.00002104611,"about_ca_topic_score_gemma":0.000029303897,"teacher_disagreement_score":0.22724572,"about_ca_system_score_codex":0.00019445749,"about_ca_system_score_gemma":0.00077530585,"threshold_uncertainty_score":0.50686085},"labels":[],"label_agreement":null},{"id":"W4411661176","doi":"10.63282/3050-9416.ijaibdcms-v4i4p105","title":"What’s Next for Infrastructure? The Future of Code-Driven Healthcare","year":2023,"lang":"en","type":"article","venue":"International Journal of AI BigData Computational and Management Studies","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Optech (Canada)","funders":"","keywords":"Health care; Code (set theory); Computer science; Business; Political science; Programming language","score_opus":0.048857138272683634,"score_gpt":0.35636302427187877,"score_spread":0.30750588599919515,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411661176","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.030405432,0.0058763563,0.51133245,0.44378576,0.0077733346,0.0006289335,0.00011086472,0.000059969258,0.00002691527],"genre_scores_gemma":[0.94627196,0.019064602,0.030692386,0.0031105552,0.0006453665,0.00002728901,0.00007634015,0.000008518437,0.00010296131],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9988307,0.000040196006,0.00040501796,0.00015062293,0.00048016483,0.00009330215],"domain_scores_gemma":[0.9983178,0.0002969218,0.0003066686,0.0001282374,0.0009213789,0.000028992914],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00041205675,0.00008577306,0.00015292616,0.00019954273,0.0001248032,0.00021204837,0.00076914387,0.00002018002,0.0000012343373],"category_scores_gemma":[0.000033583397,0.000057225927,0.0000695773,0.00020498873,0.00008652438,0.0011630853,0.00040162212,0.00008256597,0.000001463043],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006295549,0.000044767843,0.00074113737,0.00016387171,0.0008409199,0.000009590235,0.0023134744,0.018199818,0.0000123321815,0.63963246,0.03317618,0.3048025],"study_design_scores_gemma":[0.0013975602,0.00026681405,0.12753451,0.00029796577,0.00006783288,0.00007639895,0.010236155,0.07088875,0.000035207046,0.570979,0.21800353,0.00021627535],"about_ca_topic_score_codex":0.0000019583458,"about_ca_topic_score_gemma":0.000010659971,"teacher_disagreement_score":0.91586655,"about_ca_system_score_codex":0.000035414636,"about_ca_system_score_gemma":0.000039254763,"threshold_uncertainty_score":0.23336054},"labels":[],"label_agreement":null},{"id":"W4411858420","doi":"10.1007/978-3-031-92534-4_6","title":"Teaching Writing in the Time of ChatGPT: Rethinking What Counts as Learning","year":2025,"lang":"en","type":"book-chapter","venue":"","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Mathematics education; Psychology; History","score_opus":0.017946707834932407,"score_gpt":0.2568238882944543,"score_spread":0.2388771804595219,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411858420","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00007301501,0.00034931663,0.011120991,0.001334126,0.00009195517,0.00013454208,3.579231e-7,0.0000667963,0.9868289],"genre_scores_gemma":[0.06632646,0.0001745697,0.0049407706,0.0013611147,0.000115380244,0.0000064928245,0.00001843209,0.000016925003,0.92703986],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9990503,0.000073517636,0.00026441197,0.0002472513,0.0002638378,0.000100646605],"domain_scores_gemma":[0.99899864,0.00042041886,0.00013159949,0.00039926995,0.000039036295,0.0000110149185],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013479705,0.00010593853,0.0001571664,0.00010474034,0.00009718994,0.00019872378,0.0006618829,0.00014483275,0.000092552546],"category_scores_gemma":[0.00007769178,0.00008278507,0.00005714406,0.000038750473,0.00002922979,0.00031957097,0.00013941173,0.0006507166,0.00011642151],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[4.3767167e-7,0.000004143695,0.000008049327,0.000029209343,0.0000042064758,0.000001728099,0.0028200042,0.000006773071,0.0000124082135,0.81927735,0.00012481296,0.17771089],"study_design_scores_gemma":[0.00018463717,0.00009133189,0.00021101873,0.0030952166,0.000026588283,0.000030654,0.0007930507,0.029105881,0.00008579149,0.60969263,0.3560766,0.00060657423],"about_ca_topic_score_codex":0.000052397187,"about_ca_topic_score_gemma":0.000007504636,"teacher_disagreement_score":0.3559518,"about_ca_system_score_codex":0.00003868124,"about_ca_system_score_gemma":0.00006786107,"threshold_uncertainty_score":0.33758768},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Computer science; Multimedia; World Wide Web","score_opus":0.029501659790527116,"score_gpt":0.3233822716840986,"score_spread":0.2938806118935715,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412438704","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03666257,0.000033410466,0.95477074,0.0052813236,0.00034735733,0.0004350479,0.0000020153166,0.0001645915,0.0023029642],"genre_scores_gemma":[0.9415105,0.0000027576605,0.05522071,0.0015513344,0.00007350106,0.00008963424,0.0000122396805,0.0000029056177,0.0015364316],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9988435,0.00005499161,0.00029574288,0.0005023775,0.00011684914,0.00018652367],"domain_scores_gemma":[0.9988685,0.00013680449,0.000054610784,0.0007167218,0.00017879915,0.000044565193],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00047339534,0.000092837385,0.00012019788,0.000071929775,0.00021144972,0.0002404295,0.0005516746,0.00007359057,0.000027275484],"category_scores_gemma":[0.00015070951,0.00008186975,0.00006662394,0.00030639025,0.000024633162,0.0006828038,0.00012284223,0.0000654778,0.000018916564],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009035279,0.00015646417,0.0020027473,0.00008285776,0.000018972734,2.0383973e-7,0.0004606603,0.0003267338,0.089771815,0.46514174,0.008016486,0.4340123],"study_design_scores_gemma":[0.00036311324,0.00006015895,0.020613018,0.000014150666,0.000010777782,9.082545e-7,0.000037170856,0.7075495,0.22321452,0.033755932,0.01414832,0.00023243649],"about_ca_topic_score_codex":0.000041998435,"about_ca_topic_score_gemma":0.00058430625,"teacher_disagreement_score":0.9048479,"about_ca_system_score_codex":0.00009173315,"about_ca_system_score_gemma":0.00017369215,"threshold_uncertainty_score":0.33385515},"labels":[],"label_agreement":null},{"id":"W4412439187","doi":"10.1167/jov.25.9.2451","title":"Psychophysics of variable fonts: Do multiple font features interact to impact readability?","year":2025,"lang":"en","type":"article","venue":"Journal of Vision","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Font; Readability; Legibility; Variable (mathematics); Psychophysics; Typography; Computer science; Psychology; Artificial intelligence; Mathematics; Art; Perception; Visual arts; Neuroscience; Programming language","score_opus":0.008370482320446177,"score_gpt":0.32793806992256624,"score_spread":0.31956758760212006,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412439187","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4936775,0.00018645664,0.5029047,0.0016690196,0.00065988087,0.00018134204,0.000005099736,0.000016200289,0.00069976127],"genre_scores_gemma":[0.95562756,0.000013025497,0.04408873,0.00014648648,0.000049653838,0.0000012792032,6.287514e-7,0.0000035841106,0.000069026406],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99866766,0.00010861779,0.00055866555,0.00019812705,0.00032164235,0.00014529396],"domain_scores_gemma":[0.9980796,0.00038909796,0.00033495235,0.00060387707,0.00049491494,0.00009757037],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008248754,0.00011061482,0.0002862584,0.00021530152,0.000054475735,0.00010839994,0.00074753264,0.00006669387,0.000010446057],"category_scores_gemma":[0.00056316535,0.00007877964,0.00018686298,0.0005943162,0.000022000773,0.00070318504,0.00012825668,0.00021917252,0.000003866944],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008624401,0.0017008039,0.011931915,0.0001312146,0.00013941068,0.0000054109,0.0022524893,0.00424132,0.25252336,0.012184218,0.022153525,0.6918739],"study_design_scores_gemma":[0.001082368,0.0022276,0.8960728,0.0010124495,0.000039898085,0.00004149355,0.00015364573,0.0076404004,0.021746062,0.0602763,0.009430297,0.0002766935],"about_ca_topic_score_codex":0.000087739216,"about_ca_topic_score_gemma":0.000007500096,"teacher_disagreement_score":0.88414085,"about_ca_system_score_codex":0.0001526997,"about_ca_system_score_gemma":0.00017102265,"threshold_uncertainty_score":0.32125404},"labels":[],"label_agreement":null},{"id":"W4412888009","doi":"10.18653/v1/2025.findings-acl.842","title":"A Large and Balanced Corpus for Fine-grained Arabic Readability Assessment","year":2025,"lang":"en","type":"article","venue":"","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Zayed University; York University; New York University Abu Dhabi","keywords":"Readability; Computer science; Arabic; Natural language processing; Artificial intelligence; Linguistics; Programming language","score_opus":0.01269413613571176,"score_gpt":0.30108169048524575,"score_spread":0.288387554349534,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412888009","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.063734956,0.000034656237,0.92621386,0.006299613,0.00013317277,0.00049503,0.000009349363,0.0001586625,0.0029206749],"genre_scores_gemma":[0.93508434,0.0000035523108,0.06304772,0.00047425358,0.000010390677,0.00011159599,0.000009251037,0.0000021325443,0.0012567781],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9990401,0.00004789515,0.00020422113,0.0004150751,0.00009603196,0.0001966379],"domain_scores_gemma":[0.9989068,0.00032238459,0.0000412477,0.0005765974,0.0001060536,0.00004694558],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00058645254,0.00009119753,0.00014855266,0.000049228824,0.00013625059,0.00010400652,0.00029415294,0.00005268059,0.000007841762],"category_scores_gemma":[0.00014849665,0.00007522811,0.000045304005,0.00023332758,0.000035381585,0.00019978295,0.00012117557,0.00006185974,0.0000017791136],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013741391,0.0001643809,0.012093774,0.00007566,0.000011894691,2.4857715e-7,0.00013628966,0.0000039057186,0.0015147041,0.9228749,0.001432969,0.06167749],"study_design_scores_gemma":[0.001271594,0.00018490324,0.49035275,0.000025841075,0.000015778052,0.000002947542,0.00007787159,0.22052105,0.0037185536,0.2429223,0.04060393,0.00030247268],"about_ca_topic_score_codex":0.000023668734,"about_ca_topic_score_gemma":0.0001302886,"teacher_disagreement_score":0.8713494,"about_ca_system_score_codex":0.00005585073,"about_ca_system_score_gemma":0.000113802555,"threshold_uncertainty_score":0.30677134},"labels":[],"label_agreement":null},{"id":"W4413051028","doi":"10.1177/19160216251360651","title":"Readability, Reliability, and Quality Analysis of Internet-Based Patient Education Materials and Large Language Models on Meniere’s Disease","year":2025,"lang":"en","type":"article","venue":"Journal of Otolaryngology - Head and Neck Surgery","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Sciences Centre; Sunnybrook Health Science Centre; Sinai Health System; Dalhousie University; University of Toronto","funders":"","keywords":"Readability; CLARITY; Reliability (semiconductor); Medicine; Guideline; Index (typography); Plain language; Health literacy; Reading (process); Quality Score; Inclusion (mineral); Quality (philosophy); Medical education; Computer science; Psychology; Health care; World Wide Web; Pathology","score_opus":0.02087976903293051,"score_gpt":0.30006910361358036,"score_spread":0.2791893345806499,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413051028","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99085855,0.00068755425,0.006509761,0.0015229321,0.00020013843,0.00015162768,0.000021009842,0.000011834618,0.000036580263],"genre_scores_gemma":[0.99868757,0.00008534208,0.000703617,0.00047173287,0.000012482961,0.000007789857,0.000012779677,0.0000032997777,0.00001539369],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9978686,0.0005959171,0.0008640821,0.0003304857,0.00018406518,0.00015684245],"domain_scores_gemma":[0.9977271,0.0010186095,0.00046721083,0.00043576697,0.00020686515,0.00014447673],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018915578,0.00013535196,0.0006471696,0.00053030293,0.00006240712,0.00005759691,0.00015232869,0.00009770041,0.000009560595],"category_scores_gemma":[0.0005022027,0.0001107271,0.00012755426,0.00037254696,0.00013304254,0.00034395533,0.000117984506,0.00013001554,1.8714103e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007606451,0.0014465698,0.9601714,0.0006674138,0.000261798,0.000010096183,0.0014267055,0.00008397487,0.0018601785,0.017084427,0.00018828816,0.016038485],"study_design_scores_gemma":[0.00016789975,0.00012425942,0.9885274,0.00015403047,0.00014688824,0.000004606679,0.00005036542,0.00414153,0.0022392853,0.0042487164,0.000091055466,0.000103971724],"about_ca_topic_score_codex":0.00017688953,"about_ca_topic_score_gemma":0.00005046127,"teacher_disagreement_score":0.028355973,"about_ca_system_score_codex":0.000045764384,"about_ca_system_score_gemma":0.00028605296,"threshold_uncertainty_score":0.45153204},"labels":[],"label_agreement":null},{"id":"W4413888947","doi":"10.1007/978-3-032-03870-8_20","title":"Improving Text Readability to Support Student Comprehension and Learning: An LLM-Powered Approach","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Readability; Computer science; Comprehension; Multimedia; Human–computer interaction; Artificial intelligence; Natural language processing; Programming language","score_opus":0.020871257842508196,"score_gpt":0.2735095957058067,"score_spread":0.2526383378632985,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413888947","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0037059276,0.00010399105,0.99108946,0.00046762533,0.0005986723,0.00091560767,0.0000041837357,0.00025442828,0.0028601158],"genre_scores_gemma":[0.55504364,0.000012855596,0.44317052,0.0009787931,0.00014666798,0.000023015304,0.000021352365,0.000023976765,0.0005791657],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99483997,0.00015832852,0.00067187235,0.0026900223,0.0010087442,0.0006310627],"domain_scores_gemma":[0.99642855,0.0005370273,0.00025340947,0.002074724,0.0003526818,0.0003536135],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0020022783,0.0005524621,0.0006377014,0.0007020242,0.00052150036,0.0009042854,0.0028460664,0.00035845375,0.000009262714],"category_scores_gemma":[0.00023914743,0.00051315327,0.0000939298,0.0006505515,0.00054502615,0.0007533061,0.002452664,0.0011431999,0.0000121600715],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012255344,0.00014113168,0.0004220759,0.000093431125,0.0000060710113,0.000007954408,0.002248604,0.0066077304,0.00043444743,0.007899589,0.000008890102,0.98211783],"study_design_scores_gemma":[0.00050726027,0.0022411544,0.013070758,0.00031669028,0.00003128133,0.00010068812,0.000009131225,0.93628025,0.0010106316,0.039180946,0.0053630075,0.0018882147],"about_ca_topic_score_codex":0.00010135163,"about_ca_topic_score_gemma":0.00008983329,"teacher_disagreement_score":0.9802296,"about_ca_system_score_codex":0.00038285897,"about_ca_system_score_gemma":0.0005976862,"threshold_uncertainty_score":0.999732},"labels":[],"label_agreement":null},{"id":"W4414185190","doi":"10.1002/curj.350","title":"Enhancing curriculum enactment: Leveraging <scp>ChatGPT</scp> to design a spelling programme based on the British Columbia standards","year":2025,"lang":"en","type":"article","venue":"The Curriculum Journal","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Spelling; Curriculum; Literacy; Generative grammar; Teaching method; Curriculum development","score_opus":0.01800039673444461,"score_gpt":0.2527503013296735,"score_spread":0.2347499045952289,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414185190","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17341945,0.00027735916,0.8202434,0.003558447,0.0007040278,0.0008713465,0.000004505906,0.00013179489,0.00078968843],"genre_scores_gemma":[0.9789806,0.000045183227,0.01784907,0.002075571,0.00026825228,0.00008983325,0.0000016944227,0.000020164307,0.0006696595],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9963182,0.0007652669,0.00057900994,0.0005061308,0.001037882,0.0007934805],"domain_scores_gemma":[0.99725264,0.00090157916,0.00027359696,0.00081630074,0.0005246064,0.0002312634],"candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0058625937,0.00022286341,0.00027565897,0.000101288,0.002636747,0.0075915493,0.0018785896,0.000082138205,0.000035669673],"category_scores_gemma":[0.0013274634,0.0001807411,0.0002068067,0.0012984573,0.00007518969,0.00038455302,0.0002071627,0.00080625067,0.000033013166],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025248,0.0033367367,0.023184273,0.0002464266,0.0004616444,0.0003242292,0.013273889,0.070682175,0.003869315,0.014894683,0.3053115,0.5643899],"study_design_scores_gemma":[0.0024624073,0.0011650763,0.011342022,0.003518704,0.0002232391,0.00091275875,0.0076773367,0.7377813,0.009657493,0.044375706,0.18002653,0.00085744075],"about_ca_topic_score_codex":0.0014502694,"about_ca_topic_score_gemma":0.0010402865,"teacher_disagreement_score":0.8055611,"about_ca_system_score_codex":0.0005626114,"about_ca_system_score_gemma":0.0006179722,"threshold_uncertainty_score":0.9986617},"labels":[],"label_agreement":null},{"id":"W4414519711","doi":"10.3389/fpubh.2025.1619274","title":"HEAL-Summ: a lightweight and ethical framework for accessible summarization of health information","year":2025,"lang":"en","type":"article","venue":"Frontiers in Public Health","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"York University","funders":"Canada First Research Excellence Fund","keywords":"Automatic summarization; Software deployment; Health information; Scalability; Public health; Work (physics); Health communication; Key (lock)","score_opus":0.031307221388508326,"score_gpt":0.33050573203525996,"score_spread":0.2991985106467516,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414519711","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007163002,0.0004045487,0.8382548,0.1592097,0.00058267266,0.00061368383,0.000010105142,0.00005415426,0.00015400769],"genre_scores_gemma":[0.4801337,0.0004365316,0.5085928,0.010617079,0.000020403977,0.00009610698,0.000075819255,0.000004557541,0.0000230059],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99801034,0.00031812498,0.00083239976,0.0002618484,0.00020606702,0.00037124477],"domain_scores_gemma":[0.9987465,0.00021070628,0.0003542268,0.00040506496,0.00014910087,0.00013438401],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0033255406,0.000099961566,0.00033803497,0.00051663927,0.00020892898,0.00017043225,0.0004147643,0.00024421504,0.0000010559942],"category_scores_gemma":[0.00068346225,0.00009797476,0.00003264455,0.0011752294,0.00006533535,0.0009386266,0.000095157025,0.00032663607,4.2601806e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000005901602,0.000036753554,0.010710078,0.00040214616,0.000004898106,1.2000604e-8,0.0017278084,0.000006510196,1.9263824e-7,0.60110706,0.009031769,0.37696683],"study_design_scores_gemma":[0.0009493377,0.00029471167,0.14374617,0.00032416655,0.000002306868,0.0000010085607,0.0006189903,0.09088261,0.00003697966,0.56596404,0.19695318,0.00022646665],"about_ca_topic_score_codex":0.00019030571,"about_ca_topic_score_gemma":0.000028756578,"teacher_disagreement_score":0.4794174,"about_ca_system_score_codex":0.0003029126,"about_ca_system_score_gemma":0.0018798049,"threshold_uncertainty_score":0.3995295},"labels":[],"label_agreement":null},{"id":"W4414608819","doi":"10.1037/pag0000941","title":"Preserved context sensitivity in language production: Lexical differentiation in older adults.","year":2025,"lang":"en","type":"article","venue":"Psychology and Aging","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"National Institutes of Health","keywords":"Referent; Cognition; Context (archaeology); Lexical item; Language development; Lexical access; Lexico; Age of Acquisition","score_opus":0.01350896058692912,"score_gpt":0.3019600597557132,"score_spread":0.2884510991687841,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414608819","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95892626,0.00024817337,0.027859015,0.012307446,0.00024656983,0.00013666025,2.0353231e-7,0.00003324265,0.00024243802],"genre_scores_gemma":[0.99917054,0.000013273014,0.00029139826,0.00040219637,0.000016365511,0.000013011699,0.0000025213808,0.0000011076305,0.000089604815],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9992775,0.00013684358,0.0001282607,0.00031358725,0.00003575589,0.00010806143],"domain_scores_gemma":[0.99968076,0.000055994733,0.00002310821,0.00021294637,0.000013798072,0.000013398899],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033053744,0.0000515678,0.00008687104,0.00010600182,0.000035949928,0.00002061127,0.00007964434,0.00005409436,0.0000028110476],"category_scores_gemma":[0.00005323849,0.00004971791,0.000011508884,0.00022489422,0.00003512648,0.00017616428,0.000043576623,0.00013609506,0.0000018533262],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000045076453,0.00034187676,0.6128256,0.00006391084,0.000005815869,0.000014143947,0.0071895043,0.000013666142,0.0047844504,0.011833172,0.00017110894,0.36271167],"study_design_scores_gemma":[0.00039002337,0.0000054824304,0.9932166,0.000056157358,8.550883e-7,0.000004224468,0.00013806969,0.0039870976,0.00059351313,0.0015022364,0.000058961803,0.00004682755],"about_ca_topic_score_codex":0.00009579594,"about_ca_topic_score_gemma":0.00090404024,"teacher_disagreement_score":0.38039097,"about_ca_system_score_codex":0.00001201626,"about_ca_system_score_gemma":0.000007700466,"threshold_uncertainty_score":0.20274375},"labels":[],"label_agreement":null},{"id":"W4415213227","doi":"10.1177/08295735251387494","title":"Pinning Down the Accuracy Gap: Assessing Intervention Information About Dyslexia on Pinterest-Linked Web Pages","year":2025,"lang":"en","type":"article","venue":"Canadian Journal of School Psychology","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Mount Saint Vincent University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Readability; Dyslexia; Reading (process); Psychological intervention; Intervention (counseling); Set (abstract data type); Social media; Web page","score_opus":0.0506934818766968,"score_gpt":0.3593327771524466,"score_spread":0.3086392952757498,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415213227","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38894826,0.000741771,0.5111816,0.0818997,0.0044278014,0.00035417246,0.000006115537,0.000054554956,0.0123860445],"genre_scores_gemma":[0.99240756,0.00003200452,0.0011920164,0.0062152804,0.00009541121,0.000004971243,0.0000031750371,0.000003539601,0.00004604727],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99850374,0.00025542948,0.0006864398,0.00015535214,0.00013735493,0.00026170473],"domain_scores_gemma":[0.99830705,0.00020570881,0.000480135,0.0005084546,0.00026875513,0.00022987364],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011497126,0.00011801345,0.00016579404,0.0006160155,0.00027586124,0.00067540864,0.0011169742,0.00011867585,0.0000620707],"category_scores_gemma":[0.0010437166,0.00009027842,0.00012329181,0.00046253222,0.00010507999,0.0018395571,0.000029037295,0.0006160317,0.000064643384],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006464531,0.00007528119,0.016041229,0.000057389083,0.000121435856,0.000033431137,0.0014145289,0.0003974808,0.00083450525,0.060527377,0.08048996,0.83994275],"study_design_scores_gemma":[0.0010899178,0.00025455028,0.8402379,0.000563075,0.000023146406,0.00013481369,0.0003869052,0.0020789139,0.00015061753,0.013384723,0.14150289,0.00019254771],"about_ca_topic_score_codex":0.00033808683,"about_ca_topic_score_gemma":0.0017845845,"teacher_disagreement_score":0.8397502,"about_ca_system_score_codex":0.00021826118,"about_ca_system_score_gemma":0.0007526427,"threshold_uncertainty_score":0.6512981},"labels":[],"label_agreement":null},{"id":"W4415379075","doi":"10.3758/s13428-025-02806-z","title":"LexKO: A quick, reliable lexical test of Korean language proficiency","year":2025,"lang":"en","type":"article","venue":"Behavior Research Methods","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba; University of Toronto","funders":"Kyung Hee University; University of Manitoba; City University of Hong Kong","keywords":"Language proficiency; Test (biology); Korean language; Multilingualism; Language assessment; Foreign language","score_opus":0.17705806644686634,"score_gpt":0.5632092123204916,"score_spread":0.38615114587362526,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415379075","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.29941115,0.000938134,0.6863989,0.0015569926,0.0002319125,0.0015950043,0.00001214101,0.00023846915,0.00961724],"genre_scores_gemma":[0.63961023,0.000013815377,0.35573164,0.000024629511,0.000018401168,0.00032440227,0.0000035054254,0.0000073270317,0.0042660385],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9969823,0.0010027702,0.00038370315,0.0005358201,0.0006110146,0.00048439016],"domain_scores_gemma":[0.9969004,0.0012927009,0.000057990175,0.0013353812,0.00029669184,0.00011685409],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0077816383,0.00010977587,0.00022632774,0.000395591,0.00020602794,0.00011423633,0.0014477486,0.00012068909,0.00003367712],"category_scores_gemma":[0.0018941769,0.00009536908,0.000087846165,0.0019960182,0.0003393605,0.00024750954,0.0005276887,0.000472116,0.000020465986],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001423325,0.0011718647,0.021575687,0.00011165641,0.000006523277,0.000010661566,0.0016946588,0.0000043468726,0.2918729,0.07390288,0.00084036886,0.6087942],"study_design_scores_gemma":[0.0006057603,0.00088371057,0.21470852,0.00012707445,0.000030828585,0.000016085503,0.001453008,0.009156548,0.74280304,0.009370979,0.020469114,0.00037533502],"about_ca_topic_score_codex":0.00058095204,"about_ca_topic_score_gemma":0.000013271799,"teacher_disagreement_score":0.6084189,"about_ca_system_score_codex":0.00008351919,"about_ca_system_score_gemma":0.0004422888,"threshold_uncertainty_score":0.38890386},"labels":[],"label_agreement":null},{"id":"W4415966003","doi":"10.1145/3769994.3770056","title":"Hundreds of Warnings in Accessibility Checkers! How can ChatGPT Help?","year":2025,"lang":"","type":"article","venue":"","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Action (physics); Visualization; Data visualization; Key (lock); Component (thermodynamics)","score_opus":0.02123616937130161,"score_gpt":0.28361661881393585,"score_spread":0.2623804494426342,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415966003","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.79568756,0.00037434133,0.15959851,0.036913604,0.0006920192,0.0007669547,0.000010100251,0.000095749885,0.0058611454],"genre_scores_gemma":[0.9924917,0.00006265547,0.0022676822,0.00041973055,0.000025717758,0.000026937849,0.0000052817204,0.0000066648786,0.0046936013],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9965632,0.00034752736,0.00089880906,0.0011902619,0.00044510837,0.00055511895],"domain_scores_gemma":[0.99707156,0.0002513895,0.000346999,0.0018597818,0.00033770152,0.00013255968],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0017208859,0.00030330644,0.0006012678,0.00043416227,0.00014498836,0.00031568616,0.0018768562,0.00030967456,0.00011067291],"category_scores_gemma":[0.0005515146,0.0003082385,0.00018648303,0.0026521776,0.0004007615,0.00090828846,0.00072315196,0.00043973274,0.00000809905],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008359747,0.0013181858,0.3273509,0.0010416984,0.0000637526,0.0000044716066,0.019911304,0.000057858382,0.007633548,0.058536507,0.0006227759,0.5833754],"study_design_scores_gemma":[0.00092160894,0.000164168,0.8277073,0.0002775575,0.000027109063,0.0000018515021,0.0008762307,0.09119365,0.064080775,0.0115892235,0.0026917155,0.00046882738],"about_ca_topic_score_codex":0.0015922191,"about_ca_topic_score_gemma":0.002009141,"teacher_disagreement_score":0.58290654,"about_ca_system_score_codex":0.00036694866,"about_ca_system_score_gemma":0.00091762625,"threshold_uncertainty_score":0.999937},"labels":[],"label_agreement":null},{"id":"W4415974188","doi":"10.1016/j.procs.2025.09.549","title":"Content Safety and Response Quality in LLMs: A Data-Centric Refinement Approach","year":2025,"lang":"en","type":"article","venue":"Procedia Computer Science","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Chicoutimi","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Readability; Performance improvement; Quality management; Quality (philosophy); Coherence (philosophical gambling strategy); Natural language generation","score_opus":0.08154692548813655,"score_gpt":0.32179373135095823,"score_spread":0.24024680586282168,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415974188","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.099118434,0.00019189411,0.89626336,0.0033104946,0.00025670818,0.00040991185,0.0000051099564,0.000104146035,0.0003399305],"genre_scores_gemma":[0.825217,0.000032611366,0.1738598,0.00077301107,0.000021916712,0.000023673514,0.000005501235,0.0000025363954,0.00006391456],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99713635,0.00020445444,0.00050893,0.001269239,0.0004858568,0.00039515493],"domain_scores_gemma":[0.997697,0.00034071758,0.00010923154,0.0015539015,0.00017961678,0.000119518954],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006106526,0.00014703828,0.00022244715,0.00038055138,0.00023782032,0.00038419748,0.002767989,0.000045689067,7.806344e-7],"category_scores_gemma":[0.0005462882,0.00012915315,0.000019228884,0.002383828,0.00034862835,0.0012001661,0.0022200905,0.00015901124,0.0000042078877],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003947565,0.00080213154,0.033592995,0.00023348421,0.000012142298,0.000005597402,0.004329355,0.00035730205,0.0017776879,0.27956814,0.00032515754,0.67860126],"study_design_scores_gemma":[0.0005407641,0.000046729263,0.514718,0.000032994096,0.00000234314,0.0000080436575,0.000049968265,0.4806948,0.00017567203,0.0012100247,0.0023437482,0.00017688442],"about_ca_topic_score_codex":0.000077604556,"about_ca_topic_score_gemma":0.0000196197,"teacher_disagreement_score":0.7260986,"about_ca_system_score_codex":0.00020497481,"about_ca_system_score_gemma":0.00070470345,"threshold_uncertainty_score":0.5266713},"labels":[],"label_agreement":null},{"id":"W4416033663","doi":"10.18653/v1/2025.tsar-1.9","title":"OneNRC@TSAR2025 Shared Task Small Models for Readability Controlled Text Simplification","year":2025,"lang":"","type":"article","venue":"","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Readability; Task (project management); Text simplification; Feature (linguistics); Task analysis","score_opus":0.042788311038452,"score_gpt":0.28355592530195345,"score_spread":0.24076761426350146,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416033663","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004659443,0.0007855684,0.94593924,0.023605913,0.0011503025,0.008203058,0.00020864511,0.00047068845,0.01497715],"genre_scores_gemma":[0.94052845,0.00010220874,0.038331542,0.0016251726,0.00013318137,0.0016958087,0.0001632581,0.000031451124,0.017388936],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99225324,0.0006616234,0.0025375723,0.0028141923,0.0005777588,0.0011556076],"domain_scores_gemma":[0.9899042,0.0030907083,0.00068802346,0.0041171797,0.0018563337,0.0003435522],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0035802382,0.00080046756,0.0015257684,0.00047532647,0.001000572,0.0013116427,0.002737227,0.00071789534,0.00014516531],"category_scores_gemma":[0.0016782494,0.00076122786,0.0008993056,0.0016275226,0.0003654344,0.0015281673,0.00054881605,0.00047727383,0.00009703203],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014687979,0.0016581556,0.00020822379,0.0006198707,0.00030135125,6.1785187e-7,0.0014658525,0.0034971903,0.0047503687,0.7207454,0.0046070935,0.26067707],"study_design_scores_gemma":[0.0044407942,0.00021337831,0.0025871852,0.00010917714,0.000212928,0.0000015801905,0.0001571887,0.78781873,0.0026526526,0.19190247,0.009279326,0.00062457507],"about_ca_topic_score_codex":0.0005030589,"about_ca_topic_score_gemma":0.0003994198,"teacher_disagreement_score":0.935869,"about_ca_system_score_codex":0.000685497,"about_ca_system_score_gemma":0.001611486,"threshold_uncertainty_score":0.9997251},"labels":[],"label_agreement":null},{"id":"W4416037532","doi":"10.18653/v1/2025.emnlp-demos.74","title":"BAREC Demo: Resources and Tools for Sentence-level Arabic Readability Assessment","year":2025,"lang":"","type":"article","venue":"","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"York University; New York University Abu Dhabi","keywords":"Readability; Arabic; Legibility; Feature (linguistics)","score_opus":0.07263354252581768,"score_gpt":0.331101482548212,"score_spread":0.2584679400223943,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416037532","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17060512,0.00032287335,0.80509245,0.01356819,0.000573543,0.0017158337,0.000058418293,0.00013387589,0.007929707],"genre_scores_gemma":[0.90244704,0.00008731917,0.09249795,0.0008768298,0.00006453785,0.0001928592,0.000012865334,0.000009235851,0.0038113792],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99589676,0.0003587827,0.00100414,0.0016526834,0.0004410538,0.00064657396],"domain_scores_gemma":[0.9947723,0.002542041,0.00020744602,0.0016760416,0.0005754763,0.00022668747],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0024357748,0.0004020367,0.000550609,0.0001775067,0.0007683399,0.002057557,0.0010709333,0.000281584,0.000059130838],"category_scores_gemma":[0.0011220834,0.000361846,0.0002048367,0.000732117,0.00045722735,0.0018648871,0.0006171297,0.00031173174,0.000008402083],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006520945,0.00030975757,0.008627689,0.00047461654,0.00006937701,8.100457e-7,0.0009182074,0.000046604106,0.00075556705,0.13274312,0.0012155002,0.8547735],"study_design_scores_gemma":[0.000898426,0.00044682322,0.5882961,0.00026109393,0.00012673096,0.000010980527,0.002068055,0.28864667,0.0033307637,0.06628842,0.048834287,0.00079163176],"about_ca_topic_score_codex":0.00034398888,"about_ca_topic_score_gemma":0.00028799492,"teacher_disagreement_score":0.8539819,"about_ca_system_score_codex":0.0004083524,"about_ca_system_score_gemma":0.00083139277,"threshold_uncertainty_score":0.99988335},"labels":[],"label_agreement":null},{"id":"W4416037651","doi":"10.18653/v1/2025.arabicnlp-sharedtasks.46","title":"Noor at BAREC Shared Task 2025: A Hybrid Transformer-Feature Architecture for Sentence-level Readability Assessment","year":2025,"lang":"","type":"article","venue":"","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Readability; Task (project management); Architecture; Task analysis","score_opus":0.032077260013275675,"score_gpt":0.30372814434762463,"score_spread":0.271650884334349,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416037651","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011524269,0.00040461775,0.900693,0.073094726,0.0015465629,0.0046004257,0.0020284923,0.00028383406,0.005824066],"genre_scores_gemma":[0.81213236,0.000113483264,0.14988813,0.002849519,0.00019704195,0.00091506855,0.00053209416,0.00004179999,0.0333305],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99288857,0.0004504428,0.0013680153,0.002926994,0.0009565427,0.0014094231],"domain_scores_gemma":[0.9942647,0.0011959496,0.00029882163,0.0028805733,0.000895366,0.00046453867],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0017146536,0.0009448859,0.0010557038,0.00035231307,0.0012743406,0.0007732447,0.002432888,0.0005132725,0.0005115017],"category_scores_gemma":[0.00038840508,0.00082754676,0.00094122713,0.0013371927,0.0004511648,0.00085285935,0.0004691078,0.0009886419,0.000045678607],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00085906725,0.0017914415,0.003375486,0.0023975237,0.00045211028,0.000011996007,0.0028204296,0.0005166769,0.014626691,0.028642586,0.073914036,0.87059194],"study_design_scores_gemma":[0.0043845354,0.0014311335,0.13613941,0.0009470945,0.000614173,0.00011331641,0.00075204135,0.29548794,0.04728739,0.053736474,0.45608288,0.0030236195],"about_ca_topic_score_codex":0.0003549424,"about_ca_topic_score_gemma":0.0019238254,"teacher_disagreement_score":0.8675683,"about_ca_system_score_codex":0.0013897233,"about_ca_system_score_gemma":0.0019777936,"threshold_uncertainty_score":0.99941754},"labels":[],"label_agreement":null},{"id":"W4416193684","doi":"10.1080/23273798.2025.2585303","title":"Surprisal in reading: language models predict the N400 for L2 readers","year":2025,"lang":"en","type":"article","venue":"Language Cognition and Neuroscience","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Graduate Student Association, Fordham University; National Science Foundation of Sri Lanka; Alliance de recherche numérique du Canada; Social Sciences and Humanities Research Council of Canada; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"N400; Language model; Semantics (computer science); Computational linguistics; Utterance","score_opus":0.029082565216570468,"score_gpt":0.29391346949582764,"score_spread":0.26483090427925715,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416193684","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.35128698,0.00030221927,0.6389064,0.004862283,0.00038836623,0.00077234826,0.000025343237,0.00019806778,0.0032579624],"genre_scores_gemma":[0.99651116,0.000030656505,0.00067172834,0.0023375745,0.000014408267,0.000059995316,0.0000049845144,0.0000030071158,0.00036650742],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99905545,0.000073837204,0.00015380261,0.00038315446,0.00013642819,0.00019733295],"domain_scores_gemma":[0.99931884,0.00026121477,0.00004130913,0.00030590824,0.000033025954,0.000039687882],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00044067434,0.00008347689,0.000086140404,0.00010377977,0.00017335023,0.00016408783,0.00041656115,0.000039975304,0.0000013563786],"category_scores_gemma":[0.00028435685,0.00006337051,0.000028199922,0.0005045771,0.00014766528,0.00042915114,0.00008961316,0.00010669657,0.000001086859],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008943705,0.00032029138,0.0007879617,0.00017820597,0.000005829035,0.00003648,0.041247454,0.0004583875,0.58424723,0.17643677,0.0011628821,0.19502907],"study_design_scores_gemma":[0.001961762,0.00024423125,0.030674689,0.00019192245,0.000031459815,0.00005873175,0.0083285365,0.7318202,0.18398869,0.039997857,0.0021304241,0.00057145243],"about_ca_topic_score_codex":0.000045188295,"about_ca_topic_score_gemma":0.00005289838,"teacher_disagreement_score":0.73136187,"about_ca_system_score_codex":0.000013710792,"about_ca_system_score_gemma":0.000040244624,"threshold_uncertainty_score":0.25841746},"labels":[],"label_agreement":null},{"id":"W4416541694","doi":"10.48550/arxiv.2504.11814","title":"ARWI: Arabic Write and Improve","year":2025,"lang":"en","type":"preprint","venue":"ArXiv.org","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"York University; New York University Abu Dhabi","keywords":"Arabic; Grammar; Modern Standard Arabic; Profiling (computer programming); Arabic languages; Error analysis","score_opus":0.03535004254881862,"score_gpt":0.2728030644487988,"score_spread":0.2374530218999802,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416541694","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8774134,0.00069559494,0.11324607,0.0038485255,0.0012183759,0.00046942246,0.00002513375,0.00031668882,0.0027668218],"genre_scores_gemma":[0.9928493,0.00013749946,0.004428046,0.0004825626,0.000114449715,0.0000636823,0.000016499604,0.0000065610443,0.0019013832],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9982995,0.00007693615,0.00031125688,0.0009092907,0.00016243581,0.00024058575],"domain_scores_gemma":[0.99803805,0.00012874621,0.00014091525,0.0014950387,0.00010618588,0.000091055066],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00032175475,0.00022505138,0.00026988727,0.00010714575,0.000111365334,0.00018232828,0.0009770797,0.00026663337,0.0000075602075],"category_scores_gemma":[0.00010072175,0.00021756075,0.00009229827,0.00016968444,0.00008197187,0.00021561784,0.0015638669,0.0005283536,0.000061009825],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022937864,0.0003282288,0.53484696,0.0012177706,0.00016023505,0.00002049775,0.0033290316,0.0001557204,0.0048847278,0.064453125,0.0014535383,0.38912725],"study_design_scores_gemma":[0.00027254975,0.000055978446,0.9398832,0.00016654425,0.000036415768,0.0000061068267,0.000032464683,0.011065316,0.0033813938,0.030897534,0.013617624,0.00058487453],"about_ca_topic_score_codex":0.0001361291,"about_ca_topic_score_gemma":0.000026437614,"teacher_disagreement_score":0.40503624,"about_ca_system_score_codex":0.000063106236,"about_ca_system_score_gemma":0.00018200884,"threshold_uncertainty_score":0.887187},"labels":[],"label_agreement":null},{"id":"W4416829564","doi":"10.2139/ssrn.5813722","title":"Getting Personal: Individualized and User-Searchable Readability Results for a Large Corpus of Canadian Adjudicative Decisions","year":2025,"lang":"en","type":"preprint","venue":"SSRN Electronic Journal","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Readability; Tribunal; Subject (documents); Resource (disambiguation); Empirical research; Word (group theory)","score_opus":0.03315900626650401,"score_gpt":0.3049321644477418,"score_spread":0.27177315818123776,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416829564","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.099360526,0.005717009,0.8768884,0.012688549,0.0004248677,0.0020174892,0.0017222535,0.00008805802,0.0010928405],"genre_scores_gemma":[0.9660709,0.0042334828,0.028334484,0.00013735914,0.00009495482,0.00009667987,0.00011133603,0.000016650722,0.0009041834],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9955112,0.00039425603,0.00081032893,0.0007963754,0.0004521845,0.0020356565],"domain_scores_gemma":[0.99631065,0.0012825037,0.00063684926,0.0007884663,0.00069067633,0.00029083714],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.009098463,0.00026306836,0.0005250315,0.000900749,0.00057119556,0.00018724325,0.0013898334,0.00031917327,0.0000020507694],"category_scores_gemma":[0.0029723921,0.00025170375,0.0002224854,0.00066046574,0.00010363348,0.00023071974,0.00062801817,0.0026261741,9.94606e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031779727,0.00027549226,0.0029639823,0.00019199241,0.00057781255,0.0000025689844,0.008693243,0.000068444875,0.00010306368,0.8132148,0.0010481821,0.17254265],"study_design_scores_gemma":[0.0016155492,0.00036528215,0.008749837,0.0004113209,0.00010081864,0.000080458776,0.0015239008,0.010438687,0.00028087306,0.95506287,0.020890955,0.00047947903],"about_ca_topic_score_codex":0.024307888,"about_ca_topic_score_gemma":0.25251755,"teacher_disagreement_score":0.86671036,"about_ca_system_score_codex":0.0015072436,"about_ca_system_score_gemma":0.018952861,"threshold_uncertainty_score":0.9999935},"labels":[],"label_agreement":null},{"id":"W4417199398","doi":"10.3390/curroncol32120696","title":"Readability Optimization of Layperson Summaries in Urological Oncology Clinical Trials: Outcomes from the BRIDGE-AI 8 Study","year":2025,"lang":"en","type":"article","venue":"Current Oncology","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Layperson; Readability; Inclusion (mineral); Reading (process); Syntax; Jargon; Health literacy; Clinical trial","score_opus":0.4333643882947104,"score_gpt":0.5451982854766254,"score_spread":0.111833897181915,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417199398","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.73159,0.000577233,0.23457956,0.027427502,0.0035441706,0.0017161266,0.000030279376,0.000099442936,0.0004357087],"genre_scores_gemma":[0.9969667,0.000093186645,0.0021614206,0.0005589391,0.00007489193,0.00010704258,0.000025970063,0.0000031998868,0.00000860893],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9881814,0.008984252,0.0017196506,0.00067409495,0.00020163578,0.00023895527],"domain_scores_gemma":[0.9825602,0.015784679,0.0004811164,0.0009167986,0.0002006558,0.000056539142],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.011518453,0.00016497,0.0010804456,0.000098736826,0.0000981285,0.000042153635,0.0010934107,0.00031088974,0.00003337511],"category_scores_gemma":[0.011370335,0.00010600741,0.00020168557,0.00049867213,0.00041374002,0.00017352852,0.00042929983,0.00064726564,0.0000056972085],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016240514,0.0031415268,0.6827685,0.0000062784165,0.000034682183,0.0000016549362,0.0011075566,0.00047818475,0.0000024531255,0.0040719905,0.0007290959,0.30749565],"study_design_scores_gemma":[0.0013806171,0.0007983733,0.95228624,0.00000916888,0.000056615318,5.4185335e-7,0.00040378683,0.022642458,0.000007896554,0.004539652,0.017778685,0.00009597338],"about_ca_topic_score_codex":0.00035621095,"about_ca_topic_score_gemma":0.0009063614,"teacher_disagreement_score":0.3073997,"about_ca_system_score_codex":0.00024158815,"about_ca_system_score_gemma":0.0006416807,"threshold_uncertainty_score":0.9969573},"labels":[],"label_agreement":null},{"id":"W4417286768","doi":"10.64898/2025.12.11.693290","title":"Using GPT-4 to Automate the Generation of Lay Summaries for Cancer Publications","year":2025,"lang":"","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Ontario Institute for Cancer Research","funders":"University of Toronto","keywords":"Readability; Jargon; Reading (process); Sample (material); Data collection; Reading level; Comprehension","score_opus":0.0804196765853612,"score_gpt":0.30602555965615447,"score_spread":0.22560588307079327,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417286768","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21695136,0.00093749666,0.76409405,0.008927049,0.0030502896,0.003936629,0.0017461785,0.00034648352,0.000010481048],"genre_scores_gemma":[0.91314393,0.0002039854,0.083621226,0.000525324,0.0005716121,0.0018366654,0.000001284098,0.000047798967,0.000048179776],"study_design_codex":"bench_or_experimental","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9954469,0.0003474716,0.0013538873,0.001611602,0.000555571,0.00068456726],"domain_scores_gemma":[0.9917728,0.00039190165,0.0010170724,0.0034097517,0.003158103,0.0002503968],"candidate_categories":["metaepi_narrow","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0020621528,0.0005903923,0.00069103314,0.00048174246,0.0010293571,0.0010871902,0.0024106994,0.0005011113,0.000026641708],"category_scores_gemma":[0.00094024616,0.00055334065,0.0002872342,0.0022611185,0.00028478692,0.0006472802,0.0010191362,0.0004251713,0.000008939751],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003575253,0.00035729606,0.004228519,0.0010331289,0.00033193117,4.2128892e-7,0.00035035392,0.026470065,0.7880363,0.17781313,0.0011570698,0.00018603478],"study_design_scores_gemma":[0.0003339218,0.00006219865,0.058648404,0.0005024645,0.00029310142,8.428402e-9,0.000008303246,0.454423,0.41429296,0.000027711414,0.070529744,0.00087816454],"about_ca_topic_score_codex":0.0006048318,"about_ca_topic_score_gemma":0.00011000284,"teacher_disagreement_score":0.69619256,"about_ca_system_score_codex":0.00064038346,"about_ca_system_score_gemma":0.0037776963,"threshold_uncertainty_score":0.99994975},"labels":[],"label_agreement":null},{"id":"W594155444","doi":"","title":"Short-term/working memory : the Second Quebec Conference on Short-Term/Working Memory","year":2005,"lang":"en","type":"book","venue":"Psychology Press eBooks","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Serial position effect; Recall; Psychology; Forgetting; Short-term memory; Audiology; Free recall; Working memory; Cognitive psychology; Neuroscience; Medicine; Cognition","score_opus":0.10002526939281316,"score_gpt":0.3200377104078026,"score_spread":0.22001244101498946,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W594155444","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001957612,0.00080995506,0.0114947595,0.0008031779,0.002962126,0.0014868065,0.000024061535,0.00058188714,0.9798796],"genre_scores_gemma":[0.24840987,0.00006674865,0.00075489207,0.0026372266,0.0017800482,0.00037948205,0.00006849979,0.000120461234,0.7457828],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9942225,0.0006320475,0.0011264565,0.0022781196,0.0007208803,0.0010199698],"domain_scores_gemma":[0.99406505,0.00062424276,0.00046663874,0.004432372,0.00015983146,0.00025186173],"candidate_categories":["metaepi_narrow","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0010932566,0.0009522652,0.00093023153,0.00028109289,0.0005724445,0.00058196526,0.004972968,0.0012672644,0.00013883701],"category_scores_gemma":[0.000022614438,0.00080389803,0.0004043195,0.000056114393,0.00085606426,0.00021424731,0.00074206886,0.0023613474,0.0001073373],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007926301,0.00013729691,0.00009128581,0.000109547465,0.00021801011,0.00009285006,0.0035760305,0.000019779305,0.0005104091,0.093306206,0.015251878,0.88660747],"study_design_scores_gemma":[0.00088246353,0.00028293545,0.0072143814,0.0010453924,0.00021812967,0.0003907573,0.0000479311,0.0010954966,0.0018363137,0.017589357,0.9667151,0.0026817606],"about_ca_topic_score_codex":0.000048762773,"about_ca_topic_score_gemma":0.0021142773,"teacher_disagreement_score":0.9514632,"about_ca_system_score_codex":0.00030959272,"about_ca_system_score_gemma":0.0003875733,"threshold_uncertainty_score":0.9999402},"labels":[],"label_agreement":null},{"id":"W6893565298","doi":"10.5281/zenodo.3997149","title":"News Corpus for RUSSE'2020 task","year":2020,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Optech (Canada)","funders":"","keywords":"Task (project management); Corpus linguistics; Key (lock); Headline","score_opus":0.04795015764437081,"score_gpt":0.24353663564359906,"score_spread":0.19558647799922826,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6893565298","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004935573,0.00007540947,0.9501357,0.022147678,0.00014082476,0.0008621454,0.00014848504,0.0017320749,0.019822126],"genre_scores_gemma":[0.9851235,0.000060236885,0.010133149,0.0022408674,0.00037078443,1.9960736e-7,0.00087866676,0.0007789093,0.00041367504],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9985132,0.00016411801,0.00023557492,0.00053432916,0.00026373912,0.00028902266],"domain_scores_gemma":[0.9987331,0.00004317797,0.0000928933,0.00053217594,0.00035452645,0.00024412312],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00034227132,0.000114464674,0.0001284362,0.0000595765,0.0012123337,0.00096471974,0.001759847,0.000053039326,0.0008053836],"category_scores_gemma":[0.00076563994,0.00011965046,0.000062607396,0.0005947437,0.00007535651,0.00044851936,0.0008759959,0.00015513824,0.0037283327],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007455149,0.00013341136,0.000007673281,0.000104162944,0.000028414011,0.000006786834,0.003724004,0.0001075021,0.016082674,0.09151959,0.31517246,0.57303876],"study_design_scores_gemma":[0.0003386367,0.0002684603,0.00034046907,0.000005215979,0.000004952821,0.000024598086,0.000082325154,0.009813981,0.00082547206,0.0011815063,0.98697126,0.00014310275],"about_ca_topic_score_codex":0.000007920408,"about_ca_topic_score_gemma":2.5432922e-7,"teacher_disagreement_score":0.98018795,"about_ca_system_score_codex":0.00006652005,"about_ca_system_score_gemma":0.000006442218,"threshold_uncertainty_score":0.99704736},"labels":[],"label_agreement":null},{"id":"W6894028799","doi":"10.5281/zenodo.8100419","title":"Evaluating the meaning of answers to reading comprehension questions: A semantics-based approach","year":2012,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Meaning (existential); Reading comprehension; Comprehension; Reading (process); Association (psychology)","score_opus":0.11670980472727234,"score_gpt":0.32767320362955654,"score_spread":0.21096339890228422,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6894028799","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06014143,0.000051613195,0.9263477,0.0015460309,0.00009442326,0.00060270063,0.000011744429,0.0005219018,0.010682467],"genre_scores_gemma":[0.96288204,0.000002726317,0.036643025,0.0001469473,0.000047076504,1.00286165e-7,0.00007650679,0.00016491616,0.000036677284],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99820197,0.000574483,0.00024509148,0.00027306148,0.0004273872,0.0002779997],"domain_scores_gemma":[0.99850833,0.00009623637,0.00011425215,0.00069128035,0.0004666466,0.00012322131],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0021754703,0.00009071231,0.00010640566,0.00015356048,0.0014083366,0.00034415384,0.0011364612,0.000035291374,0.00012568195],"category_scores_gemma":[0.00093177037,0.00007678676,0.0000390292,0.0007638433,0.000084556275,0.0003773442,0.0006499615,0.00015446503,0.0003889853],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000087190456,0.00065739395,0.00010517832,0.00024308138,0.00004892962,8.419114e-7,0.025184222,0.019395407,0.12386935,0.30678663,0.008626724,0.51499504],"study_design_scores_gemma":[0.00094651204,0.0010541605,0.010112402,0.0002416275,0.000055481683,0.00012327718,0.0021976705,0.6330298,0.011175307,0.001656172,0.33874592,0.0006616662],"about_ca_topic_score_codex":0.000018010658,"about_ca_topic_score_gemma":7.733981e-8,"teacher_disagreement_score":0.9027406,"about_ca_system_score_codex":0.00009181663,"about_ca_system_score_gemma":0.0000056538274,"threshold_uncertainty_score":0.9998917},"labels":[],"label_agreement":null},{"id":"W6901949952","doi":"10.6084/m9.figshare.13141541.v1","title":"Additional file 2 of A strategic initiative to facilitate knowledge translation research in rehabilitation","year":2020,"lang":"en","type":"article","venue":"Figshare","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Trois-Rivières; McMaster University; McGill University; Université Laval; Université de Montréal; Centre for Interdisciplinary Research in Rehabilitation","funders":"","keywords":"Rehabilitation; Knowledge translation; Information system; Key (lock); Context (archaeology)","score_opus":0.5972495769037591,"score_gpt":0.37944692620657117,"score_spread":0.21780265069718796,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6901949952","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00007936718,0.000012496864,0.00013719474,0.0013295228,0.00000460965,0.00034900915,0.9908038,0.000037942194,0.0072460645],"genre_scores_gemma":[0.17024487,1.4059185e-7,0.011842671,0.000103542974,0.00004096997,0.0017339642,0.81599206,0.000006109952,0.000035685596],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988357,0.00024852055,0.00022684665,0.00030326383,0.00024086783,0.00014479183],"domain_scores_gemma":[0.9929587,0.0063837734,0.000041973464,0.00018551503,0.00034543083,0.00008461148],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00011842963,0.000063336374,0.0000967332,0.00014329486,0.00004271038,0.00003425694,0.00031838033,0.00005158835,0.72880024],"category_scores_gemma":[0.004066263,0.00006743695,0.0000365005,0.0012265455,0.000012755181,0.00036177677,0.00006117906,0.00015191338,0.0026450318],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000093149365,0.000048189573,7.1371056e-7,0.00011764303,0.0000013812858,6.6948377e-7,0.008889635,0.00007109571,0.000031585627,0.00040346672,0.97577333,0.01465297],"study_design_scores_gemma":[0.0002499933,0.00071828143,0.011669904,0.0014818091,5.8319955e-7,7.656616e-7,0.0013327008,0.04016603,0.00014985405,0.010411126,0.9335973,0.00022163277],"about_ca_topic_score_codex":0.000004172904,"about_ca_topic_score_gemma":0.000048184873,"teacher_disagreement_score":0.72615516,"about_ca_system_score_codex":0.00005432994,"about_ca_system_score_gemma":0.0002426656,"threshold_uncertainty_score":0.9981315},"labels":[],"label_agreement":null},{"id":"W6925973559","doi":"10.18910/56253","title":"トロントでの転機","year":2016,"lang":"ja","type":"article","venue":"Institutional Repositories DataBase (IRDB)","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Nucleofection; Gestational period; TSG101; Dysgeusia; Liquation; Diafiltration; Emperipolesis; Triacetin; Demotion","score_opus":0.02580569893708496,"score_gpt":0.260597535282951,"score_spread":0.23479183634586603,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6925973559","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09726365,0.0022435768,0.83905387,0.016611157,0.02309035,0.0010071363,0.0026523913,0.00082534115,0.01725253],"genre_scores_gemma":[0.9842826,0.00023805261,0.009366287,0.00030342417,0.0022437046,0.000061180755,0.00018734799,0.000020621655,0.0032967583],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99560285,0.00022101005,0.0008900038,0.0013331079,0.0012489224,0.00070413767],"domain_scores_gemma":[0.9957122,0.00057151634,0.00032552716,0.0023572533,0.00062518317,0.0004082776],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00074988214,0.0004430853,0.0003659925,0.00016995132,0.0011488838,0.00059852126,0.0015188764,0.00024405163,0.00016676725],"category_scores_gemma":[0.0011931845,0.0003313442,0.00020009714,0.00068501406,0.0010993544,0.004120661,0.0008170013,0.00028472306,0.0013289867],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012349768,0.00050647237,0.003332534,0.00013652467,0.00010769978,0.00026383373,0.0005342788,0.000026483882,0.053189576,0.894338,0.010738863,0.03670225],"study_design_scores_gemma":[0.0012074626,0.00020672505,0.022371747,0.0010441514,0.00007986274,0.00072645897,0.00006695647,0.0008661958,0.042012043,0.004091859,0.9262271,0.0010994253],"about_ca_topic_score_codex":0.00048795217,"about_ca_topic_score_gemma":0.000086959495,"teacher_disagreement_score":0.91548824,"about_ca_system_score_codex":0.0006806306,"about_ca_system_score_gemma":0.0014621518,"threshold_uncertainty_score":0.9999139},"labels":[],"label_agreement":null},{"id":"W6930753170","doi":"10.5281/zenodo.15823213","title":"FIGURE 2. Lagenopolycystis peresi A–C in On the genus Lagenopolycystis Artois and Schockaert, 2000 (Platyhelminthes, Kalyptorhynchia, Polycystididae)","year":2025,"lang":"en","type":"other","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Stylet; Depiction; Single specimen; Line drawings; Taxonomy (biology)","score_opus":0.018804300045749067,"score_gpt":0.22302821882778176,"score_spread":0.2042239187820327,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6930753170","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006084554,0.0022682922,0.015958194,0.0061211246,0.00030901004,0.0014439811,0.0005683962,0.0014971703,0.9712254],"genre_scores_gemma":[0.1275903,0.002049066,0.0027272396,0.0021005103,0.0009247312,0.0000021743108,0.0017196982,0.006602068,0.8562842],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99674696,0.00072555844,0.00040183475,0.0010258565,0.00055639754,0.0005433809],"domain_scores_gemma":[0.9977203,0.0001545487,0.00022164943,0.0015569879,0.00015745257,0.00018908866],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.000852237,0.00037842576,0.00034160406,0.00069588795,0.0013431329,0.0017839429,0.0027064357,0.00032911813,0.0102814445],"category_scores_gemma":[0.0008981167,0.00032972547,0.00007541873,0.0009843009,0.00027544986,0.00026325817,0.0014008273,0.0007634649,0.0044115093],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004806733,0.00012943758,0.000003945835,0.00010171115,0.000053887317,0.000030743802,0.0009394553,0.000007474564,0.00021828867,0.041797936,0.7279506,0.22871847],"study_design_scores_gemma":[0.00031118197,0.00013016023,0.00069476996,0.00023283467,0.000014257297,0.0000395637,0.00008907901,0.00038653915,0.00016086518,0.00047257837,0.99714506,0.0003230931],"about_ca_topic_score_codex":0.00051696016,"about_ca_topic_score_gemma":0.00002096409,"teacher_disagreement_score":0.26919448,"about_ca_system_score_codex":0.00028812242,"about_ca_system_score_gemma":0.000041877003,"threshold_uncertainty_score":0.99995697},"labels":[],"label_agreement":null},{"id":"W6931079774","doi":"10.5281/zenodo.4370543","title":"Jatropha gossypiifolia Linnaeus 1753","year":2007,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Jatropha; Genus; Type (biology); Taxon; Pongamia","score_opus":0.032604208013211074,"score_gpt":0.2544820401408193,"score_spread":0.22187783212760825,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6931079774","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.030169187,0.0000959858,0.83370256,0.0018483307,0.00026138613,0.00040893926,0.000031037427,0.0021043897,0.13137817],"genre_scores_gemma":[0.993312,0.00002399684,0.004869345,0.00023817451,0.00016723388,1.7240009e-8,0.00019764571,0.00040800765,0.000783564],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982868,0.00016621061,0.0002773073,0.0004700377,0.00038037938,0.0004192875],"domain_scores_gemma":[0.9983671,0.00004035901,0.00009098027,0.00083811465,0.00045712263,0.00020632883],"candidate_categories":["sts","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.001358636,0.00011881214,0.00011018344,0.0002004965,0.001539384,0.00087516865,0.001932821,0.000071164846,0.0014608833],"category_scores_gemma":[0.00041677727,0.00012388558,0.000054530195,0.00077888154,0.000112853675,0.0005061973,0.0010128708,0.00022897757,0.008351612],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000358781,0.0002055615,0.000013247884,0.000033405915,0.000020687168,0.00002262942,0.0017656522,0.000033294247,0.008756835,0.15802613,0.04961506,0.7814716],"study_design_scores_gemma":[0.00024744196,0.00014098498,0.0051025716,0.000008204594,0.000003608835,0.000092526694,0.00008534257,0.0010928592,0.0019619125,0.0017125685,0.9893862,0.00016576027],"about_ca_topic_score_codex":0.000015712556,"about_ca_topic_score_gemma":5.366879e-7,"teacher_disagreement_score":0.9631428,"about_ca_system_score_codex":0.00014714086,"about_ca_system_score_gemma":0.0000044300023,"threshold_uncertainty_score":0.99976045},"labels":[],"label_agreement":null},{"id":"W6932070038","doi":"10.5683/sp3/uflt9d","title":"Slow heating rates increase thermal tolerance and alter mRNA HSP expression in juvenile white sturgeon (Acipenser transmontanus)","year":2023,"lang":"en","type":"dataset","venue":"Borealis","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Sturgeon; Juvenile; Hsp70; Messenger RNA; Ectotherm; Thermal; Acclimatization","score_opus":0.016596619613404286,"score_gpt":0.25986093041748515,"score_spread":0.24326431080408087,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6932070038","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015918847,0.00029071493,0.0009784632,0.000677865,0.00020383307,0.0005671602,0.9811187,0.00015790554,0.00008656025],"genre_scores_gemma":[0.007898302,0.00026701693,0.0013869689,0.00035962058,0.00015720236,0.00019027581,0.9896293,0.000030054129,0.00008121005],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9975625,0.00028837973,0.0005479561,0.0008250872,0.0003730998,0.00040294553],"domain_scores_gemma":[0.99822134,0.00025700804,0.00019432095,0.0011215551,0.000060637478,0.00014514521],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00067362876,0.00034223296,0.0004637171,0.00019425023,0.00015280624,0.00025125386,0.0008204917,0.0002795077,0.000012006414],"category_scores_gemma":[0.00009530829,0.00030036859,0.00008114178,0.00033341625,0.000067427776,0.0005317572,0.0002174965,0.00042026438,0.000021605016],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000045025477,0.00009009049,0.00042734432,0.00016669257,0.000008359344,0.0000708596,0.00078050914,0.00014821673,0.00063522405,0.000024494659,0.9900952,0.007507994],"study_design_scores_gemma":[0.0014654153,0.00018331526,0.15800367,0.001276597,0.00004650946,0.000040257913,0.00015419355,0.010975663,0.0022399996,0.0007497497,0.8234321,0.0014325194],"about_ca_topic_score_codex":0.03750418,"about_ca_topic_score_gemma":0.017858904,"teacher_disagreement_score":0.16666308,"about_ca_system_score_codex":0.00006530462,"about_ca_system_score_gemma":0.000090393274,"threshold_uncertainty_score":0.99994487},"labels":[],"label_agreement":null},{"id":"W6939099005","doi":"10.60692/m7hdm-s4m11","title":"Proceedings of the 5th Workshop on Natural Language Processing Techniques for Educational Applications","year":2018,"lang":"en","type":"article","venue":"Greater South Information System","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Office of the Chief Medical Examiner","funders":"","keywords":"Comprehension; Coherence (philosophical gambling strategy); Set (abstract data type); Reading comprehension; Interpretation (philosophy); Semantic interpretation; Natural language; Identification (biology)","score_opus":0.025367748906420757,"score_gpt":0.2651448984971112,"score_spread":0.23977714959069044,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6939099005","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1884542,0.000010791476,0.7971437,0.001860906,0.00036819855,0.0029271548,0.000048923026,0.0005119853,0.008674117],"genre_scores_gemma":[0.9901992,1.7151763e-8,0.008884657,0.0001465517,0.000132984,0.0004667788,0.000004817838,0.0000034687034,0.00016150496],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.999202,0.000007920788,0.00032989006,0.00013516052,0.0002086031,0.00011642091],"domain_scores_gemma":[0.998843,0.0000151423565,0.0003222929,0.00027129942,0.0005228541,0.00002537878],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00025813776,0.00008714965,0.000089312955,0.00010723064,0.00023169674,0.00018147758,0.0005187939,0.000055100958,0.0000012378168],"category_scores_gemma":[0.000032087897,0.000058019836,0.00004970346,0.00037811487,0.000058295154,0.0007897657,0.000055280725,0.000059007845,0.000025465935],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010085893,0.00004483852,0.02157549,0.0024461977,0.000042335978,2.1148399e-8,0.4537996,0.00001121706,0.00037826353,0.250729,0.0017344399,0.26913774],"study_design_scores_gemma":[0.0026740646,0.00053639244,0.41841102,0.0037155186,0.00012721043,0.00014893572,0.0854849,0.2117674,0.23879223,0.0013500575,0.03472452,0.0022677537],"about_ca_topic_score_codex":0.0000010527092,"about_ca_topic_score_gemma":1.1467107e-7,"teacher_disagreement_score":0.801745,"about_ca_system_score_codex":0.00007595636,"about_ca_system_score_gemma":0.00006445996,"threshold_uncertainty_score":0.23659803},"labels":[],"label_agreement":null},{"id":"W6939365645","doi":"10.6084/m9.figshare.13141538.v1","title":"Additional file 1 of A strategic initiative to facilitate knowledge translation research in rehabilitation","year":2020,"lang":"en","type":"article","venue":"Figshare","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Trois-Rivières; McMaster University; McGill University; Université Laval; Université de Montréal; Centre for Interdisciplinary Research in Rehabilitation","funders":"Fonds de Recherche du Québec - Santé","keywords":"Selection (genetic algorithm); Rehabilitation; Knowledge translation; Context (archaeology)","score_opus":0.6070556953444278,"score_gpt":0.38021883051418776,"score_spread":0.22683686483024007,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6939365645","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00007983561,0.000012286697,0.00014010306,0.0013352237,0.0000045783204,0.00034930598,0.9909633,0.000037915477,0.0070774853],"genre_scores_gemma":[0.17266858,1.3682366e-7,0.012099259,0.00010344829,0.000040331357,0.0017666542,0.8132799,0.0000061133396,0.000035536494],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988354,0.00024860504,0.00022674343,0.00030349282,0.0002409281,0.00014484538],"domain_scores_gemma":[0.9928642,0.006477049,0.00004192339,0.00018591613,0.00034628392,0.00008464251],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.000119086224,0.000063356725,0.00009670928,0.00014338967,0.00004270722,0.00003418201,0.00031855938,0.00005158805,0.7325811],"category_scores_gemma":[0.004116239,0.00006745923,0.000036507634,0.0012275083,0.000012755359,0.0003615266,0.000061187755,0.00015194871,0.0026737673],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009349894,0.000048120277,7.360204e-7,0.000116369905,0.0000013788319,6.503213e-7,0.008866392,0.00007062723,0.00003267227,0.00039572187,0.9762277,0.014230251],"study_design_scores_gemma":[0.0002546029,0.0007364614,0.012164523,0.0015387393,6.0025735e-7,7.83418e-7,0.0013808948,0.041467126,0.00015464444,0.010591578,0.93148226,0.00022776371],"about_ca_topic_score_codex":0.000004130855,"about_ca_topic_score_gemma":0.00004789854,"teacher_disagreement_score":0.72990733,"about_ca_system_score_codex":0.000054314223,"about_ca_system_score_gemma":0.00024376105,"threshold_uncertainty_score":0.9981028},"labels":[],"label_agreement":null},{"id":"W6957999761","doi":"10.6084/m9.figshare.13141541","title":"Additional file 2 of A strategic initiative to facilitate knowledge translation research in rehabilitation","year":2020,"lang":"en","type":"article","venue":"Figshare","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Trois-Rivières; McMaster University; McGill University; Université Laval; Université de Montréal; Centre for Interdisciplinary Research in Rehabilitation","funders":"","keywords":"Rehabilitation; Knowledge translation; Information system; Key (lock); Context (archaeology)","score_opus":0.5972495769037591,"score_gpt":0.37944692620657117,"score_spread":0.21780265069718796,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6957999761","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00007936718,0.000012496864,0.00013719474,0.0013295228,0.00000460965,0.00034900915,0.9908038,0.000037942194,0.0072460645],"genre_scores_gemma":[0.17024487,1.4059185e-7,0.011842671,0.000103542974,0.00004096997,0.0017339642,0.81599206,0.000006109952,0.000035685596],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988357,0.00024852055,0.00022684665,0.00030326383,0.00024086783,0.00014479183],"domain_scores_gemma":[0.9929587,0.0063837734,0.000041973464,0.00018551503,0.00034543083,0.00008461148],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00011842963,0.000063336374,0.0000967332,0.00014329486,0.00004271038,0.00003425694,0.00031838033,0.00005158835,0.72880024],"category_scores_gemma":[0.004066263,0.00006743695,0.0000365005,0.0012265455,0.000012755181,0.00036177677,0.00006117906,0.00015191338,0.0026450318],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000093149365,0.000048189573,7.1371056e-7,0.00011764303,0.0000013812858,6.6948377e-7,0.008889635,0.00007109571,0.000031585627,0.00040346672,0.97577333,0.01465297],"study_design_scores_gemma":[0.0002499933,0.00071828143,0.011669904,0.0014818091,5.8319955e-7,7.656616e-7,0.0013327008,0.04016603,0.00014985405,0.010411126,0.9335973,0.00022163277],"about_ca_topic_score_codex":0.000004172904,"about_ca_topic_score_gemma":0.000048184873,"teacher_disagreement_score":0.72615516,"about_ca_system_score_codex":0.00005432994,"about_ca_system_score_gemma":0.0002426656,"threshold_uncertainty_score":0.9981315},"labels":[],"label_agreement":null},{"id":"W6968009259","doi":"10.5281/zenodo.12169584","title":"Promoting multilingualism and bibliodiversity by enhancing discoverability","year":2024,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université de Montréal","funders":"European Commission","keywords":"Discoverability; Multilingualism; French; First language; Publication; Historical linguistics; Diversity (politics); Spoken language; English language","score_opus":0.026638772097803923,"score_gpt":0.2531051101091931,"score_spread":0.2264663380113892,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6968009259","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.604958,0.0005545509,0.37782255,0.004170092,0.00023630296,0.0006590129,0.00020718023,0.003095299,0.0082970355],"genre_scores_gemma":[0.99866974,0.000041057578,0.00079902576,0.000050399947,0.000034145458,1.7828837e-8,0.00014948013,0.00013393033,0.00012222379],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9986508,0.0002165959,0.00016540656,0.00052012486,0.00023395555,0.00021315072],"domain_scores_gemma":[0.99925154,0.000055889992,0.000034649354,0.00037739114,0.00016836579,0.000112154215],"candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0010156333,0.000089375666,0.00008279387,0.00022467438,0.001369108,0.0021491903,0.00071514444,0.000042127387,0.00033949665],"category_scores_gemma":[0.00042140414,0.00008952413,0.00002893407,0.00091137044,0.00010569555,0.00086727797,0.0011314199,0.00018977957,0.00062660006],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013062593,0.00016455103,0.000030100076,0.0003639769,0.000032285396,0.000013754165,0.022279438,0.000008440322,0.05227483,0.018506233,0.02861354,0.8776998],"study_design_scores_gemma":[0.0002134746,0.00013460952,0.0014016605,0.00006205374,0.0000092942755,0.000085192536,0.0002871325,0.029033897,0.008659517,0.00219035,0.95766884,0.00025396506],"about_ca_topic_score_codex":0.000028200857,"about_ca_topic_score_gemma":4.0097703e-7,"teacher_disagreement_score":0.92905533,"about_ca_system_score_codex":0.00009096428,"about_ca_system_score_gemma":0.0000042465995,"threshold_uncertainty_score":0.999931},"labels":[],"label_agreement":null},{"id":"W6968313569","doi":"10.5281/zenodo.14301374","title":"Vers une classification automatique de didascalies en français avec des grands modèles de langue","year":2024,"lang":"fr","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Domain (mathematical analysis); Context (archaeology); Field (mathematics)","score_opus":0.04214523564787754,"score_gpt":0.26573472612946236,"score_spread":0.22358949048158483,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6968313569","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.056199454,0.0018613463,0.8689271,0.017210318,0.00037099078,0.0005044448,0.0002508568,0.0026424143,0.052033074],"genre_scores_gemma":[0.9902802,0.0005109363,0.005288608,0.00011649992,0.00021774953,2.5473776e-7,0.00044507557,0.00058592454,0.0025547373],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99717295,0.0009881163,0.000335579,0.0005940559,0.00036338478,0.0005459164],"domain_scores_gemma":[0.9985188,0.0001556194,0.000068081186,0.00062769296,0.00037904692,0.0002507218],"candidate_categories":["sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.001692243,0.0002015934,0.00016648497,0.00025587555,0.0016112461,0.0025053953,0.0013060389,0.00019764552,0.0025063502],"category_scores_gemma":[0.0007170236,0.00022210123,0.00010067061,0.0012225313,0.00050139695,0.0009594873,0.00054994185,0.0004430512,0.0053604785],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022109718,0.00017261825,0.0000286578,0.0005769337,0.000064336506,0.000033886925,0.059166115,0.0004321389,0.008999671,0.23643321,0.036027033,0.6580433],"study_design_scores_gemma":[0.00018667939,0.00013614942,0.027731663,0.00020395582,0.000030431114,0.0002608501,0.000624704,0.19505493,0.00094758015,0.007869064,0.7667183,0.00023568993],"about_ca_topic_score_codex":0.00081493304,"about_ca_topic_score_gemma":0.000017556438,"teacher_disagreement_score":0.9340808,"about_ca_system_score_codex":0.0006917481,"about_ca_system_score_gemma":0.00004277602,"threshold_uncertainty_score":0.9996885},"labels":[],"label_agreement":null},{"id":"W6976627463","doi":"10.60692/stpvv-m1h43","title":"A multi-criteria vertical coordination framework for a reliable aid distribution","year":2017,"lang":"en","type":"article","venue":"Greater South Information System","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Humanitarian Logistics; Humanitarian aid; Supply chain; Process (computing); Quality (philosophy); Order (exchange)","score_opus":0.05603057695129492,"score_gpt":0.2800731072372538,"score_spread":0.22404253028595889,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6976627463","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.062962376,9.44101e-7,0.9346695,0.00067219936,0.0006549141,0.0005585855,0.000095373405,0.0002568651,0.00012922278],"genre_scores_gemma":[0.95161504,4.0961492e-8,0.04795791,0.00006486634,0.000063878506,0.00019084314,0.000062245475,0.0000045089046,0.000040675037],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9987851,0.000035441702,0.00047921002,0.00022301868,0.00022730758,0.00024991654],"domain_scores_gemma":[0.9981559,0.000021326969,0.00026574088,0.0011262615,0.00033974025,0.00009101531],"candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0005797721,0.00013648995,0.00017481642,0.00006648209,0.00074667373,0.0013387464,0.0006997033,0.00016690325,0.0000031463842],"category_scores_gemma":[0.0003537363,0.00012150259,0.00008101035,0.000091006325,0.0000434155,0.0028589831,0.00012540222,0.000086703185,0.00023653793],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003796732,0.000064923406,0.11765604,0.002037219,0.00010870673,0.0000030759536,0.08943327,0.00021708281,0.00009200563,0.76892376,0.0024308837,0.018653346],"study_design_scores_gemma":[0.0019122971,0.00010974755,0.254035,0.0002523277,0.000024215482,0.00002252079,0.0011384079,0.73520935,0.0020906741,0.0005285992,0.004266246,0.00041059533],"about_ca_topic_score_codex":0.000010244347,"about_ca_topic_score_gemma":2.0966606e-7,"teacher_disagreement_score":0.8886527,"about_ca_system_score_codex":0.0001746363,"about_ca_system_score_gemma":0.00004248711,"threshold_uncertainty_score":0.999698},"labels":[],"label_agreement":null},{"id":"W7015866577","doi":"","title":"University of Amsterdam at the CLEF 2022 SimpleText Track","year":2022,"lang":"en","type":"article","venue":"UvA-DARE (University of Amsterdam)","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek; Universiteit van Amsterdam; Canadian Institute of Steel Construction","keywords":"Clef; Context (archaeology); Misinformation; Readability; Reading (process); Relevance (law); Set (abstract data type); Rewriting","score_opus":0.01408198109943822,"score_gpt":0.1891549743513123,"score_spread":0.17507299325187406,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7015866577","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95695657,0.00011433012,0.031850684,0.0057470878,0.00026544987,0.00042425946,0.00023400078,0.00011915788,0.004288459],"genre_scores_gemma":[0.99306005,0.000024418081,0.0011537739,0.00012291696,0.000012543297,2.0600582e-7,0.000035378966,0.000007434014,0.0055832826],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99812204,0.0003605471,0.00017317805,0.00050721527,0.00055760087,0.0002794297],"domain_scores_gemma":[0.9980329,0.00021142476,0.00033201533,0.0011850051,0.00013885678,0.000099767996],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00051263854,0.00015134,0.00028144923,0.00014247897,0.0011212656,0.00002064146,0.0023172866,0.000067149515,0.0017425823],"category_scores_gemma":[0.0000143290445,0.00017485966,0.00024473143,0.0007052706,0.00036758705,0.00050841767,0.0021076188,0.00026478936,0.00006158314],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016402989,0.0023564012,0.02528532,0.0005856806,0.00064429245,0.00039316743,0.15197153,0.0074487003,0.026456239,0.05714615,0.110944614,0.6151276],"study_design_scores_gemma":[0.0033511291,0.0011651983,0.22646065,0.00004505868,0.00017616861,0.0001074174,0.05596945,0.021655329,0.0011949976,0.0030474605,0.68579966,0.0010274581],"about_ca_topic_score_codex":0.0010247447,"about_ca_topic_score_gemma":0.00095983455,"teacher_disagreement_score":0.61410016,"about_ca_system_score_codex":0.0002818415,"about_ca_system_score_gemma":0.00013817816,"threshold_uncertainty_score":0.99916995},"labels":[],"label_agreement":null},{"id":"W7039670831","doi":"","title":"Multi-scale analysis of the effects of forestry operations on the stream morphology and sedimentology of the Cascapédia River, eastern Québec","year":2004,"lang":"en","type":"other","venue":"Library and Archives Canada (Government of Canada)","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Sedimentology; Tributary; Hydrology (agriculture); Sediment; STREAMS; Turbidity current; Turbidity; Drainage basin","score_opus":0.0037240571431055645,"score_gpt":0.15975937401214818,"score_spread":0.15603531686904262,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7039670831","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9101345,0.0013455836,0.004068504,0.010671661,0.00082769344,0.0017688726,0.0013002855,0.00001920986,0.0698637],"genre_scores_gemma":[0.9877529,0.00006150513,0.0010311366,0.00032672557,0.000010278393,0.00001018934,0.000004280351,0.000016472159,0.010786521],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9984899,0.00018804647,0.00026949472,0.00024403195,0.00067094935,0.00013756395],"domain_scores_gemma":[0.9984269,0.00038796113,0.0003181788,0.00080860866,0.0000015413856,0.000056793877],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000018163546,0.00015553946,0.00033750272,0.000044352186,0.000087877605,0.000007782359,0.0008320327,0.000059125134,0.000011836823],"category_scores_gemma":[0.000012207472,0.00008963414,0.000072933566,0.00020154873,0.0003950763,0.000063491876,0.0003365147,0.00012636722,1.2698919e-9],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023359213,0.0008378232,0.45706126,0.002107963,0.004249101,0.000026278276,0.004220041,0.0052177142,0.07771249,0.42666426,0.0070854775,0.014583981],"study_design_scores_gemma":[0.0007279849,0.00019987875,0.8706902,0.00042704862,0.00051849615,0.000006216435,0.0006912171,0.014507024,0.10816782,0.0011077747,0.002654218,0.00030211222],"about_ca_topic_score_codex":0.024699427,"about_ca_topic_score_gemma":0.18757129,"teacher_disagreement_score":0.42555648,"about_ca_system_score_codex":0.000008565835,"about_ca_system_score_gemma":0.0007849762,"threshold_uncertainty_score":0.9817952},"labels":[],"label_agreement":null},{"id":"W7066335524","doi":"","title":"Investigation of antimicrobial resistance in Salmonella, Escherichia coli and Campylobacter isolated from Ontario sheep flocks","year":2009,"lang":"en","type":"dissertation","venue":"The Atrium (University of Guelph)","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Flock; Tetracycline; Antibiotic resistance; Antimicrobial; Campylobacter; Feces; Enteric bacteria; Drug resistance","score_opus":0.011338420738094384,"score_gpt":0.19083491899591837,"score_spread":0.179496498257824,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7066335524","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.996619,0.00014119831,0.0018721393,0.0004969835,0.000113179216,0.00026060196,0.00001944013,0.000024409444,0.00045306777],"genre_scores_gemma":[0.9941276,0.00004725181,0.0043390375,0.000030263109,0.000012468271,1.5350926e-7,0.00021883842,0.0000053983317,0.0012190216],"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","domain_scores_codex":[0.99893016,0.00013143134,0.00024596168,0.00036573922,0.00018613275,0.00014059254],"domain_scores_gemma":[0.9987692,0.000087445434,0.0004248519,0.0005224026,0.0001497787,0.00004630194],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00022761116,0.00015949478,0.00032721672,0.0001321785,0.00011468483,0.000028429882,0.0007459946,0.0002512292,0.00001752715],"category_scores_gemma":[0.0000142927975,0.00017214159,0.00007570162,0.00040111388,0.00011525238,0.00031916628,0.000069055546,0.00029035073,0.0000040740892],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011955913,0.00012306421,0.014252043,0.0002911323,0.000119145196,0.000014218912,0.0981589,0.00007901413,0.87899834,0.0015778241,0.0012912558,0.0038994495],"study_design_scores_gemma":[0.00038219022,0.000038380338,0.9936309,0.0001397724,0.00005159877,3.7965452e-7,0.00061983895,0.0005560098,0.0018542405,0.0023165192,0.00023304803,0.00017713914],"about_ca_topic_score_codex":0.059522368,"about_ca_topic_score_gemma":0.36159718,"teacher_disagreement_score":0.9793788,"about_ca_system_score_codex":0.00013312174,"about_ca_system_score_gemma":0.00026515895,"threshold_uncertainty_score":0.9467403},"labels":[],"label_agreement":null},{"id":"W7072117608","doi":"","title":"Une approche computationnelle de la complexité linguistique par le traitement automatique du langage naturel et l'oculométrie","year":2021,"lang":"fr","type":"other","venue":"Open MIND","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Linguistic analysis; Acoustic phonetics; Agrégation","score_opus":0.0391672517334494,"score_gpt":0.33290613863124274,"score_spread":0.29373888689779337,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7072117608","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005602498,0.0006580951,0.5462992,0.008949049,0.0003981287,0.0012769073,0.00007541713,0.000026990067,0.4367137],"genre_scores_gemma":[0.21910046,0.000060939296,0.6849957,0.0009832362,0.00044389878,0.00014411115,0.00074458093,0.00012860436,0.09339844],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9960128,0.0016991976,0.0005850729,0.000991551,0.00031786357,0.00039350113],"domain_scores_gemma":[0.99738985,0.0009647759,0.00041694927,0.0008031122,0.00022940278,0.00019588515],"candidate_categories":["metaepi_narrow","scholarly_communication","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0020527763,0.00042069345,0.00056446955,0.00010043829,0.00034116747,0.0013550819,0.0016538628,0.0006361567,0.0031485565],"category_scores_gemma":[0.00054972974,0.00044461945,0.0001559722,0.0005364107,0.0002774007,0.0001889607,0.000607736,0.0008493266,0.0002235275],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000039772443,0.0030179762,0.0005118088,0.00069325796,0.00042478272,0.00038639363,0.08756376,0.008350985,0.0026438267,0.5421577,0.02871672,0.325493],"study_design_scores_gemma":[0.00080020924,0.000067249144,0.010673853,0.00049573736,0.000038127244,0.00010094897,0.0006263381,0.085001335,0.0017301033,0.009708248,0.89016765,0.00059019757],"about_ca_topic_score_codex":0.00306182,"about_ca_topic_score_gemma":0.0025924041,"teacher_disagreement_score":0.8614509,"about_ca_system_score_codex":0.00020113359,"about_ca_system_score_gemma":0.0017226761,"threshold_uncertainty_score":0.99980056},"labels":[],"label_agreement":null},{"id":"W7084071794","doi":"10.64628/aap.wy3stv9jq","title":"Un nouveau médicament prometteur pour réduire les crises d'asthme","year":2019,"lang":"fr","type":"article","venue":"","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Government (linguistics); Perspective (graphical); Field (mathematics); Context (archaeology)","score_opus":0.041215783914395655,"score_gpt":0.26587216740665676,"score_spread":0.2246563834922611,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7084071794","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.40767372,0.00347466,0.35198343,0.18565042,0.0027413215,0.0013433044,0.000020732727,0.00045063152,0.04666177],"genre_scores_gemma":[0.8841915,0.00010328407,0.027799519,0.001227685,0.00018508657,0.000028402997,0.0000062564227,0.000018474544,0.08643978],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9974559,0.00022422186,0.00046475284,0.00082466163,0.00048106664,0.0005493946],"domain_scores_gemma":[0.99805504,0.00020754748,0.00015163062,0.0011795361,0.00019782632,0.00020844818],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.00054419937,0.00028025152,0.0003003103,0.000103936545,0.0001883891,0.0003936336,0.00095556845,0.00020391318,0.0037564083],"category_scores_gemma":[0.00007351284,0.00025433028,0.00016052659,0.0004775867,0.00014718038,0.0008595949,0.00034499605,0.0002688185,0.0054197945],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000944257,0.0006768293,0.010834199,0.00017980626,0.000039704017,0.00000902685,0.0013840783,0.00010253172,0.0014311216,0.45642343,0.008793686,0.52011615],"study_design_scores_gemma":[0.0010624701,0.000664096,0.18605763,0.00022197401,0.000055723867,0.00013256082,0.001074954,0.056818277,0.011960859,0.027916007,0.71294045,0.0010950017],"about_ca_topic_score_codex":0.00060159154,"about_ca_topic_score_gemma":0.0000349842,"teacher_disagreement_score":0.70414674,"about_ca_system_score_codex":0.00014737487,"about_ca_system_score_gemma":0.00026970208,"threshold_uncertainty_score":0.9999909},"labels":[],"label_agreement":null},{"id":"W7099729388","doi":"","title":"Does the Length of the Period Really Matter for the Identification and the Modelling of Monetary Policy Shocks?","year":2005,"lang":"en","type":"article","venue":"","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Monetary policy; Portfolio; Identification (biology); Period (music); Quarter (Canadian coin); Lag; Interest rate; Inflation (cosmology)","score_opus":0.017175890047988192,"score_gpt":0.24029052365336695,"score_spread":0.22311463360537875,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7099729388","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.111486994,0.00014710931,0.74260545,0.14469813,0.00006532899,0.0006674641,0.0000059937674,0.000014319271,0.00030924025],"genre_scores_gemma":[0.9964473,0.00005821485,0.0022104098,0.00060219277,0.0000640045,0.000038024973,6.648184e-7,0.000003354028,0.00057579455],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9991599,0.0001012201,0.00030261997,0.00016570716,0.00017203079,0.0000985699],"domain_scores_gemma":[0.99831635,0.0004688757,0.0001622859,0.0009558566,0.00008562019,0.000010995535],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00092534476,0.00006705493,0.000087768065,0.000019490191,0.00026913977,0.000089881476,0.000939317,0.000028715453,0.0000058306355],"category_scores_gemma":[0.000041042003,0.000019090716,0.00007889685,0.00014758269,0.00026970124,0.00020532908,0.00011961539,0.0000673481,0.0000018323839],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011950845,0.0001480821,0.0034515406,0.00009904647,0.00011447692,2.2029683e-8,0.044650283,0.10489185,0.0027317377,0.6826882,0.0013200054,0.15978524],"study_design_scores_gemma":[0.0002126723,0.000007549436,0.030291341,0.0000066918715,0.000023070588,0.000002537608,0.0005911971,0.9376195,0.00440835,0.025758842,0.0010247384,0.000053498297],"about_ca_topic_score_codex":0.00046788575,"about_ca_topic_score_gemma":0.00016727507,"teacher_disagreement_score":0.88496035,"about_ca_system_score_codex":0.000011782532,"about_ca_system_score_gemma":0.000038216258,"threshold_uncertainty_score":0.20700327},"labels":[],"label_agreement":null},{"id":"W7104265732","doi":"10.71781/5344","title":"Une approche computationnelle de la complexité linguistique par le traitement automatique du langage naturel et l'oculométrie","year":2021,"lang":"fr","type":"dissertation","venue":"Papyrus : Institutional Repository (Université de Montréal)","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Linguistic analysis; Acoustic phonetics; Agrégation","score_opus":0.00803999034162245,"score_gpt":0.21225247885793666,"score_spread":0.2042124885163142,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7104265732","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5507172,0.0108660245,0.3796057,0.0065565826,0.0016652386,0.0010878148,0.00013495612,0.0005784282,0.04878807],"genre_scores_gemma":[0.9497502,0.00026171523,0.039449733,0.00046045013,0.00023052403,0.00006328548,0.0015272754,0.00003895952,0.008217878],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9958319,0.0012924478,0.00065254315,0.0009991141,0.00071963295,0.00050436176],"domain_scores_gemma":[0.9968433,0.0008434718,0.00058301294,0.00061757583,0.0007453259,0.00036731316],"candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.000962196,0.00054654205,0.00054011063,0.00023626829,0.0063216207,0.00038195465,0.00086978043,0.0008337558,0.000017758604],"category_scores_gemma":[0.00041284805,0.0006734365,0.00039207554,0.0007527467,0.00043404987,0.00050661736,0.00025732437,0.0010956012,0.000023904393],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015542832,0.0009974057,0.0024172731,0.00053447054,0.00032126586,0.0017270447,0.2032042,0.039663784,0.01270398,0.732994,0.0012072287,0.0040738843],"study_design_scores_gemma":[0.003216961,0.00023835068,0.3541175,0.001156795,0.00042035646,0.0029252234,0.07185396,0.38094574,0.02921594,0.022669664,0.13116886,0.002070651],"about_ca_topic_score_codex":0.07333794,"about_ca_topic_score_gemma":0.013948192,"teacher_disagreement_score":0.71032435,"about_ca_system_score_codex":0.0036561796,"about_ca_system_score_gemma":0.0062621823,"threshold_uncertainty_score":0.9995717},"labels":[],"label_agreement":null},{"id":"W7117310638","doi":"10.2139/ssrn.5970054","title":"Estimating Consumer Preferences for LLMs: Evidence from LMArena","year":2025,"lang":"","type":"preprint","venue":"SSRN Electronic Journal","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Counterfactual thinking; Context (archaeology); Quality (philosophy); Consumer welfare; Economic surplus; Consumer choice; Taste; Product (mathematics); Pairwise comparison","score_opus":0.04872354047087291,"score_gpt":0.31802766975288277,"score_spread":0.26930412928200986,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7117310638","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.047741402,0.027857855,0.91639525,0.00262111,0.0036372535,0.0013801005,0.00010586196,0.000117699026,0.0001434866],"genre_scores_gemma":[0.88058704,0.016394911,0.099544436,0.0001508192,0.001252611,0.0002612159,0.000055219905,0.000032971282,0.0017207622],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9896362,0.00083175855,0.0019945567,0.0020471083,0.0009703151,0.00452008],"domain_scores_gemma":[0.991279,0.0035641077,0.0018585974,0.0018092747,0.0012004869,0.00028849917],"candidate_categories":["metaepi_narrow","sts","scholarly_communication","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.007809912,0.00086721894,0.0010939303,0.00034968587,0.0013511569,0.0016760483,0.0050748247,0.0007101943,0.00006181865],"category_scores_gemma":[0.0028329364,0.0008284568,0.00072891574,0.0005300451,0.00029291352,0.0014208411,0.0011968361,0.007383357,0.000048012982],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024032853,0.0002688424,0.0036146245,0.00039167228,0.0010071215,0.0000016492532,0.0032231896,0.0059395693,0.00022403394,0.05973984,0.00020243393,0.9251467],"study_design_scores_gemma":[0.00056322716,0.00043784457,0.0014881646,0.0027693459,0.00035285656,0.00007383393,0.00063857576,0.19131657,0.00028456605,0.80049324,0.00079630443,0.0007854921],"about_ca_topic_score_codex":0.0014394206,"about_ca_topic_score_gemma":0.0027030308,"teacher_disagreement_score":0.9243612,"about_ca_system_score_codex":0.0031152177,"about_ca_system_score_gemma":0.03167995,"threshold_uncertainty_score":0.9999489},"labels":[],"label_agreement":null},{"id":"W7125886133","doi":"","title":"The Tree, an Adequate Visualization Tool to Grasp the Complexity of Multiplicity ","year":2021,"lang":"en","type":"article","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"GRASP; Visualization; Data visualization; Multiplicity (mathematics); Information visualization","score_opus":0.033897991825435625,"score_gpt":0.2652707685079859,"score_spread":0.2313727766825503,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7125886133","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17421198,0.00011713669,0.8016628,0.020558659,0.00009410073,0.0002754145,0.000008631291,0.00010814826,0.0029631252],"genre_scores_gemma":[0.9697826,0.00003749911,0.02883,0.00019471932,0.0000094301395,0.000037366095,0.00004662755,0.000008988165,0.0010527929],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99444205,0.004098299,0.000407925,0.000441061,0.00038107333,0.00022957503],"domain_scores_gemma":[0.99389136,0.0013414144,0.00022203244,0.0025444776,0.0019005968,0.00010010278],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004397793,0.00012647476,0.00014502679,0.000041961608,0.00073583366,0.0004027064,0.0016276333,0.00005779511,0.000018926796],"category_scores_gemma":[0.0015922802,0.00009219561,0.0000881143,0.00088206516,0.00032942605,0.00031886296,0.00050260086,0.00013451533,0.000019124618],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004264943,0.0002481125,0.0007335871,0.000007420106,0.000010162923,3.6606284e-7,0.006611457,0.000032517823,0.005797637,0.8545269,0.00011802196,0.13190956],"study_design_scores_gemma":[0.0005888256,0.000003011317,0.31007054,0.00017632243,0.000023997958,0.000016819598,0.00079287775,0.25495243,0.35244557,0.056460068,0.023992607,0.00047690934],"about_ca_topic_score_codex":0.000522464,"about_ca_topic_score_gemma":0.004584934,"teacher_disagreement_score":0.7980668,"about_ca_system_score_codex":0.0000468008,"about_ca_system_score_gemma":0.00014052917,"threshold_uncertainty_score":0.5659512},"labels":[],"label_agreement":null},{"id":"W7130716444","doi":"10.1109/swc65939.2025.00064","title":"Linguistic Analysis of Japanese Text Simplification and Implications for AI-Driven Educational Tools","year":2025,"lang":"","type":"article","venue":"","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Athabasca University","funders":"","keywords":"Determiner; Dependency (UML); Noun; Linguistic analysis; Noun phrase; Cognition; Error analysis","score_opus":0.03261379606745928,"score_gpt":0.34006497113829753,"score_spread":0.30745117507083825,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7130716444","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.037572414,0.00055496587,0.9095364,0.045070007,0.00036202936,0.0015930389,0.00039535217,0.00006169582,0.0048541045],"genre_scores_gemma":[0.98434544,0.000076280674,0.012255826,0.0005899915,0.00006604188,0.00029831874,0.00031190086,0.000008284175,0.0020479402],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9972159,0.00011436213,0.0011282795,0.0010256309,0.000192061,0.0003237458],"domain_scores_gemma":[0.99370956,0.0025690882,0.00041128765,0.0015421517,0.0016249933,0.0001429309],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005765019,0.00026375297,0.0005702957,0.00095395994,0.00042938156,0.00039125822,0.0008564485,0.0001998652,0.0000758234],"category_scores_gemma":[0.001853144,0.00027650292,0.00031003996,0.0037058676,0.00030678828,0.00044078685,0.00018693748,0.00013339084,0.000006913087],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002604883,0.0005568048,0.017227912,0.00023237041,0.000802683,1.6278145e-8,0.0038837267,0.0011163146,0.0026367812,0.88470775,0.00052644336,0.08828317],"study_design_scores_gemma":[0.00026431243,0.000065110115,0.6886433,0.000034766577,0.0015362218,9.0367195e-7,0.00018392364,0.27553278,0.0002375235,0.030542424,0.0027034215,0.0002553184],"about_ca_topic_score_codex":0.00023470623,"about_ca_topic_score_gemma":0.0001941884,"teacher_disagreement_score":0.946773,"about_ca_system_score_codex":0.00014439519,"about_ca_system_score_gemma":0.0007292694,"threshold_uncertainty_score":0.9999687},"labels":[],"label_agreement":null},{"id":"W7132634471","doi":"","title":"Citation amnesia: on the recency bias of NLP and other academic fields","year":2025,"lang":"en","type":"article","venue":"NPARC","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Citation; Context (archaeology); Field (mathematics); Citation analysis; Bibliometrics; Work (physics)","score_opus":0.05912769644485198,"score_gpt":0.2941826836974612,"score_spread":0.2350549872526092,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7132634471","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7992142,0.000063024505,0.12530486,0.035547998,0.0001561417,0.00021022704,0.0000015292864,0.000047983405,0.039454013],"genre_scores_gemma":[0.99756634,0.000016740154,0.0011383684,0.00096786715,0.000009099574,0.00000764773,2.0952615e-7,0.00000105382,0.00029264178],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99957037,0.000062438325,0.00011125461,0.00011859976,0.000082299775,0.00005503916],"domain_scores_gemma":[0.99936205,0.0003142882,0.000040626135,0.00024634207,0.000026340795,0.000010360519],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00030474784,0.000035855268,0.000048299946,0.00003988752,0.00004491118,0.000015044465,0.00022869685,0.000055997658,0.000015649672],"category_scores_gemma":[0.0001550904,0.000023986762,0.00001426711,0.00020379486,0.000035790898,0.000063802276,0.000032859185,0.00010184504,0.000004966539],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000041302164,0.000014337847,0.0033757286,0.000012411155,0.0000033185447,5.58101e-8,0.00084232347,0.0000050019103,0.004537298,0.8796357,0.0015217486,0.11004797],"study_design_scores_gemma":[0.00018929176,0.000094109164,0.12796786,0.00008160671,0.000007773809,0.0000012453928,0.0001542101,0.010348922,0.030961754,0.8155903,0.014493885,0.00010900112],"about_ca_topic_score_codex":0.000008795577,"about_ca_topic_score_gemma":0.0000045255006,"teacher_disagreement_score":0.19835216,"about_ca_system_score_codex":0.000007732864,"about_ca_system_score_gemma":0.000022077875,"threshold_uncertainty_score":0.09781518},"labels":[],"label_agreement":null},{"id":"W7135995046","doi":"","title":"Overview of the CLEF 2024 SimpleText Task 3: Simplify Scientific Text","year":2024,"lang":"en","type":"article","venue":"UvA-DARE (University of Amsterdam)","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek; Universiteit van Amsterdam; Agence Nationale de la Recherche; Canadian Institute of Steel Construction","keywords":"Clef; Task (project management); Complement (music); Distortion (music); Text simplification; Information source (mathematics)","score_opus":0.030748763760591456,"score_gpt":0.24201022877701445,"score_spread":0.21126146501642298,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7135995046","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.78785735,0.0038934713,0.16597666,0.022194847,0.0046646553,0.0013007246,0.0004643472,0.00053432654,0.013113616],"genre_scores_gemma":[0.9936858,0.00003584354,0.0013356656,0.000094174866,0.000024636907,3.6328666e-7,0.0000085859065,0.000008242289,0.0048066843],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99830407,0.00013169508,0.00022827597,0.0005819757,0.00049613725,0.0002578521],"domain_scores_gemma":[0.99811053,0.00017559895,0.00014487654,0.0013000129,0.00018121384,0.00008778958],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00048517034,0.00015229406,0.00024732566,0.00020243763,0.00034598386,0.00017082428,0.0018824417,0.00010155328,0.00028713833],"category_scores_gemma":[0.000034042703,0.00013760824,0.00028885098,0.0014580105,0.0004827712,0.0007604176,0.00083075423,0.00020549017,0.00016444518],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004066182,0.00037361396,0.0020551302,0.0020906182,0.00021025237,0.000041359755,0.023811478,0.00021380898,0.023475917,0.26955414,0.068441644,0.6096914],"study_design_scores_gemma":[0.00065145583,0.0002265588,0.0916285,0.0008540963,0.00014971603,0.00004312808,0.002875221,0.03365857,0.0026716029,0.0240803,0.8424618,0.00069902866],"about_ca_topic_score_codex":0.00020517196,"about_ca_topic_score_gemma":0.00022331007,"teacher_disagreement_score":0.7740202,"about_ca_system_score_codex":0.00009145585,"about_ca_system_score_gemma":0.00025334506,"threshold_uncertainty_score":0.56115013},"labels":[],"label_agreement":null},{"id":"W7138308848","doi":"10.18653/v1/2025.sciprodllm-1.2","title":"Human-Centered Disability Bias Detection in Large Language Models","year":2025,"lang":"","type":"article","venue":"","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Language model; Noise (video); Feature (linguistics); Data collection; Natural language","score_opus":0.05454424794295367,"score_gpt":0.3174023805049431,"score_spread":0.2628581325619895,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7138308848","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5195337,0.00012616838,0.47381082,0.0008599042,0.0003373516,0.00046162665,0.000009021408,0.00011695854,0.004744466],"genre_scores_gemma":[0.99758375,0.000009819496,0.00053292554,0.0002647274,0.000031242937,0.00003905455,0.000006746607,0.0000064739097,0.0015252649],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9969189,0.00047629944,0.0008031277,0.0010002662,0.00027470742,0.00052667345],"domain_scores_gemma":[0.99803853,0.0001342101,0.0001161306,0.0015364194,0.000086837004,0.000087850305],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0014667022,0.000251419,0.00032616543,0.00017726887,0.000283015,0.00030664838,0.0008124814,0.00023339271,0.00013563564],"category_scores_gemma":[0.00013390023,0.00025180052,0.00016033572,0.0012625209,0.00015542272,0.0010446378,0.0004440752,0.00036811674,0.000040400002],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007226264,0.0049484284,0.037231635,0.00047578377,0.000045608784,0.0000070967635,0.0115069905,0.0014126986,0.008265457,0.29691428,0.00010688806,0.6390129],"study_design_scores_gemma":[0.0010447748,0.00007625676,0.19458856,0.00008637984,0.000013259335,0.00000132329,0.0009890756,0.76354104,0.008857996,0.030248743,0.00023973902,0.00031283015],"about_ca_topic_score_codex":0.0019382649,"about_ca_topic_score_gemma":0.015405735,"teacher_disagreement_score":0.76212835,"about_ca_system_score_codex":0.00048733805,"about_ca_system_score_gemma":0.0000924815,"threshold_uncertainty_score":0.99999344},"labels":[],"label_agreement":null},{"id":"W7143477898","doi":"10.1109/icecit67774.2025.11451012","title":"CoNST: Context-Aware Neural Method for Word Replacement and Sentence Simplification to Improve Text Accessibility","year":2025,"lang":"","type":"article","venue":"","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Sentence; Word (group theory); Text simplification; Feature (linguistics); Artificial neural network","score_opus":0.03129774292692168,"score_gpt":0.3509232729462942,"score_spread":0.31962553001937255,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7143477898","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05330018,0.00021813504,0.91118854,0.02900285,0.0010658135,0.0045383614,0.00008131214,0.00016502324,0.00043979794],"genre_scores_gemma":[0.9361134,0.000022878801,0.05469803,0.0058857473,0.00005727575,0.00056114706,0.00001775992,0.000013324954,0.0026304093],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9944488,0.00046469225,0.0013789134,0.002607923,0.00037251794,0.0007271907],"domain_scores_gemma":[0.9943467,0.0016578137,0.00038763892,0.0023294578,0.00090123893,0.0003772018],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0027772218,0.00049900677,0.0006401324,0.00024896066,0.00070852163,0.0010193669,0.0010364115,0.00026811816,0.00006007457],"category_scores_gemma":[0.0010114515,0.0004739664,0.00018850033,0.00096203026,0.00028130622,0.000993634,0.0008640047,0.00029032046,0.000017907503],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00046067874,0.00030204144,0.0062886537,0.00039670235,0.000058109395,4.2939013e-7,0.0008803274,0.00008974193,0.0054346756,0.04798789,0.001407924,0.93669283],"study_design_scores_gemma":[0.0015057365,0.0005165888,0.08268894,0.00011759708,0.00010368469,0.000008567756,0.001283092,0.87333626,0.018997995,0.009341136,0.011436099,0.00066428387],"about_ca_topic_score_codex":0.0005116365,"about_ca_topic_score_gemma":0.00040021143,"teacher_disagreement_score":0.93602854,"about_ca_system_score_codex":0.00032856158,"about_ca_system_score_gemma":0.000489594,"threshold_uncertainty_score":0.9997712},"labels":[],"label_agreement":null},{"id":"W7152387304","doi":"10.1109/icecet63943.2025.11472110","title":"Developing a Grammatical Error Correction System for French Second Language Written Texts","year":2025,"lang":"","type":"article","venue":"","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Error detection and correction; Error analysis; Second language; Natural language; French","score_opus":0.023371038735135238,"score_gpt":0.2918910967705224,"score_spread":0.26852005803538714,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7152387304","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023979168,0.00023106126,0.96044016,0.0027634313,0.0040534805,0.0013129495,0.000012244074,0.00032425596,0.0068832645],"genre_scores_gemma":[0.93032265,0.0000017054888,0.050730627,0.00032877963,0.00011621969,0.00019291815,0.000017560289,0.00001039064,0.018279178],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99736583,0.00017507387,0.0008352131,0.000850962,0.00025522927,0.0005176874],"domain_scores_gemma":[0.997902,0.0006436697,0.00016950564,0.00084573147,0.00032442732,0.00011469013],"candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0009524194,0.0002816458,0.00040984128,0.000237548,0.00048769265,0.00055763917,0.0007527932,0.0002796724,0.00008942885],"category_scores_gemma":[0.0002967102,0.00026791554,0.00017527223,0.0008756281,0.00008860879,0.00046941073,0.0002221884,0.00022237771,0.00009271972],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025426662,0.00015252427,0.0004672228,0.0024482291,0.000091681264,0.0000037874554,0.004414677,0.000032208354,0.0008108668,0.45697805,0.0058498536,0.5287255],"study_design_scores_gemma":[0.0010502831,0.00017849682,0.019327866,0.0009144035,0.000093088085,0.000052374748,0.004466646,0.93613815,0.016644122,0.006424076,0.013994134,0.00071634166],"about_ca_topic_score_codex":0.00020693101,"about_ca_topic_score_gemma":0.00083210756,"teacher_disagreement_score":0.93610597,"about_ca_system_score_codex":0.0005873135,"about_ca_system_score_gemma":0.0006585427,"threshold_uncertainty_score":0.9999773},"labels":[],"label_agreement":null}]}