{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":1067,"total_is_capped":false,"direct_labels_cover":6,"predictions_cover":1067,"direct_label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline (scores rank; they never assert a category)","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"query_hash":"87bbbb5d5913","filters":{"topic":"Second Language Acquisition and Learning"}},"results":[{"id":"W4233063693","doi":"10.3138/cmlr.63.1.59","title":"How Large a Vocabulary is Needed For Reading and Listening?","year":2006,"lang":"en","type":"article","venue":"Canadian Modern Language Review/ La Revue canadienne des langues vivantes","topic":"Second Language Acquisition and Learning","field":"Psychology","cited_by":1422,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"University of Cambridge","keywords":"Vocabulary; Reading comprehension; Computer science; Active listening; Linguistics; Word (group theory); Reading (process); Comprehension; Natural language processing; Artificial intelligence; Listening comprehension; Psychology; Communication","retraction":null,"screen_n_in":null,"score":{"opus":0.01101669428534497,"gpt":0.2542969430756896,"spread":0.2432802487903447,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005707468,0.0003712596,0.0005953303,0.0003402566,0.0003112267,0.0001722752,0.0002795938,0.0002035913,0.002066622],"category_scores_gemma":[0.0003681586,0.0003757081,0.0002064424,0.0002823911,0.0001211839,0.0001713069,0.0000304339,0.0002693472,0.00002644392],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002338649,"about_ca_system_score_gemma":0.00007529357,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.1319755,"about_ca_topic_score_gemma":0.1850333,"domain_scores_codex":[0.9975961,0.0001809407,0.0003541614,0.0006396074,0.00006879899,0.001160402],"domain_scores_gemma":[0.998201,0.0002524473,0.000173571,0.0005659348,0.0001246573,0.0006824175],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001626138,0.0002306212,0.006088395,0.01633442,0.001135743,0.01919406,0.3338859,0.000006813748,0.02415391,0.04690034,0.2489689,0.3029383],"study_design_scores_gemma":[0.002322119,0.0002105176,0.01361368,0.005174823,0.0005436807,0.003695877,0.04982799,0.001369429,0.0001899435,0.0009783957,0.9201968,0.001876739],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5628653,0.4206382,0.001307643,0.003000761,0.0002878204,0.001020999,0.001070549,0.0001686677,0.009640099],"genre_scores_gemma":[0.9457372,0.0008890327,0.00152698,0.0237981,0.0009033666,0.0002626695,0.0009845892,0.0001817064,0.02571633],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6712279,"threshold_uncertainty_score":0.9998695,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2097674935","doi":"10.1002/j.1545-7249.2007.tb00058.x","title":"Is There an “Academic Vocabulary”?","year":2007,"lang":"en","type":"article","venue":"TESOL Quarterly","topic":"Second Language Acquisition and Learning","field":"Psychology","cited_by":742,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Intertek (Canada)","funders":"","keywords":"Vocabulary; Discipline; Collocation (remote sensing); Repertoire; English for academic purposes; Linguistics; Meaning (existential); Lexical item; Range (aeronautics); Term (time); Lexical density; Register (sociolinguistics); Mathematics education; Psychology; Computer science; Sociology; Social science; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.02653160914391622,"gpt":0.3568331609104449,"spread":0.3303015517665286,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0005109917,0.0001384298,0.000133861,0.000114209,0.00008781312,0.00002456135,0.0002237116,0.00020105,0.1279522],"category_scores_gemma":[0.00000662102,0.0001309317,0.00006514139,0.0001424081,0.00004252407,0.0001322051,0.00000483553,0.0004287923,0.004629488],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001757371,"about_ca_system_score_gemma":0.000009657181,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001302406,"about_ca_topic_score_gemma":0.00001207272,"domain_scores_codex":[0.9987937,0.00009574482,0.0002541554,0.0003074725,0.0001384361,0.0004104691],"domain_scores_gemma":[0.9992107,0.0000876555,0.00007938287,0.000434907,0.00002990715,0.0001574607],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0002124372,0.0002700252,0.01152481,0.00001591196,0.0001271295,0.0008129322,0.2535842,5.84204e-7,0.006984429,0.01104917,0.03045154,0.6849669],"study_design_scores_gemma":[0.003150477,0.003409572,0.6823694,0.00005219128,0.00007038912,0.0005236522,0.1444838,0.0001380924,0.0009558332,0.002313886,0.161442,0.001090605],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9326963,0.003970963,0.001809572,0.0002527827,0.0004060881,0.0001185655,0.000004837051,0.000275123,0.06046578],"genre_scores_gemma":[0.9775553,7.767623e-7,0.0001716326,0.01582876,0.0005665433,0.000007224801,0.00001968266,0.00003217276,0.005817896],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6838762,"threshold_uncertainty_score":0.9961455,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2166562747","doi":"10.3138/cmlr.59.4.567","title":"Vocabulary Acquisition in a Second Language: Do Learners Really Acquire Most Vocabulary by Reading? Some Empirical Evidence","year":2003,"lang":"en","type":"article","venue":"Canadian Modern Language Review/ La Revue canadienne des langues vivantes","topic":"Second Language Acquisition and Learning","field":"Psychology","cited_by":389,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Vocabulary; Reading (process); Computer science; Linguistics; Natural language processing; Word (group theory); Empirical evidence; Vocabulary development; Artificial intelligence; Empirical research; Mathematics; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.02093432348339362,"gpt":0.2941218775973948,"spread":0.2731875541140011,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001725479,0.0006861672,0.001008177,0.0006992726,0.0002597321,0.0001592432,0.0006961396,0.0004639155,0.0251887],"category_scores_gemma":[0.00144355,0.0007212903,0.0002702336,0.001000162,0.0002869284,0.0005787605,0.00005165326,0.0009095421,0.0003883695],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001055763,"about_ca_system_score_gemma":0.0003863555,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.06553566,"about_ca_topic_score_gemma":0.1239141,"domain_scores_codex":[0.9944451,0.001413455,0.0008923968,0.001244519,0.0002150634,0.001789458],"domain_scores_gemma":[0.9963552,0.0005394309,0.0003038834,0.001258988,0.0001305413,0.001411928],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002676906,0.0005014162,0.02448923,0.009277527,0.0009378958,0.08738608,0.43387,0.00006340834,0.07401175,0.006201476,0.2437122,0.1192813],"study_design_scores_gemma":[0.008329207,0.001531775,0.1052381,0.05055542,0.001391113,0.02238604,0.2781077,0.001126152,0.001731978,0.001577243,0.5165284,0.01149693],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5924061,0.3977662,0.00006049232,0.0005415063,0.0002143537,0.0006079844,0.0002706475,0.000123211,0.008009475],"genre_scores_gemma":[0.95781,0.003859212,0.0003739993,0.02891283,0.0003440476,0.0002212198,0.0009530044,0.0002173534,0.007308316],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.393907,"threshold_uncertainty_score":0.9995238,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2033839438","doi":"10.3138/cmlr.64.3.429","title":"L2 Learner Production and Processing of Collocation: A Multi-study Perspective","year":2008,"lang":"en","type":"article","venue":"Canadian Modern Language Review/ La Revue canadienne des langues vivantes","topic":"Second Language Acquisition and Learning","field":"Psychology","cited_by":389,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Collocation (remote sensing); Adjective; Linguistics; Fluency; Intuition; Psychology; Noun; First language; Quarter (Canadian coin); Popularity; Natural language processing; Artificial intelligence; Computer science; Mathematics education; History","retraction":null,"screen_n_in":null,"score":{"opus":0.03208603812425773,"gpt":0.2999055873221322,"spread":0.2678195491978745,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0004436239,0.0002419159,0.0004653286,0.0003053907,0.0002684661,0.00002106153,0.0001815131,0.00009429843,0.001472815],"category_scores_gemma":[0.0008138699,0.0002369676,0.00008048301,0.0004384045,0.0002632741,0.0001435104,0.00002105735,0.0002536825,0.00002243796],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002868981,"about_ca_system_score_gemma":0.0001721603,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.1447354,"about_ca_topic_score_gemma":0.2487958,"domain_scores_codex":[0.9982381,0.0003125252,0.0003535108,0.0005393866,0.00007704776,0.0004794248],"domain_scores_gemma":[0.9985956,0.00006627914,0.0001884377,0.0004320884,0.0002965964,0.0004210092],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.00004529359,0.0003155999,0.01279796,0.00224014,0.0002975268,0.005660706,0.9071593,0.00001917682,0.004008531,0.0006081273,0.001576001,0.06527159],"study_design_scores_gemma":[0.002147625,0.0005875197,0.3970932,0.006836478,0.0006020459,0.01332118,0.565476,0.000920548,0.0001613929,0.0000874555,0.01102544,0.001741052],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7875528,0.2086711,0.00008044096,0.0002872447,0.0001049075,0.0006697042,0.00003743946,0.00005393109,0.002542348],"genre_scores_gemma":[0.993795,0.0008687736,0.0004323121,0.0009312257,0.0001743294,0.00009471759,0.00003861377,0.00005205512,0.003612952],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3842953,"threshold_uncertainty_score":0.99944,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2613581942","doi":"10.1075/itl.168.1.02web","title":"The updated Vocabulary Levels Test","year":2017,"lang":"en","type":"article","venue":"ITL Review of Applied Linguistics","topic":"Second Language Acquisition and Learning","field":"Psychology","cited_by":354,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University","funders":"","keywords":"Vocabulary; Test (biology); Word (group theory); Natural language processing; Coca; Quality (philosophy); Computer science; Artificial intelligence; Psychology; Vocabulary development; Linguistics; Epistemology","retraction":null,"screen_n_in":null,"score":{"opus":0.02897059110613764,"gpt":0.360601813804685,"spread":0.3316312226985473,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007354802,0.0001329721,0.000282172,0.00002079507,0.0004449634,0.00005348077,0.0006024191,0.00007221135,0.009621116],"category_scores_gemma":[0.004253233,0.00009429429,0.00008370684,0.00005140774,0.0001825514,0.000005692914,0.00008368064,0.0002447164,0.0006747021],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001064962,"about_ca_system_score_gemma":0.0000346141,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001229887,"about_ca_topic_score_gemma":0.000001269977,"domain_scores_codex":[0.9989682,0.00003744816,0.0004094926,0.0002008932,0.0001617375,0.0002222675],"domain_scores_gemma":[0.9976597,0.0003703138,0.0005147982,0.001210636,0.0001827722,0.00006182292],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00005958423,0.0002030712,0.000257196,0.001833282,0.0002392476,0.0001412571,0.00111881,0.000001434794,0.0003498124,0.5747803,0.2040214,0.2169946],"study_design_scores_gemma":[0.0002599135,0.00002474709,0.003669761,0.0005829338,0.00007077088,0.000005752022,0.0001634399,0.000008057375,0.0001155337,0.0005415462,0.9944273,0.0001302971],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.0004305173,0.08176752,0.00007816889,0.0003716846,0.001365266,0.0003784974,0.00003439897,0.00005604846,0.9155179],"genre_scores_gemma":[0.9764149,0.00410945,0.0009516832,0.01337534,0.001683768,0.00004789846,0.00006340403,0.00005228485,0.003301264],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9759844,"threshold_uncertainty_score":0.9912843,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1974364203","doi":"10.1177/0741088303262846","title":"Textual Borrowing in Second-Language Writing","year":2004,"lang":"en","type":"article","venue":"Written Communication","topic":"Second Language Acquisition and Learning","field":"Psychology","cited_by":320,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Task (project management); Second language writing; Affect (linguistics); Linguistics; Acknowledgement; Psychology; Composition (language); English for academic purposes; First language; Second language; Computer science; Mathematics education","retraction":null,"screen_n_in":null,"score":{"opus":0.01664593052061106,"gpt":0.3215003104826403,"spread":0.3048543799620292,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00054462,0.0001043077,0.0001329962,0.0001644008,0.0001309656,0.00004681249,0.0003540778,0.0001043259,0.01711059],"category_scores_gemma":[0.0000557926,0.0001178834,0.00004780743,0.0001917084,0.00004437104,0.0001692328,0.00007935155,0.0004413184,0.000562164],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008521386,"about_ca_system_score_gemma":0.00001888307,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006367971,"about_ca_topic_score_gemma":0.0003335431,"domain_scores_codex":[0.998913,0.0002476154,0.0003038999,0.0001955062,0.0000940091,0.0002459963],"domain_scores_gemma":[0.9989496,0.0001445748,0.00009032323,0.0007437845,0.0000259994,0.00004570525],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.0002158725,0.001393465,0.0146775,0.00009245152,0.0001787056,0.0006491508,0.393556,0.0005758726,0.04583955,0.200262,0.004033445,0.338526],"study_design_scores_gemma":[0.008400068,0.0001715998,0.4079797,0.0004661337,0.00003299486,0.0003387346,0.5560892,0.0002041081,0.002032516,0.001520682,0.02172502,0.001039262],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.838672,0.006892899,0.0002212702,0.0009017429,0.000049338,0.0001345423,0.000003990571,0.0001301426,0.1529941],"genre_scores_gemma":[0.9926115,0.000006988175,0.001324619,0.004968225,0.00007593294,0.00003882725,0.0001050419,0.00002235245,0.0008464562],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3933022,"threshold_uncertainty_score":0.9837879,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2107300313","doi":"10.3138/cmlr.57.4.541","title":"Acquiring Vocabulary through Reading: Effects of Frequency and Contextual Richness","year":2001,"lang":"en","type":"article","venue":"Canadian Modern Language Review/ La Revue canadienne des langues vivantes","topic":"Second Language Acquisition and Learning","field":"Psychology","cited_by":310,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"about_ca":true},"ca_institutions":"University of Toronto; Université du Québec à Montréal; McGill University","funders":"","keywords":"Vocabulary; Reading (process); Psychology; Linguistics; Vocabulary development; Context (archaeology); Word lists by frequency; Cognitive psychology; Geography","retraction":null,"screen_n_in":null,"score":{"opus":0.01293839548535165,"gpt":0.266301159073759,"spread":0.2533627635884074,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0004232485,0.0003593171,0.0007217962,0.000266028,0.0001668942,0.00003901587,0.0003460392,0.0001919506,0.00306836],"category_scores_gemma":[0.000693127,0.0003567282,0.0001503922,0.0004011211,0.0002809078,0.0002048089,0.00003894796,0.0003129042,0.00004793304],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002062436,"about_ca_system_score_gemma":0.00008458126,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.1249807,"about_ca_topic_score_gemma":0.06793666,"domain_scores_codex":[0.9976534,0.0003468036,0.0004801306,0.0005552308,0.00008500917,0.000879379],"domain_scores_gemma":[0.9979317,0.0004463533,0.0002128381,0.0006429091,0.000115238,0.0006509908],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"observational","study_design_scores_codex":[0.00008950303,0.0001997724,0.02104469,0.01855471,0.001182785,0.06045931,0.4151751,0.000007905746,0.05647611,0.03097027,0.00537361,0.3904663],"study_design_scores_gemma":[0.01123435,0.002018367,0.4096151,0.08356677,0.003410623,0.04821258,0.1493008,0.0008531014,0.002781352,0.007112571,0.2721975,0.009696862],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6402395,0.3466797,0.0003245938,0.0001786998,0.0002071069,0.0003972879,0.00005862467,0.00006829871,0.01184624],"genre_scores_gemma":[0.9874319,0.004995342,0.0004963216,0.004874314,0.0002426329,0.00007293531,0.0001336764,0.00008716342,0.001665673],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3885704,"threshold_uncertainty_score":0.9998885,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2346680633","doi":"10.5539/elt.v9n6p123","title":"Learners’ Listening Comprehension Difficulties in English Language Learning: A Literature Review","year":2016,"lang":"en","type":"review","venue":"English Language Teaching","topic":"Second Language Acquisition and Learning","field":"Psychology","cited_by":296,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Active listening; Psychology; Informational listening; Listening comprehension; Appreciative listening; Vocabulary; Reading (process); Reflective listening; Reading comprehension; Mathematics education; Linguistics; Pedagogy; Communication","retraction":null,"screen_n_in":null,"score":{"opus":0.0166910323128738,"gpt":0.3385595962435265,"spread":0.3218685639306527,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["metaepi_narrow"],"category_scores_codex":[0.002471289,0.001286547,0.003184854,0.0009876048,0.0003116013,0.0003321997,0.0009558101,0.001060623,0.0131115],"category_scores_gemma":[0.004959338,0.000956153,0.001151693,0.0007853446,0.000100634,0.0004170256,0.0003499629,0.006950058,0.0005417228],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003014438,"about_ca_system_score_gemma":0.00007856332,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009462362,"about_ca_topic_score_gemma":0.00001446988,"domain_scores_codex":[0.9901203,0.005089373,0.00152445,0.001516092,0.0005537295,0.00119606],"domain_scores_gemma":[0.9956882,0.001588542,0.001020656,0.001310972,0.0001066186,0.0002850196],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001119566,0.0000855782,0.0000052177,0.01262943,0.0001465218,0.002182342,0.3753644,0.000001293804,0.000005074768,0.0001819687,0.002603315,0.6067836],"study_design_scores_gemma":[0.0006868248,0.00007504765,0.000003389502,0.1703694,0.0002581183,0.0001866608,0.1018536,0.000001544106,3.510318e-7,5.297938e-7,0.7256435,0.0009209536],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.001024832,0.9628662,0.00001780536,0.00002139403,0.001987918,0.001143357,0.00005900575,0.001286988,0.03159247],"genre_scores_gemma":[0.0007106772,0.9711303,0.0001873706,0.001208631,0.003690934,0.0002566193,0.001561909,0.0003373766,0.02091621],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.7230402,"threshold_uncertainty_score":0.9999886,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2920898950","doi":"10.1111/lang.12343","title":"The Effects of Repetition on Incidental Vocabulary Learning: A Meta‐Analysis of Correlational Studies","year":2019,"lang":"en","type":"article","venue":"Language Learning","topic":"Second Language Acquisition and Learning","field":"Psychology","cited_by":291,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University","funders":"","keywords":"Vocabulary; Repetition (rhetorical device); Moderation; Psychology; Vocabulary development; Meta-analysis; Comprehension; Test (biology); Cognitive psychology; Mathematics education; Linguistics; Social psychology; Teaching method","retraction":null,"screen_n_in":null,"score":{"opus":0.01667857370846555,"gpt":0.3326683406391708,"spread":0.3159897669307053,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007290745,0.0001528249,0.0005696618,0.0003096272,0.0001550426,0.00001501084,0.0001464221,0.00009087518,0.01109776],"category_scores_gemma":[0.0008256868,0.0001102039,0.0005217822,0.0005594894,0.000087165,0.00005889113,0.00005300536,0.000530165,0.000182174],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002511481,"about_ca_system_score_gemma":0.0000110729,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000105424,"about_ca_topic_score_gemma":0.00001087756,"domain_scores_codex":[0.9979811,0.0008458241,0.0003606279,0.0002773,0.0003300821,0.0002050988],"domain_scores_gemma":[0.9961259,0.002974103,0.000470646,0.0003034917,0.00009223677,0.00003360301],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"meta_analysis","study_design_gemma":"qualitative","study_design_scores_codex":[0.001199241,0.000547387,0.1026859,0.0006328921,0.3982864,0.0005234221,0.3387182,0.07134806,0.03822335,0.03008613,0.0006040147,0.01714491],"study_design_scores_gemma":[0.004996832,0.004191428,0.4054296,0.0003282854,0.1172568,0.00009116716,0.4462421,0.005776005,0.007550266,0.0001218803,0.006731466,0.001284108],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.956198,0.03577602,0.0000799853,0.0000514032,0.0003150948,0.0001880101,0.000002014265,0.00006108141,0.007328413],"genre_scores_gemma":[0.9850838,0.00003204304,0.00003685726,0.0003307713,0.00005268109,0.00002561038,0.00006358198,0.00002094616,0.01435375],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3027437,"threshold_uncertainty_score":0.9898062,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1643889703","doi":"","title":"Iranian Journal of Language Teaching Research","year":2014,"lang":"en","type":"article","venue":"SSRN Electronic Journal","topic":"Second Language Acquisition and Learning","field":"Psychology","cited_by":281,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Mathematics education; Linguistics; Psychology; Computer science; Political science; Philosophy","retraction":null,"screen_n_in":null,"score":{"opus":0.01987851724072839,"gpt":0.3796032515255573,"spread":0.3597247342848289,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01668248,0.0001110448,0.0002109039,0.0004579716,0.0003431033,0.00008096172,0.0004506425,0.0001042384,0.009301762],"category_scores_gemma":[0.0005991269,0.00009138737,0.0001509107,0.0001737634,0.00005908989,0.000147361,0.00002811215,0.006876541,0.0002518816],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003237651,"about_ca_system_score_gemma":0.000439759,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007275544,"about_ca_topic_score_gemma":0.00003969998,"domain_scores_codex":[0.9954144,0.001702973,0.0004079739,0.0001418957,0.0004448845,0.001887869],"domain_scores_gemma":[0.9989082,0.0002977031,0.0002741934,0.0002243912,0.0001604721,0.0001350244],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"qualitative","study_design_scores_codex":[0.0003103501,0.0002436738,0.000846532,0.000009720758,0.0004371202,0.0001965402,0.04741879,0.00002131073,0.005786004,0.4609358,0.004186604,0.4796076],"study_design_scores_gemma":[0.009052889,0.005800582,0.007356816,0.0002276757,0.0001430076,0.03845812,0.6677781,0.0001221103,0.0003742736,0.107667,0.1622149,0.0008045249],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9283533,0.01916431,0.009068202,0.0008229937,0.0006836153,0.00006120211,5.010186e-7,0.00002411279,0.04182174],"genre_scores_gemma":[0.9908917,0.00005696225,0.0001483636,0.001089637,0.002072537,0.000001010017,0.000001186418,0.00003046731,0.005708153],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6203594,"threshold_uncertainty_score":0.9954146,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4254230712","doi":"10.3138/cmlr.61.3.355","title":"Learning L2 Vocabulary through Extensive Reading: A Measurement Study","year":2005,"lang":"en","type":"article","venue":"Canadian Modern Language Review/ La Revue canadienne des langues vivantes","topic":"Second Language Acquisition and Learning","field":"Psychology","cited_by":255,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"Concordia University","keywords":"Profiling (computer programming); Computer science; Vocabulary; Checklist; Reading (process); Natural language processing; Artificial intelligence; Language acquisition; Vocabulary development; Extensive reading; Mathematics education; Linguistics; Psychology; Programming language; Cognitive psychology","retraction":null,"screen_n_in":null,"score":{"opus":0.02985659371394066,"gpt":0.2875400997152444,"spread":0.2576835060013037,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001431574,0.0005340489,0.0008212797,0.0003503776,0.0004136494,0.00009988157,0.0005383376,0.0001874036,0.01141179],"category_scores_gemma":[0.001171519,0.0005344623,0.000258973,0.0004941754,0.000145437,0.0002596202,0.00005455173,0.0007695447,0.000607414],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001053745,"about_ca_system_score_gemma":0.0001938547,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.1424524,"about_ca_topic_score_gemma":0.2930026,"domain_scores_codex":[0.9959121,0.000897312,0.0006644003,0.0009105611,0.0002364948,0.0013791],"domain_scores_gemma":[0.99726,0.0001890733,0.0002616879,0.0009566877,0.0003602561,0.0009723217],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00005996471,0.0003402009,0.00281535,0.001545901,0.0009865998,0.02040519,0.6056294,0.0001339258,0.004501567,0.001281005,0.01396893,0.348332],"study_design_scores_gemma":[0.003076112,0.001033569,0.05077064,0.008815036,0.001128792,0.005501323,0.2758576,0.0007939715,0.0001145732,0.0001876625,0.6496072,0.003113521],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6560627,0.3139882,0.0002429875,0.0009624118,0.0003220295,0.001252502,0.00006857089,0.0002695156,0.02683102],"genre_scores_gemma":[0.9809088,0.001171513,0.0005222542,0.01142176,0.0007345488,0.0002007917,0.0001587938,0.0001525732,0.004729027],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6356383,"threshold_uncertainty_score":0.9997107,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2137705686","doi":"10.64152/10125/44117","title":"Computing the vocabulary demands of L2 reading","year":2007,"lang":"en","type":"article","venue":"Language learning & technology","topic":"Second Language Acquisition and Learning","field":"Psychology","cited_by":238,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Concordia University; Victoria University; Victoria University of Wellington","keywords":"Reading (process); Computer science; Vocabulary; Section (typography); Process (computing); Mathematics education; Linguistics; Artificial intelligence; Natural language processing; Programming language; Psychology","retraction":null,"screen_n_in":null,"score":{"opus":0.006300680055530206,"gpt":0.3040111798258792,"spread":0.297710499770349,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001393704,0.0001727794,0.0002788233,0.0004642172,0.000248351,0.00001594369,0.0004377653,0.0003310904,0.005982581],"category_scores_gemma":[0.000419271,0.0001381055,0.00009536483,0.0007798326,0.0002447502,0.00003714053,0.0001386735,0.001138057,0.0002111864],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003036653,"about_ca_system_score_gemma":0.00001408177,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001538534,"about_ca_topic_score_gemma":0.00001311588,"domain_scores_codex":[0.9983767,0.0001709863,0.0004173781,0.0003300064,0.0001568931,0.0005480126],"domain_scores_gemma":[0.9986022,0.0004670543,0.0003073009,0.0005203657,0.00005653655,0.00004661436],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"qualitative","study_design_scores_codex":[0.000182873,0.0001803842,0.06647267,0.00006468204,0.0004015912,0.002027976,0.129068,0.0004014944,0.04649229,0.05473696,0.001120779,0.6988503],"study_design_scores_gemma":[0.003645055,0.001111808,0.1366803,0.0003349365,0.0002188095,0.002933525,0.7539372,0.001098914,0.03299426,0.0006242209,0.06514198,0.001278992],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9443942,0.007214611,0.01381331,0.0004797311,0.0003223076,0.0001394777,6.925948e-7,0.0006384553,0.03299722],"genre_scores_gemma":[0.9948581,0.000002874606,0.0008766387,0.001323517,0.0002103187,0.000004545382,0.00001263515,0.00003959009,0.002671745],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6975713,"threshold_uncertainty_score":0.9949261,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2042225150","doi":"10.1191/0265532204lt273oa","title":"Evaluation of an in-depth vocabulary knowledge measure for assessing reading performance","year":2004,"lang":"en","type":"article","venue":"Language Testing","topic":"Second Language Acquisition and Learning","field":"Psychology","cited_by":237,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Test of English as a Foreign Language; Vocabulary; Reading comprehension; Reading (process); Context (archaeology); Measure (data warehouse); Test (biology); Psychology; Language proficiency; Sample (material); Vocabulary development; Mathematics education; Language assessment; Computer science; Linguistics; Teaching method","retraction":null,"screen_n_in":null,"score":{"opus":0.09731813955004215,"gpt":0.406059529447716,"spread":0.3087413898976738,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003130488,0.0001159232,0.0001701122,0.0001833873,0.0000918697,0.0000286197,0.0001204321,0.00008907282,0.000684517],"category_scores_gemma":[0.001180775,0.0001191045,0.00003596853,0.0003366669,0.00002430502,0.0002627604,0.00001592381,0.0001812512,0.00001850328],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001189025,"about_ca_system_score_gemma":0.0001165607,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001404246,"about_ca_topic_score_gemma":0.00006481753,"domain_scores_codex":[0.9987161,0.000245617,0.0002819153,0.0002590074,0.0002365545,0.0002608483],"domain_scores_gemma":[0.9990966,0.0001957119,0.0001609505,0.0002437646,0.0002571928,0.00004576704],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0000292533,0.0002303176,0.01357269,0.0001056226,0.0000321651,0.00003624922,0.0734766,0.003579995,0.04331007,0.000230644,0.000007649212,0.8653888],"study_design_scores_gemma":[0.01145313,0.0005833753,0.7942628,0.001905661,0.0003484047,0.0002122004,0.1017742,0.07069571,0.01734526,0.0004423854,0.00005584531,0.0009210572],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.961946,0.003043764,0.0008335939,0.0000104177,0.0001758834,0.0002867959,0.000001583915,0.0000956072,0.03360632],"genre_scores_gemma":[0.9922594,1.295822e-7,0.007199365,0.0001514823,0.0002222943,0.00005180746,0.00002797069,0.00003035981,0.00005718436],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8644677,"threshold_uncertainty_score":0.7494982,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2152366126","doi":"10.1177/1362168814559800","title":"Second language vocabulary learning through extensive reading with audio support: How do frequency and distribution of occurrence affect learning?","year":2014,"lang":"en","type":"article","venue":"Language Teaching Research","topic":"Second Language Acquisition and Learning","field":"Psychology","cited_by":222,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University","funders":"","keywords":"Active listening; Vocabulary; Reading (process); Psychology; Vocabulary learning; Affect (linguistics); Vocabulary development; Foreign language; Linguistics; Extensive reading; Language acquisition; Mathematics education; Teaching method; Communication","retraction":null,"screen_n_in":null,"score":{"opus":0.02136595153413768,"gpt":0.3635056566139777,"spread":0.34213970507984,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004401638,0.0003003745,0.0004683313,0.0002733821,0.0006412007,0.0001958651,0.0003282737,0.0002182854,0.007244783],"category_scores_gemma":[0.002730135,0.0002591952,0.00008835334,0.0004074157,0.000364609,0.0003318261,0.0001614793,0.003192117,0.0001002944],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008270622,"about_ca_system_score_gemma":0.00005147554,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007168282,"about_ca_topic_score_gemma":0.0000356177,"domain_scores_codex":[0.9940796,0.003341628,0.0002961141,0.0007676774,0.0006433446,0.000871575],"domain_scores_gemma":[0.9971869,0.001624363,0.0002542882,0.0005734517,0.0001789814,0.0001820425],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.0005384514,0.0003316493,0.05999762,0.0007568626,0.0004153607,0.002296402,0.699253,0.00008099252,0.06920244,0.01584345,0.006473561,0.1448103],"study_design_scores_gemma":[0.007057361,0.00763154,0.1170424,0.001511471,0.0002028649,0.002025483,0.8294719,0.0007775432,0.007271124,0.0003409786,0.0244105,0.002256876],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9686398,0.003540892,0.002796188,0.0001758905,0.0001091756,0.0003320945,0.00003808247,0.0002033753,0.02416453],"genre_scores_gemma":[0.9935716,0.00001023369,0.0004761902,0.0002398762,0.0002722339,0.00003840095,0.0004720475,0.00005231919,0.004867051],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1425534,"threshold_uncertainty_score":0.9999861,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2755237317","doi":"10.1111/lang.12253","title":"The Academic Spoken Word List","year":2017,"lang":"en","type":"article","venue":"Language Learning","topic":"Second Language Acquisition and Learning","field":"Psychology","cited_by":213,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University","funders":"","keywords":"Vocabulary; Linguistics; British National Corpus; Computer science; Spoken language; English for academic purposes; American English; Word lists by frequency; Discipline; Lexical density; Psychology; Word list; Natural language processing; Lexical item; World Wide Web; Index (typography); Sociology; Sentence","retraction":null,"screen_n_in":null,"score":{"opus":0.01957480886760424,"gpt":0.3672021094661021,"spread":0.3476273005984979,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.000753856,0.0001467021,0.0001442025,0.00004780981,0.002077237,0.0003261106,0.0007567807,0.0001556692,0.0302594],"category_scores_gemma":[0.000863278,0.0001084252,0.00009244413,0.00005425105,0.0001600576,0.0001409602,0.0001411361,0.001338221,0.002129452],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002197476,"about_ca_system_score_gemma":0.00001232003,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004454351,"about_ca_topic_score_gemma":0.00003982476,"domain_scores_codex":[0.9986258,0.0002512666,0.0002020471,0.0002897782,0.0001690956,0.0004620718],"domain_scores_gemma":[0.9984623,0.0003094015,0.0002804753,0.0008275051,0.00002570568,0.00009465146],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000148192,0.00002609564,0.02511732,0.0000117389,0.0001419496,0.0009465147,0.07056071,0.00003429624,0.003153827,0.01064164,0.01001454,0.8792032],"study_design_scores_gemma":[0.001157233,0.00006722472,0.2078688,0.00006213813,0.00003612193,0.0001538832,0.07254402,0.0001684976,0.0002549097,0.0001031335,0.7171485,0.0004355904],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7651992,0.01177164,0.00009046918,0.001366465,0.0009657796,0.0001182152,0.000001280316,0.0002404197,0.2202465],"genre_scores_gemma":[0.8847122,0.0000203677,0.0000471137,0.00205075,0.0009135269,0.00002116768,0.00001048877,0.00003551861,0.1121888],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8787676,"threshold_uncertainty_score":0.9992219,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2009388101","doi":"10.3138/cmlr.63.1.149","title":"Comparing Focus on Form and Focus on FormS in Second-Language Vocabulary Learning","year":2006,"lang":"en","type":"article","venue":"Canadian Modern Language Review/ La Revue canadienne des langues vivantes","topic":"Second Language Acquisition and Learning","field":"Psychology","cited_by":213,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Vocabulary; Focus (optics); Focus on form; Vocabulary learning; Comprehension; Focus group; Linguistics; Phase (matter); Psychology; Mathematics education; Computer science; Sociology; Grammar; Philosophy","retraction":null,"screen_n_in":null,"score":{"opus":0.01291875970282817,"gpt":0.2506099678092087,"spread":0.2376912081063805,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007153322,0.0005108422,0.0008081233,0.000730324,0.000244862,0.0000986194,0.0003501803,0.0002365142,0.00437711],"category_scores_gemma":[0.0002686123,0.0004935054,0.0001753756,0.0004162747,0.0001390912,0.000166055,0.0000419227,0.0008737781,0.000159896],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005863831,"about_ca_system_score_gemma":0.00007320807,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.2236035,"about_ca_topic_score_gemma":0.6904173,"domain_scores_codex":[0.9968669,0.0003424094,0.0005915227,0.0007804898,0.0001218642,0.001296828],"domain_scores_gemma":[0.9980862,0.0003650312,0.0002104622,0.0006295092,0.00004845684,0.0006603634],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0002953238,0.0003682994,0.0334426,0.004820737,0.0004395644,0.05173215,0.2080711,0.0003121433,0.007633896,0.04217948,0.006173936,0.6445308],"study_design_scores_gemma":[0.01085651,0.002236249,0.729377,0.03214642,0.0005884304,0.008793697,0.09490929,0.00572581,0.001130599,0.007939134,0.09853803,0.007758858],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8197591,0.1144004,0.0000344114,0.0003505524,0.0001184886,0.0005202979,0.0000874223,0.0001136317,0.06461568],"genre_scores_gemma":[0.9922292,0.0003964856,0.00009078234,0.003214018,0.0002830446,0.0001012098,0.0002863027,0.0001200152,0.003278945],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6959344,"threshold_uncertainty_score":0.9997517,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2340292428","doi":"10.1177/1362168816639619","title":"Examining second language receptive knowledge of collocation and factors that affect learning","year":2016,"lang":"en","type":"article","venue":"Language Teaching Research","topic":"Second Language Acquisition and Learning","field":"Psychology","cited_by":184,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University","funders":"","keywords":"Collocation (remote sensing); Adjective; Noun; Psychology; Affect (linguistics); Word lists by frequency; Linguistics; Natural language processing; Word (group theory); Artificial intelligence; Computer science; Communication; Sentence","retraction":null,"screen_n_in":null,"score":{"opus":0.09338241142896415,"gpt":0.428313576559644,"spread":0.3349311651306799,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003812564,0.0001915287,0.0002925539,0.0005432621,0.0003367781,0.00005644939,0.0002510042,0.0001769715,0.02463088],"category_scores_gemma":[0.00160579,0.0001379027,0.00005851625,0.0002657681,0.0002236434,0.0001893819,0.0001613197,0.001024525,0.0001935932],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009899334,"about_ca_system_score_gemma":0.00003688804,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005988567,"about_ca_topic_score_gemma":0.0001003314,"domain_scores_codex":[0.9957801,0.002616551,0.0002425656,0.0004995287,0.0003028199,0.0005584538],"domain_scores_gemma":[0.9958586,0.003378172,0.0001344085,0.0004041496,0.00007702478,0.0001476424],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.00009935351,0.0001118048,0.04153715,0.0000859333,0.0001047155,0.00006551421,0.556027,6.098724e-7,0.201034,0.001038134,0.0007584672,0.1991373],"study_design_scores_gemma":[0.001916172,0.0007014194,0.1954302,0.0004337087,0.00002239067,0.00004924556,0.775719,0.00003439703,0.02180582,0.00002765027,0.003446232,0.0004137281],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9477259,0.005622577,0.0002604222,0.00004654427,0.000148691,0.0002622676,0.00001247012,0.0001353631,0.04578577],"genre_scores_gemma":[0.9682706,0.000007538217,0.0001213025,0.00005592593,0.0001599674,0.00003029436,0.00002597799,0.00005062522,0.03127774],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2196921,"threshold_uncertainty_score":0.9762607,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2144425798","doi":"10.1017/s0272263114000606","title":"HOW DOES PRIOR WORD KNOWLEDGE AFFECT VOCABULARY LEARNING PROGRESS IN AN EXTENSIVE READING PROGRAM?","year":2015,"lang":"en","type":"article","venue":"Studies in Second Language Acquisition","topic":"Second Language Acquisition and Learning","field":"Psychology","cited_by":169,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University","funders":"","keywords":"Vocabulary; Reading (process); Affect (linguistics); Psychology; Vocabulary learning; Vocabulary development; Set (abstract data type); Term (time); Extensive reading; Test (biology); Word (group theory); Foreign language; Linguistics; Mathematics education; Computer science; Communication","retraction":null,"screen_n_in":null,"score":{"opus":0.04165403979136326,"gpt":0.3972143078418069,"spread":0.3555602680504436,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001324426,0.0004194623,0.0006349634,0.0006496942,0.0001728132,0.0001696465,0.0002722189,0.0002546016,0.002703573],"category_scores_gemma":[0.0003892106,0.0003528214,0.0001061873,0.0007320427,0.0002949326,0.0006598302,0.0001678897,0.0007656455,0.0001041979],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003092833,"about_ca_system_score_gemma":0.00005192284,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000357576,"about_ca_topic_score_gemma":0.0006361799,"domain_scores_codex":[0.9964157,0.001195697,0.0004697481,0.0008624526,0.0002513276,0.0008050551],"domain_scores_gemma":[0.9984522,0.0003500945,0.0002527206,0.0005028655,0.000251651,0.0001904423],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.0006144753,0.0009448946,0.0375839,0.0003406996,0.0002496727,0.004736294,0.5905583,0.000021634,0.0006835791,0.0005335242,0.001429164,0.3623039],"study_design_scores_gemma":[0.00473297,0.00115389,0.09858634,0.0006201806,0.00005464158,0.0001904829,0.8896319,0.0001818066,0.0004870187,0.0001609124,0.003306119,0.0008937039],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9121994,0.08138894,0.00001572378,0.0001736756,0.001092451,0.0009237403,0.000007136096,0.0003621574,0.003836733],"genre_scores_gemma":[0.9941481,0.00002780764,0.0006441958,0.000965433,0.0007344846,0.0006156371,0.0001572403,0.00007578828,0.002631312],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3614102,"threshold_uncertainty_score":0.9998924,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2937653323","doi":"10.1080/09588221.2019.1595664","title":"Intelligent personal assistants: can they understand and be understood by accented L2 learners?","year":2019,"lang":"en","type":"article","venue":"Computer Assisted Language Learning","topic":"Second Language Acquisition and Learning","field":"Psychology","cited_by":166,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Concordia University","funders":"","keywords":"Pronunciation; Intelligibility (philosophy); Psychology; Stress (linguistics); Variety (cybernetics); Set (abstract data type); Computer science; Linguistics; Artificial intelligence; Speech recognition","retraction":null,"screen_n_in":null,"score":{"opus":0.02168386917764846,"gpt":0.2890587565500597,"spread":0.2673748873724113,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0004089752,0.0003758282,0.0004190508,0.0002359259,0.000248883,0.0002723142,0.0002717998,0.0002461356,0.02474965],"category_scores_gemma":[0.00004307604,0.0003635075,0.0001463519,0.0002526692,0.0001003173,0.0001387572,0.00015534,0.001042821,0.0002886135],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001721807,"about_ca_system_score_gemma":0.00003879977,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002800444,"about_ca_topic_score_gemma":0.00005290255,"domain_scores_codex":[0.9972354,0.0006227018,0.000366107,0.000793228,0.0003457844,0.0006368289],"domain_scores_gemma":[0.9987577,0.0003382833,0.00023499,0.0003720641,0.00005352639,0.0002434846],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.0007680098,0.0008507601,0.04485369,0.0003553347,0.002281107,0.001402872,0.6188332,0.0005673849,0.01107598,0.002639671,0.02084467,0.2955273],"study_design_scores_gemma":[0.007622154,0.001252112,0.04945862,0.0004133976,0.0002228094,0.0008302665,0.8910314,0.01223675,0.0002302511,0.00003166131,0.03460369,0.002066887],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9658245,0.00575789,0.01019282,0.0006884154,0.000824932,0.000334331,0.00002383029,0.0004225516,0.01593078],"genre_scores_gemma":[0.9831834,0.00001233054,0.0003897693,0.005739667,0.0002049445,0.000006374998,0.0002575078,0.00008225026,0.01012378],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2934604,"threshold_uncertainty_score":0.9998817,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2945854349","doi":"10.1017/s0272263119000020","title":"INCIDENTAL VOCABULARY LEARNING THROUGH LISTENING TO SONGS","year":2019,"lang":"en","type":"article","venue":"Studies in Second Language Acquisition","topic":"Second Language Acquisition and Learning","field":"Psychology","cited_by":157,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University","funders":"","keywords":"Active listening; Vocabulary; Meaning (existential); Psychology; Collocation (remote sensing); Vocabulary learning; Appreciative listening; Linguistics; Cognitive psychology; Communication; Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.01989880753150786,"gpt":0.3610573823177168,"spread":0.341158574786209,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0005929383,0.0003042608,0.0004665405,0.0003050332,0.0001710242,0.00005426967,0.0002431657,0.0001624728,0.1327951],"category_scores_gemma":[0.0001579123,0.0003107305,0.0001299007,0.0005114576,0.00007682892,0.0003687855,0.0002263766,0.0005596922,0.004048929],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002038811,"about_ca_system_score_gemma":0.00001847524,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000226022,"about_ca_topic_score_gemma":0.0001106424,"domain_scores_codex":[0.9976114,0.0003381891,0.000481881,0.0006807848,0.0002656276,0.0006221231],"domain_scores_gemma":[0.9988962,0.0003459417,0.0001618737,0.0004316305,0.00007642827,0.00008795752],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.0004253569,0.0001896269,0.01010088,0.0002573216,0.0004356157,0.002129729,0.9419879,0.00050985,0.01917929,0.001808906,0.01192052,0.01105505],"study_design_scores_gemma":[0.002486307,0.0005259092,0.0278434,0.0003688742,0.00003513915,0.0002964588,0.9558257,0.00003663661,0.001230189,0.0001456716,0.0104478,0.0007578784],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9171835,0.02454694,0.00009694781,0.0001261188,0.00144935,0.0004455572,0.000009027592,0.0002009036,0.05594162],"genre_scores_gemma":[0.9715409,0.00001867807,0.0004860687,0.01184248,0.0004697785,0.00009663557,0.00009421807,0.0000583412,0.01539292],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1287462,"threshold_uncertainty_score":0.9999345,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2049167996","doi":"10.1111/j.1540-4781.2009.00894.x","title":"Some Input on the Easy/Difficult Grammar Question: An Empirical Study","year":2009,"lang":"en","type":"article","venue":"Modern Language Journal","topic":"Second Language Acquisition and Learning","field":"Psychology","cited_by":156,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Concordia University","funders":"","keywords":"Possessive; Salience (neuroscience); Grammar; Linguistics; Computer science; Perception; Psychology; Artificial intelligence","retraction":null,"screen_n_in":null,"score":{"opus":0.02983580718680734,"gpt":0.3699441107187552,"spread":0.3401083035319479,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0009841545,0.0002110093,0.0002111238,0.000142764,0.0004122274,0.0002207329,0.0003798076,0.0001172536,0.0205654],"category_scores_gemma":[0.0001245796,0.0001323719,0.0001098349,0.0001659387,0.00003504295,0.0001913298,0.00001925203,0.001074166,0.0004115074],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006111639,"about_ca_system_score_gemma":0.0000287345,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002457355,"about_ca_topic_score_gemma":0.000006996197,"domain_scores_codex":[0.9975137,0.00106748,0.0003265345,0.0003010507,0.0003986626,0.0003925802],"domain_scores_gemma":[0.9989348,0.0001136258,0.0001564765,0.0005016673,0.00007511799,0.0002182822],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"observational","study_design_scores_codex":[0.001283161,0.009194266,0.004554017,0.000006075966,0.0005194675,0.01839326,0.5081004,0.001035638,0.004708522,0.007559727,0.03303162,0.4116138],"study_design_scores_gemma":[0.008577039,0.009305841,0.7383886,0.0001218854,0.0002418308,0.007636225,0.215812,0.003095802,0.0002055751,0.006109361,0.008976785,0.001529043],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9890586,0.003331063,0.0007832866,0.002614963,0.0004872405,0.0002203697,0.000002874282,0.0001333939,0.003368273],"genre_scores_gemma":[0.9559841,0.000002936616,0.00007064557,0.03924858,0.002430169,0.000008419466,0.000009538559,0.00002456838,0.002221006],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7338346,"threshold_uncertainty_score":0.9803299,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2110411447","doi":"10.18806/tesl.v20i1.935","title":"Formulaic Language Acquisition and Production: Implications for Teaching","year":2002,"lang":"en","type":"article","venue":"TESL Canada Journal","topic":"Second Language Acquisition and Learning","field":"Psychology","cited_by":152,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"Thinkpath Engineering Services (Canada)","funders":"","keywords":"Computer science; Language production; Second-language acquisition; Developmental linguistics; Linguistics; Comprehension approach; Production (economics); Second-language attrition; Language acquisition; Universal Networking Language; Subject (documents); Language assessment; Natural language processing; Psychology; Natural language; Cognition","retraction":null,"screen_n_in":null,"score":{"opus":0.01867821539928453,"gpt":0.2970407497652864,"spread":0.2783625343660018,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002481263,0.00007793654,0.00008708808,0.00006854874,0.0004985153,0.00004806692,0.00007151015,0.00003585899,0.1152993],"category_scores_gemma":[0.00008958685,0.00007347605,0.00003063708,0.00005322432,0.00001918205,0.0001045891,0.000007733982,0.0002541463,0.000007780654],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009380774,"about_ca_system_score_gemma":0.00003487016,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003836154,"about_ca_topic_score_gemma":0.001946586,"domain_scores_codex":[0.999342,0.00005891208,0.000165137,0.0001438222,0.00007902074,0.0002111025],"domain_scores_gemma":[0.999525,0.00007334742,0.00009874732,0.0001394112,0.0000500993,0.0001134353],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00003134141,0.00007595341,0.000229905,0.0000213221,0.0001107663,0.00006439689,0.01254328,0.00002312687,0.003245205,0.007266351,0.7822084,0.1941799],"study_design_scores_gemma":[0.004032773,0.0004443268,0.1003263,0.0001027044,0.0001917411,0.01874807,0.04111207,0.000549207,0.0003091709,0.001980439,0.8312029,0.001000319],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.715204,0.2258242,0.004335638,0.0364912,0.002363489,0.0006231501,0.00006651918,0.0001477116,0.01494411],"genre_scores_gemma":[0.9212559,0.000007419593,0.000717851,0.07381458,0.001194726,0.00002617489,0.00001515241,0.00001927539,0.00294896],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2258167,"threshold_uncertainty_score":0.8855095,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1944677660","doi":"10.21832/9781853597954","title":"Second Language Writing Systems","year":2005,"lang":"en","type":"book","venue":"Multilingual Matters eBooks","topic":"Second Language Acquisition and Learning","field":"Psychology","cited_by":146,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Computer science; Writing system; Linguistics; Programming language; Philosophy","retraction":null,"screen_n_in":null,"score":{"opus":0.01893929779669764,"gpt":0.3111845773733291,"spread":0.2922452795766314,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.000450274,0.0006297827,0.0007230153,0.0004084336,0.0001793892,0.0001992073,0.0004566344,0.000727524,0.08625458],"category_scores_gemma":[0.00002219762,0.0006722903,0.000298285,0.00002624713,0.0001322412,0.00004315097,0.0001083844,0.001323376,0.005007285],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002250202,"about_ca_system_score_gemma":0.0001207813,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007939136,"about_ca_topic_score_gemma":0.00002456633,"domain_scores_codex":[0.9970173,0.0002224182,0.0008147344,0.0008615472,0.0003420553,0.0007419233],"domain_scores_gemma":[0.9980266,0.0003305428,0.0004975282,0.0008530747,0.00007708542,0.0002151777],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002012103,0.0001281204,0.00001445729,0.001124257,0.001200059,0.006504822,0.1320109,0.00004166382,0.002204216,0.004226206,0.6236018,0.2287423],"study_design_scores_gemma":[0.001361785,0.00006575292,0.00004459347,0.0005275793,0.0001124744,0.0004864369,0.01300557,0.00006192601,0.0001306008,0.00001510543,0.9831884,0.0009997686],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.01273476,0.009074219,0.00002639713,0.00005511262,0.00240491,0.0005977086,0.0001551102,0.0005555663,0.9743962],"genre_scores_gemma":[0.01960347,6.424062e-7,0.0001241258,0.01942614,0.004116028,0.00007325428,0.0002898532,0.0002577412,0.9561087],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.3595866,"threshold_uncertainty_score":0.9995728,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2121305807","doi":"10.64152/10125/44021","title":"Expanding academic vocabulary with an interactive on-line database","year":2005,"lang":"en","type":"article","venue":"Language learning & technology","topic":"Second Language Acquisition and Learning","field":"Psychology","cited_by":140,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Concordia University","keywords":"Computer science; Vocabulary; Context (archaeology); Natural language processing; Suite; Artificial intelligence; Set (abstract data type); Class (philosophy); Hypertext; Word (group theory); World Wide Web; Linguistics","retraction":null,"screen_n_in":null,"score":{"opus":0.01835314322062025,"gpt":0.3552022517356505,"spread":0.3368491085150302,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0003304352,0.0002916277,0.0003074844,0.0007459542,0.0002131327,0.00003030865,0.000438403,0.0004099847,0.02168314],"category_scores_gemma":[0.0002223844,0.0002559909,0.00004870563,0.0005343286,0.000159008,0.0002778276,0.0001014573,0.002797546,0.001466095],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008801965,"about_ca_system_score_gemma":0.0000218504,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007122521,"about_ca_topic_score_gemma":0.00002615173,"domain_scores_codex":[0.9979953,0.0002535857,0.0002861747,0.000688647,0.0001841243,0.0005922067],"domain_scores_gemma":[0.9987472,0.0001817635,0.000216446,0.0006895052,0.00004413545,0.0001209839],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"qualitative","study_design_scores_codex":[0.002255153,0.0007185075,0.007218662,0.00003298842,0.0004579707,0.004724288,0.08496193,0.003612675,0.04353365,0.01106116,0.001318065,0.8401049],"study_design_scores_gemma":[0.01765378,0.01512164,0.007102291,0.001223167,0.00039319,0.007482211,0.6844112,0.007041858,0.07221777,0.0002532219,0.1827908,0.00430884],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9803587,0.002877083,0.003521614,0.001327993,0.0001715358,0.0002151984,0.000007156279,0.001532633,0.009988153],"genre_scores_gemma":[0.9871569,0.000008400752,0.001966211,0.005247728,0.0005439286,0.00007027425,0.0001673828,0.00008331172,0.004755844],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8357961,"threshold_uncertainty_score":0.9999892,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2098266286","doi":"10.1017/s095834400700033x","title":"Enhancing a process-oriented approach to literacy and language learning: The role of corpus consultation literacy","year":2007,"lang":"en","type":"article","venue":"ReCALL","topic":"Second Language Acquisition and Learning","field":"Psychology","cited_by":137,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"","funders":"Irish Research Council; McGill University","keywords":"Literacy; Language acquisition; Context (archaeology); Process (computing); Computer science; Psychology; Pedagogy; Mathematics education","retraction":null,"screen_n_in":null,"score":{"opus":0.006491499034284186,"gpt":0.3140453065704065,"spread":0.3075538075361223,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005974337,0.0001010397,0.0001366653,0.0001191569,0.0000846224,0.00003553453,0.00008592462,0.00007022935,0.0008481125],"category_scores_gemma":[0.0003065083,0.00007749592,0.00003107079,0.0003148098,0.00003662005,0.00008832391,0.00002196002,0.0002523038,0.00004577375],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001239549,"about_ca_system_score_gemma":0.00001108137,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008260467,"about_ca_topic_score_gemma":0.00000317529,"domain_scores_codex":[0.9990284,0.0001376531,0.0002624018,0.0002304471,0.0001230409,0.0002180274],"domain_scores_gemma":[0.9991442,0.0003825827,0.0001372296,0.0001612414,0.00009263516,0.00008211414],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.0003620681,0.0001833681,0.003482708,0.00006262902,0.00005587738,0.00002429424,0.6803144,0.00004212411,0.02894347,0.006548823,0.00002294269,0.2799573],"study_design_scores_gemma":[0.006806442,0.001261053,0.1278501,0.000540594,0.0001803413,0.0008273466,0.4917502,0.004300061,0.07898322,0.0006201974,0.2854841,0.001396392],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9625556,0.004110571,0.005467157,0.00005617827,0.00007725786,0.000244033,0.000002378439,0.00006011104,0.02742665],"genre_scores_gemma":[0.9956864,0.000002837518,0.0009844141,0.001061025,0.0001045349,0.00001894047,0.00003290698,0.00001686237,0.002092101],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2854612,"threshold_uncertainty_score":0.9286237,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2955464867","doi":"10.1075/itl.18034.rod","title":"Incidental vocabulary learning through viewing television","year":2019,"lang":"en","type":"article","venue":"ITL Review of Applied Linguistics","topic":"Second Language Acquisition and Learning","field":"Psychology","cited_by":136,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University; Carleton University","funders":"","keywords":"Vocabulary; Incidental learning; Vocabulary learning; Meaning (existential); Psychology; Drama; Test (biology); Vocabulary development; Linguistics; Cognitive psychology","retraction":null,"screen_n_in":null,"score":{"opus":0.01392951554526247,"gpt":0.3216166212941362,"spread":0.3076871057488737,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0006603572,0.0001979228,0.0005324716,0.00006035707,0.00006911849,0.00001466831,0.0002347128,0.000112618,0.03820498],"category_scores_gemma":[0.0007997968,0.0001851052,0.0001497935,0.0002370006,0.00004385822,0.00001551275,0.00008805477,0.0004807031,0.002698067],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003149867,"about_ca_system_score_gemma":0.00003020896,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002135424,"about_ca_topic_score_gemma":1.236199e-7,"domain_scores_codex":[0.9983723,0.0001036124,0.0006122016,0.00034931,0.0002871537,0.0002754659],"domain_scores_gemma":[0.9987274,0.0002392867,0.0003911035,0.0004497229,0.0001328453,0.00005961463],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0004108663,0.0008118877,0.003965807,0.04001587,0.0007848623,0.0004678807,0.03894248,0.0003564077,0.00519243,0.5349919,0.04062507,0.3334346],"study_design_scores_gemma":[0.0005474769,0.0001037428,0.0005094413,0.004123474,0.00009807585,0.00002063507,0.001889082,0.00003921026,0.000196389,0.0002247965,0.9919482,0.0002994324],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.02346301,0.1799192,0.0003801306,0.00003101811,0.001535553,0.0006349499,0.00000475714,0.0001304195,0.793901],"genre_scores_gemma":[0.9794179,0.004458732,0.002840255,0.01089351,0.0008667876,0.00002202202,0.0001178966,0.00006469766,0.001318158],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9559549,"threshold_uncertainty_score":0.9980785,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2140785772","doi":"10.1017/s0261444815000075","title":"How much vocabulary is needed to use English? Replication of van Zeeland & Schmitt (2012), Nation (2006) and Cobb (2007)","year":2015,"lang":"en","type":"article","venue":"Language Teaching","topic":"Second Language Acquisition and Learning","field":"Psychology","cited_by":131,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université du Québec; Université du Québec à Montréal","funders":"","keywords":"Vocabulary; Variety (cybernetics); Linguistics; Reading (process); Active listening; Reading comprehension; CobB; Psychology; Extensive reading; Computer science; Artificial intelligence; Communication","retraction":null,"screen_n_in":null,"score":{"opus":0.04104313037572568,"gpt":0.3222367788607766,"spread":0.2811936484850509,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001148444,0.0001770038,0.0002342946,0.0002719616,0.0001082536,0.0001499923,0.0001602918,0.0001610214,0.002559055],"category_scores_gemma":[0.0017947,0.0001749422,0.00004726067,0.0001706663,0.00003282794,0.0004447905,0.00006495609,0.0004001018,0.0001006314],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004818743,"about_ca_system_score_gemma":0.00002030286,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001683749,"about_ca_topic_score_gemma":0.00005838493,"domain_scores_codex":[0.9983829,0.0003486925,0.0002586191,0.0004846721,0.0002371568,0.0002879215],"domain_scores_gemma":[0.998461,0.0001747045,0.0001847159,0.0008124552,0.0001475865,0.0002195056],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002457974,0.0002186127,0.008263375,0.00005361303,0.0001532096,0.00006787838,0.7329171,0.0000127476,0.01535281,0.003329777,0.1379731,0.101412],"study_design_scores_gemma":[0.005009532,0.0005352019,0.01962386,0.0001885449,0.0001628304,0.0002279297,0.3786403,0.0002893351,0.003084135,0.0002402488,0.5908135,0.001184645],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9807743,0.003298941,0.006095781,0.0009435125,0.0004433743,0.0002975919,0.00002946021,0.0001913955,0.007925624],"genre_scores_gemma":[0.971333,0.000002778738,0.003938694,0.006942972,0.000513751,0.00002315419,0.0001974038,0.00004239373,0.01700586],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4528403,"threshold_uncertainty_score":0.9983528,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2072551071","doi":"10.1111/0026-7902.00062","title":"Reading‐Based Exercises in Second Language Vocabulary Learning: An Introspective Study","year":2000,"lang":"en","type":"article","venue":"Modern Language Journal","topic":"Second Language Acquisition and Learning","field":"Psychology","cited_by":129,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa","funders":"Social Sciences and Humanities Research Council of Canada; University of Ottawa","keywords":"Vocabulary; Reading (process); Reading comprehension; Computer science; Introspection; Elaboration; Linguistics; Psychology; Process (computing); Comprehension; Vocabulary development; Natural language processing; Cognitive psychology","retraction":null,"screen_n_in":null,"score":{"opus":0.01025948402460304,"gpt":0.3156710930495735,"spread":0.3054116090249705,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0009981401,0.000309973,0.0004323582,0.0004673519,0.0002593154,0.0002065281,0.0003728755,0.0001657383,0.3673455],"category_scores_gemma":[0.00007158041,0.0002912875,0.0001344119,0.0003101235,0.00005292534,0.0003560245,0.00002512436,0.00156577,0.0004963059],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001478503,"about_ca_system_score_gemma":0.00005324755,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003083032,"about_ca_topic_score_gemma":0.000152806,"domain_scores_codex":[0.9970087,0.0009951711,0.0005097531,0.0005190224,0.0003533891,0.0006140054],"domain_scores_gemma":[0.9989148,0.0001182028,0.0001830019,0.0004680413,0.00005170463,0.0002642706],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.001308259,0.002763715,0.02231382,0.00001899774,0.0001990011,0.02433343,0.6894982,0.003075247,0.005377353,0.00003189522,0.0007075306,0.2503725],"study_design_scores_gemma":[0.01449944,0.002924794,0.3759028,0.0001431361,0.0001527009,0.002814353,0.5912877,0.007955802,0.000753652,0.0001920157,0.001910802,0.001462767],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9740784,0.003956414,0.0003821191,0.00005289405,0.000222456,0.0003111028,0.000007508094,0.0001703251,0.0208188],"genre_scores_gemma":[0.9856805,0.000003709255,0.0002038511,0.002438439,0.0006380953,0.00003101168,0.00003371876,0.00007852932,0.01089213],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3668492,"threshold_uncertainty_score":0.9999539,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1989474612","doi":"10.3138/cmlr.63.1.13","title":"Uses and Functions of Formulaic Sequences in Second Language Speech: An Exploration of the Foundations of Fluency","year":2006,"lang":"en","type":"article","venue":"Canadian Modern Language Review/ La Revue canadienne des langues vivantes","topic":"Second Language Acquisition and Learning","field":"Psychology","cited_by":127,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Fluency; Repetition (rhetorical device); Narrative; Rhetorical question; Linguistics; Computer science; Range (aeronautics); Spoken language; Speech production; Psychology; Speech recognition; Natural language processing","retraction":null,"screen_n_in":null,"score":{"opus":0.02892807838186524,"gpt":0.2860038371324001,"spread":0.2570757587505349,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0004040594,0.0001674073,0.0003964929,0.0003234874,0.00007780917,0.00001411803,0.0002341136,0.00009292373,0.002629129],"category_scores_gemma":[0.0002466488,0.0001430832,0.00009875079,0.0004625511,0.0002415281,0.0003323621,0.00001861033,0.0001548148,0.000003691568],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009977306,"about_ca_system_score_gemma":0.0001139502,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.2250071,"about_ca_topic_score_gemma":0.7612886,"domain_scores_codex":[0.9985425,0.0002845346,0.0005263832,0.0002564451,0.00006956623,0.0003205046],"domain_scores_gemma":[0.9987916,0.0001681091,0.0002929599,0.0004810753,0.0001157269,0.0001505357],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"observational","study_design_scores_codex":[0.00007636026,0.0004919528,0.04943785,0.01232601,0.0004127585,0.001339626,0.4772662,0.0003398626,0.2216146,0.04921795,0.001483318,0.1859935],"study_design_scores_gemma":[0.00334867,0.000791444,0.6294813,0.01564955,0.000882093,0.001770547,0.308885,0.001302751,0.008784332,0.01023941,0.01655156,0.002313335],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9331517,0.06145091,0.00008055132,0.0001091214,0.0001055763,0.0003497427,0.0003972328,0.0000144402,0.004340732],"genre_scores_gemma":[0.9976306,0.0002210191,0.0002731084,0.0003215533,0.00006270004,0.00003158376,0.000194143,0.00002553932,0.001239729],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5800435,"threshold_uncertainty_score":0.9982826,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4248788492","doi":"10.3138/cmlr.61.1.107","title":"The Relationship between Depth of Vocabulary Knowledge and L2 Learners' Lexical Inferencing Strategy Use and Success","year":2004,"lang":"en","type":"article","venue":"Canadian Modern Language Review/ La Revue canadienne des langues vivantes","topic":"Second Language Acquisition and Learning","field":"Psychology","cited_by":125,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"University of Victoria","funders":"","keywords":"Vocabulary; Context (archaeology); Meaning (existential); Vocabulary development; Polysemy; Computer science; Psychology; Linguistics; Natural language processing","retraction":null,"screen_n_in":null,"score":{"opus":0.0519452814072455,"gpt":0.3128670904794478,"spread":0.2609218090722023,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006226004,0.0002412897,0.0004183097,0.0001976921,0.0003125722,0.00009872771,0.0002250374,0.0001627933,0.0002439715],"category_scores_gemma":[0.001237861,0.000201085,0.00007981337,0.0002629306,0.0003474744,0.0001853875,0.00003831457,0.0004141933,0.00001415849],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001618304,"about_ca_system_score_gemma":0.0001695938,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.1167016,"about_ca_topic_score_gemma":0.4428132,"domain_scores_codex":[0.9982268,0.0003670608,0.0004001654,0.0003723163,0.00005696094,0.0005767331],"domain_scores_gemma":[0.9974883,0.00123198,0.0001465128,0.0004244574,0.00008867917,0.0006200531],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00003344097,0.00004643123,0.5596891,0.003565162,0.0003719287,0.001964761,0.1362273,0.00003269984,0.0006297712,0.05005921,0.0004802838,0.2468999],"study_design_scores_gemma":[0.0005198982,0.00008781593,0.9814532,0.002359295,0.0001535307,0.0004991919,0.01004835,0.00003924016,0.00001552675,0.0008128189,0.003630616,0.0003804922],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7624915,0.2351122,0.0001084154,0.0002216355,0.00004804206,0.0002337088,0.00007055718,0.0000294466,0.001684437],"genre_scores_gemma":[0.9967928,0.001665705,0.0001222731,0.0005357474,0.0001297202,0.00002282862,0.000111598,0.00004292097,0.0005764311],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4217641,"threshold_uncertainty_score":0.8891804,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1973859361","doi":"10.3138/cmlr.1204.1","title":"Vocabulary Learning through Assisted and Unassisted Repeated Reading","year":2012,"lang":"en","type":"article","venue":"Canadian Modern Language Review/ La Revue canadienne des langues vivantes","topic":"Second Language Acquisition and Learning","field":"Psychology","cited_by":121,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"National Science Council","keywords":"Vocabulary; Fluency; Reading (process); Reading comprehension; Context (archaeology); Extensive reading; Test (biology); Vocabulary learning; Psychology; Vocabulary development; Computer science; Meaning (existential); Linguistics; Mathematics education","retraction":null,"screen_n_in":null,"score":{"opus":0.02249609531482978,"gpt":0.2823876533354259,"spread":0.2598915580205962,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000979525,0.0004360315,0.0006784949,0.0003049211,0.000394109,0.00008425105,0.0002846371,0.0002578012,0.007212498],"category_scores_gemma":[0.0009439957,0.0004360228,0.0001718767,0.00051823,0.0002037903,0.0003363546,0.00005006816,0.0006455433,0.0001657919],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004083241,"about_ca_system_score_gemma":0.00007811611,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.1171959,"about_ca_topic_score_gemma":0.04164288,"domain_scores_codex":[0.996582,0.0007468172,0.0005215222,0.0005977547,0.00009903457,0.001452896],"domain_scores_gemma":[0.9974439,0.0003233613,0.0002382999,0.0006464795,0.0001099154,0.001238101],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00007993353,0.0001804124,0.0283063,0.005604563,0.001202166,0.01339955,0.427153,0.00001258963,0.02291089,0.008540571,0.01141074,0.4811993],"study_design_scores_gemma":[0.002130809,0.0002783423,0.3800002,0.01195374,0.001101492,0.01857406,0.08240805,0.0005265903,0.0001766102,0.0001798809,0.499363,0.003307232],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5961929,0.3685516,0.0001793557,0.0003276519,0.0003156623,0.000392812,0.00007647675,0.000225694,0.03373782],"genre_scores_gemma":[0.9822474,0.00204582,0.000780279,0.006445389,0.000457318,0.00008056282,0.0005575165,0.0001374145,0.00724829],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4879523,"threshold_uncertainty_score":0.9998091,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1978242712","doi":"10.3138/cmlr.59.3.393","title":"Analyzing Late Interlanguage with Learner Corpora: Québec Replications of Three European Studies","year":2003,"lang":"en","type":"article","venue":"Canadian Modern Language Review/ La Revue canadienne des langues vivantes","topic":"Second Language Acquisition and Learning","field":"Psychology","cited_by":114,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Interlanguage; Context (archaeology); Second-language acquisition; Computer science; Literacy; Linguistics; Character (mathematics); Psychology; Mathematics education; Pedagogy; History; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.02980851529886725,"gpt":0.2806767301598688,"spread":0.2508682148610016,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001042753,0.0003689155,0.0007093693,0.0003941521,0.0002132452,0.00003514695,0.0004045286,0.00008552524,0.004881306],"category_scores_gemma":[0.001218985,0.0003174481,0.0001859612,0.0005718332,0.0003616106,0.0001167153,0.00003018442,0.0003698513,0.0001183904],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003789603,"about_ca_system_score_gemma":0.0002452657,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.2802177,"about_ca_topic_score_gemma":0.7750379,"domain_scores_codex":[0.9973183,0.0006637599,0.000570389,0.0006218085,0.00008243798,0.0007432867],"domain_scores_gemma":[0.9973067,0.0003053966,0.0003724307,0.001082081,0.0002375502,0.0006958608],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001195354,0.0002816918,0.04224495,0.009682691,0.004480663,0.03034166,0.5531161,0.0002099141,0.01291777,0.02448837,0.01449433,0.3076224],"study_design_scores_gemma":[0.005783167,0.001423503,0.192361,0.03393554,0.003752818,0.014461,0.2733164,0.0004378236,0.0005763181,0.001267216,0.4659182,0.006767035],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5924342,0.3789337,0.0005381033,0.0003676551,0.00009984484,0.0004104274,0.0001118351,0.0001003421,0.02700397],"genre_scores_gemma":[0.9888583,0.00138738,0.0008788242,0.002924257,0.0001084157,0.00006555498,0.0001422356,0.0001247704,0.005510252],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4948202,"threshold_uncertainty_score":0.9999278,"prediction_status":"machine_predicted_unvalidated"},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":[],"domain":null,"study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":true,"confidence":"low"}],"label_agreement":"agree"},{"id":"W3095919386","doi":"10.1111/modl.12671","title":"How Effective Are Intentional Vocabulary‐Learning Activities? A Meta‐Analysis","year":2020,"lang":"en","type":"article","venue":"Modern Language Journal","topic":"Second Language Acquisition and Learning","field":"Psychology","cited_by":113,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University","funders":"","keywords":"Recall; Meaning (existential); Psychology; Moderation; Vocabulary; Word (group theory); Vocabulary learning; Cognitive psychology; Meta-analysis; Linguistics; Social psychology; Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.02946023086717044,"gpt":0.3028643435045122,"spread":0.2734041126373418,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0004421497,0.0002652307,0.0007032048,0.0003285288,0.0003001811,0.0003645666,0.0002524362,0.000136199,0.08101808],"category_scores_gemma":[0.0002116953,0.0002221403,0.001260551,0.0004958069,0.00005072657,0.0003146251,0.00006368895,0.001353645,0.0001098762],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005130077,"about_ca_system_score_gemma":0.00001945995,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001969076,"about_ca_topic_score_gemma":0.000006038749,"domain_scores_codex":[0.9976875,0.0008430437,0.0002547565,0.0004037605,0.0003964384,0.0004144799],"domain_scores_gemma":[0.9987575,0.0002216516,0.0004159617,0.0001972926,0.00009183346,0.0003157766],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"meta_analysis","study_design_gemma":"qualitative","study_design_scores_codex":[0.001240459,0.0005667993,0.004954692,0.0001067003,0.548764,0.01836744,0.3332809,0.007796938,0.01678179,0.0005608005,0.005564723,0.06201476],"study_design_scores_gemma":[0.009523909,0.001769853,0.05069451,0.00006876221,0.2657486,0.005681446,0.5853849,0.05395516,0.001920483,0.0004168145,0.02151109,0.003324451],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5754051,0.07763329,0.3331026,0.00719102,0.0004608456,0.0003793381,0.00004900211,0.0004306238,0.005348145],"genre_scores_gemma":[0.983699,0.000005253444,0.0003973651,0.01049262,0.000800836,0.00003548591,0.00003533758,0.00004437845,0.004489722],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4082939,"threshold_uncertainty_score":0.919822,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2036982923","doi":"10.2307/40264524","title":"From Receptive to Productive: Improving ESL Learners' Use of Vocabulary in a Postreading Composition Task","year":2006,"lang":"en","type":"article","venue":"TESOL Quarterly","topic":"Second Language Acquisition and Learning","field":"Psychology","cited_by":113,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"Simon Fraser University","funders":"","keywords":"Vocabulary; Reading (process); Computer science; Vocabulary development; Task (project management); Psychology; Linguistics; Mathematics education","retraction":null,"screen_n_in":null,"score":{"opus":0.01233218125153658,"gpt":0.2742474164422008,"spread":0.2619152351906642,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001610388,0.0001541206,0.000235037,0.0002703764,0.00004573094,0.00004091945,0.000106067,0.00009984083,0.003324314],"category_scores_gemma":[0.00002523465,0.0001656865,0.00005814071,0.0002819271,0.00004035936,0.0002242068,0.00001180477,0.0002358693,0.0002558901],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006418415,"about_ca_system_score_gemma":0.00001516331,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01209745,"about_ca_topic_score_gemma":0.000116918,"domain_scores_codex":[0.998575,0.0002474886,0.0003436222,0.0004328181,0.000124041,0.0002769743],"domain_scores_gemma":[0.999259,0.0001697901,0.0001451394,0.0003142322,0.00005803091,0.00005380096],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.0007351928,0.000651647,0.00910874,0.00002341609,0.00008456311,0.0002326835,0.1724021,0.0001946803,0.6676688,0.0006969158,0.003915406,0.1442859],"study_design_scores_gemma":[0.006021835,0.005097671,0.8090923,0.0005466474,0.0001502458,0.0001126723,0.1553664,0.001217593,0.01652732,0.0009960996,0.003185011,0.001686237],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9962552,0.000324513,0.001285634,0.0002097753,0.0002137061,0.0003405604,0.00003999761,0.00008475724,0.001245845],"genre_scores_gemma":[0.9964333,1.020988e-7,0.001796548,0.0007048695,0.0003071497,0.00003280606,0.0001669703,0.00002700795,0.0005313125],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7999835,"threshold_uncertainty_score":0.9975868,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2160050968","doi":"10.3138/cmlr.57.2.295","title":"One Size Fits All? Francophone Learners and English Vocabulary Tests","year":2000,"lang":"en","type":"article","venue":"Canadian Modern Language Review/ La Revue canadienne des langues vivantes","topic":"Second Language Acquisition and Learning","field":"Psychology","cited_by":111,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Vocabulary; French; Interlanguage; Test (biology); Language proficiency; Psychology; Linguistics; Measure (data warehouse); Language assessment; Computer science; Mathematics education","retraction":null,"screen_n_in":null,"score":{"opus":0.0126007201040314,"gpt":0.2490481411339069,"spread":0.2364474210298755,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005590455,0.0004242532,0.0007089635,0.0002261184,0.0002077215,0.00008586188,0.000391923,0.0002562063,0.05434059],"category_scores_gemma":[0.0008707311,0.0004582648,0.0001670383,0.0004534842,0.0002374797,0.0001791604,0.0000278754,0.0005519789,0.0004255858],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002426885,"about_ca_system_score_gemma":0.0001180106,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.1154997,"about_ca_topic_score_gemma":0.1778765,"domain_scores_codex":[0.9970695,0.0003896949,0.0004756664,0.0007612468,0.0001110972,0.001192828],"domain_scores_gemma":[0.9971745,0.0004400645,0.0001247799,0.0007860265,0.0001101918,0.001364415],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00004645153,0.00008319633,0.001084542,0.001905924,0.0004240888,0.007716755,0.1878944,0.00001358979,0.002689802,0.0003268952,0.01081232,0.7870021],"study_design_scores_gemma":[0.003106412,0.000431496,0.1959017,0.009390792,0.0006118394,0.003654438,0.04352346,0.0003376115,0.00007492459,0.0003443468,0.7392869,0.003336108],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6847519,0.2897823,0.000007066091,0.0005071699,0.0002276151,0.0004093203,0.0001855703,0.0001511223,0.02397796],"genre_scores_gemma":[0.9522519,0.008771262,0.0005249504,0.02393279,0.0008371156,0.0001121683,0.0003448329,0.0001626672,0.01306238],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.783666,"threshold_uncertainty_score":0.9997869,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1585873828","doi":"","title":"Effects of focused instruction of formulaic sequences on fluent expression in second language narratives: A case study","year":2009,"lang":"en","type":"article","venue":"DOAJ (DOAJ: Directory of Open Access Journals)","topic":"Second Language Acquisition and Learning","field":"Psychology","cited_by":111,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Carleton University","funders":"","keywords":"Linguistics; Narrative; Expression (computer science); Psychology; Computer science; Philosophy; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.1126928974768185,"gpt":0.5366803975881587,"spread":0.4239875001113402,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0008232933,0.0002404825,0.000696272,0.00108675,0.00009692098,0.0001102877,0.0007056404,0.0001162061,0.03247492],"category_scores_gemma":[0.0001625222,0.0002032326,0.0001291045,0.0007125805,0.00007152637,0.000856738,0.0001049128,0.0004082228,0.000004358422],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000584115,"about_ca_system_score_gemma":0.00004031143,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009294337,"about_ca_topic_score_gemma":0.0001247294,"domain_scores_codex":[0.9972205,0.0009160276,0.0008705283,0.0003653226,0.0003808828,0.0002468097],"domain_scores_gemma":[0.9979872,0.0004019199,0.001017925,0.0003715863,0.0001136352,0.0001077567],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.001228326,0.002458402,0.05050031,0.0002063086,0.0002120159,0.003872786,0.1108351,0.0001385607,0.768273,0.00006217881,0.0009107201,0.06130236],"study_design_scores_gemma":[0.005158363,0.0004527968,0.6932657,0.0009628198,0.00004962531,0.000270632,0.07233405,0.00001273523,0.2265306,0.0005072615,0.00009630324,0.0003591454],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9875346,0.009022132,0.00003838002,0.00001523126,0.0003122053,0.0008346915,0.000009693798,0.00001849964,0.002214605],"genre_scores_gemma":[0.999339,0.00004621964,0.0001008612,0.0002905647,0.00006659966,0.00003539729,0.000004191681,0.00002055646,0.00009655671],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6427653,"threshold_uncertainty_score":0.9684095,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4220895812","doi":"10.1017/s0272263121000954","title":"Text reading in English as a second language: Evidence from the Multilingual Eye-Movements Corpus","year":2022,"lang":"en","type":"article","venue":"Studies in Second Language Acquisition","topic":"Second Language Acquisition and Learning","field":"Psychology","cited_by":107,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"McMaster University","funders":"Social Sciences and Humanities Research Council of Canada; Universiteit Gent; Saint Petersburg State University; Israel Science Foundation; Fonds Wetenschappelijk Onderzoek; Eesti Teadusagentuur","keywords":"Fluency; Reading (process); Reading comprehension; Computer science; Variety (cybernetics); Psychology; Resource (disambiguation); Comprehension; Language proficiency; Eye movement; Extensive reading; Eye tracking; Linguistics; Cognitive psychology; Artificial intelligence; Mathematics education","retraction":null,"screen_n_in":null,"score":{"opus":0.02953301557774695,"gpt":0.369024896442975,"spread":0.339491880865228,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001676309,0.0003923416,0.0005288447,0.0003551853,0.0004717262,0.0000778826,0.0006372455,0.0001322382,0.2144475],"category_scores_gemma":[0.001054641,0.0003599872,0.0001483452,0.0007769357,0.000185988,0.0003338237,0.0005590475,0.001135587,0.0002462123],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004920139,"about_ca_system_score_gemma":0.00006128453,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002214257,"about_ca_topic_score_gemma":0.002523086,"domain_scores_codex":[0.9958566,0.001268183,0.0007619123,0.0009079368,0.0004802866,0.0007250222],"domain_scores_gemma":[0.9966133,0.002051823,0.0003420543,0.0008177394,0.00009387408,0.00008125001],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.0005201158,0.0002604832,0.008984966,0.0000624995,0.0002788384,0.003230656,0.9576244,0.0001111549,0.007103636,0.0001657118,0.006050583,0.01560697],"study_design_scores_gemma":[0.002928591,0.0002488484,0.04770624,0.0002819677,0.00003634573,0.000054352,0.9406688,0.0000558793,0.001284056,0.0001143116,0.006078043,0.0005425258],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9013922,0.0871774,0.000004202944,0.0001333437,0.002146689,0.0006163573,0.0001952574,0.0001494546,0.008185071],"genre_scores_gemma":[0.9753902,0.00005715401,0.00006738544,0.01613352,0.0008249283,0.0004829507,0.0002469986,0.00006147482,0.00673537],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2142013,"threshold_uncertainty_score":0.9998852,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2082397665","doi":"10.1353/cml.2006.0048","title":"Comparing Phonological and Orthographic Vocabulary Size: Do Vocabulary Tests Underestimate the Knowledge of Some Learners","year":2006,"lang":"en","type":"article","venue":"Canadian Modern Language Review/ La Revue canadienne des langues vivantes","topic":"Second Language Acquisition and Learning","field":"Psychology","cited_by":105,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Vocabulary; Linguistics; Orthographic projection; Natural language processing; Computer science; Psychology; Cognitive psychology; Artificial intelligence; Philosophy","retraction":null,"screen_n_in":null,"score":{"opus":0.01923326185539021,"gpt":0.2701535085945204,"spread":0.2509202467391302,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007263489,0.0003735552,0.0006912529,0.0002829045,0.0002637538,0.00006776556,0.0004524709,0.0001955509,0.001798173],"category_scores_gemma":[0.0004334408,0.000298874,0.0001903219,0.0004693777,0.0005801654,0.0001201538,0.00006753832,0.0004922924,0.0000454483],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001381312,"about_ca_system_score_gemma":0.0001086788,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.1084377,"about_ca_topic_score_gemma":0.2055351,"domain_scores_codex":[0.9974435,0.0005154655,0.0005289647,0.0005586941,0.00007396027,0.0008794447],"domain_scores_gemma":[0.9978551,0.000653486,0.0002204428,0.0006979164,0.00008877595,0.0004843232],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0002323345,0.0007623342,0.1945552,0.01694918,0.002185488,0.02514062,0.2124412,0.0005411329,0.02924724,0.1009161,0.0191654,0.3978638],"study_design_scores_gemma":[0.001874352,0.0002780103,0.91408,0.006869784,0.0007063904,0.004968339,0.02759341,0.001718796,0.00005893668,0.002623111,0.03735109,0.001877832],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6243599,0.3697351,0.0000304508,0.000276072,0.0001025322,0.0002966902,0.0000546607,0.00006345516,0.005081126],"genre_scores_gemma":[0.994507,0.001968581,0.0001977091,0.001934452,0.0002211752,0.00005233251,0.0001256803,0.00006692263,0.0009261716],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7195248,"threshold_uncertainty_score":0.9999464,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2408477286","doi":"10.1177/1362168815586083","title":"The Word Part Levels Test","year":2015,"lang":"en","type":"article","venue":"Language Teaching Research","topic":"Second Language Acquisition and Learning","field":"Psychology","cited_by":105,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University","funders":"","keywords":"Affix; Linguistics; Test (biology); Psychology; Rasch model; Meaning (existential); Natural language processing; Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.1931340518419367,"gpt":0.4874869866649238,"spread":0.2943529348229871,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.008880352,0.000119432,0.0001250622,0.0001457059,0.0007582386,0.000247978,0.000581591,0.0001000106,0.01381789],"category_scores_gemma":[0.004974936,0.00008118813,0.00005635605,0.0002671953,0.0001767124,0.00008411005,0.0001596031,0.001771961,0.003960529],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008552246,"about_ca_system_score_gemma":0.00006874752,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007534578,"about_ca_topic_score_gemma":0.00006483927,"domain_scores_codex":[0.9963819,0.001686011,0.0002113573,0.0003235691,0.0006335358,0.0007636523],"domain_scores_gemma":[0.9960957,0.002722397,0.00004694402,0.0007844979,0.0001013171,0.0002491683],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001004216,0.0002322419,0.00237585,0.000009209889,0.00007175333,0.0009578142,0.2144951,0.000004437918,0.001217888,0.01590405,0.3191018,0.4455294],"study_design_scores_gemma":[0.001069868,0.0002143602,0.008343693,0.00004045136,0.000007041775,0.0001361569,0.2768096,0.00006401882,0.0001454531,0.0004790428,0.7124394,0.0002508686],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5918601,0.01271451,0.00008645782,0.002440063,0.0007568116,0.0002802045,0.00001120184,0.0002694147,0.3915813],"genre_scores_gemma":[0.8942302,0.000001750479,0.0001255991,0.001337783,0.001046394,0.00005394106,0.00001334896,0.00003509146,0.1031559],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4452786,"threshold_uncertainty_score":0.996815,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2893795767","doi":"10.1002/tesq.453","title":"Roles of Vocabulary Knowledge for Success in English‐Medium Instruction: Self‐Perceptions and Academic Outcomes of Japanese Undergraduates","year":2018,"lang":"en","type":"article","venue":"TESOL Quarterly","topic":"Second Language Acquisition and Learning","field":"Psychology","cited_by":101,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University","funders":"Waseda University","keywords":"Vocabulary; Active listening; Psychology; Reading (process); Perception; Mathematics education; Linguistics; Communication","retraction":null,"screen_n_in":null,"score":{"opus":0.01777008921644983,"gpt":0.3318921048609014,"spread":0.3141220156444515,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002521414,0.0001307724,0.0002884974,0.0002503279,0.00005360052,0.000008624719,0.0001420268,0.000170086,0.001736105],"category_scores_gemma":[0.00005097079,0.0001218433,0.00006137485,0.0001908547,0.0001966094,0.0001382702,0.00001199607,0.0001856776,0.00002340491],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001521536,"about_ca_system_score_gemma":0.0000216298,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008529479,"about_ca_topic_score_gemma":0.000158667,"domain_scores_codex":[0.9989748,0.0001164471,0.000398656,0.0002319853,0.00007672104,0.0002013994],"domain_scores_gemma":[0.9991475,0.0002867721,0.0001451314,0.000210585,0.00015536,0.00005468257],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"observational","study_design_scores_codex":[0.0001433585,0.0003720354,0.1708125,0.0001866808,0.0001786049,0.000003051929,0.7964143,9.264764e-7,0.002903256,0.002491846,0.001210215,0.02528325],"study_design_scores_gemma":[0.003636028,0.00145939,0.7928181,0.00008209904,0.00007212933,0.00002868964,0.1996757,0.000180383,0.0003558678,0.0006315946,0.0007837753,0.0002762105],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9959338,0.001169085,0.00007230091,0.0001593078,0.0004586409,0.0002357272,0.00001747121,0.0000788146,0.001874892],"genre_scores_gemma":[0.998834,0.000004519043,0.0002959852,0.0001823048,0.0002940011,0.00004684591,0.00001791233,0.00001844721,0.0003060255],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6220056,"threshold_uncertainty_score":0.9991764,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2100069223","doi":"10.1016/s0093-934x(03)00141-x","title":"Pervasive influence of semantics in letter and category fluency: A multidimensional approach","year":2003,"lang":"en","type":"article","venue":"Brain and Language","topic":"Second Language Acquisition and Learning","field":"Psychology","cited_by":100,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Victoria","funders":"","keywords":"Psychology; Fluency; Semantics (computer science); Cognitive psychology; Verbal fluency test; Linguistics; Cognitive science; Cognition; Neuropsychology; Computer science; Programming language; Psychiatry; Mathematics education","retraction":null,"screen_n_in":null,"score":{"opus":0.008591358076784579,"gpt":0.2700383830267306,"spread":0.261447024949946,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002601681,0.00009475795,0.0001478943,0.0001055225,0.00003023921,0.000007715423,0.00003659336,0.00007902314,0.001480922],"category_scores_gemma":[0.000129836,0.00008488342,0.00002027179,0.00009687762,0.00009026745,0.00004753143,0.00001757584,0.0001547405,0.000009616641],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000004986477,"about_ca_system_score_gemma":0.00001151532,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002007929,"about_ca_topic_score_gemma":0.00001488445,"domain_scores_codex":[0.9992248,0.0001792266,0.000151888,0.0002119945,0.00007122022,0.0001608452],"domain_scores_gemma":[0.9995912,0.0001571959,0.00004960523,0.0001372307,0.00001617758,0.00004854026],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"observational","study_design_scores_codex":[0.0002456779,0.0008576662,0.08877051,0.0005565948,0.0001995188,0.001897142,0.6000601,0.0003993864,0.1699205,0.119047,0.007534979,0.01051086],"study_design_scores_gemma":[0.005474142,0.0001804397,0.8925765,0.0001123329,0.00003453313,0.0007433361,0.08905577,0.0003282593,0.002121819,0.0001967958,0.00850406,0.0006720083],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9889631,0.005373021,0.00005491243,0.0001794229,0.00002821802,0.000107733,0.00000301769,0.0000138488,0.005276677],"genre_scores_gemma":[0.9892697,0.00000424717,0.0007146448,0.009209647,0.00002145647,0.000008562802,0.00000840423,0.00001050034,0.0007528365],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.803806,"threshold_uncertainty_score":0.9994318,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3081900102","doi":"10.1017/s0272263120000297","title":"HOW DOES MODE OF INPUT AFFECT THE INCIDENTAL LEARNING OF COLLOCATIONS?","year":2020,"lang":"en","type":"article","venue":"Studies in Second Language Acquisition","topic":"Second Language Acquisition and Learning","field":"Psychology","cited_by":96,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University","funders":"","keywords":"Active listening; Reading (process); Psychology; Vocabulary; Affect (linguistics); Word learning; Linguistics; Incidental learning; Vocabulary learning; Mode (computer interface); Cognitive psychology; Matching (statistics); Communication; Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.02520463230377441,"gpt":0.3493806442952,"spread":0.3241760119914256,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0003294726,0.0001639565,0.0003699867,0.0001317354,0.0001071386,0.00001868521,0.0002142006,0.00008466723,0.008031523],"category_scores_gemma":[0.0004343581,0.0001133329,0.0001119348,0.000439069,0.0002599914,0.0001511921,0.0001117592,0.0002995156,0.00001890945],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004254469,"about_ca_system_score_gemma":0.00001925425,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008824086,"about_ca_topic_score_gemma":0.0001126171,"domain_scores_codex":[0.9984989,0.0004442665,0.0003673158,0.0002793652,0.0001930114,0.0002171982],"domain_scores_gemma":[0.9987289,0.0005589877,0.0003176443,0.0002521465,0.0001016317,0.00004063277],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.0004484291,0.0002056542,0.008808079,0.0007176219,0.000731819,0.0002140827,0.8946434,0.0004918671,0.07538527,0.005732332,0.003371872,0.009249589],"study_design_scores_gemma":[0.002087778,0.0004852221,0.02119767,0.0001923483,0.00008445521,0.00003701265,0.9495707,0.000326501,0.0246727,0.0001684304,0.0008517677,0.0003254892],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9799702,0.01469817,0.0002322212,0.00079633,0.0002956761,0.0003076577,0.00003351025,0.00004770537,0.003618568],"genre_scores_gemma":[0.996169,0.00003459989,0.00009148141,0.002683243,0.0002270035,0.0000539536,0.00004661603,0.00002067554,0.0006734134],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05492726,"threshold_uncertainty_score":0.9928753,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2901271358","doi":"10.1111/modl.12661","title":"Incidental Vocabulary Learning Through Listening to Teacher Talk","year":2020,"lang":"en","type":"article","venue":"Modern Language Journal","topic":"Second Language Acquisition and Learning","field":"Psychology","cited_by":92,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University","funders":"","keywords":"Active listening; Vocabulary; Psychology; Vocabulary learning; Context (archaeology); Recall; Meaning (existential); Vocabulary development; Incidental learning; Test (biology); Linguistics; Reading (process); Word (group theory); Cognitive psychology; Teaching method; Mathematics education; Communication","retraction":null,"screen_n_in":null,"score":{"opus":0.02127390054691639,"gpt":0.3163226764210219,"spread":0.2950487758741054,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0003427363,0.000214996,0.0002639157,0.00009678108,0.0003028726,0.0001864955,0.0003095321,0.0001281605,0.1230934],"category_scores_gemma":[0.0002255799,0.0002026539,0.0001704479,0.0002085687,0.00002681023,0.0002615884,0.0001123104,0.001373687,0.001253412],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006482848,"about_ca_system_score_gemma":0.00002701629,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001076507,"about_ca_topic_score_gemma":0.000003525279,"domain_scores_codex":[0.9981493,0.0003402812,0.0003605743,0.000345785,0.0003276363,0.000476452],"domain_scores_gemma":[0.9991725,0.00005072827,0.0001689,0.0001813386,0.00004553486,0.0003809677],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.0003970839,0.0001355237,0.001887774,0.00002068952,0.0002927387,0.0151671,0.8109099,0.002403728,0.05015782,0.0000942478,0.01942281,0.09911064],"study_design_scores_gemma":[0.00926305,0.002352218,0.02523945,0.0003377347,0.0003201199,0.02514643,0.7523708,0.01432783,0.002663451,0.0002781936,0.1648046,0.002896114],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9189651,0.01174749,0.04052392,0.001737816,0.0004226262,0.0001238681,0.00000287633,0.0002202453,0.02625606],"genre_scores_gemma":[0.9512575,0.000003029184,0.001671349,0.03901069,0.002032549,0.000007248567,0.00001593297,0.00006950053,0.005932244],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1453818,"threshold_uncertainty_score":0.9995242,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2158773143","doi":"10.1017/s0272263115000297","title":"LEXICAL PROFILES OF COMPREHENSIBLE SECOND LANGUAGE SPEECH","year":2015,"lang":"en","type":"article","venue":"Studies in Second Language Acquisition","topic":"Second Language Acquisition and Learning","field":"Psychology","cited_by":92,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Concordia University; Western University","funders":"","keywords":"Lexis; Linguistics; Lexical choice; Fluency; Lexical density; Psychology; Lexical item; Vocabulary; Variation (astronomy); Lexicology; Computer science; Natural language processing","retraction":null,"screen_n_in":null,"score":{"opus":0.05742282413847523,"gpt":0.3836705367306295,"spread":0.3262477125921543,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0008022561,0.0003187421,0.0006465944,0.0004067208,0.00007664876,0.0000254695,0.0002759136,0.0002133659,0.08464856],"category_scores_gemma":[0.0002059082,0.0003009039,0.0001406069,0.0004868628,0.0003140188,0.0002267436,0.000163645,0.0004029216,0.0004512104],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001298463,"about_ca_system_score_gemma":0.00005466521,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001593167,"about_ca_topic_score_gemma":0.0003182213,"domain_scores_codex":[0.9974836,0.0004268143,0.0006771615,0.0005440323,0.0003333364,0.0005351246],"domain_scores_gemma":[0.9984258,0.0003647158,0.0002728706,0.0005963419,0.0001912171,0.0001489852],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.001223861,0.001156102,0.004961345,0.001066504,0.001093588,0.005468365,0.8057312,0.00005262336,0.0544611,0.007652088,0.09289208,0.02424116],"study_design_scores_gemma":[0.006365301,0.0007266154,0.01886797,0.0003384135,0.00008093662,0.0005342111,0.937059,0.00004545545,0.02789608,0.0006045607,0.006579114,0.0009023219],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.871884,0.05444294,0.00002458524,0.00007281052,0.0009439609,0.0003522148,0.00008635686,0.0001273819,0.07206571],"genre_scores_gemma":[0.9884591,0.00001316901,0.0006642258,0.003333374,0.0005227848,0.00007011708,0.0001715063,0.00004738107,0.006718405],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1313278,"threshold_uncertainty_score":0.9999443,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2891493583","doi":"10.1177/1362168818799371","title":"Investigating the role of vocabulary size in second language speaking ability","year":2018,"lang":"en","type":"article","venue":"Language Teaching Research","topic":"Second Language Acquisition and Learning","field":"Psychology","cited_by":88,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University","funders":"","keywords":"Vocabulary; Psychology; Sophistication; Task (project management); Linguistics; Vocabulary development; Test (biology); Language proficiency; Cognitive psychology; Mathematics education","retraction":null,"screen_n_in":null,"score":{"opus":0.03178698970439157,"gpt":0.404120285384388,"spread":0.3723332956799965,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.008397473,0.000157768,0.0002458134,0.0002589441,0.0003526514,0.00007122521,0.0006411306,0.0001418113,0.04278313],"category_scores_gemma":[0.003800064,0.0001213546,0.00007986691,0.0005241121,0.0005514571,0.0001228804,0.00024536,0.001980418,0.0002782082],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008172076,"about_ca_system_score_gemma":0.00005785891,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00736745,"about_ca_topic_score_gemma":0.001088694,"domain_scores_codex":[0.9951467,0.002787569,0.0004178803,0.0004525208,0.0005063257,0.0006889903],"domain_scores_gemma":[0.9962657,0.002514951,0.0001206849,0.0009131659,0.00008275776,0.000102711],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.00004715235,0.0001399537,0.02511395,0.00004602074,0.00004161154,0.0001277705,0.6913341,0.000002180805,0.1731223,0.003175604,0.000362343,0.1064871],"study_design_scores_gemma":[0.001082277,0.000268733,0.1973352,0.0002034115,0.00001017031,0.00007988605,0.7799636,0.0004638784,0.01439673,0.0009776036,0.004887927,0.0003305937],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8710558,0.004521796,0.00001202036,0.0001616076,0.0001140956,0.0002735254,0.000007599019,0.00007119337,0.1237824],"genre_scores_gemma":[0.9962155,4.52793e-7,0.0005213905,0.0009843332,0.0006133129,0.00002973543,0.00001007397,0.00003814363,0.001587043],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1722212,"threshold_uncertainty_score":0.9992426,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4316038657","doi":"10.1017/s0261444822000507","title":"How effective is second language incidental vocabulary learning? A meta-analysis","year":2023,"lang":"en","type":"article","venue":"Language Teaching","topic":"Second Language Acquisition and Learning","field":"Psychology","cited_by":86,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University","funders":"","keywords":"Active listening; Vocabulary; Psychology; Contrast (vision); Moderation; Reading (process); Meaning (existential); Vocabulary development; Affect (linguistics); Language acquisition; Incidental learning; Vocabulary learning; Cognitive psychology; Variation (astronomy); Meta-analysis; Control (management); Linguistics; Mathematics education; Teaching method; Computer science; Social psychology; Artificial intelligence; Communication","retraction":null,"screen_n_in":null,"score":{"opus":0.02177258594853049,"gpt":0.3344554714392208,"spread":0.3126828854906903,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.001576315,0.0003878756,0.0009166049,0.0009263295,0.0004010153,0.0002765074,0.0003727418,0.0002140486,0.1213948],"category_scores_gemma":[0.0003250345,0.0003402388,0.001355944,0.001117586,0.00005625111,0.0002722342,0.0001696518,0.001415037,0.002029011],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006339581,"about_ca_system_score_gemma":0.00001100618,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008936781,"about_ca_topic_score_gemma":0.0001536973,"domain_scores_codex":[0.996344,0.001485876,0.000309361,0.0007868843,0.0003988289,0.0006750247],"domain_scores_gemma":[0.9981824,0.000626618,0.0002403264,0.0007458742,0.00002648896,0.0001783183],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.00007969051,0.0001531821,0.002740452,0.0000624367,0.1171969,0.006083573,0.8226857,0.0001217594,0.01081669,0.0007488782,0.009904742,0.02940601],"study_design_scores_gemma":[0.002554333,0.0003784503,0.03420246,0.00001574044,0.08359417,0.0003706434,0.8489813,0.002058035,0.002660119,0.00005211481,0.02327611,0.001856563],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9627009,0.01195387,0.000840615,0.0005291615,0.0002456327,0.0003806299,0.0000684105,0.001111503,0.02216927],"genre_scores_gemma":[0.8974504,9.544076e-7,0.0002021088,0.00584875,0.000325617,0.0001406292,0.0003687006,0.00007731503,0.09558553],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1193658,"threshold_uncertainty_score":0.999905,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2149304711","doi":"10.1177/1362168809346497","title":"Translation and short-term L2 vocabulary retention: Hindrance or help?","year":2010,"lang":"en","type":"article","venue":"Language Teaching Research","topic":"Second Language Acquisition and Learning","field":"Psychology","cited_by":86,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Université Laval","funders":"Université Laval","keywords":"Copying; Vocabulary; Rote learning; Vocabulary learning; Psychology; Second language; Task (project management); Recall; Vocabulary development; Translation (biology); Cognition; Term (time); Linguistics; Memorization; Teaching method; Computer science; Mathematics education; Cognitive psychology; Cooperative learning","retraction":null,"screen_n_in":null,"score":{"opus":0.09836645637053835,"gpt":0.4433781848546612,"spread":0.3450117284841229,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00283665,0.0001359167,0.0001606784,0.0002687583,0.0004476348,0.0001455017,0.0002411733,0.0001986408,0.03439536],"category_scores_gemma":[0.0002832456,0.0001139559,0.00005290127,0.0001893035,0.000144993,0.0001810302,0.00005315736,0.00231723,0.0002484357],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001810662,"about_ca_system_score_gemma":0.00002585252,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003076222,"about_ca_topic_score_gemma":0.000171873,"domain_scores_codex":[0.9977264,0.0007269389,0.0002165441,0.0004478581,0.0004002378,0.0004820214],"domain_scores_gemma":[0.9988101,0.0004576906,0.00003159403,0.0005038538,0.00004498529,0.0001517464],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0002670425,0.0001276861,0.004765218,0.00006007581,0.00004901413,0.001063723,0.09457544,5.197697e-7,0.1102168,0.002162068,0.001474842,0.7852376],"study_design_scores_gemma":[0.009687787,0.002020344,0.6006783,0.0006483622,0.000149471,0.004981391,0.2353893,0.002747479,0.005877523,0.0006979473,0.134283,0.002839061],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9588308,0.004206982,0.0003413539,0.00047563,0.0003899741,0.0002725226,0.000007211479,0.0001647855,0.03531072],"genre_scores_gemma":[0.9873064,0.000006654928,0.001052322,0.0004810303,0.000703186,0.00003815998,0.00005837764,0.00003803465,0.0103159],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7823985,"threshold_uncertainty_score":0.9999844,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2989936866","doi":"10.1111/lang.12384","title":"To What Extent Are Multiword Sequences Associated With Oral Fluency?","year":2019,"lang":"en","type":"article","venue":"Language Learning","topic":"Second Language Acquisition and Learning","field":"Psychology","cited_by":83,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Western University","funders":"University of Reading","keywords":"Fluency; Psychology; Phraseology; Linguistics; Variety (cybernetics); Test (biology); Task (project management); Second language; Association (psychology); Cognitive psychology; Computer science; Artificial intelligence; Mathematics education","retraction":null,"screen_n_in":null,"score":{"opus":0.01264886595070651,"gpt":0.297887295716632,"spread":0.2852384297659255,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0004189504,0.0002244303,0.0003035067,0.0001679516,0.0001383307,0.0002058815,0.0002251205,0.0001360325,0.06629531],"category_scores_gemma":[0.0002213808,0.0001874527,0.00007424275,0.0004110875,0.00003251588,0.0003178567,0.00005017595,0.0006019374,0.003926721],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000687513,"about_ca_system_score_gemma":0.00001829982,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002952817,"about_ca_topic_score_gemma":0.0001221644,"domain_scores_codex":[0.9980635,0.0004097953,0.0002145223,0.000505063,0.0002788628,0.0005282492],"domain_scores_gemma":[0.9990246,0.0002042347,0.0001954321,0.000345874,0.00007343163,0.0001564231],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.000606766,0.0004082627,0.3414636,0.00006100929,0.0007544754,0.00430811,0.347914,0.01066966,0.01883263,0.0006968469,0.001324482,0.2729602],"study_design_scores_gemma":[0.003132658,0.0009847061,0.3776605,0.0009471714,0.00007313152,0.0001275553,0.6004838,0.000497959,0.0005424499,0.000008662176,0.01445629,0.001085142],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9874319,0.003230369,0.0001671476,0.0002727959,0.0004730589,0.0002981291,0.000001944444,0.0003476536,0.007777006],"genre_scores_gemma":[0.9614615,0.000002867736,0.0003067857,0.007217719,0.0001190999,0.00003404273,0.00005522096,0.00005378685,0.03074894],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.271875,"threshold_uncertainty_score":0.9968488,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2086354528","doi":"10.3138/cmlr.65.3.441","title":"The Effects of Pre-learning Vocabulary on Reading Comprehension and Writing","year":2009,"lang":"en","type":"article","venue":"Canadian Modern Language Review/ La Revue canadienne des langues vivantes","topic":"Second Language Acquisition and Learning","field":"Psychology","cited_by":83,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Vocabulary; Reading comprehension; Task (project management); Test (biology); Reading (process); Psychology; Comprehension; Vocabulary development; Vocabulary learning; Computer science; Linguistics; Cognitive psychology","retraction":null,"screen_n_in":null,"score":{"opus":0.007694038680486226,"gpt":0.260127636101913,"spread":0.2524335974214268,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006168066,0.0002628817,0.0004458835,0.0001974885,0.0003857438,0.00005543469,0.0002547854,0.0001197422,0.0003506581],"category_scores_gemma":[0.0009241906,0.0002169477,0.000116098,0.0002303026,0.0001423911,0.00007333899,0.00002139923,0.0004533769,0.00001693442],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001366336,"about_ca_system_score_gemma":0.00004049525,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01677184,"about_ca_topic_score_gemma":0.01139698,"domain_scores_codex":[0.9979514,0.0004990999,0.0003827939,0.0003964677,0.0000814185,0.0006888187],"domain_scores_gemma":[0.9976742,0.00110225,0.0001953252,0.0004691332,0.00007679685,0.0004823169],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00006147525,0.0000401522,0.0009585487,0.002829853,0.0001659133,0.004100521,0.06739041,0.0000193445,0.02083825,0.007174757,0.001578919,0.8948418],"study_design_scores_gemma":[0.00389018,0.00310276,0.731433,0.07117765,0.0009824315,0.006594187,0.05550191,0.003705725,0.001360867,0.001528688,0.1171895,0.003533041],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7382129,0.2558425,0.00004128121,0.0003224946,0.0001312792,0.00036185,0.00001333837,0.0000585425,0.005015796],"genre_scores_gemma":[0.9905884,0.003737335,0.0001229328,0.00431,0.0001640488,0.00002300988,0.00005909174,0.0000433487,0.0009518038],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8913088,"threshold_uncertainty_score":0.9897755,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2106214072","doi":"10.5539/ies.v5n3p134","title":"The Effect of Using Vocabulary Flash Card on Iranian Pre-University Students’ Vocabulary Knowledge","year":2012,"lang":"en","type":"article","venue":"International Education Studies","topic":"Second Language Acquisition and Learning","field":"Psychology","cited_by":82,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Vocabulary; Homogeneous; Psychology; Flash (photography); Mathematics education; Treatment and control groups; Vocabulary development; Vocabulary learning; Significant difference; Teaching method; Computer science; Linguistics; Mathematics; Statistics","retraction":null,"screen_n_in":null,"score":{"opus":0.03836133416652591,"gpt":0.4300447959882481,"spread":0.3916834618217221,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005270737,0.000117688,0.0001492186,0.0001420732,0.0002276567,0.0000193347,0.0002855795,0.00004625048,0.0007881964],"category_scores_gemma":[0.0002488678,0.00009102041,0.00008931953,0.0001186226,0.0001002056,0.0001143839,0.00009069454,0.000142763,0.0002259118],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001587956,"about_ca_system_score_gemma":0.000034127,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004447955,"about_ca_topic_score_gemma":0.000005421925,"domain_scores_codex":[0.998946,0.0003329225,0.0001763878,0.0001542814,0.0002265716,0.0001638612],"domain_scores_gemma":[0.998715,0.0005844624,0.0001464395,0.0002015382,0.0003047003,0.00004783483],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0009896491,0.001104246,0.7770866,0.0000729838,0.003356845,0.000009125422,0.0904315,0.0000660282,0.0004157631,0.008913218,0.04507931,0.07247471],"study_design_scores_gemma":[0.001488666,0.0002814938,0.6468057,0.0001790932,0.0001993635,0.00004326249,0.04598894,0.00003013461,0.0006388697,0.00003678133,0.3040164,0.000291296],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9653555,0.01285204,0.00004735631,0.000186439,0.007567059,0.0001624494,0.00000570775,0.0000273073,0.01379614],"genre_scores_gemma":[0.9870513,0.00004157643,0.00005217311,0.0003039076,0.0005992019,0.00001156853,0.00001310439,0.00001182855,0.01191533],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2589371,"threshold_uncertainty_score":0.8630198,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}