{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":5,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":5,"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":"fc2b4103dbeb","filters":{"venue":"Vocabulary Learning and Instruction"}},"results":[{"id":"W4213305977","doi":"10.7820/vli.v10.2.mizumoto","title":"Comparisons of word lists on new word level checker","year":2021,"lang":"en","type":"article","venue":"Vocabulary Learning and Instruction","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Carleton University","funders":"Japan Society for the Promotion of Science","keywords":"Word (group theory); Computer science; Natural language processing; Linguistics; Artificial intelligence; Philosophy","retraction":null,"screen_n_in":null,"score":{"opus":0.02571747992163879,"gpt":0.2767666383681596,"spread":0.2510491584465208,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001235407,0.0001078038,0.0001593016,0.0001085714,0.0001247288,0.00009165092,0.0001610555,0.00008713851,0.00001356707],"category_scores_gemma":[0.0001105899,0.0001033764,0.0000371771,0.0004033639,0.00004161104,0.0002853597,0.0001251474,0.0003693412,0.00000448678],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002263714,"about_ca_system_score_gemma":0.00008025722,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005447503,"about_ca_topic_score_gemma":0.000006199058,"domain_scores_codex":[0.9991405,0.00007385862,0.0001721721,0.0002903537,0.0001848699,0.0001382209],"domain_scores_gemma":[0.9995128,0.00002767937,0.000118195,0.0001989844,0.00007967577,0.00006268546],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00002149347,0.00003472299,0.003828767,0.00004454311,0.00001940621,0.00001955045,0.0006775091,0.00006007372,0.008777536,0.01614662,0.001243219,0.9691266],"study_design_scores_gemma":[0.003393942,0.0009293163,0.07848648,0.001811647,0.00008012307,0.001421961,0.0008934572,0.0590606,0.6833624,0.03251673,0.1362353,0.001808118],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5057285,0.003900193,0.4870986,0.0009793041,0.0005531367,0.00008634784,0.000001034258,0.0006120963,0.001040858],"genre_scores_gemma":[0.6365599,0.00006874536,0.3621372,0.00006618204,0.00007102121,0.000001262172,0.000005747464,0.0000074421,0.001082489],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9673184,"threshold_uncertainty_score":0.4215569,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4213141158","doi":"10.7820/vli.v10.2.mclean","title":"The internal consistency and accuracy of automatically scored written receptive meaning-recall data: A preliminary study","year":2021,"lang":"en","type":"article","venue":"Vocabulary Learning and Instruction","topic":"Second Language Acquisition and Learning","field":"Psychology","cited_by":5,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Carleton University","funders":"Japan Society for the Promotion of Science","keywords":"Recall; Consistency (knowledge bases); Meaning (existential); Internal consistency; Computer science; Natural language processing; Precision and recall; Psychology; Artificial intelligence; Cognitive psychology; Psychometrics; Developmental psychology","retraction":null,"screen_n_in":null,"score":{"opus":0.02340135669395839,"gpt":0.3193501383761505,"spread":0.2959487816821921,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.000632089,0.0001314367,0.0002108427,0.00007072484,0.0003833375,0.00009378902,0.0001328324,0.00008259261,0.0010579],"category_scores_gemma":[0.0009500567,0.0001057802,0.00003005399,0.0001581338,0.0001992734,0.0002037305,0.0002204279,0.0004776883,0.00001170972],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001169144,"about_ca_system_score_gemma":0.0000395366,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001005042,"about_ca_topic_score_gemma":0.0000141405,"domain_scores_codex":[0.9981581,0.0007353608,0.0003632853,0.000409921,0.0001578385,0.000175473],"domain_scores_gemma":[0.9987273,0.0005162766,0.0002277882,0.0003457249,0.0001183769,0.00006455679],"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":[0.0008678806,0.0003087886,0.06632912,0.00007408481,0.0006611012,0.0002735298,0.04435189,0.0000180482,0.001345844,0.002624267,0.0006829581,0.8824625],"study_design_scores_gemma":[0.004774465,0.002733872,0.6276844,0.0003315575,0.0003211885,0.003191895,0.3395976,0.006302368,0.0001676714,0.000386334,0.01403095,0.000477656],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9901214,0.00420799,0.000237869,0.0002136278,0.0004233824,0.0001717025,0.000003678419,0.00007089661,0.00454949],"genre_scores_gemma":[0.9979054,0.00009796832,0.0006289959,0.0001526015,0.0001180836,0.0000108491,0.00004589272,0.00001725889,0.001022968],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8819848,"threshold_uncertainty_score":0.9998553,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4238316020","doi":"10.7820/vli.v04.1.webb","title":"Researching Vocabulary in the EFL Context: A Commentary on Four Studies for JALT Vocabulary SIG","year":2015,"lang":"en","type":"article","venue":"Vocabulary Learning and Instruction","topic":"Second Language Acquisition and Learning","field":"Psychology","cited_by":0,"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; Context (archaeology); Linguistics; Psychology; English vocabulary; Computer science; History; Philosophy","retraction":null,"screen_n_in":null,"score":{"opus":0.09424561063835392,"gpt":0.3882283965775048,"spread":0.2939827859391509,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002238244,0.0002789395,0.000359234,0.0003995267,0.0005604998,0.0001063296,0.0002106444,0.0001716223,0.0002454341],"category_scores_gemma":[0.0005897456,0.0002229259,0.000100702,0.0003312198,0.0001982308,0.000239389,0.00007332052,0.001151476,0.00006307196],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001055741,"about_ca_system_score_gemma":0.00003421308,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003115874,"about_ca_topic_score_gemma":0.00003554141,"domain_scores_codex":[0.9967211,0.001442674,0.0004241636,0.0005405305,0.0003673718,0.0005041171],"domain_scores_gemma":[0.9984686,0.0007953068,0.000173575,0.0003157419,0.0001130154,0.0001337868],"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":[0.00392075,0.0004621687,0.02765282,0.0002418637,0.0007164526,0.0007908822,0.1761886,0.001375847,0.0005576235,0.006142662,0.09010155,0.6918487],"study_design_scores_gemma":[0.01445424,0.004596171,0.03082621,0.0005602552,0.0001484778,0.001425125,0.591828,0.00430245,0.0001621429,0.002564187,0.3480475,0.001085273],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9784021,0.01111024,0.000428653,0.005456301,0.001079869,0.0006680617,0.000006522754,0.0001401869,0.002708102],"genre_scores_gemma":[0.9844075,0.00009939411,0.000287678,0.01338887,0.0008424,0.0001740555,0.00009557061,0.00004857399,0.0006559632],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6907635,"threshold_uncertainty_score":0.9090652,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4409328024","doi":"10.29140/vli.v14n1.2097","title":"Metrics for investigations into L2 knowledge of derivational affixes","year":2025,"lang":"en","type":"article","venue":"Vocabulary Learning and Instruction","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"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":"Computer science; Natural language processing; Linguistics; Philosophy","retraction":null,"screen_n_in":null,"score":{"opus":0.0103303198614561,"gpt":0.2836840507048554,"spread":0.2733537308433993,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0001926965,0.00006440714,0.00008941832,0.0003552672,0.0002096644,0.00005218637,0.0001402557,0.00006397323,8.133933e-7],"category_scores_gemma":[0.000468952,0.000062794,0.00002451106,0.0007711212,0.0000690211,0.0003185124,0.00008407021,0.0001208711,3.132893e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002516588,"about_ca_system_score_gemma":0.00008116914,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001524613,"about_ca_topic_score_gemma":0.000002181498,"domain_scores_codex":[0.9995077,0.000036064,0.0001508698,0.0001699281,0.00006229283,0.00007320393],"domain_scores_gemma":[0.9995322,0.0001085883,0.00008371229,0.00008753303,0.0001669407,0.00002109168],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000006705733,0.00002177572,0.005403515,0.0002159782,0.00002166631,1.45454e-7,0.0009109174,0.00005361712,0.01350665,0.4116012,0.0002881069,0.5679697],"study_design_scores_gemma":[0.001057946,0.0003374071,0.004221492,0.0004378514,0.00004846617,0.00002893099,0.000340709,0.2015287,0.2066849,0.5396243,0.04526006,0.0004292309],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1018529,0.002943477,0.8939964,0.000425304,0.0002034702,0.00009982497,5.012659e-7,0.00022277,0.000255417],"genre_scores_gemma":[0.5185752,0.00002767474,0.4811846,0.00002514483,0.0000204808,0.00001108258,0.000006450858,0.000002579419,0.0001468206],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.5675405,"threshold_uncertainty_score":0.2560665,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3196454181","doi":"10.7820/vli.v08.1.pinchbeck","title":"Validating the construct of readability in EFL contexts: A proposal for criteria","year":2019,"lang":"en","type":"article","venue":"Vocabulary Learning and Instruction","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Carleton University","funders":"","keywords":"Readability; Construct (python library); Computer science; Psychology; Linguistics; Natural language processing; Programming language; Philosophy","retraction":null,"screen_n_in":null,"score":{"opus":0.01096833977897327,"gpt":0.2677708520025041,"spread":0.2568025122235308,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008730934,0.00008139833,0.0001532625,0.00006202902,0.0001132443,0.00006416417,0.0001611222,0.00006256993,0.000006995807],"category_scores_gemma":[0.0002028042,0.00006216134,0.00003585212,0.0001905707,0.0001147389,0.0003671627,0.00005608572,0.0001672753,0.000001634184],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002814518,"about_ca_system_score_gemma":0.00007213332,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008210362,"about_ca_topic_score_gemma":0.00001138832,"domain_scores_codex":[0.9989827,0.0002068891,0.0002846964,0.0002864368,0.0001105711,0.0001286724],"domain_scores_gemma":[0.9993056,0.0001992613,0.000145444,0.0002452183,0.00008314913,0.00002132757],"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":[0.00009996798,0.0000501394,0.2136748,0.0002859572,0.00001560442,3.275949e-7,0.003290334,0.0002109998,0.028789,0.08789759,0.00001531674,0.66567],"study_design_scores_gemma":[0.00374984,0.001777598,0.4428148,0.0004119343,0.00003600278,0.0002872934,0.005585026,0.3947133,0.04423135,0.09644406,0.009118739,0.0008300898],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9726133,0.00005429612,0.02587471,0.0005723058,0.0002270003,0.000425799,0.00000157932,0.00004565026,0.0001853756],"genre_scores_gemma":[0.9848855,0.000007630169,0.01500467,0.00001922604,0.00002307624,0.00001837706,0.000005134618,0.000004296693,0.00003212924],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6648399,"threshold_uncertainty_score":0.2534866,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}