{"meta":{"query_hash":"fc2b4103dbeb","filters":{"venue":"Vocabulary Learning and Instruction"},"cohort_total":5,"direct_labels_cover":0,"predictions_cover":5,"exported":5,"export_cap":100000,"truncated":false,"label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"permalink":"https://metacan.xera.ac/q/fc2b4103dbeb","api":"https://metacan.xera.ac/api/v1/cohort?venue=Vocabulary+Learning+and+Instruction"},"results":[{"id":"W3196454181","doi":"10.7820/vli.v08.1.pinchbeck","title":"Validating the construct of readability in EFL contexts: A proposal for criteria","year":2019,"lang":"en","type":"article","venue":"Vocabulary Learning and Instruction","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Readability; Construct (python library); Computer science; Psychology; Linguistics; Natural language processing; Programming language; Philosophy","score_opus":0.010968339778973272,"score_gpt":0.2677708520025041,"score_spread":0.25680251222353084,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3196454181","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9726133,0.000054296124,0.02587471,0.00057230575,0.00022700032,0.000425799,0.00000157932,0.000045650257,0.00018537557],"genre_scores_gemma":[0.98488545,0.000007630169,0.015004669,0.000019226036,0.00002307624,0.000018377063,0.000005134618,0.0000042966926,0.000032129243],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9989827,0.00020688915,0.0002846964,0.00028643684,0.00011057111,0.00012867239],"domain_scores_gemma":[0.9993056,0.00019926133,0.00014544398,0.0002452183,0.00008314913,0.000021327574],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00087309344,0.00008139833,0.0001532625,0.00006202902,0.00011324434,0.00006416417,0.00016112215,0.00006256993,0.000006995807],"category_scores_gemma":[0.00020280416,0.00006216134,0.00003585212,0.00019057067,0.00011473893,0.0003671627,0.000056085722,0.00016727533,0.0000016341836],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009996798,0.0000501394,0.21367478,0.0002859572,0.000015604417,3.2759488e-7,0.0032903343,0.00021099983,0.028788997,0.08789759,0.00001531674,0.66567],"study_design_scores_gemma":[0.00374984,0.0017775983,0.4428148,0.00041193428,0.000036002777,0.00028729343,0.005585026,0.39471325,0.04423135,0.09644406,0.009118739,0.00083008985],"about_ca_topic_score_codex":0.000082103616,"about_ca_topic_score_gemma":0.000011388315,"teacher_disagreement_score":0.66483986,"about_ca_system_score_codex":0.000028145178,"about_ca_system_score_gemma":0.00007213332,"threshold_uncertainty_score":0.2534866},"labels":[],"label_agreement":null},{"id":"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.023401356693958385,"score_gpt":0.3193501383761505,"score_spread":0.29594878168219213,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4213141158","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99012136,0.0042079897,0.000237869,0.00021362778,0.00042338236,0.00017170252,0.0000036784188,0.00007089661,0.0045494903],"genre_scores_gemma":[0.9979054,0.00009796832,0.0006289959,0.00015260147,0.00011808359,0.000010849096,0.000045892724,0.000017258892,0.0010229675],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9981581,0.0007353608,0.00036328533,0.000409921,0.00015783854,0.00017547302],"domain_scores_gemma":[0.99872726,0.00051627663,0.00022778817,0.00034572493,0.00011837686,0.000064556785],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00063208904,0.00013143673,0.00021084269,0.00007072484,0.00038333752,0.00009378902,0.0001328324,0.00008259261,0.0010579005],"category_scores_gemma":[0.00095005665,0.00010578018,0.00003005399,0.00015813381,0.00019927337,0.00020373052,0.00022042794,0.00047768827,0.00001170972],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008678806,0.00030878864,0.06632912,0.00007408481,0.0006611012,0.00027352985,0.044351894,0.000018048197,0.0013458441,0.0026242672,0.0006829581,0.8824625],"study_design_scores_gemma":[0.0047744648,0.0027338723,0.6276844,0.00033155753,0.00032118853,0.003191895,0.33959764,0.006302368,0.00016767142,0.00038633402,0.014030947,0.00047765597],"about_ca_topic_score_codex":0.00010050417,"about_ca_topic_score_gemma":0.000014140503,"teacher_disagreement_score":0.88198483,"about_ca_system_score_codex":0.000011691442,"about_ca_system_score_gemma":0.0000395366,"threshold_uncertainty_score":0.9998553},"labels":[],"label_agreement":null},{"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.025717479921638794,"score_gpt":0.2767666383681596,"score_spread":0.2510491584465208,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4213305977","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5057285,0.003900193,0.48709857,0.0009793041,0.0005531367,0.00008634784,0.000001034258,0.0006120963,0.0010408581],"genre_scores_gemma":[0.6365599,0.000068745365,0.3621372,0.000066182045,0.00007102121,0.0000012621721,0.0000057474645,0.0000074421005,0.0010824886],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9991405,0.000073858624,0.00017217212,0.00029035372,0.00018486987,0.00013822092],"domain_scores_gemma":[0.9995128,0.000027679373,0.000118195014,0.00019898443,0.000079675774,0.00006268546],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00012354073,0.00010780382,0.00015930159,0.00010857136,0.00012472885,0.000091650916,0.00016105555,0.000087138505,0.000013567073],"category_scores_gemma":[0.000110589855,0.000103376435,0.0000371771,0.00040336387,0.00004161104,0.00028535965,0.0001251474,0.0003693412,0.00000448678],"study_design_candidate":"design_other","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021493472,0.000034722987,0.0038287672,0.00004454311,0.00001940621,0.000019550449,0.0006775091,0.000060073722,0.008777536,0.01614662,0.0012432189,0.9691266],"study_design_scores_gemma":[0.0033939423,0.00092931633,0.07848648,0.0018116469,0.00008012307,0.0014219615,0.0008934572,0.059060596,0.68336236,0.03251673,0.1362353,0.0018081177],"about_ca_topic_score_codex":0.000054475033,"about_ca_topic_score_gemma":0.000006199058,"teacher_disagreement_score":0.9673184,"about_ca_system_score_codex":0.000022637143,"about_ca_system_score_gemma":0.000080257225,"threshold_uncertainty_score":0.42155686},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Vocabulary; Context (archaeology); Linguistics; Psychology; English vocabulary; Computer science; History; Philosophy","score_opus":0.09424561063835392,"score_gpt":0.3882283965775048,"score_spread":0.2939827859391509,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4238316020","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9784021,0.011110237,0.00042865303,0.0054563014,0.0010798695,0.0006680617,0.000006522754,0.00014018685,0.002708102],"genre_scores_gemma":[0.9844075,0.00009939411,0.00028767798,0.013388869,0.00084239995,0.00017405546,0.00009557061,0.000048573987,0.0006559632],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.99672115,0.001442674,0.0004241636,0.00054053054,0.00036737177,0.00050411705],"domain_scores_gemma":[0.9984686,0.0007953068,0.00017357497,0.00031574193,0.00011301538,0.00013378682],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002238244,0.0002789395,0.00035923402,0.0003995267,0.0005604998,0.00010632957,0.00021064444,0.00017162232,0.00024543412],"category_scores_gemma":[0.0005897456,0.00022292585,0.00010070202,0.00033121984,0.00019823077,0.00023938896,0.00007332052,0.0011514764,0.00006307196],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00392075,0.00046216868,0.027652824,0.00024186369,0.0007164526,0.0007908822,0.17618865,0.0013758466,0.00055762345,0.0061426624,0.090101555,0.6918487],"study_design_scores_gemma":[0.014454239,0.0045961714,0.030826205,0.0005602552,0.0001484778,0.0014251254,0.591828,0.0043024505,0.00016214294,0.0025641874,0.3480475,0.0010852733],"about_ca_topic_score_codex":0.00031158736,"about_ca_topic_score_gemma":0.00003554141,"teacher_disagreement_score":0.6907635,"about_ca_system_score_codex":0.00010557405,"about_ca_system_score_gemma":0.000034213077,"threshold_uncertainty_score":0.90906525},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Computer science; Natural language processing; Linguistics; Philosophy","score_opus":0.010330319861456098,"score_gpt":0.28368405070485536,"score_spread":0.27335373084339926,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409328024","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.101852864,0.0029434771,0.89399636,0.000425304,0.00020347016,0.00009982497,5.012659e-7,0.00022276997,0.00025541696],"genre_scores_gemma":[0.5185752,0.000027674743,0.4811846,0.000025144833,0.0000204808,0.000011082579,0.0000064508577,0.0000025794186,0.00014682059],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99950767,0.000036063997,0.00015086983,0.00016992808,0.00006229283,0.000073203926],"domain_scores_gemma":[0.99953216,0.00010858832,0.00008371229,0.00008753303,0.00016694068,0.000021091677],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00019269653,0.00006440714,0.00008941832,0.00035526723,0.00020966436,0.000052186373,0.00014025571,0.00006397323,8.1339334e-7],"category_scores_gemma":[0.00046895203,0.000062793995,0.000024511062,0.0007711212,0.0000690211,0.00031851244,0.000084070205,0.00012087111,3.1328935e-7],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006705733,0.000021775722,0.005403515,0.00021597817,0.000021666308,1.45454e-7,0.0009109174,0.000053617117,0.01350665,0.41160122,0.0002881069,0.56796974],"study_design_scores_gemma":[0.0010579464,0.00033740708,0.0042214915,0.00043785144,0.00004846617,0.00002893099,0.00034070903,0.20152873,0.20668493,0.5396243,0.045260057,0.0004292309],"about_ca_topic_score_codex":0.000015246132,"about_ca_topic_score_gemma":0.0000021814978,"teacher_disagreement_score":0.56754047,"about_ca_system_score_codex":0.000025165877,"about_ca_system_score_gemma":0.000081169135,"threshold_uncertainty_score":0.25606647},"labels":[],"label_agreement":null}]}