{"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","author_layer_release":"2026-06-26"},"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","authors":[{"name":"Atsushi Mizumoto","is_ca":false},{"name":"Geoffrey G. Pinchbeck","is_ca":true},{"name":"Stuart McLean","is_ca":false}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005781513,0.0009741817,0.001166726,0.006157673,0.0006848416,0.003932679,0.001533741,0.0008700316,0.02486857],"category_scores_gemma":[0.05699515,0.0005514302,0.0007103061,0.004124746,0.000766936,0.00713972,0.004260314,0.001343695,0.009327418],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009235704,"about_ca_system_score_gemma":0.001188064,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001608206,"about_ca_topic_score_gemma":0.00187355,"domain_scores_codex":[0.9897251,0.002628304,0.002206363,0.001729409,0.003331597,0.0003792616],"domain_scores_gemma":[0.9547529,0.0262996,0.002680075,0.006472718,0.008846566,0.0009481318],"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":[0.00327292,0.0006715205,0.02422065,0.001596085,0.0001834053,0.0007535581,0.002779332,0.003568123,0.02933797,0.02040148,0.03915177,0.8740633],"study_design_scores_gemma":[0.001055482,0.002844918,0.09248458,0.001376155,0.0005048329,0.003555439,0.006326374,0.1317481,0.2018105,0.07236985,0.485093,0.0008306551],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4092222,0.001716289,0.425034,0.0006482492,0.001900153,0.001921796,0.02165362,0.07693979,0.06096397],"genre_scores_gemma":[0.5491101,0.0004607267,0.3942962,0.0007471761,0.0002005946,0.001654434,0.02858537,0.009077246,0.01586809],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02486857,"threshold_uncertainty_score":0.08319366,"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","authors":[{"name":"Stuart McLean","is_ca":false},{"name":"Paul Raine","is_ca":false},{"name":"Geoffrey G. Pinchbeck","is_ca":true},{"name":"Laura Huston","is_ca":false},{"name":"Young Ae Kim","is_ca":false},{"name":"S Nishiyama","is_ca":false},{"name":"S. Ueno","is_ca":false}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0372174,0.0006705064,0.001060105,0.002276311,0.0007193866,0.002048883,0.001420195,0.001048167,0.001615588],"category_scores_gemma":[0.08160827,0.0005987172,0.002269783,0.001420014,0.00150849,0.001605519,0.00174827,0.001238017,0.0008611353],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006630218,"about_ca_system_score_gemma":0.000643788,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009691895,"about_ca_topic_score_gemma":0.001365062,"domain_scores_codex":[0.9741002,0.008392019,0.004314699,0.003430783,0.00914095,0.0006212521],"domain_scores_gemma":[0.8820125,0.0718283,0.01281792,0.009709579,0.02242536,0.001206283],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001165309,0.001004264,0.915759,0.0005284944,0.001021986,0.0001817226,0.0112631,0.001439107,0.003138537,0.001039757,0.001579048,0.06187969],"study_design_scores_gemma":[0.0001253022,0.001835084,0.9773406,0.0002538093,0.000328259,0.0005727464,0.00304664,0.007226387,0.004041378,0.001519408,0.003604031,0.0001063253],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9861333,0.0005055677,0.007948698,0.0001428496,0.0001351656,0.0005129925,0.0004827136,0.0001087595,0.004029976],"genre_scores_gemma":[0.9908842,0.0001400447,0.006257243,0.0000974869,0.00005118972,0.0008335109,0.0007545438,0.00007136063,0.0009105337],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9627826,"threshold_uncertainty_score":0.1968268,"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","authors":[{"name":"Stuart Webb","is_ca":true},{"name":"Anna C-S Chang","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.06017132,0.001193856,0.001917929,0.004647068,0.01450795,0.01195724,0.009152063,0.03184517,0.002890629],"category_scores_gemma":[0.2303646,0.00115284,0.002197274,0.005565421,0.04264074,0.01733484,0.008834268,0.06758147,0.001398514],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.01918621,"about_ca_system_score_gemma":0.02902493,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.08404698,"about_ca_topic_score_gemma":0.1282448,"domain_scores_codex":[0.9476202,0.02744796,0.007645228,0.005229817,0.009810089,0.002246677],"domain_scores_gemma":[0.5038763,0.4360803,0.009416997,0.005560629,0.03819112,0.00687464],"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":[0.0001044209,0.00003262941,0.0007704637,0.001989416,0.00005673005,0.0006776648,0.0417599,0.00006858546,0.0002662638,0.03608104,0.9006745,0.01751829],"study_design_scores_gemma":[0.00006357332,0.00009521405,0.002304936,0.009110915,0.00007029105,0.0006763078,0.04557808,0.0001020827,0.000660228,0.01297647,0.928212,0.0001496619],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"commentary","genre_gemma":"commentary","genre_scores_codex":[0.0004295033,0.02312236,0.0001789257,0.9488839,0.0261635,0.0000136447,0.0000415971,0.000006693861,0.001159908],"genre_scores_gemma":[0.01526597,0.02080976,0.0008011045,0.9216983,0.03872383,0.0002027897,0.00004656262,0.00009324543,0.002358547],"genre_candidate":"commentary","genre_consensus":"commentary","teacher_disagreement_score":0.08404698,"threshold_uncertainty_score":0.3182201,"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","authors":[{"name":"Dale Brown","is_ca":false},{"name":"Phil Bennett","is_ca":false},{"name":"Geoffrey G. Pinchbeck","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008165122,0.001038048,0.0009440486,0.009019487,0.001128406,0.003061077,0.001011741,0.0008949396,0.00796966],"category_scores_gemma":[0.07812022,0.0003248422,0.0009354665,0.013957,0.001439105,0.004710197,0.003063668,0.001972039,0.001820873],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001447642,"about_ca_system_score_gemma":0.001228366,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005324838,"about_ca_topic_score_gemma":0.004831035,"domain_scores_codex":[0.993077,0.002530953,0.0008542324,0.0009558487,0.002285046,0.0002968158],"domain_scores_gemma":[0.9177635,0.05929927,0.007496301,0.007727487,0.006405536,0.001307925],"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":[0.0005789652,0.0005082922,0.2903005,0.001930521,0.0004895527,0.0002839191,0.01280138,0.008608235,0.01785113,0.07131597,0.02020771,0.5751239],"study_design_scores_gemma":[0.00006524168,0.001517391,0.6604934,0.0008373758,0.0001423191,0.001247692,0.0107191,0.03416347,0.02031811,0.1015822,0.1685704,0.000343315],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.6041061,0.005890677,0.2885653,0.001327173,0.0002445187,0.001275668,0.03502372,0.004056104,0.05951074],"genre_scores_gemma":[0.7710347,0.0008539187,0.2063296,0.0001096501,0.00005892229,0.002185453,0.01537628,0.001022539,0.003028913],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.009019487,"threshold_uncertainty_score":0.04318178,"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","authors":[{"name":"Geoffrey G. Pinchbeck","is_ca":true}],"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.08787927,0.001144558,0.001395295,0.01301706,0.003063321,0.005891575,0.003733407,0.00200627,0.001656912],"category_scores_gemma":[0.2880566,0.0005561543,0.001737147,0.008256751,0.01328512,0.01180594,0.006987584,0.002584715,0.0005390042],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004772112,"about_ca_system_score_gemma":0.005676786,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005698729,"about_ca_topic_score_gemma":0.004575738,"domain_scores_codex":[0.9291843,0.03915319,0.01136939,0.005264262,0.0134738,0.00155509],"domain_scores_gemma":[0.6967593,0.1847758,0.02189424,0.02632156,0.06725626,0.002992875],"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":[0.0009301573,0.001046547,0.2967831,0.002029277,0.0004482725,0.0004351453,0.05842085,0.003471646,0.006133949,0.2395835,0.005275185,0.3854423],"study_design_scores_gemma":[0.0005139565,0.003846768,0.4097274,0.002794118,0.0006202832,0.0008758431,0.05216435,0.0512885,0.02202674,0.4051503,0.05028593,0.000705881],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3996097,0.00184052,0.523079,0.006380825,0.000408123,0.00522763,0.0008704565,0.0009051047,0.06167871],"genre_scores_gemma":[0.8052281,0.0001670183,0.1887023,0.0003443394,0.00009601301,0.003865782,0.00052648,0.0001550169,0.0009149773],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.08787927,"threshold_uncertainty_score":0.4647555,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}