{"meta":{"query_hash":"3202f460c37a","filters":{"venue":"Large-scale Assessments in Education"},"cohort_total":4,"direct_labels_cover":0,"predictions_cover":4,"exported":4,"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/3202f460c37a","api":"https://metacan.xera.ac/api/v1/cohort?venue=Large-scale+Assessments+in+Education"},"results":[{"id":"W2589097440","doi":"10.1186/s40536-017-0042-x","title":"A structural equation modeling approach for examining position effects in large-scale assessments","year":2017,"lang":"en","type":"article","venue":"Large-scale Assessments in Education","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Structural equation modeling; Position (finance); Equivalence (formal languages); Item response theory; Scale (ratio); Multilevel model; Context (archaeology); Computer science; Econometrics; Position paper; Psychometrics; Statistics; Mathematics; Machine learning","score_opus":0.34450591978879197,"score_gpt":0.5186875194954802,"score_spread":0.17418159970668823,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2589097440","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":[0.5305983,0.00006447565,0.46426615,0.00006488831,0.0016207225,0.00076209457,0.000014758581,0.000025849668,0.002582789],"genre_scores_gemma":[0.69211864,0.000008768279,0.30684033,0.0001024708,0.00020011775,0.00036618923,0.0001338015,0.000023497529,0.00020620337],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.99503636,0.00074218976,0.0011583888,0.0011453113,0.0011422146,0.00077555876],"domain_scores_gemma":[0.99399525,0.0033365183,0.0009694097,0.0012131805,0.00035343994,0.00013220457],"candidate_categories":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.009607917,0.0003111528,0.0005721632,0.0009971969,0.0007515107,0.0009065805,0.0011741315,0.00025693234,0.000028597602],"category_scores_gemma":[0.010536568,0.0002846973,0.00011170534,0.0009741644,0.000038718932,0.0018704183,0.0002772745,0.00039069657,0.0000059610134],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007775569,0.00078011904,0.8626212,0.00008078671,0.000016838825,0.0000011968041,0.0013130978,0.010171282,0.00046721095,0.0008644145,0.00012947166,0.123476654],"study_design_scores_gemma":[0.0011739118,0.000089118534,0.38934442,0.00008713156,0.000013254442,0.0000021771039,0.00431423,0.58610415,0.000043147164,0.01859403,0.000033499673,0.00020092123],"about_ca_topic_score_codex":0.00016620728,"about_ca_topic_score_gemma":0.00012574097,"teacher_disagreement_score":0.57593286,"about_ca_system_score_codex":0.00046068645,"about_ca_system_score_gemma":0.0003419928,"threshold_uncertainty_score":0.99996054},"labels":[],"label_agreement":null},{"id":"W3011227050","doi":"10.1186/s40536-020-00080-3","title":"Are large surveys of adult literacy skills as comparable over time as we think?","year":2020,"lang":"en","type":"article","venue":"Large-scale Assessments in Education","topic":"Education Systems and Policy","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Institut National de la Recherche Scientifique","funders":"Canadian Institutes of Health Research; Social Sciences and Humanities Research Council of Canada; Fonds de Recherche du Québec-Société et Culture","keywords":"Ceteris paribus; Literacy; Cohort; Adult literacy; Cohort effect; Survey data collection; Psychology; Demographic economics; Demography; Medicine; Pedagogy; Sociology; Economics; Statistics","score_opus":0.020482071847167334,"score_gpt":0.40942203019787937,"score_spread":0.38893995835071205,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3011227050","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":[0.95005494,0.00018944983,0.00013448708,0.0063668736,0.0012499985,0.0005611796,0.00008240377,0.000054180375,0.041306466],"genre_scores_gemma":[0.9828734,0.00015584963,0.00064282987,0.0031752961,0.0007096202,0.000058942765,0.0001125606,0.000022324528,0.012249192],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99707705,0.0010504375,0.00053796935,0.00035426457,0.0005463241,0.00043393343],"domain_scores_gemma":[0.9982982,0.00020942095,0.000556651,0.00029873135,0.00038437668,0.0002526045],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0013093486,0.00016512255,0.00033921804,0.00013239525,0.0002458285,0.00013793187,0.00035948024,0.00015558967,0.002385242],"category_scores_gemma":[0.00042876074,0.0001748054,0.000082734776,0.0008497009,0.000054098033,0.00069480017,0.00005194241,0.0002122532,0.0006744289],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011191406,0.0026449647,0.747181,0.000118950804,0.00003434353,9.334114e-7,0.18061148,0.000008426026,0.00013832726,0.022394832,0.044852905,0.0020026611],"study_design_scores_gemma":[0.0009574575,0.00007850242,0.5208185,0.0004150042,0.000026150748,9.764053e-7,0.08744726,0.00026694767,0.00026071107,0.003954035,0.38535175,0.00042273715],"about_ca_topic_score_codex":0.00464516,"about_ca_topic_score_gemma":0.0008774623,"teacher_disagreement_score":0.34049883,"about_ca_system_score_codex":0.00020960384,"about_ca_system_score_gemma":0.0013652829,"threshold_uncertainty_score":0.9985267},"labels":[],"label_agreement":null},{"id":"W4384942374","doi":"10.1186/s40536-023-00177-5","title":"Incorporating test-taking engagement into the item selection algorithm in low-stakes computerized adaptive tests","year":2023,"lang":"en","type":"article","venue":"Large-scale Assessments in Education","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computerized adaptive testing; Test (biology); Selection (genetic algorithm); Psychology; Computer science; Trait; Machine learning; Psychometrics; Developmental psychology","score_opus":0.22621138543561922,"score_gpt":0.48643086407962577,"score_spread":0.2602194786440065,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384942374","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":[0.8694857,0.00008672995,0.12396698,0.0006881715,0.0026853913,0.00077796594,0.000006555131,0.00014753816,0.0021549885],"genre_scores_gemma":[0.75973773,0.000017959439,0.23933049,0.00020919196,0.00020831317,0.00019121886,0.000024293808,0.000017153248,0.00026364863],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99521804,0.0015003581,0.0010471314,0.00072879344,0.0010305477,0.00047511893],"domain_scores_gemma":[0.97649634,0.021790117,0.00087928463,0.00047607286,0.00028840042,0.000069802125],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.014077806,0.00021354797,0.00033939688,0.0012656159,0.00040592017,0.00036040548,0.0007245248,0.000106701555,0.00004951039],"category_scores_gemma":[0.023254363,0.00016061502,0.000063363164,0.00912062,0.00005017805,0.0005403825,0.00028082443,0.00050020235,0.00004263187],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006795857,0.000335582,0.46743602,0.0000074958934,0.0000062074955,0.0000022440313,0.0027942935,0.0009741139,0.00028568882,0.00018102769,0.0004704804,0.52750003],"study_design_scores_gemma":[0.0003787735,0.00007571436,0.6898748,0.00011486379,0.0000040887485,0.000002052246,0.018801054,0.27498505,0.000074803494,0.014924453,0.00061387685,0.00015047615],"about_ca_topic_score_codex":0.00037966642,"about_ca_topic_score_gemma":0.0004709535,"teacher_disagreement_score":0.5273496,"about_ca_system_score_codex":0.00039717698,"about_ca_system_score_gemma":0.00040647405,"threshold_uncertainty_score":0.9849732},"labels":[],"label_agreement":null},{"id":"W4392361000","doi":"10.1186/s40536-024-00194-y","title":"An engagement-aware predictive model to evaluate problem-solving performance from the study of adult skills' (PIAAC 2012) process data","year":2024,"lang":"en","type":"article","venue":"Large-scale Assessments in Education","topic":"Online Learning and Analytics","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Task (project management); Scale (ratio); Process (computing); Learning analytics; Computer science; Test (biology); Analytics; Psychology; Artificial intelligence; Data science","score_opus":0.02761815327562231,"score_gpt":0.3969492216172661,"score_spread":0.36933106834164375,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392361000","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":[0.8527056,0.00006749991,0.14421,0.0014686311,0.0005153617,0.00071108964,0.00006337158,0.000092129645,0.00016634678],"genre_scores_gemma":[0.9721726,0.00003178727,0.026978863,0.00017017718,0.00014802632,0.000115283394,0.00016797012,0.000018201465,0.0001970595],"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9977825,0.00026796022,0.00038037886,0.0007231162,0.0005759831,0.00027001635],"domain_scores_gemma":[0.9981644,0.00010679634,0.00012296626,0.0012741495,0.0002600917,0.00007155884],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011588716,0.00016503561,0.00016614934,0.00013742823,0.00016546504,0.00024607655,0.0017816301,0.000046854173,0.000008685558],"category_scores_gemma":[0.00005151491,0.00012779974,0.00001906192,0.0007377678,0.000015178437,0.0018988851,0.00044613658,0.00039277226,0.000009360037],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028458358,0.011995597,0.32085007,0.00032885367,0.00021195016,0.0000022416557,0.14816414,0.38350734,0.000102925274,0.00068493246,0.0029666189,0.13115686],"study_design_scores_gemma":[0.00022831545,0.00024410248,0.049473066,0.0003608333,0.000047813894,3.1337137e-7,0.010184194,0.9381561,0.00002029974,0.0010688093,0.000081428036,0.00013471073],"about_ca_topic_score_codex":0.00012550179,"about_ca_topic_score_gemma":0.00021095367,"teacher_disagreement_score":0.55464876,"about_ca_system_score_codex":0.000096987606,"about_ca_system_score_gemma":0.00079246325,"threshold_uncertainty_score":0.5211522},"labels":[],"label_agreement":null}]}