{"meta":{"query_hash":"e405b7fc60cc","filters":{"venue":"Evaluation & Research in Education"},"cohort_total":6,"direct_labels_cover":0,"predictions_cover":6,"exported":6,"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/e405b7fc60cc","api":"https://metacan.xera.ac/api/v1/cohort?venue=Evaluation+%26+Research+in+Education"},"results":[{"id":"W1986795511","doi":"10.1080/09500790308668296","title":"Home Education in Quebec: Family First","year":2003,"lang":"en","type":"article","venue":"Evaluation & Research in Education","topic":"Diverse Education Studies and Reforms","field":"Social Sciences","cited_by":38,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Curriculum; Home education; Sociology; Context (archaeology); Politics; Portrait; Population; State (computer science); Pedagogy; Gender studies; Psychology; Political science; Geography; Law","score_opus":0.18193108795141977,"score_gpt":0.5187662292371854,"score_spread":0.33683514128576564,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1986795511","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":[0.6806825,0.0018145115,0.000005871863,0.0173794,0.0039953953,0.0015477034,0.000001044823,0.000021832167,0.29455173],"genre_scores_gemma":[0.96743274,0.00124457,0.00026632735,0.0002313274,0.0004516781,0.0008995608,0.000034303936,0.000012360512,0.02942715],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9956241,0.0015612658,0.0003583553,0.00036147266,0.0015908021,0.00050400855],"domain_scores_gemma":[0.99800676,0.00023222041,0.00008787464,0.00026545124,0.001261347,0.00014632255],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01161382,0.000101002355,0.00012936197,0.00097310083,0.0006487056,0.00018429058,0.00023420196,0.00012117962,0.00085026986],"category_scores_gemma":[0.0020162596,0.00009780068,0.000035446068,0.0022582477,0.00024102315,0.00068778003,0.000025859037,0.00030269995,0.0004077589],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020116726,0.0025573536,0.0816356,0.000046709534,0.000009665468,3.171705e-7,0.08449107,0.00015031679,0.000028132261,0.18683928,0.08699909,0.55722237],"study_design_scores_gemma":[0.00029145734,0.000017420545,0.21410908,0.00009349908,0.0000033936608,1.8541571e-7,0.2461735,0.00003144654,0.00000651067,0.023254404,0.5158899,0.00012920653],"about_ca_topic_score_codex":0.117287144,"about_ca_topic_score_gemma":0.17352009,"teacher_disagreement_score":0.55709314,"about_ca_system_score_codex":0.0032663022,"about_ca_system_score_gemma":0.020240149,"threshold_uncertainty_score":0.9853142},"labels":[],"label_agreement":null},{"id":"W2005737134","doi":"10.1080/09500790308668292","title":"Homeschooling and Canadian Educational Politics: Rights, Pluralism and Pedagogical Individualism","year":2003,"lang":"en","type":"article","venue":"Evaluation & Research in Education","topic":"Diverse Education Studies and Reforms","field":"Social Sciences","cited_by":40,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"McMaster University","funders":"","keywords":"Individualism; Pluralism (philosophy); Politics; Sociology; Cultural pluralism; Pedagogy; Political science; Epistemology; Law; Philosophy","score_opus":0.3485658580605485,"score_gpt":0.5438291850275195,"score_spread":0.19526332696697102,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2005737134","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":[0.8261289,0.0020372153,9.065619e-7,0.05418884,0.0011341777,0.0007383405,0.000006054698,0.000009035734,0.11575656],"genre_scores_gemma":[0.9923241,0.00065737515,0.0003295549,0.0002770655,0.0005526895,0.00019409791,0.000038351274,0.000006248228,0.0056204847],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9969937,0.0009985028,0.00021128813,0.00029390966,0.0010136003,0.0004889855],"domain_scores_gemma":[0.9982385,0.00027554095,0.000047474896,0.00012445501,0.00084530655,0.00046871576],"candidate_categories":["sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0069427616,0.000085759646,0.00009933462,0.0006751645,0.0015556706,0.00024821734,0.00010570125,0.00010787323,0.0009415941],"category_scores_gemma":[0.0017721452,0.00007628262,0.000015587713,0.0006170807,0.00041347832,0.00037574998,0.000022556549,0.00026079523,0.000052633208],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000015488457,0.000119599514,0.026039064,0.000010062595,0.000009946126,2.1665326e-7,0.06604984,0.0000031436975,0.0000023883817,0.88291436,0.0093859555,0.015463885],"study_design_scores_gemma":[0.0002628654,0.000016456617,0.1613327,0.000042734515,0.000008981756,0.0000028306658,0.12050907,0.000018205554,0.00000337065,0.21821737,0.49944428,0.00014113261],"about_ca_topic_score_codex":0.20061581,"about_ca_topic_score_gemma":0.1012197,"teacher_disagreement_score":0.664697,"about_ca_system_score_codex":0.0010644064,"about_ca_system_score_gemma":0.008138738,"threshold_uncertainty_score":0.9999717},"labels":[],"label_agreement":null},{"id":"W2013836468","doi":"10.1080/09500790.2010.490875","title":"Assessment use, self-efficacy and mathematics achievement: comparative analysis of PISA 2003 data of Finland, Canada and the USA","year":2010,"lang":"en","type":"article","venue":"Evaluation & Research in Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Division of Mathematical Sciences","keywords":"Student achievement; Mathematics education; Academic achievement; Psychology; Test (biology); Achievement test; Standardized test; Pedagogy","score_opus":0.27445317848692796,"score_gpt":0.5499734689545585,"score_spread":0.2755202904676305,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2013836468","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":[0.9928948,0.00006547527,0.000017999277,0.0017847428,0.00013459088,0.0010003843,0.00001734194,0.0000014508355,0.004083178],"genre_scores_gemma":[0.996965,0.00018690998,0.0023876557,0.00001706957,0.000038517603,0.000056892786,0.000082343075,0.0000020796767,0.00026353172],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9968417,0.0010273593,0.00029617277,0.00018518747,0.0015016766,0.00014786406],"domain_scores_gemma":[0.99686074,0.0014208201,0.00017528802,0.00034107442,0.0011501199,0.000051963347],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011580428,0.00005610737,0.00018942398,0.00024932722,0.00021182052,0.00008319369,0.00029665156,0.000034966128,0.00021211742],"category_scores_gemma":[0.0011453219,0.000042913067,0.000009314172,0.0018425072,0.00034404284,0.00025075383,0.000106395426,0.00019007885,6.710512e-7],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000031130512,0.0012119007,0.8807703,0.00003992162,0.00038843995,6.104295e-8,0.044249635,0.00005675967,0.0002637191,0.062019393,0.00412392,0.0068447976],"study_design_scores_gemma":[0.0005699018,0.000015628511,0.9640101,0.000013732543,0.0001777702,3.438608e-8,0.016390882,0.016013406,0.000009377681,0.00052878645,0.0022261858,0.000044148546],"about_ca_topic_score_codex":0.37347364,"about_ca_topic_score_gemma":0.8909272,"teacher_disagreement_score":0.51745355,"about_ca_system_score_codex":0.00013788702,"about_ca_system_score_gemma":0.0040447824,"threshold_uncertainty_score":0.717527},"labels":[],"label_agreement":null},{"id":"W2015487218","doi":"10.2167/eri413.0","title":"Problematising Discourse Completion Tasks: Voices from Verbal Report","year":2008,"lang":"en","type":"article","venue":"Evaluation & Research in Education","topic":"Language, Discourse, Communication Strategies","field":"Arts and Humanities","cited_by":38,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"British Academy; Ontario Council on Graduate Studies, Council of Ontario Universities","keywords":"Psychology; Pragmatics; Respondent; Task (project management); Perspective (graphical); Protocol analysis; Focus (optics); Discourse analysis; Conjunction (astronomy); Linguistics; Computer science; Cognitive science","score_opus":0.35858020914276917,"score_gpt":0.5021252802466025,"score_spread":0.14354507110383335,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2015487218","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":[0.89123154,0.0016762629,0.000074773096,0.009937999,0.0008594215,0.0012659392,0.000024207106,0.00007714514,0.094852686],"genre_scores_gemma":[0.9938571,0.00010760438,0.00075367437,0.00006933239,0.0009276346,0.0006248598,0.0012312237,0.000023814224,0.0024047552],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9956539,0.0013177159,0.00059892854,0.00039344205,0.0017056401,0.00033032123],"domain_scores_gemma":[0.9971707,0.00034234035,0.0002544206,0.00078758376,0.0013632922,0.00008167824],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0040575857,0.0001472911,0.00018846369,0.00047088566,0.0008321106,0.00036559987,0.00037916517,0.00005936698,0.0034490654],"category_scores_gemma":[0.00052659377,0.00013883054,0.00004753624,0.0002666117,0.00063381676,0.001193216,0.00008141413,0.00040176496,0.0003366256],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011389809,0.0030193047,0.010631863,0.0001533684,0.00010641359,0.00003493864,0.52578175,0.00072834914,0.0012372119,0.29268005,0.08645426,0.07905858],"study_design_scores_gemma":[0.0019110461,0.00020155871,0.14168546,0.0010874235,0.00008978108,0.00007475933,0.48534146,0.00936563,0.00036981216,0.24020626,0.11874284,0.0009239598],"about_ca_topic_score_codex":0.009061531,"about_ca_topic_score_gemma":0.006137787,"teacher_disagreement_score":0.1310536,"about_ca_system_score_codex":0.00048799894,"about_ca_system_score_gemma":0.0017726589,"threshold_uncertainty_score":0.9975372},"labels":[],"label_agreement":null},{"id":"W2017441749","doi":"10.1080/09500790.2010.489150","title":"English language immersion and students' academic achievement in English, Chinese and mathematics","year":2010,"lang":"en","type":"article","venue":"Evaluation & Research in Education","topic":"Second Language Learning and Teaching","field":"Arts and Humanities","cited_by":46,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Mathematics education; Competence (human resources); English language; Psychology; Academic achievement; Chinese language; Pedagogy; Linguistics","score_opus":0.05915999621493336,"score_gpt":0.4322044878152381,"score_spread":0.3730444916003048,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2017441749","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":[0.992073,0.0008659807,7.147596e-7,0.0005492549,0.00063144095,0.0004974495,0.0000016599788,0.00002210743,0.005358374],"genre_scores_gemma":[0.9978856,0.00006360858,0.000118732474,0.00006678157,0.0008019366,0.00012257842,0.000045132732,0.000012974281,0.00088265055],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9982907,0.00038784157,0.00023534647,0.00022783862,0.00064682105,0.00021141191],"domain_scores_gemma":[0.99918944,0.0002909198,0.00005813139,0.00015826941,0.00024019608,0.000063055806],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0071494957,0.00009043907,0.00010358742,0.0004932359,0.00017966614,0.0002089543,0.00013028795,0.00007004155,0.00070319895],"category_scores_gemma":[0.0017716232,0.00007913643,0.000011368893,0.00011782158,0.0001022735,0.000320716,0.00007552641,0.001080994,0.00001132094],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010190391,0.00031931707,0.057940062,0.00006653218,0.0000051989896,5.896129e-7,0.7979133,0.0000044770545,0.0007565032,0.0054384777,0.00022975224,0.13731559],"study_design_scores_gemma":[0.00115058,0.000079117184,0.11418729,0.00019626848,0.000011407711,0.0000014555272,0.87442124,0.002142106,0.00005307938,0.0023268035,0.0052298945,0.00020073183],"about_ca_topic_score_codex":0.0009630655,"about_ca_topic_score_gemma":0.0022385304,"teacher_disagreement_score":0.13711485,"about_ca_system_score_codex":0.00008417456,"about_ca_system_score_gemma":0.000119439326,"threshold_uncertainty_score":0.76995355},"labels":[],"label_agreement":null},{"id":"W2171520323","doi":"10.1080/09500790308668302","title":"Creating Policy from Discursive Exchanges on Compulsory Education and Schooling in Sweden","year":2003,"lang":"en","type":"article","venue":"Evaluation & Research in Education","topic":"Youth Education and Societal Dynamics","field":"Social Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Compulsory education; Sociology; Political science; Pedagogy; Mathematics education; Psychology","score_opus":0.19482477800802223,"score_gpt":0.5412948480369557,"score_spread":0.3464700700289335,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2171520323","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":[0.91293734,0.0011617427,0.000012232757,0.013128483,0.0008815339,0.001003314,0.000003115701,0.00001637637,0.07085586],"genre_scores_gemma":[0.9957579,0.0005275552,0.0007775664,0.00032987248,0.0006584787,0.00041810633,0.00009625401,0.00001361354,0.00142065],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99492615,0.0029301154,0.00028646603,0.0003788693,0.0010924801,0.00038593516],"domain_scores_gemma":[0.9982178,0.00067128916,0.00010039828,0.0002074736,0.00062193087,0.00018109924],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00703286,0.00010463308,0.00012574368,0.0008672339,0.00054498407,0.00021212206,0.00015936285,0.00013209043,0.00022095977],"category_scores_gemma":[0.0068132514,0.000117425734,0.000024835545,0.0014536513,0.00019557583,0.0003963283,0.000021309066,0.00040908935,0.000050864473],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022836637,0.0020051082,0.10021038,0.000036346337,0.000010582544,2.3315386e-7,0.38997114,0.00038019056,0.00012960739,0.21500723,0.0020927282,0.2901336],"study_design_scores_gemma":[0.0004397323,0.00004130509,0.38264838,0.0003440551,0.0000070483147,4.578277e-7,0.45706233,0.0014873509,0.000026344538,0.15183075,0.0059043947,0.0002078453],"about_ca_topic_score_codex":0.022870481,"about_ca_topic_score_gemma":0.0069527025,"teacher_disagreement_score":0.28992575,"about_ca_system_score_codex":0.00213942,"about_ca_system_score_gemma":0.0084721465,"threshold_uncertainty_score":0.9971489},"labels":[],"label_agreement":null}]}