{"meta":{"query_hash":"94626412b82e","filters":{"venue":"Educational Assessment"},"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/94626412b82e","api":"https://metacan.xera.ac/api/v1/cohort?venue=Educational+Assessment"},"results":[{"id":"W1999929076","doi":"10.1080/10627197.2011.584042","title":"Voices From Test-Takers: Further Evidence for Language Assessment Validation and Use","year":2011,"lang":"en","type":"article","venue":"Educational Assessment","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":56,"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":"Guangdong University of Foreign Studies; Ministry of Education, India; Ministry of Earth Sciences","keywords":"Test (biology); Language assessment; Psychology; Test validity; Scale (ratio); Coding (social sciences); Test score; Computer science; Psychometrics; Mathematics education; Standardized test; Developmental psychology","score_opus":0.14416238535195033,"score_gpt":0.4552257976525222,"score_spread":0.3110634123005719,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1999929076","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":[0.97403026,0.00030018852,0.0015928847,0.010550683,0.0011033136,0.001072566,0.00007065481,0.00007311721,0.011206351],"genre_scores_gemma":[0.94155943,0.00015377358,0.05300405,0.00026791875,0.000772633,0.00033142228,0.0001056562,0.000016937325,0.0037881832],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99835074,0.000155092,0.0002588482,0.00039361944,0.0005638489,0.0002778464],"domain_scores_gemma":[0.996206,0.0030606699,0.00019156748,0.0001979789,0.00020477736,0.00013903186],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007981853,0.00015677555,0.0001553686,0.00007561059,0.00041121343,0.00031899475,0.00025587875,0.000075164746,0.0019312112],"category_scores_gemma":[0.0004854253,0.00015149346,0.0000648942,0.00015313749,0.00013188836,0.0010562473,0.0000540769,0.000103133236,0.000024136674],"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":[0.00001592754,0.0005150101,0.9355121,0.000013006553,0.00007642732,4.885773e-7,0.032213062,8.068428e-7,0.00094858604,0.024442112,0.0037961684,0.0024662935],"study_design_scores_gemma":[0.00031712864,0.00007924424,0.9670038,0.00006335666,0.000074931115,2.0413238e-7,0.02250137,0.0000601529,0.00010872531,0.005017477,0.004552266,0.00022130254],"about_ca_topic_score_codex":0.004590329,"about_ca_topic_score_gemma":0.00073400576,"teacher_disagreement_score":0.051411163,"about_ca_system_score_codex":0.00027462622,"about_ca_system_score_gemma":0.0007396631,"threshold_uncertainty_score":0.9989812},"labels":[],"label_agreement":null},{"id":"W2072296938","doi":"10.1080/10627190802394222","title":"Validity Issues in Assessing English Language Learners' Language Proficiency","year":2008,"lang":"en","type":"article","venue":"Educational Assessment","topic":"Educational Assessment and Pedagogy","field":"Social Sciences","cited_by":47,"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":"Memorial University of Newfoundland","keywords":"Accountability; Legislation; Language proficiency; Language assessment; Psychology; English language; Pedagogy; Medical education; Mathematics education; Political science; Medicine","score_opus":0.06769468706590388,"score_gpt":0.4642791324549266,"score_spread":0.3965844453890227,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2072296938","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":[0.8618351,0.00027407068,0.000034650493,0.011620677,0.0013049114,0.00027416868,0.0000063400794,0.000065692024,0.12458434],"genre_scores_gemma":[0.973793,0.000108112035,0.0033782679,0.00025173154,0.0023930306,0.00012050659,0.00013431748,0.000015419346,0.019805588],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99759924,0.00045913455,0.00031676193,0.00036434922,0.00083122024,0.00042930664],"domain_scores_gemma":[0.9986358,0.0006841822,0.00013318982,0.00020656991,0.00019255602,0.00014769369],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0011506334,0.00015872986,0.00018940752,0.00020527343,0.00063717243,0.00013557571,0.00033490115,0.000093398994,0.0026259045],"category_scores_gemma":[0.00046175555,0.00016564083,0.00007119505,0.0005360638,0.00021916613,0.00065336144,0.000043907545,0.0002995697,0.00007027048],"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":[0.000002684473,0.00086052803,0.76778364,0.000014774939,0.000008443942,0.000008852683,0.17896527,0.000021189791,0.00021825307,0.045344364,0.006036397,0.00073557236],"study_design_scores_gemma":[0.00021252518,0.000025673296,0.76801455,0.000028518081,0.000007542934,0.0000027012354,0.20436825,0.000028418497,0.000059749233,0.0012165587,0.025770046,0.0002654959],"about_ca_topic_score_codex":0.005210772,"about_ca_topic_score_gemma":0.0014634536,"teacher_disagreement_score":0.11195788,"about_ca_system_score_codex":0.0005886259,"about_ca_system_score_gemma":0.0037652745,"threshold_uncertainty_score":0.99828583},"labels":[],"label_agreement":null},{"id":"W2086203028","doi":"10.1080/10627190802602384","title":"Identifying Potential Test Item Misalignment Using Student Verbal Reports","year":2008,"lang":"en","type":"article","venue":"Educational Assessment","topic":"Educational Strategies and Epistemologies","field":"Psychology","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre for Advancing Health Outcomes; University of Alberta","funders":"","keywords":"Ambiguity; Psychology; Cognition; Construct (python library); Test (biology); Item analysis; Confidence interval; Cognitive psychology; Applied psychology; Psychometrics; Statistics; Developmental psychology; Computer science; Mathematics","score_opus":0.08693562939927937,"score_gpt":0.43889796600229253,"score_spread":0.3519623366030131,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2086203028","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":[0.9713944,0.00042781254,0.00045401018,0.0029625872,0.007034181,0.00029108868,0.000012348366,0.000050503008,0.017373024],"genre_scores_gemma":[0.9872023,0.000021413027,0.0044016605,0.00024623764,0.0013431031,0.00016079069,0.00011920883,0.000023737633,0.0064815655],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9978017,0.00008631657,0.0005740978,0.0005215114,0.00063564576,0.00038068436],"domain_scores_gemma":[0.99862736,0.00038328732,0.00029568223,0.0003998957,0.00015794726,0.00013580763],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00028947572,0.00021208505,0.00020184838,0.00009616116,0.0005055607,0.000086701984,0.0002116672,0.00008232327,0.0037353444],"category_scores_gemma":[0.000051439463,0.00021100635,0.00011901667,0.00016886386,0.00011790744,0.00015819063,0.00008489518,0.00017835571,0.000111401954],"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":[0.0000093338485,0.0030918191,0.9190874,0.000023406748,0.00023980178,0.0003116279,0.0032368307,0.0005325554,0.0017039804,0.022535572,0.049115766,0.00011188281],"study_design_scores_gemma":[0.00018672549,0.000062522,0.9864224,0.00002216115,0.00003571622,0.0016587413,0.0054887673,0.000028140354,0.000040498828,0.0021503884,0.0036657413,0.00023817447],"about_ca_topic_score_codex":0.000494841,"about_ca_topic_score_gemma":0.000005056147,"teacher_disagreement_score":0.067335,"about_ca_system_score_codex":0.00059416145,"about_ca_system_score_gemma":0.0008488973,"threshold_uncertainty_score":0.9971754},"labels":[],"label_agreement":null},{"id":"W2523280788","doi":"10.1080/10627197.2016.1236677","title":"Approaches to Classroom Assessment Inventory: A New Instrument to Support Teacher Assessment Literacy","year":2016,"lang":"en","type":"article","venue":"Educational Assessment","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":112,"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":"Accountability; Literacy; Construct (python library); Educational assessment; Psychology; Construct validity; Mathematics education; Standards for Educational and Psychological Testing; Standardized test; Standards-based assessment; Process (computing); Authentic assessment; Pedagogy; Psychometrics; Higher education; Computer science; Political science; Education theory; Curriculum","score_opus":0.1328510477980371,"score_gpt":0.4138136676963231,"score_spread":0.28096261989828597,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2523280788","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"codex-gemma-dda1882f352a","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.30927852,0.000033405107,0.014911635,0.36437052,0.0045100856,0.003225704,0.00005206717,0.00025590978,0.30336216],"genre_scores_gemma":[0.82009065,0.000029956174,0.067322545,0.0022806055,0.0026613267,0.0011042957,0.00009056259,0.00006454351,0.106355526],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99369234,0.0005027596,0.00086074014,0.0011637593,0.0025868574,0.0011935503],"domain_scores_gemma":[0.9966627,0.00045192652,0.00030388124,0.0007284671,0.00026234594,0.0015906955],"candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.002028214,0.00052702887,0.00049784157,0.0004921709,0.0007090205,0.00068553135,0.0011602287,0.00018273835,0.01548139],"category_scores_gemma":[0.0001594285,0.00044023775,0.00024995767,0.000910048,0.00014109148,0.0009534593,0.000465869,0.00033858125,0.00086905464],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.00002856046,0.0016464771,0.4679083,0.000016602367,0.00020546667,0.0000033929766,0.007234884,0.000015375812,0.0005151807,0.24789315,0.21180186,0.06273077],"study_design_scores_gemma":[0.0009153515,0.00040994148,0.5247065,0.00010793844,0.00005839437,0.0000015967586,0.003616989,0.000023775132,0.000027674914,0.004222504,0.46525434,0.00065501116],"about_ca_topic_score_codex":0.00081102573,"about_ca_topic_score_gemma":0.00052938797,"teacher_disagreement_score":0.5108121,"about_ca_system_score_codex":0.0042622015,"about_ca_system_score_gemma":0.008313227,"threshold_uncertainty_score":0.99990886},"labels":[],"label_agreement":null},{"id":"W2975545495","doi":"10.1080/10627197.2019.1670056","title":"Toward a Teacher Professional Learning Continuum in Assessment for Learning","year":2019,"lang":"en","type":"article","venue":"Educational Assessment","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":52,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Council of Ministers of Education; Queen's University","funders":"","keywords":"Mathematics education; Assessment for learning; Professional learning community; Psychology; Pedagogy; Professional development; Observational study; Empirical research; Epistemology; Mathematics; Formative assessment","score_opus":0.033801063854011035,"score_gpt":0.43057365010553394,"score_spread":0.3967725862515229,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2975545495","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":[0.83547693,0.000058661895,0.00045763026,0.018468117,0.0028286995,0.0016423712,0.000002691561,0.00007515764,0.14098972],"genre_scores_gemma":[0.8476893,0.000019263365,0.005641949,0.00014044659,0.0007247759,0.0005816449,0.0001116243,0.00002275537,0.14506827],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99729943,0.00043838358,0.00039125362,0.00045187867,0.0008761868,0.00054285146],"domain_scores_gemma":[0.99834937,0.0009686424,0.00022376892,0.00011738212,0.00021499665,0.00012581694],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002017099,0.00019121182,0.00027583062,0.00017470724,0.00048381256,0.0001692837,0.00031987153,0.00012705219,0.0044025443],"category_scores_gemma":[0.00021771154,0.00019169555,0.00012447628,0.00030598967,0.000073664574,0.00034845097,0.000086103166,0.0006095305,0.0001070032],"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":[0.000024334431,0.0005829385,0.9368763,0.000028583208,0.00003735599,6.2963244e-7,0.0059503103,0.000104370214,0.0003577297,0.05041696,0.0044079786,0.0012125055],"study_design_scores_gemma":[0.001005154,0.000109012835,0.8243383,0.00007458145,0.000013776539,4.4814743e-7,0.027664308,0.00068127,0.000004558175,0.002396688,0.14344212,0.00026978386],"about_ca_topic_score_codex":0.0002991836,"about_ca_topic_score_gemma":0.00025432918,"teacher_disagreement_score":0.13903415,"about_ca_system_score_codex":0.00086897146,"about_ca_system_score_gemma":0.0021794639,"threshold_uncertainty_score":0.9965076},"labels":[],"label_agreement":null},{"id":"W3113373418","doi":"10.1080/10627197.2020.1858783","title":"The Effect of Linguistic Factors on Assessment of English Language Learners’ Mathematical Ability: A Differential Item Functioning Analysis","year":2020,"lang":"en","type":"article","venue":"Educational Assessment","topic":"Cognitive and developmental aspects of mathematical skills","field":"Mathematics","cited_by":25,"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 Toronto","funders":"","keywords":"Differential item functioning; Ell; Psychology; Achievement test; Test (biology); Standardized test; Mathematics education; Language proficiency; Item response theory; Confirmatory factor analysis; Item analysis; Language assessment; Linguistics; Psychometrics; Developmental psychology; Teaching method; Mathematics; Statistics; Vocabulary development","score_opus":0.021624478290005487,"score_gpt":0.3490916083046128,"score_spread":0.3274671300146073,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3113373418","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":[0.98169404,0.00001133264,0.0077585527,0.0004567842,0.00023883127,0.00045985373,0.000027513724,0.000033129174,0.009319987],"genre_scores_gemma":[0.9959021,0.00000170601,0.003550489,0.000023047312,0.00024006401,0.000068233414,0.000055446555,0.000018311475,0.00014056919],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.99767315,0.00028210657,0.0006906986,0.0003026577,0.0008398209,0.00021158808],"domain_scores_gemma":[0.983105,0.015867768,0.00034707662,0.00026381804,0.00027944375,0.00013687075],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0006599482,0.00023575316,0.0005961654,0.00009519693,0.00014455676,0.00004940426,0.00022652085,0.000054314263,0.0011619733],"category_scores_gemma":[0.011278565,0.00014646124,0.0003429452,0.00044757235,0.00012123211,0.000041885974,0.00010509806,0.00024536168,0.000007069213],"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":[0.00024263134,0.004504393,0.39743873,0.002974872,0.007652943,0.0000050198933,0.044456232,0.00012400525,0.0025133584,0.5350029,0.0012275857,0.0038573106],"study_design_scores_gemma":[0.0022776444,0.0028120119,0.83950716,0.0005499497,0.0038760512,0.0000012338102,0.016151514,0.008579496,0.014139894,0.11099636,0.00017028283,0.00093843194],"about_ca_topic_score_codex":0.00000686083,"about_ca_topic_score_gemma":0.0000031039942,"teacher_disagreement_score":0.4420684,"about_ca_system_score_codex":0.00014571234,"about_ca_system_score_gemma":0.00016672262,"threshold_uncertainty_score":0.9997511},"labels":[],"label_agreement":null}]}