{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":6,"total_is_capped":false,"direct_labels_cover":0,"predictions_cover":6,"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"},"query_hash":"94626412b82e","filters":{"venue":"Educational Assessment"}},"results":[{"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.1328510477980371,"gpt":0.4138136676963231,"spread":0.280962619898286,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.002028214,0.0005270289,0.0004978416,0.0004921709,0.0007090205,0.0006855314,0.001160229,0.0001827384,0.01548139],"category_scores_gemma":[0.0001594285,0.0004402378,0.0002499577,0.000910048,0.0001410915,0.0009534593,0.000465869,0.0003385812,0.0008690546],"about_ca_system_candidate":true,"about_ca_system_consensus":true,"about_ca_system_score_codex":0.004262201,"about_ca_system_score_gemma":0.008313227,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008110257,"about_ca_topic_score_gemma":0.000529388,"domain_scores_codex":[0.9936923,0.0005027596,0.0008607401,0.001163759,0.002586857,0.00119355],"domain_scores_gemma":[0.9966627,0.0004519265,0.0003038812,0.0007284671,0.0002623459,0.001590695],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00002856046,0.001646477,0.4679083,0.00001660237,0.0002054667,0.000003392977,0.007234884,0.00001537581,0.0005151807,0.2478932,0.2118019,0.06273077],"study_design_scores_gemma":[0.0009153515,0.0004099415,0.5247065,0.0001079384,0.00005839437,0.000001596759,0.003616989,0.00002377513,0.00002767491,0.004222504,0.4652543,0.0006550112],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.3092785,0.00003340511,0.01491163,0.3643705,0.004510086,0.003225704,0.00005206717,0.0002559098,0.3033622],"genre_scores_gemma":[0.8200907,0.00002995617,0.06732254,0.002280605,0.002661327,0.001104296,0.00009056259,0.00006454351,0.1063555],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5108121,"threshold_uncertainty_score":0.9999089,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.1441623853519503,"gpt":0.4552257976525222,"spread":0.3110634123005719,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007981853,0.0001567756,0.0001553686,0.00007561059,0.0004112134,0.0003189947,0.0002558788,0.00007516475,0.001931211],"category_scores_gemma":[0.0004854253,0.0001514935,0.0000648942,0.0001531375,0.0001318884,0.001056247,0.0000540769,0.0001031332,0.00002413667],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002746262,"about_ca_system_score_gemma":0.0007396631,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004590329,"about_ca_topic_score_gemma":0.0007340058,"domain_scores_codex":[0.9983507,0.000155092,0.0002588482,0.0003936194,0.0005638489,0.0002778464],"domain_scores_gemma":[0.996206,0.00306067,0.0001915675,0.0001979789,0.0002047774,0.0001390319],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00001592754,0.0005150101,0.9355121,0.00001300655,0.00007642732,4.885773e-7,0.03221306,8.068428e-7,0.000948586,0.02444211,0.003796168,0.002466294],"study_design_scores_gemma":[0.0003171286,0.00007924424,0.9670038,0.00006335666,0.00007493111,2.041324e-7,0.02250137,0.0000601529,0.0001087253,0.005017477,0.004552266,0.0002213025],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9740303,0.0003001885,0.001592885,0.01055068,0.001103314,0.001072566,0.00007065481,0.00007311721,0.01120635],"genre_scores_gemma":[0.9415594,0.0001537736,0.05300405,0.0002679187,0.000772633,0.0003314223,0.0001056562,0.00001693733,0.003788183],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05141116,"threshold_uncertainty_score":0.9989812,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.03380106385401103,"gpt":0.4305736501055339,"spread":0.3967725862515229,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002017099,0.0001912118,0.0002758306,0.0001747072,0.0004838126,0.0001692837,0.0003198715,0.0001270522,0.004402544],"category_scores_gemma":[0.0002177115,0.0001916956,0.0001244763,0.0003059897,0.00007366457,0.000348451,0.00008610317,0.0006095305,0.0001070032],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008689715,"about_ca_system_score_gemma":0.002179464,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002991836,"about_ca_topic_score_gemma":0.0002543292,"domain_scores_codex":[0.9972994,0.0004383836,0.0003912536,0.0004518787,0.0008761868,0.0005428515],"domain_scores_gemma":[0.9983494,0.0009686424,0.0002237689,0.0001173821,0.0002149966,0.0001258169],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00002433443,0.0005829385,0.9368763,0.00002858321,0.00003735599,6.296324e-7,0.00595031,0.0001043702,0.0003577297,0.05041696,0.004407979,0.001212506],"study_design_scores_gemma":[0.001005154,0.0001090128,0.8243383,0.00007458145,0.00001377654,4.481474e-7,0.02766431,0.00068127,0.000004558175,0.002396688,0.1434421,0.0002697839],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8354769,0.0000586619,0.0004576303,0.01846812,0.0028287,0.001642371,0.000002691561,0.00007515764,0.1409897],"genre_scores_gemma":[0.8476893,0.00001926337,0.005641949,0.0001404466,0.0007247759,0.0005816449,0.0001116243,0.00002275537,0.1450683],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1390342,"threshold_uncertainty_score":0.9965076,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.06769468706590388,"gpt":0.4642791324549266,"spread":0.3965844453890227,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001150633,0.0001587299,0.0001894075,0.0002052734,0.0006371724,0.0001355757,0.0003349012,0.00009339899,0.002625905],"category_scores_gemma":[0.0004617556,0.0001656408,0.00007119505,0.0005360638,0.0002191661,0.0006533614,0.00004390754,0.0002995697,0.00007027048],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005886259,"about_ca_system_score_gemma":0.003765275,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005210772,"about_ca_topic_score_gemma":0.001463454,"domain_scores_codex":[0.9975992,0.0004591345,0.0003167619,0.0003643492,0.0008312202,0.0004293066],"domain_scores_gemma":[0.9986358,0.0006841822,0.0001331898,0.0002065699,0.000192556,0.0001476937],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000002684473,0.000860528,0.7677836,0.00001477494,0.000008443942,0.000008852683,0.1789653,0.00002118979,0.0002182531,0.04534436,0.006036397,0.0007355724],"study_design_scores_gemma":[0.0002125252,0.0000256733,0.7680146,0.00002851808,0.000007542934,0.000002701235,0.2043682,0.0000284185,0.00005974923,0.001216559,0.02577005,0.0002654959],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8618351,0.0002740707,0.00003465049,0.01162068,0.001304911,0.0002741687,0.000006340079,0.00006569202,0.1245843],"genre_scores_gemma":[0.973793,0.000108112,0.003378268,0.0002517315,0.002393031,0.0001205066,0.0001343175,0.00001541935,0.01980559],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1119579,"threshold_uncertainty_score":0.9982858,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.02162447829000549,"gpt":0.3490916083046128,"spread":0.3274671300146073,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0006599482,0.0002357532,0.0005961654,0.00009519693,0.0001445568,0.00004940426,0.0002265208,0.00005431426,0.001161973],"category_scores_gemma":[0.01127857,0.0001464612,0.0003429452,0.0004475724,0.0001212321,0.00004188597,0.0001050981,0.0002453617,0.000007069213],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001457123,"about_ca_system_score_gemma":0.0001667226,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000686083,"about_ca_topic_score_gemma":0.000003103994,"domain_scores_codex":[0.9976732,0.0002821066,0.0006906986,0.0003026577,0.0008398209,0.0002115881],"domain_scores_gemma":[0.983105,0.01586777,0.0003470766,0.000263818,0.0002794437,0.0001368707],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.0002426313,0.004504393,0.3974387,0.002974872,0.007652943,0.000005019893,0.04445623,0.0001240053,0.002513358,0.5350029,0.001227586,0.003857311],"study_design_scores_gemma":[0.002277644,0.002812012,0.8395072,0.0005499497,0.003876051,0.00000123381,0.01615151,0.008579496,0.01413989,0.1109964,0.0001702828,0.0009384319],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.981694,0.00001133264,0.007758553,0.0004567842,0.0002388313,0.0004598537,0.00002751372,0.00003312917,0.009319987],"genre_scores_gemma":[0.9959021,0.00000170601,0.003550489,0.00002304731,0.000240064,0.00006823341,0.00005544656,0.00001831148,0.0001405692],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4420684,"threshold_uncertainty_score":0.9997511,"prediction_status":"machine_predicted_unvalidated"},"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,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"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","retraction":null,"screen_n_in":null,"score":{"opus":0.08693562939927937,"gpt":0.4388979660022925,"spread":0.3519623366030131,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0002894757,0.0002120851,0.0002018484,0.00009616116,0.0005055607,0.00008670198,0.0002116672,0.00008232327,0.003735344],"category_scores_gemma":[0.00005143946,0.0002110064,0.0001190167,0.0001688639,0.0001179074,0.0001581906,0.00008489518,0.0001783557,0.000111402],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005941615,"about_ca_system_score_gemma":0.0008488973,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000494841,"about_ca_topic_score_gemma":0.000005056147,"domain_scores_codex":[0.9978017,0.00008631657,0.0005740978,0.0005215114,0.0006356458,0.0003806844],"domain_scores_gemma":[0.9986274,0.0003832873,0.0002956822,0.0003998957,0.0001579473,0.0001358076],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000009333849,0.003091819,0.9190874,0.00002340675,0.0002398018,0.0003116279,0.003236831,0.0005325554,0.00170398,0.02253557,0.04911577,0.0001118828],"study_design_scores_gemma":[0.0001867255,0.000062522,0.9864224,0.00002216115,0.00003571622,0.001658741,0.005488767,0.00002814035,0.00004049883,0.002150388,0.003665741,0.0002381745],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9713944,0.0004278125,0.0004540102,0.002962587,0.007034181,0.0002910887,0.00001234837,0.00005050301,0.01737302],"genre_scores_gemma":[0.9872023,0.00002141303,0.004401661,0.0002462376,0.001343103,0.0001607907,0.0001192088,0.00002373763,0.006481566],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.067335,"threshold_uncertainty_score":0.9971754,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}