{"meta":{"page":1,"per_page":50,"max_per_page":100,"total":860,"total_is_capped":false,"direct_labels_cover":1,"predictions_cover":860,"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":"028605329201","filters":{"topic":"Student Assessment and Feedback"}},"results":[{"id":"W2624412722","doi":"10.3102/0034654316689306","title":"Rethinking the Use of Tests: A Meta-Analysis of Practice Testing","year":2017,"lang":"en","type":"article","venue":"Review of Educational Research","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":536,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Simon Fraser University","funders":"","keywords":"Psychology; Meta-analysis; Test (biology); Best practice; Presentation (obstetrics); Mathematics education; Applied psychology; Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.7954275058930537,"gpt":0.643213236651155,"spread":0.1522142692418986,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01333356,0.00005219842,0.0004587626,0.0001412096,0.0006692388,0.00008326961,0.0009011544,0.00002788055,0.0014831],"category_scores_gemma":[0.1543893,0.00003318381,0.0003584912,0.001219851,0.0007048753,0.0003956729,0.0001572289,0.0001771927,0.000007481653],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004670007,"about_ca_system_score_gemma":0.001123243,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006231942,"about_ca_topic_score_gemma":0.0004336831,"domain_scores_codex":[0.9963712,0.001128286,0.0004194855,0.0001411301,0.001776495,0.0001633773],"domain_scores_gemma":[0.9671686,0.02814018,0.0007928132,0.0006104821,0.003246295,0.00004163515],"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":[0.00002744297,0.001441232,0.2150051,0.00393856,0.07487441,8.058294e-7,0.03111603,0.00002031982,0.0003698409,0.6287912,0.03585434,0.00856071],"study_design_scores_gemma":[0.0001640399,0.0001353945,0.5232499,0.002957338,0.1197802,9.254803e-7,0.007367696,0.00008137718,0.00005583377,0.01051603,0.335398,0.0002933253],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.03606445,0.2325587,0.00001237089,0.3699527,0.0002572706,0.002796807,0.00006019995,0.000007462227,0.35829],"genre_scores_gemma":[0.8991355,0.07381168,0.01773002,0.0005213657,0.0002724349,0.0001530594,0.0000148891,0.00001342292,0.008347641],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.863071,"threshold_uncertainty_score":0.9994297,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2885480655","doi":"10.1111/medu.13645","title":"Assessment, feedback and the alchemy of learning","year":2018,"lang":"en","type":"article","venue":"Medical Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":416,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto; Western University","funders":"","keywords":"Formative assessment; Summative assessment; Competence (human resources); CLARITY; Assessment for learning; Judgement; Psychology; Peer feedback; Pedagogy; Medical education; Social psychology; Medicine; Political science","retraction":null,"screen_n_in":null,"score":{"opus":0.01469089774875304,"gpt":0.3976035401559191,"spread":0.3829126424071661,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001473357,0.00003749304,0.0000799803,0.00002239707,0.0002969926,0.00003042952,0.000147506,0.00005287528,0.00134963],"category_scores_gemma":[0.001070233,0.00002522231,0.00002099733,0.0001574883,0.001091849,0.00006762557,0.0000345936,0.0001123649,0.00001689747],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002382253,"about_ca_system_score_gemma":0.0007435432,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006289145,"about_ca_topic_score_gemma":0.0001685428,"domain_scores_codex":[0.9990102,0.0001939758,0.0001164386,0.00008603642,0.0004868904,0.0001064396],"domain_scores_gemma":[0.9995126,0.0002008571,0.00007165873,0.0000596274,0.00009791645,0.00005736945],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00003546731,0.0003212567,0.3868549,0.00002110278,0.0000457952,1.5402e-7,0.06734312,7.316738e-8,0.00008167806,0.3550224,0.03715706,0.1531171],"study_design_scores_gemma":[0.001633114,0.00009435846,0.4128882,0.00009226897,0.00005382319,0.000001000764,0.07357973,0.0003531657,0.00004968468,0.00520319,0.5058989,0.0001525972],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5962722,0.0001732948,0.0003243654,0.02839682,0.0009443159,0.0002123156,1.162381e-7,0.0000266014,0.37365],"genre_scores_gemma":[0.9947814,0.000183422,0.0002627277,0.0006316566,0.0007019123,0.00001175621,0.000002016797,0.000002855348,0.003422265],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4687418,"threshold_uncertainty_score":0.9995633,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2183435816","doi":"10.1007/s11092-015-9233-6","title":"Teacher assessment literacy: a review of international standards and measures","year":2015,"lang":"en","type":"review","venue":"Educational Assessment Evaluation and Accountability","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":253,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Queen's University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Literacy; Educational assessment; Mainland; Psychology; Pedagogy; Geography","retraction":null,"screen_n_in":null,"score":{"opus":0.1374248929728662,"gpt":0.5795117938372106,"spread":0.4420869008643444,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01989881,0.0003648247,0.001121853,0.0002033982,0.0002839256,0.0002925214,0.0004009207,0.0002018631,0.004369651],"category_scores_gemma":[0.001066191,0.0003140791,0.0002119145,0.000385426,0.000352463,0.0006630399,0.0001730027,0.0003782468,0.000004934088],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002266516,"about_ca_system_score_gemma":0.01331173,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002951071,"about_ca_topic_score_gemma":0.0001042388,"domain_scores_codex":[0.9920936,0.001714225,0.001078812,0.0006411524,0.00422735,0.0002448302],"domain_scores_gemma":[0.9944112,0.0006462519,0.0008778481,0.0003379707,0.003531978,0.0001946938],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000003666461,0.000416556,0.008758956,0.009534821,0.0002063789,8.375743e-8,0.001017851,8.103374e-8,9.133324e-8,0.003787145,0.01047102,0.9658033],"study_design_scores_gemma":[0.0002945763,0.0000268005,0.009968014,0.01069064,0.0008722066,0.000001745219,0.0008651337,0.00002604948,9.680338e-9,0.001504737,0.9754583,0.0002917486],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0000709102,0.9466183,0.00002833235,0.0029385,0.001037275,0.002312272,0.0002103592,0.00002144773,0.04676258],"genre_scores_gemma":[0.0005903608,0.9954776,0.001223664,0.0001656051,0.0007095266,0.0006238716,0.0007282111,0.00002123979,0.0004599099],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9655116,"threshold_uncertainty_score":0.9999312,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2167980328","doi":"10.1007/s10459-010-9263-2","title":"Exploring the divergence between self-assessment and self-monitoring","year":2010,"lang":"en","type":"article","venue":"Advances in Health Sciences Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":190,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia; University of British Columbia Hospital","funders":"","keywords":"Self-assessment; Self-monitoring; Self evaluation; Psychology; Medicine; Applied psychology; Social psychology","retraction":null,"screen_n_in":null,"score":{"opus":0.06736112885207077,"gpt":0.4562451782461324,"spread":0.3888840493940616,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.003047338,0.00009467966,0.0001171431,0.0001130458,0.001897837,0.0001612887,0.0004694977,0.00002656247,0.00001329096],"category_scores_gemma":[0.00005682069,0.00007433657,0.00001682109,0.0008383776,0.0003078048,0.001821945,0.0000708329,0.0002521523,0.000004791396],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002219096,"about_ca_system_score_gemma":0.001347656,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001847669,"about_ca_topic_score_gemma":0.001489955,"domain_scores_codex":[0.9982615,0.0001697719,0.0002766715,0.000314219,0.0005558048,0.0004220237],"domain_scores_gemma":[0.9990632,0.0004375753,0.0001701273,0.0001361084,0.00005794288,0.0001350754],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[3.268843e-7,0.00005079174,0.9164429,0.00001604566,0.000001404766,3.897206e-8,0.01671493,0.000004060073,0.000005099174,0.01367078,0.000009729284,0.05308384],"study_design_scores_gemma":[0.00005468462,0.0000423595,0.9389399,0.00004067421,0.000003700989,2.307782e-7,0.02440102,0.00002249308,0.000009757865,0.001986356,0.03440037,0.00009845752],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9826915,0.001073263,0.00002754536,0.004484038,0.005581111,0.0004176181,4.238735e-7,0.00007510979,0.005649436],"genre_scores_gemma":[0.9706532,0.01646019,0.01168895,0.00008105054,0.0009458847,0.0001342602,5.496632e-7,0.000003998116,0.00003185645],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05298539,"threshold_uncertainty_score":0.9994016,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2159609851","doi":"10.1191/0265532204lt288oa","title":"ESL/EFL instructors’ classroom assessment practices: purposes, methods, and procedures","year":2004,"lang":"en","type":"article","venue":"Language Testing","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":184,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"University of Alberta; Queen's University","funders":"","keywords":"Psychology; English as a foreign language; Mathematics education; Tertiary level; Pedagogy; Second language; Language assessment; Linguistics","retraction":null,"screen_n_in":null,"score":{"opus":0.06401151606627827,"gpt":0.4566933338742858,"spread":0.3926818178080075,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001259492,0.0001602916,0.0001926141,0.00007346245,0.0006034473,0.0003334264,0.0002522462,0.00009594835,0.00007815419],"category_scores_gemma":[0.004276884,0.000147588,0.00003457235,0.0003582949,0.0001592115,0.0004974992,0.000119671,0.000250586,0.000009544773],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001551925,"about_ca_system_score_gemma":0.0004715754,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005643806,"about_ca_topic_score_gemma":0.002757241,"domain_scores_codex":[0.9983709,0.0002323285,0.000230163,0.0003362223,0.0004226617,0.0004077303],"domain_scores_gemma":[0.9984898,0.0007326702,0.0003897482,0.0001591591,0.00008756423,0.0001410448],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00001790745,0.0003189038,0.571827,0.0002207024,0.0001452855,0.0001653321,0.1659635,0.00002255949,0.03583076,0.04561178,0.0003762064,0.1795001],"study_design_scores_gemma":[0.004627989,0.0005317705,0.5233849,0.0008702152,0.0004278018,0.00009897222,0.417603,0.0002602982,0.002466767,0.02205466,0.025515,0.002158609],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8899671,0.001086575,0.0009146828,0.001141978,0.0003414859,0.0005238556,0.000003373891,0.0003853021,0.1056356],"genre_scores_gemma":[0.6683367,0.00004521573,0.3304719,0.0002061011,0.0004152005,0.00002397043,0.000004750965,0.00001726388,0.0004788553],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3295572,"threshold_uncertainty_score":0.8531784,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2108604890","doi":"10.1177/1478210314566733","title":"International trends in the implementation of assessment for learning: Implications for policy and practice","year":2015,"lang":"en","type":"article","venue":"Policy Futures in Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":179,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"Brock University; Queen's University","funders":"","keywords":"Summative assessment; Globe; Policy learning; Political science; Educational assessment; International comparisons; Public administration; Policy analysis; Economic growth; Sociology; Regional science; Formative assessment; Pedagogy; Economics; Psychology","retraction":null,"screen_n_in":null,"score":{"opus":0.0812123857192674,"gpt":0.5733258516846382,"spread":0.4921134659653709,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001315983,0.0000532481,0.0000663732,0.00040642,0.0001233564,0.00007013453,0.0001816821,0.00003779979,0.0000048695],"category_scores_gemma":[0.00098151,0.00004746196,0.00002539813,0.0004747277,0.00005371624,0.0002764229,0.00001784782,0.00005523251,1.56438e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003623526,"about_ca_system_score_gemma":0.001034935,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01375279,"about_ca_topic_score_gemma":0.005532595,"domain_scores_codex":[0.9992592,0.0001394879,0.0001875149,0.0001132237,0.0001617502,0.0001388027],"domain_scores_gemma":[0.9990494,0.0005036236,0.0001655814,0.0000718162,0.0001815414,0.00002801367],"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":[0.00002051552,0.0001653623,0.0448606,0.000004168007,0.000007795455,5.338644e-9,0.0564802,0.00001084415,0.00003870302,0.7227168,0.004404896,0.1712901],"study_design_scores_gemma":[0.0005673313,0.00005431566,0.4864552,0.000003423039,0.00001146412,5.611893e-7,0.2132607,0.00001965693,0.000003810023,0.02483237,0.2747358,0.00005538727],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.1912237,0.0001363748,0.001037366,0.6645848,0.001155001,0.002031402,0.00004445962,0.00002602974,0.1397609],"genre_scores_gemma":[0.9923033,0.0001090339,0.003852905,0.0007156581,0.002099111,0.0005578865,0.0001087765,0.000005319721,0.0002480269],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8010796,"threshold_uncertainty_score":0.9928147,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1520074575","doi":"10.19173/irrodl.v15i3.1680","title":"Peer assessment for massive open online courses (MOOCs)","year":2014,"lang":"en","type":"article","venue":"The International Review of Research in Open and Distributed Learning","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":178,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Formative assessment; Summative assessment; Peer assessment; Computer science; Peer feedback; Credibility; Assessment for learning; Online assessment; Peer evaluation; Open education; Credentialing; Multimedia; Higher education; World Wide Web; Medical education; Mathematics education; Psychology","retraction":null,"screen_n_in":null,"score":{"opus":0.1579032256599237,"gpt":0.5635018527575003,"spread":0.4055986270975765,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01530165,0.00006903954,0.0002267407,0.00006002905,0.0004281645,0.0004932071,0.002042391,0.00003156428,0.0003772105],"category_scores_gemma":[0.005133747,0.00004868918,0.00004136611,0.0002903387,0.0002473067,0.0002867873,0.001071538,0.0003306181,0.00000529092],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001327554,"about_ca_system_score_gemma":0.0003223164,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001819373,"about_ca_topic_score_gemma":0.0004217518,"domain_scores_codex":[0.9973372,0.0008137721,0.0002725857,0.0001957596,0.001135983,0.000244705],"domain_scores_gemma":[0.9968232,0.001876705,0.0001506101,0.0001239123,0.0009592709,0.00006631918],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002064782,0.0005589129,0.1811721,0.0007106852,0.0001518112,0.000003855546,0.001513507,0.00006660505,0.00005103762,0.640419,0.08181829,0.09332766],"study_design_scores_gemma":[0.0009254918,0.0001149449,0.02620484,0.002722742,0.00001209786,4.003177e-7,0.01555422,0.001073585,0.000005284282,0.005540534,0.9477525,0.00009333788],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.04654768,0.006684458,0.003298247,0.5230848,0.0006664086,0.008373031,0.0003879824,0.00003127737,0.4109261],"genre_scores_gemma":[0.965138,0.02089837,0.001495151,0.0005266897,0.0002604533,0.0002976015,0.0005743887,0.00001136584,0.01079794],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9185904,"threshold_uncertainty_score":0.6145945,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2105451781","doi":"10.1191/0265532204lt287oa","title":"Teacher formative assessment and talk in classroom contexts: assessment as discourse and assessment of discourse","year":2004,"lang":"en","type":"article","venue":"Language Testing","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":159,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Formative assessment; Psychology; Pedagogy; Discourse analysis; Applied linguistics; Mathematics education; Assessment for learning; Systemic functional linguistics; Linguistics","retraction":null,"screen_n_in":null,"score":{"opus":0.03032002706073061,"gpt":0.4286908790492009,"spread":0.3983708519884703,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001395828,0.0002527186,0.0004196861,0.000153969,0.0003267148,0.0001746399,0.0002231136,0.000107439,0.0001004092],"category_scores_gemma":[0.0002220149,0.0002263329,0.00005128387,0.000374452,0.000480266,0.0006579131,0.0002028843,0.0004338013,0.000001621174],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004164316,"about_ca_system_score_gemma":0.0005470617,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007168258,"about_ca_topic_score_gemma":0.003914115,"domain_scores_codex":[0.9977274,0.0002386689,0.0004745305,0.0003772012,0.0006771764,0.0005050161],"domain_scores_gemma":[0.9987569,0.0004686003,0.0003281348,0.0001996349,0.00008004533,0.0001666697],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000009927094,0.0005870681,0.8351541,0.00007148167,0.00007616492,0.000109113,0.09371276,0.00004194808,0.002073702,0.03619533,0.00002822531,0.03194013],"study_design_scores_gemma":[0.002046388,0.0002367015,0.6623685,0.0003387458,0.00006070044,0.000006857245,0.332113,0.0005101711,0.00003959758,0.001887427,0.0000566251,0.0003353139],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9221969,0.0003018323,0.000573084,0.001138191,0.0001137976,0.0005960678,0.00001091914,0.00006635585,0.07500283],"genre_scores_gemma":[0.9810621,0.00006002154,0.01820872,0.000108062,0.0001288971,0.00005495936,0.0000127587,0.00002223536,0.0003422976],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2384002,"threshold_uncertainty_score":0.9994431,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2112485328","doi":"10.1080/15434303.2015.1010726","title":"Teachers’ Grading Decision Making: Multiple Influencing Factors and Methods","year":2015,"lang":"en","type":"article","venue":"Language Assessment Quarterly","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":138,"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":"Grading (engineering); Psychology; Mathematics education; English language; Multivariate analysis of variance; Statistics; Engineering; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.04392888403571169,"gpt":0.4426289617588582,"spread":0.3987000777231465,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002215324,0.0002165094,0.0002843175,0.0001521183,0.0004279438,0.000414697,0.0003085519,0.0001270034,0.00009018436],"category_scores_gemma":[0.0002537668,0.0001872555,0.00007811721,0.0003026884,0.0001150815,0.0006288868,0.00006152047,0.0002338022,0.00001224679],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002860255,"about_ca_system_score_gemma":0.0001520136,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002273368,"about_ca_topic_score_gemma":0.001829075,"domain_scores_codex":[0.9976478,0.0005109212,0.000293084,0.0003663804,0.0006636434,0.0005181679],"domain_scores_gemma":[0.9984816,0.0007907837,0.0001499985,0.0002398501,0.00007483536,0.0002629701],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"qualitative","study_design_scores_codex":[0.000008713797,0.000048826,0.5265206,0.000004065987,0.0000347703,0.0000151809,0.376552,0.000001497073,0.0009257618,0.001428913,0.0002979,0.09416176],"study_design_scores_gemma":[0.0009254496,0.0002467533,0.2873632,0.00006240925,0.00005070329,0.00000158546,0.7060346,0.000321111,0.0000403012,0.00169127,0.002886578,0.0003760849],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9721803,0.0002567901,0.01473934,0.0001306893,0.0005319277,0.0003126729,0.000002428814,0.0001793628,0.01166647],"genre_scores_gemma":[0.9285433,0.000006457129,0.07078302,0.0001119689,0.0002082865,0.00001600317,0.000006128478,0.00002115638,0.0003036593],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3294826,"threshold_uncertainty_score":0.7636056,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1600384676","doi":"","title":"Teaching to the Test: What Every Educator and Policy-Maker Should Know.","year":2004,"lang":"en","type":"article","venue":"Canadian Journal of Educational Administration and Policy","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":125,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Standardized test; Mathematics education; Test (biology); Curriculum; Psychology; Strengths and weaknesses; Norm (philosophy); Medical education; Pedagogy; Medicine; Social psychology; Political science","retraction":null,"screen_n_in":null,"score":{"opus":0.03360182513708301,"gpt":0.3962923616583372,"spread":0.3626905365212542,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004647513,0.00008917863,0.00009449381,0.000308943,0.0008439271,0.0006182513,0.0001708376,0.00005311249,0.0001529277],"category_scores_gemma":[0.001288956,0.00007294511,0.00003712855,0.0002562252,0.0001701919,0.0005012964,0.000008240929,0.0001754472,0.00001564309],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003216913,"about_ca_system_score_gemma":0.02124344,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.03618321,"about_ca_topic_score_gemma":0.1456331,"domain_scores_codex":[0.9991733,0.00006354595,0.0002169668,0.00009719325,0.0002141097,0.0002348905],"domain_scores_gemma":[0.998552,0.0002885508,0.0001120877,0.00006867346,0.0001352547,0.000843433],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001060136,0.00009891674,0.03932765,0.000008507594,0.00003568161,0.000003427604,0.06896251,0.000006863689,0.00003826648,0.854513,0.02493488,0.01205964],"study_design_scores_gemma":[0.0002770108,0.0001953972,0.2097647,0.0001082051,0.00002554703,0.0001061952,0.03589637,5.673701e-7,0.00001320899,0.02597607,0.7274441,0.0001926156],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.312189,0.0005581348,0.000004094878,0.6725001,0.0005096623,0.0001323018,0.00001094176,0.000002089179,0.01409365],"genre_scores_gemma":[0.9812863,0.0002037534,0.0002449032,0.008492419,0.004649378,0.000004834608,0.000002962541,0.000006450991,0.005108982],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.828537,"threshold_uncertainty_score":0.9843052,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2116070328","doi":"10.1177/0265532210376379","title":"Think-aloud protocols in research on essay rating: An empirical study of their veridicality and reactivity","year":2010,"lang":"en","type":"article","venue":"Language Testing","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":121,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"York University","funders":"","keywords":"Think aloud protocol; Psychology; Protocol analysis; Perception; Empirical research; Sample (material); Qualitative research; Rating scale; Social psychology; Nomothetic and idiographic; Cognitive psychology; Applied psychology; Developmental psychology; Epistemology; Cognitive science","retraction":null,"screen_n_in":null,"score":{"opus":0.2923764194054679,"gpt":0.5510859877479262,"spread":0.2587095683424582,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006440684,0.000083672,0.0001775743,0.00007915629,0.0003393473,0.00009831074,0.0002602454,0.00008569542,0.00003783099],"category_scores_gemma":[0.003381105,0.00006686147,0.00001369408,0.0005312032,0.0002182454,0.00016641,0.0001173351,0.000689057,0.000001792791],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003987847,"about_ca_system_score_gemma":0.0001467037,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006873621,"about_ca_topic_score_gemma":0.0138442,"domain_scores_codex":[0.9975994,0.001020123,0.0001965475,0.0002779067,0.000615862,0.0002901692],"domain_scores_gemma":[0.9976435,0.001847386,0.00008194242,0.0002457829,0.00009258107,0.00008882382],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00002434618,0.0009123872,0.6528844,0.000009748273,0.000002838422,0.0000147292,0.3272898,3.739633e-7,0.01173417,0.0001797215,0.000008902451,0.006938535],"study_design_scores_gemma":[0.0005041019,0.0004316432,0.7267394,0.00004266435,0.000001945941,3.425733e-7,0.2713432,0.00013408,0.0003647935,0.0003241998,0.00002581715,0.00008783205],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9803934,0.000002900598,7.588783e-7,0.000104596,0.00003270371,0.004111891,0.000001182957,0.00005459703,0.01529796],"genre_scores_gemma":[0.9991723,1.434238e-7,0.0003921033,0.0000196967,0.0001780559,0.0001737892,6.945806e-7,0.00000772996,0.00005546028],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.07385501,"threshold_uncertainty_score":0.9997397,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1986967177","doi":"10.3109/0142159x.2010.486063","title":"Assessment steers learning down the right road: Impact of progress testing on licensing examination performance","year":2010,"lang":"en","type":"article","venue":"Medical Teacher","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":121,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto; McMaster University","funders":"","keywords":"Formative assessment; Test (biology); Curriculum; Psychology; Medicine; Medical education; Mathematics education; Pedagogy","retraction":null,"screen_n_in":null,"score":{"opus":0.02780155950402934,"gpt":0.3811736229013911,"spread":0.3533720633973618,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003853756,0.0001057026,0.0001415954,0.00004873321,0.0005301847,0.00007418874,0.0003150327,0.0001380663,0.001686484],"category_scores_gemma":[0.001045943,0.00006294251,0.00006732045,0.000291735,0.0004619003,0.0001409634,0.00005274032,0.0008718335,0.00001624208],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001049584,"about_ca_system_score_gemma":0.0002250835,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003287865,"about_ca_topic_score_gemma":0.0001149875,"domain_scores_codex":[0.9976656,0.0003575294,0.0002036826,0.0001665694,0.001308992,0.0002976546],"domain_scores_gemma":[0.999244,0.0002453075,0.0001564206,0.0001302764,0.0001015612,0.0001223886],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00000352221,0.0001157798,0.7888505,0.00000476341,0.00002324766,0.000001865684,0.004602669,0.000006891829,0.0001127418,0.0004188263,0.0001406532,0.2057185],"study_design_scores_gemma":[0.0002525103,0.000155625,0.9850033,0.00005550816,0.00001358477,8.035344e-7,0.001733734,0.0108064,0.00001290379,0.00001071345,0.00185983,0.00009508433],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8681741,0.0000105879,0.00001398906,0.0005715039,0.0002633554,0.0001830477,1.103636e-7,0.00005148966,0.1307318],"genre_scores_gemma":[0.9976144,0.000007531216,0.0002433726,0.00002060754,0.0005083873,0.00001120355,0.000002435537,0.000009662216,0.00158235],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2056234,"threshold_uncertainty_score":0.9992261,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2136543334","doi":"10.3138/cmlr.64.1.135","title":"A New Washback Model of Students’ Learning","year":2007,"lang":"en","type":"article","venue":"Canadian Modern Language Review/ La Revue canadienne des langues vivantes","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":119,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Test (biology); Mathematics education; Context (archaeology); Psychology; English as a foreign language; Pedagogy; Geography","retraction":null,"screen_n_in":null,"score":{"opus":0.02422845520616734,"gpt":0.3123421666566812,"spread":0.2881137114505139,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001924073,0.0002676478,0.0005554741,0.0002858102,0.000334956,0.00007678496,0.0008395838,0.0001551239,0.0003996969],"category_scores_gemma":[0.0007692307,0.0002779652,0.0002063531,0.0005409211,0.0002307243,0.0002064909,0.00006227203,0.0002992373,0.00003364992],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006909453,"about_ca_system_score_gemma":0.0006335968,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.3892992,"about_ca_topic_score_gemma":0.8877521,"domain_scores_codex":[0.9975261,0.0001767738,0.0004871894,0.0003823344,0.0002987661,0.001128839],"domain_scores_gemma":[0.9976276,0.0002283912,0.0002111188,0.0003556921,0.0001844196,0.001392775],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00004648559,0.0001291563,0.1329942,0.003524052,0.0004918544,0.001538286,0.5646811,0.0002629322,0.0133543,0.01970495,0.009782875,0.2534898],"study_design_scores_gemma":[0.00441402,0.0005686952,0.1753515,0.02871575,0.001902274,0.0002137536,0.2528486,0.005519224,0.0006829042,0.006646393,0.5167316,0.006405171],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8977669,0.04877086,0.002509062,0.000599193,0.0002169311,0.0008377918,0.00006395344,0.0001163714,0.0491189],"genre_scores_gemma":[0.9670827,0.01186402,0.003401076,0.000554314,0.0003868736,0.00001272332,0.0000613335,0.00006346067,0.01657345],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5069488,"threshold_uncertainty_score":0.9999673,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3191701502","doi":"10.1080/0142159x.2021.1957088","title":"Ottawa 2020 consensus statement for programmatic assessment – 1. Agreement on the principles","year":2021,"lang":"en","type":"article","venue":"Medical Teacher","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":115,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"The Wilson Centre; University of Toronto","funders":"","keywords":"Operationalization; Medical education; Curriculum; Program evaluation; Engineering ethics; Medicine; Psychology; Political science; Pedagogy; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.07826089378203037,"gpt":0.4097405264132591,"spread":0.3314796326312287,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003866223,0.000135594,0.0001903854,0.00001616631,0.0004948003,0.0001359265,0.0003431294,0.00009678915,0.01101056],"category_scores_gemma":[0.001253738,0.00008767218,0.0001205672,0.0001728853,0.0002732927,0.00002391205,0.00009959526,0.0002499265,0.00008431805],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002461123,"about_ca_system_score_gemma":0.0007199071,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001047988,"about_ca_topic_score_gemma":0.00108017,"domain_scores_codex":[0.9966165,0.0005358532,0.0003874056,0.0002872428,0.001723628,0.000449363],"domain_scores_gemma":[0.9988264,0.0004747662,0.0001154181,0.0002405453,0.0001150104,0.0002277943],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00003706308,0.002579601,0.0900499,0.00009598891,0.0005817222,0.0001343552,0.01532624,0.000006110052,0.00003554557,0.4634986,0.3822259,0.04542902],"study_design_scores_gemma":[0.0007923783,0.0001229305,0.005421168,0.00006623169,0.00004630975,6.656558e-7,0.01821395,0.00104638,0.00002012316,0.001236625,0.9728657,0.0001675335],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.3000464,0.0002135977,0.001242553,0.3118043,0.001328619,0.002795127,0.000007051676,0.0001538391,0.3824086],"genre_scores_gemma":[0.9142879,0.0001350095,0.003159609,0.002266363,0.001243004,0.0009615988,0.00004149887,0.00002814251,0.07787691],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6142415,"threshold_uncertainty_score":0.9898935,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2148189517","doi":"10.1111/j.1365-2729.2008.00290.x","title":"Peering into large lectures: examining peer and expert mark agreement using peerScholar, an online peer assessment tool","year":2008,"lang":"en","type":"article","venue":"Journal of Computer Assisted Learning","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":114,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"The Scarborough Hospital; University of Toronto","funders":"","keywords":"Peer assessment; Peering; Class (philosophy); Computer science; Accountability; Class size; Peer evaluation; Rank (graph theory); Peer feedback; Mathematics education; Online assessment; World Wide Web; Multimedia; Higher education; The Internet; Psychology; Artificial intelligence; Formative assessment; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.08174915342893448,"gpt":0.3820792831741884,"spread":0.3003301297452539,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.003487561,0.0002630577,0.0004797551,0.0003134316,0.001547417,0.0004896019,0.0004042166,0.0001508458,0.0001959985],"category_scores_gemma":[0.0002572032,0.0002443668,0.0001462094,0.0003158753,0.000116081,0.001090377,0.0001988812,0.001039869,0.000002033338],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003926846,"about_ca_system_score_gemma":0.0003218343,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001254003,"about_ca_topic_score_gemma":0.00005878198,"domain_scores_codex":[0.9954913,0.0007052255,0.0006921841,0.0003058628,0.002289351,0.0005160747],"domain_scores_gemma":[0.9976903,0.0002415302,0.000611992,0.000151911,0.001031623,0.000272602],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001446852,0.001023064,0.7131329,0.00004812596,0.0006550683,0.000651986,0.1885707,0.006100516,0.004975659,0.000266344,0.002909601,0.0815213],"study_design_scores_gemma":[0.002504215,0.0007788959,0.8532051,0.000280025,0.0001054738,0.0002424302,0.03213751,0.02155172,0.00002010852,0.00003010984,0.08853702,0.0006073761],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9415874,0.0002942947,0.05482085,0.0009054405,0.0009196801,0.000139583,8.33965e-7,0.00004708664,0.00128475],"genre_scores_gemma":[0.8733247,0.0001152987,0.1231871,0.0002644648,0.001839224,0.000001395246,0.000009288213,0.00002859543,0.001229984],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1564332,"threshold_uncertainty_score":0.9997525,"prediction_status":"machine_predicted_unvalidated"},"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,"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":"W2138588257","doi":"10.18806/tesl.v27i2.1052","title":"A Peer Review Training Workshop: Coaching Students to Give and Evaluate Peer Feedback","year":2010,"lang":"en","type":"review","venue":"TESL Canada Journal","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":109,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Peer feedback; Coaching; Psychology; Peer review; Training (meteorology); Consciousness; Pedagogy; Medical education; Mathematics education; Political science","retraction":null,"screen_n_in":null,"score":{"opus":0.1447572715000492,"gpt":0.4614545996722544,"spread":0.3166973281722052,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts","research_integrity","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01159246,0.0005523813,0.00187558,0.0001905717,0.001412186,0.001031733,0.001497835,0.0002965244,0.006694117],"category_scores_gemma":[0.003929837,0.0004508086,0.0003422031,0.0006152594,0.0001181621,0.0002407349,0.0002788027,0.002434675,0.00003304402],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001047073,"about_ca_system_score_gemma":0.007356185,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.03191997,"about_ca_topic_score_gemma":0.2792474,"domain_scores_codex":[0.9897516,0.0008384931,0.0009844606,0.0004957632,0.006980821,0.0009488158],"domain_scores_gemma":[0.9959936,0.0006317591,0.0007656455,0.0002853444,0.001281533,0.00104218],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000002219545,0.0000163206,0.00003195015,0.0009947136,0.0001885391,0.00008158017,0.003715105,1.380504e-7,3.627215e-8,0.00005637639,0.3256215,0.6692916],"study_design_scores_gemma":[0.000207568,0.00002148719,0.00008413236,0.02127506,0.001011878,0.00009280541,0.002987547,3.312478e-7,3.734673e-9,0.00002941511,0.973776,0.0005137943],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.00002176702,0.9795824,0.000007306663,0.01063723,0.002218802,0.001169271,0.00003091556,0.00002409089,0.006308186],"genre_scores_gemma":[0.00000892187,0.9620692,0.0003294332,0.01095669,0.001772781,0.00004489524,0.00002106119,0.00006215407,0.0247349],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.6687778,"threshold_uncertainty_score":0.9998878,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2897106912","doi":"10.1111/medu.13746","title":"When I say … feedback","year":2018,"lang":"en","type":"article","venue":"Medical Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":108,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of British Columbia","funders":"","keywords":"Constructive; Process (computing); Term (time); Space (punctuation); Series (stratigraphy); Psychology; Computer science; Social psychology; Sociology; Physics; Programming language","retraction":null,"screen_n_in":null,"score":{"opus":0.01926714578388553,"gpt":0.3851389734389596,"spread":0.365871827655074,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0006412268,0.00004703331,0.00006046597,0.00003524098,0.0002895071,0.00005105847,0.000245873,0.00009071287,0.0179762],"category_scores_gemma":[0.0009163546,0.00004242638,0.00002462288,0.0001544043,0.0003491032,0.0001158694,0.00002589685,0.0000773038,0.001353332],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007561449,"about_ca_system_score_gemma":0.001410838,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001040115,"about_ca_topic_score_gemma":0.001123126,"domain_scores_codex":[0.9988129,0.0000857691,0.0001073212,0.0001263497,0.0006830176,0.0001846041],"domain_scores_gemma":[0.9995804,0.00005030125,0.00003419623,0.00009754932,0.0001163322,0.0001212543],"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":[0.00000376658,0.0001760778,0.02589721,0.000002282793,0.000005815975,2.029153e-7,0.02402595,2.103335e-9,0.00000773045,0.01728823,0.8406276,0.0919652],"study_design_scores_gemma":[0.0001028966,0.00002295031,0.02537014,0.00001898905,0.000005897344,2.441247e-7,0.005034504,0.000006852243,0.00001389961,0.00305829,0.9662996,0.00006575257],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.1541451,0.0001046231,0.0002650173,0.1054223,0.004954424,0.0001957101,2.927488e-7,0.00010174,0.7348108],"genre_scores_gemma":[0.9394937,0.00006388929,0.0008579573,0.01250129,0.005763225,0.00002290335,0.000009210155,0.000007366567,0.04128043],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7853486,"threshold_uncertainty_score":0.9994242,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2122826394","doi":"10.5539/ass.v4n3p78","title":"Student Perceptions and Preferences for Feedback","year":2009,"lang":"en","type":"article","venue":"Asian Social Science","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":107,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"Macquarie University","keywords":"ROWE; Quality (philosophy); Perception; Psychology; Key (lock); Undergraduate research; Element (criminal law); Medical education; Mathematics education; Computer science; Marketing; Political science; Business; Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.0368983349792774,"gpt":0.392057273630894,"spread":0.3551589386516166,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0009362705,0.00008809939,0.0001182088,0.00006900632,0.002863994,0.000413778,0.0004847343,0.00006561208,0.00009596422],"category_scores_gemma":[0.00008331751,0.00008324609,0.00004848662,0.0005620921,0.00117374,0.0005025998,0.00004608195,0.00007715182,0.00001688235],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001079905,"about_ca_system_score_gemma":0.0002045663,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005719905,"about_ca_topic_score_gemma":0.0001837555,"domain_scores_codex":[0.9984353,0.00004720546,0.0001260277,0.0003016969,0.0006407392,0.000448983],"domain_scores_gemma":[0.9995527,0.00004552266,0.0000570631,0.00007054716,0.0001275239,0.0001466959],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00001119607,0.0001651857,0.03640093,0.000003097095,0.000008465351,5.481244e-7,0.1725431,4.018542e-8,0.001404648,0.3479996,0.002815683,0.4386475],"study_design_scores_gemma":[0.0001879304,0.00007848674,0.9034857,0.000004159882,0.00001090462,1.303133e-7,0.0783758,9.733268e-7,0.000008451728,0.01007137,0.007649754,0.000126327],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.2905108,0.00002918069,0.000146528,0.006420318,0.0002745372,0.0004712931,0.000004197837,0.00007593474,0.7020672],"genre_scores_gemma":[0.9971195,0.00004334259,0.0007248466,0.000280766,0.0004747719,0.00001853046,0.00000109684,0.000002888564,0.001334284],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8670848,"threshold_uncertainty_score":0.9984341,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2479837187","doi":"10.1007/978-3-319-39211-0","title":"Assessment for Learning: Meeting the Challenge of Implementation","year":2016,"lang":"en","type":"book","venue":"˜The œenabling power of assessment","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":105,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa","funders":"","keywords":"Engineering ethics; Computer science; Engineering management; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.04101925382497879,"gpt":0.3993390365835251,"spread":0.3583197827585463,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00606455,0.0004261607,0.0007209726,0.0001956256,0.001089521,0.0001453854,0.001275863,0.0002925408,0.0007451876],"category_scores_gemma":[0.00005847196,0.0002590475,0.0005378406,0.0001857283,0.0005246155,0.0001780641,0.0002990459,0.0005600529,0.000006918143],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007360511,"about_ca_system_score_gemma":0.002290685,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002509535,"about_ca_topic_score_gemma":0.0006073341,"domain_scores_codex":[0.9952216,0.0005109159,0.00112086,0.0005454264,0.001920119,0.0006810949],"domain_scores_gemma":[0.994444,0.002031962,0.002106157,0.0006105457,0.0007175409,0.00008982651],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001503788,0.0007545823,0.008483741,0.0008573803,0.003856692,0.000005424309,0.04816981,0.0001259723,0.001276515,0.8022463,0.08058632,0.05348691],"study_design_scores_gemma":[0.00153886,0.0007409215,0.002025842,0.0005755175,0.000587409,3.233278e-7,0.02942942,0.00004638092,0.00004996288,0.0149391,0.9495035,0.0005628109],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.0007362181,0.0009855552,0.004992268,0.007128504,0.002159127,0.004150488,0.00009335468,0.0001023658,0.9796521],"genre_scores_gemma":[0.6246248,0.001853576,0.002097195,0.0001583155,0.001447929,0.0005289683,0.0001399409,0.0001554486,0.3689938],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.8689171,"threshold_uncertainty_score":0.9999862,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2568968076","doi":"10.1177/1362168816684366","title":"Developing the assessment literacy of teachers in Chinese language classrooms: A focus on assessment task design","year":2017,"lang":"en","type":"article","venue":"Language Teaching Research","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":103,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Toronto; University of Calgary","funders":"","keywords":"Task (project management); Literacy; Psychology; Mathematics education; Professional development; Pedagogy; Task analysis; Authentic assessment; Quality (philosophy); Faculty development; Language assessment; Curriculum","retraction":null,"screen_n_in":null,"score":{"opus":0.09606259991720532,"gpt":0.5312202756607064,"spread":0.4351576757435011,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.02126425,0.000227872,0.0003526236,0.0003606108,0.002429437,0.0008925637,0.002118654,0.0001435179,0.0001711353],"category_scores_gemma":[0.002310554,0.0001575261,0.0001153194,0.0003458471,0.0005158896,0.0005049199,0.0005113065,0.001920951,0.00002352158],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008858742,"about_ca_system_score_gemma":0.0007146316,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01782575,"about_ca_topic_score_gemma":0.004326982,"domain_scores_codex":[0.9919218,0.00428806,0.0004108639,0.0004671501,0.002017332,0.0008947812],"domain_scores_gemma":[0.9961212,0.0023686,0.0002550959,0.001021855,0.0001110479,0.0001222096],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"observational","study_design_scores_codex":[0.00004449388,0.0004513084,0.2916088,0.00003612549,0.00008668657,0.0001694214,0.5341461,0.00002153481,0.003746394,0.03750178,0.0004977845,0.1316896],"study_design_scores_gemma":[0.001633005,0.0002692696,0.773909,0.0004784393,0.00001773734,0.000001517785,0.2169586,0.0006885606,0.0001542788,0.003502205,0.001938801,0.0004485746],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8886061,0.0002053623,0.002660341,0.007043086,0.0002066929,0.001064317,0.000005694693,0.00006248024,0.100146],"genre_scores_gemma":[0.9879083,0.00005905707,0.008476843,0.00007240548,0.000361044,0.0001211893,0.000006750198,0.00003148512,0.002962906],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4823001,"threshold_uncertainty_score":0.9988692,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2122362059","doi":"10.1191/0265532206lt322oa","title":"Aiming for positive washback: a case study of international teaching assistants","year":2005,"lang":"en","type":"article","venue":"Language Testing","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":102,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Université Laval","funders":"","keywords":"Test (biology); Psychology; Language proficiency; Process (computing); Mathematics education; Empirical research; Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.05418180584152639,"gpt":0.417552964658704,"spread":0.3633711588171776,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007105966,0.00006760054,0.0001042936,0.00005648265,0.0004002398,0.00006266831,0.000160414,0.0000264458,0.00003904515],"category_scores_gemma":[0.0009049757,0.00006699014,0.00003172235,0.000101326,0.00003463605,0.0001861593,0.00005213873,0.00009001935,0.000002092163],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008201926,"about_ca_system_score_gemma":0.00003300066,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005183866,"about_ca_topic_score_gemma":0.005065913,"domain_scores_codex":[0.9991629,0.00007986378,0.0001786317,0.0001430193,0.0002568784,0.0001787081],"domain_scores_gemma":[0.9990917,0.0005825684,0.0001277636,0.000068469,0.00009271935,0.00003674204],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.00001842531,0.0005926692,0.2616042,0.000008992158,0.00009007394,0.000386716,0.6251513,0.00003314335,0.002364049,0.0009155349,0.0001074889,0.1087273],"study_design_scores_gemma":[0.001206595,0.0001576592,0.0180886,0.00007474444,0.00005805515,0.00003765854,0.9781072,0.001685571,0.0001075276,0.00002420987,0.0002692359,0.0001829938],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9689544,0.00003273317,0.0002297826,0.0001360328,0.0001407786,0.0003280746,0.000006541906,0.00005797715,0.0301137],"genre_scores_gemma":[0.9845323,3.072115e-7,0.01427359,0.00004243792,0.0005142501,0.00001456001,0.00000259419,0.00000862757,0.0006113448],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3529558,"threshold_uncertainty_score":0.783649,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2131806896","doi":"","title":"The Evolving Culture of Large-Scale Assessments in Canadian Education.","year":2008,"lang":"en","type":"article","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":102,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Gatekeeping; Scale (ratio); Accountability; Christian ministry; Educational assessment; Political science; Medical education; Public relations; Geography; Psychology; Pedagogy; Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.0193088662006192,"gpt":0.3692644063024438,"spread":0.3499555401018246,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000396356,0.00004276058,0.00006114064,0.00004580116,0.0006341307,0.00003185239,0.0002321167,0.00004440181,0.0003811064],"category_scores_gemma":[0.00004944875,0.00003032716,0.00002616812,0.0002915664,0.00008416042,0.000142765,0.00001648497,0.00006659553,0.00001782744],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001853619,"about_ca_system_score_gemma":0.001519849,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.5154262,"about_ca_topic_score_gemma":0.9432378,"domain_scores_codex":[0.9992211,0.00005929243,0.0001131423,0.0000814739,0.0002438681,0.0002811015],"domain_scores_gemma":[0.9996442,0.00004082107,0.0000343642,0.00008931982,0.00008901755,0.0001022419],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000001076295,0.00005755863,0.9200382,0.000001010418,0.000004970818,5.407481e-7,0.02775792,4.018757e-7,0.00001052248,0.01184851,0.03983032,0.0004490252],"study_design_scores_gemma":[0.0001120167,0.00000828206,0.6659837,0.000007947744,0.000002545689,1.94933e-7,0.08478463,0.00003077465,0.000008566895,0.0003078694,0.2486897,0.00006375119],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.2161639,0.0002644784,0.000008180164,0.001102697,0.0003542024,0.0001697962,0.000001554483,0.00001021903,0.781925],"genre_scores_gemma":[0.9611298,0.0002621904,0.0004615021,0.0001654979,0.00008036283,0.00001020249,0.000002405823,0.00000269008,0.03788532],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7449659,"threshold_uncertainty_score":0.4878006,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2090290510","doi":"10.3138/cmlr.64.1.009","title":"AFL Research in the L2 Classroom and Evidence of Usefulness: Taking Formative Assessment to the Next Level","year":2007,"lang":"en","type":"article","venue":"Canadian Modern Language Review/ La Revue canadienne des langues vivantes","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":102,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Formative assessment; Assessment for learning; Mathematics education; Psychology; Curriculum; Pedagogy; Bridge (graph theory)","retraction":null,"screen_n_in":null,"score":{"opus":0.1996400635777524,"gpt":0.4220425672263123,"spread":0.2224025036485599,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0106884,0.0001841327,0.000355209,0.0003305282,0.0006114084,0.0001702933,0.0009912907,0.00008869395,0.00006950532],"category_scores_gemma":[0.001728973,0.0001266817,0.00008310501,0.001185937,0.00046119,0.0003516937,0.00008954675,0.0004309898,0.000009597355],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007731929,"about_ca_system_score_gemma":0.0004727678,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.4403425,"about_ca_topic_score_gemma":0.9675052,"domain_scores_codex":[0.9969258,0.0009164999,0.0004357957,0.000314114,0.0003831481,0.001024606],"domain_scores_gemma":[0.9966396,0.002051632,0.0001713854,0.0004526493,0.0002452791,0.000439419],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.00001716664,0.00003935793,0.02267307,0.001953881,0.00006244834,0.0005808625,0.7654226,0.000005665282,0.000904787,0.017393,0.001867381,0.1890797],"study_design_scores_gemma":[0.0003019885,0.0001609726,0.4102632,0.01616888,0.00009671182,0.00005324414,0.5117558,0.0002106771,0.00003400872,0.001227034,0.05914835,0.0005791428],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9074288,0.0704557,0.0003977606,0.007621207,0.0001458436,0.00195242,0.0000477945,0.00001734523,0.01193315],"genre_scores_gemma":[0.9910566,0.006778504,0.0004962279,0.001030686,0.0001946963,0.0001171087,0.000007822695,0.00001859609,0.0002997936],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5271627,"threshold_uncertainty_score":0.5633843,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W3202681787","doi":"10.1111/bjet.13169","title":"COVID‐19 as the tipping point for integrating e‐assessment in higher education practices","year":2021,"lang":"en","type":"article","venue":"British Journal of Educational Technology","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":102,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false},"ca_institutions":"Université de Sherbrooke","funders":"Université de Sherbrooke","keywords":"Tipping point (physics); Coronavirus disease 2019 (COVID-19); 2019-20 coronavirus outbreak; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Higher education; Medicine; Virology; Economics; Engineering; Economic growth","retraction":null,"screen_n_in":null,"score":{"opus":0.0578890967993076,"gpt":0.4468809123947186,"spread":0.388991815595411,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001347107,0.00006575776,0.0001451146,0.0001801148,0.000469502,0.0002021837,0.0003664788,0.0001087523,0.001762991],"category_scores_gemma":[0.007503178,0.00006580407,0.00007066727,0.0005734078,0.0001741053,0.0003289364,0.00004346906,0.0003987671,0.000004226457],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005136135,"about_ca_system_score_gemma":0.00985722,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006658109,"about_ca_topic_score_gemma":0.002035484,"domain_scores_codex":[0.9987925,0.0001719064,0.0003929258,0.0001440056,0.000306773,0.0001918558],"domain_scores_gemma":[0.9974123,0.001031665,0.0007574284,0.00008470682,0.0006265666,0.00008734094],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001085322,0.0006000108,0.04896361,0.00001578908,0.0000540003,0.00001428125,0.002002438,0.000004736034,0.0002849862,0.9090035,0.01996114,0.01908468],"study_design_scores_gemma":[0.0005500519,0.00007333575,0.05576666,0.0002340044,0.0000340782,0.0006618462,0.1057531,0.000004027952,0.00003183589,0.3696238,0.467113,0.0001543347],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.1996197,0.005283923,0.0001111287,0.7592499,0.002465698,0.000338388,0.000002935999,0.00001536574,0.032913],"genre_scores_gemma":[0.9792018,0.001025279,0.01037748,0.002317798,0.001082071,0.00008468591,0.000009872285,0.000008813709,0.005892235],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7795821,"threshold_uncertainty_score":0.9991496,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1996728665","doi":"10.1080/08878730.2012.760024","title":"Pedagogies for Preservice Assessment Education: Supporting Teacher Candidates' Assessment Literacy Development","year":2013,"lang":"en","type":"article","venue":"The Teacher Educator","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":95,"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":"Praxis; Accountability; Teacher education; Literacy; Pedagogy; Psychology; Mathematics education; Perspective (graphical); Political science","retraction":null,"screen_n_in":null,"score":{"opus":0.0388884580724605,"gpt":0.4471513230062795,"spread":0.408262864933819,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002210647,0.0003106249,0.0002934245,0.0001013771,0.001483834,0.0009106394,0.001114716,0.0001220937,0.006297973],"category_scores_gemma":[0.0001318262,0.0002324095,0.0001296113,0.0003010185,0.0001688559,0.0007889031,0.000212549,0.0003724695,0.0002546083],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007535766,"about_ca_system_score_gemma":0.005455612,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003970104,"about_ca_topic_score_gemma":0.0004209213,"domain_scores_codex":[0.9969537,0.0003877104,0.0005745394,0.0004755791,0.00075347,0.0008550379],"domain_scores_gemma":[0.9981105,0.0003425159,0.0003490484,0.0005380173,0.0003926409,0.0002672249],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001392711,0.001775664,0.4913778,0.00009082542,0.0002479794,3.457783e-7,0.2074198,0.000001401146,0.0001872107,0.008826475,0.2116377,0.07842083],"study_design_scores_gemma":[0.0003252013,0.00003690456,0.3329954,0.00004297244,0.00007303208,7.74341e-7,0.1408407,0.00007603928,0.00003823042,0.001354138,0.5238052,0.0004113851],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8630193,0.000321672,0.0002482549,0.02551409,0.00186047,0.002889199,0.000003455022,0.0002100512,0.1059335],"genre_scores_gemma":[0.8715669,0.00002257004,0.01556473,0.0007626903,0.001841648,0.002948789,0.00006211134,0.00004683417,0.1071837],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3121675,"threshold_uncertainty_score":0.9998161,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2906729407","doi":"10.5539/ies.v12n1p61","title":"Application of Rubrics in the Classroom: A Vital Tool for Improvement in Assessment, Feedback and Learning","year":2018,"lang":"en","type":"article","venue":"International Education Studies","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":89,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Rubric; Grading (engineering); Strengths and weaknesses; Mathematics education; Computer science; Peer assessment; Standards-based assessment; Teaching method; Psychology; Educational assessment; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.0463357328462515,"gpt":0.449002478674172,"spread":0.4026667458279205,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001003366,0.00005775615,0.00009045981,0.0001105226,0.0001594037,0.00004471074,0.0001651651,0.00002625989,0.00001047407],"category_scores_gemma":[0.0004332836,0.00004837084,0.00002205951,0.0001916046,0.0001655466,0.0001595285,0.00004181722,0.00007621019,0.000002191737],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001624937,"about_ca_system_score_gemma":0.000130992,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004067672,"about_ca_topic_score_gemma":0.0008508089,"domain_scores_codex":[0.9991999,0.00006647657,0.0002223048,0.0001388308,0.0002699813,0.0001024792],"domain_scores_gemma":[0.9988834,0.000367417,0.0001351244,0.00005269059,0.0005517465,0.000009574587],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00002424605,0.0004095818,0.8380501,0.00002031424,0.00005729069,5.682081e-8,0.04244693,0.000004166368,0.0005279401,0.0649056,0.001497761,0.05205598],"study_design_scores_gemma":[0.0006706396,0.0001439486,0.7112288,0.00004576656,0.00001406092,2.555068e-7,0.2036289,0.0003264718,0.00004611897,0.009037979,0.07473084,0.0001262719],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9825398,0.0001548527,0.001303667,0.004550615,0.0007182398,0.000553283,0.000002698393,0.000007997497,0.01016881],"genre_scores_gemma":[0.9966707,0.0002095071,0.001423631,0.0001930021,0.0003022325,0.0003461052,0.000008965236,0.000003431215,0.0008424304],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1611819,"threshold_uncertainty_score":0.1972506,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2107226435","doi":"10.6018/ijes.13.2.185891","title":"Washback in language assessment","year":2013,"lang":"en","type":"article","venue":"International Journal of English Studies","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":88,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Test (biology); Psychology; Quarter (Canadian coin); Mathematics education; Medical education; Pedagogy; Medicine; Geography","retraction":null,"screen_n_in":null,"score":{"opus":0.02948544944097654,"gpt":0.421665550082896,"spread":0.3921801006419194,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000668818,0.00007048898,0.0001719321,0.0001691139,0.00005893762,0.0001105224,0.0004180047,0.00003079157,0.0004411562],"category_scores_gemma":[0.001204817,0.00005752169,0.00007795257,0.0001148836,0.0001041865,0.0005495373,0.0000803781,0.0001620046,0.00001881556],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002745065,"about_ca_system_score_gemma":0.00008868298,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002108298,"about_ca_topic_score_gemma":0.0002574878,"domain_scores_codex":[0.9986073,0.00008869126,0.0003369192,0.00007228401,0.00074524,0.0001495505],"domain_scores_gemma":[0.9974218,0.0002431815,0.0002056422,0.0000425671,0.002041301,0.00004551518],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"qualitative","study_design_scores_codex":[0.0000267976,0.000531397,0.5472085,0.00000920187,0.001024495,0.0001405071,0.351491,0.000050773,0.0002501019,0.01513827,0.0738667,0.01026225],"study_design_scores_gemma":[0.00173507,0.0001009875,0.3604697,0.0001859376,0.00002338323,0.0000018585,0.5536358,0.00001262622,0.0000638337,0.002617204,0.08093354,0.0002200157],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8751909,0.001046688,0.00001328877,0.002945794,0.005485129,0.0001154109,0.000001231325,0.0000138325,0.1151877],"genre_scores_gemma":[0.9946085,0.001308703,0.0007253274,0.0001767054,0.002167045,0.000007056288,6.079992e-7,0.000004569722,0.00100155],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2021448,"threshold_uncertainty_score":0.4830351,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2781958120","doi":"10.1016/j.tate.2017.12.010","title":"Changing approaches to classroom assessment: An empirical study across teacher career stages","year":2018,"lang":"en","type":"article","venue":"Teaching and Teacher Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":87,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Queen's University","funders":"","keywords":"Set (abstract data type); Psychology; Mathematics education; Empirical research; Pedagogy; Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.159263218109638,"gpt":0.4565673728995994,"spread":0.2973041547899614,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.004514802,0.0002183979,0.0002176132,0.0001723531,0.002346124,0.0005697726,0.0003403882,0.0001276054,0.0001248514],"category_scores_gemma":[0.0001602218,0.0002065777,0.00004335192,0.0003130054,0.0001670719,0.0005481593,0.0001442375,0.0005521157,0.00003828597],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002602764,"about_ca_system_score_gemma":0.0002560583,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002681846,"about_ca_topic_score_gemma":0.001797184,"domain_scores_codex":[0.9968874,0.001163137,0.0002384408,0.0005680025,0.0005395712,0.000603416],"domain_scores_gemma":[0.9991355,0.00008114454,0.00009493272,0.0003238735,0.00006987972,0.000294665],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000006570539,0.001113904,0.5245724,0.000002978598,0.00002042262,2.12347e-7,0.4029814,2.94581e-7,0.00002326501,0.0004085716,0.001191764,0.06967823],"study_design_scores_gemma":[0.0002138329,0.0002423812,0.5088378,0.00001427047,0.0000350736,4.534822e-7,0.468236,0.0000576681,0.000002750204,0.0001523133,0.02197213,0.0002353888],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9688776,0.00004632098,0.0005988568,0.003300142,0.0006548404,0.0006827968,0.000002266191,0.0002059986,0.02563123],"genre_scores_gemma":[0.9773437,0.000001631888,0.002236043,0.0003491013,0.002566831,0.0001175858,0.00002232347,0.00003184844,0.01733092],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.06944284,"threshold_uncertainty_score":0.9989527,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1599897745","doi":"10.18806/tesl.v23i2.53","title":"Effects of Peer Feedback on EFL Student Writers at Different Levels of English Proficiency: A Japanese Context","year":2006,"lang":"en","type":"article","venue":"TESL Canada Journal","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":84,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Peer feedback; Psychology; Context (archaeology); Peer evaluation; Mathematics education; English as a foreign language; Peer group; Higher education; Pedagogy; Social psychology","retraction":null,"screen_n_in":null,"score":{"opus":0.01525476707009359,"gpt":0.284865287494137,"spread":0.2696105204240434,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005624786,0.0001856927,0.0003820943,0.0001005015,0.0003661317,0.00006440729,0.0004716497,0.00006896954,0.00186263],"category_scores_gemma":[0.0003215563,0.0001489244,0.0001275804,0.0002199507,0.0001963718,0.00009845271,0.00006727572,0.000231132,0.000001954499],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008700248,"about_ca_system_score_gemma":0.0005463428,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.1073532,"about_ca_topic_score_gemma":0.2460792,"domain_scores_codex":[0.9962593,0.0002110226,0.0004774362,0.0001804989,0.002419038,0.0004526589],"domain_scores_gemma":[0.9981148,0.0004189871,0.0004030982,0.0001277001,0.0007521787,0.0001832563],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"observational","study_design_scores_codex":[0.0005846207,0.003320567,0.3901051,0.0004204182,0.0006792498,0.0003121728,0.178495,0.0001548242,0.0195074,0.009912883,0.3919967,0.004511025],"study_design_scores_gemma":[0.002277045,0.0003713608,0.9591452,0.0001959037,0.0000945178,0.000002508994,0.02042215,0.000004482956,0.005220189,0.00007715531,0.01187729,0.0003121451],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9874128,0.001331302,0.000002193123,0.0005260746,0.001797857,0.0003741332,0.00001765293,0.00001221051,0.008525826],"genre_scores_gemma":[0.9949715,0.00001511961,0.00001128232,0.0007519248,0.0006885882,0.000006539398,0.000001716048,0.00001314757,0.00354018],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5690402,"threshold_uncertainty_score":0.9990498,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2461301006","doi":"10.5539/elt.v9n8p106","title":"Effectiveness of Using Screencast Feedback on EFL Students’ Writing and Perception","year":2016,"lang":"en","type":"article","venue":"English Language Teaching","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":83,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Psychology; Perception; Peer feedback; Constructive; Video feedback; Control (management); Mathematics education; Pedagogy; Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.01930918518031864,"gpt":0.3550008529784101,"spread":0.3356916677980915,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002928851,0.0001197233,0.0001863232,0.00009498822,0.0003857406,0.0001002277,0.0002166329,0.00007450909,0.00008531089],"category_scores_gemma":[0.0006219578,0.00009282995,0.00005341491,0.00009291847,0.0001323732,0.0003500441,0.00009725403,0.0001630751,0.000005592598],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001385975,"about_ca_system_score_gemma":0.00002051887,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008120852,"about_ca_topic_score_gemma":0.00005353777,"domain_scores_codex":[0.9980769,0.000742465,0.0001717361,0.0002434241,0.0005072107,0.0002582674],"domain_scores_gemma":[0.9989868,0.0006774951,0.00009425802,0.0001291248,0.00004276777,0.0000695273],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0000760273,0.0001468917,0.592762,0.00006901531,0.00004831751,0.000009646579,0.2745705,0.000003436622,0.07861347,0.004332264,0.00001323734,0.04935524],"study_design_scores_gemma":[0.002012707,0.0001386676,0.5098861,0.001568717,0.0000550471,0.000001051087,0.484771,0.00002108578,0.0009258764,0.00008010784,0.0001542966,0.000385313],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9856686,0.0000579088,0.0004740479,0.00002173852,0.0002130826,0.0002352804,0.000004462658,0.00008408751,0.01324079],"genre_scores_gemma":[0.998669,0.00001625751,0.0006185136,0.00001434402,0.0004698085,0.000004247484,0.000001932218,0.00001594716,0.0001899322],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2102005,"threshold_uncertainty_score":0.3785495,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1975314479","doi":"10.3138/cmlr.64.1.199","title":"Assessment for Learning: Integrating Assessment, Teaching, and Learning in the ESL/EFL Writing Classroom","year":2007,"lang":"en","type":"article","venue":"Canadian Modern Language Review/ La Revue canadienne des langues vivantes","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":82,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Assessment for learning; Mathematics education; Writing assessment; Pedagogy; Psychology; Computer science; Formative assessment","retraction":null,"screen_n_in":null,"score":{"opus":0.02022232402502297,"gpt":0.33829144772885,"spread":0.318069123703827,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.01120589,0.0003077693,0.0004978601,0.0002908822,0.001654146,0.0003215362,0.0005436676,0.0001521999,0.00005579579],"category_scores_gemma":[0.002793053,0.0002671605,0.0001482551,0.0003780079,0.0002416331,0.0002617735,0.00004781303,0.001377371,0.000002277324],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009754366,"about_ca_system_score_gemma":0.0004094025,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.2122739,"about_ca_topic_score_gemma":0.8421261,"domain_scores_codex":[0.9962596,0.00124012,0.000533979,0.0004865865,0.0002195978,0.001260136],"domain_scores_gemma":[0.9966921,0.002179859,0.0002470523,0.0002432695,0.000124719,0.0005130065],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"qualitative","study_design_scores_codex":[0.000007482498,0.00006183634,0.2574134,0.001659178,0.0001075602,0.0006914184,0.2532305,0.00001714842,0.001717211,0.04319862,0.0007673794,0.4411283],"study_design_scores_gemma":[0.0008406452,0.0002225032,0.2587015,0.005385499,0.0002186333,0.00009860351,0.4581854,0.003012024,0.000003313706,0.001017962,0.2712432,0.001070622],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8675956,0.02244808,0.003998598,0.002723422,0.0001996424,0.001808559,0.0000366318,0.0001353617,0.1010541],"genre_scores_gemma":[0.9850439,0.002679275,0.008712091,0.001003734,0.0004415141,0.0001035845,0.000119158,0.00005271067,0.001843986],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6298521,"threshold_uncertainty_score":0.9999781,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2782375796","doi":"10.1016/j.stueduc.2017.12.008","title":"Re-conceptualizing classroom assessment fairness: A systematic meta-ethnography of assessment literature and beyond","year":2018,"lang":"en","type":"article","venue":"Studies In Educational Evaluation","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":82,"is_retracted":false,"has_abstract":false,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Queen's University","funders":"","keywords":"Conceptualization; Accountability; Construct (python library); Educational assessment; Psychology; Ethnography; Standards-based assessment; Process (computing); Pedagogy; Alternative assessment; Mathematics education; Sociology; Computer science; Political science","retraction":null,"screen_n_in":null,"score":{"opus":0.1824586292219303,"gpt":0.5132713437504184,"spread":0.330812714528488,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006089516,0.0001811818,0.0005254899,0.0003139467,0.0004747396,0.00009028619,0.0001976261,0.00008745705,0.0002659176],"category_scores_gemma":[0.0008890752,0.0001514035,0.0001183353,0.000955768,0.0008144926,0.0004169374,0.00008448522,0.0001396649,0.000003137873],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000424731,"about_ca_system_score_gemma":0.0006364452,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008026866,"about_ca_topic_score_gemma":0.001054059,"domain_scores_codex":[0.9961613,0.001157314,0.0006193485,0.0003465121,0.001476608,0.0002389314],"domain_scores_gemma":[0.9966658,0.001143116,0.0004174353,0.0002019972,0.001520175,0.00005148473],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.00001978682,0.0006333817,0.1340922,0.003170358,0.003342903,5.696983e-7,0.5813432,0.00002424203,0.0001119724,0.2698024,0.006290936,0.001168078],"study_design_scores_gemma":[0.001213354,0.0003106268,0.1888143,0.00246649,0.002823114,7.778413e-7,0.6834535,0.0007619327,0.00001496803,0.1191397,0.0005362915,0.0004650339],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6998417,0.05310109,0.0004897928,0.01513653,0.006444265,0.007136467,0.0000370961,0.00008246341,0.2177307],"genre_scores_gemma":[0.9896287,0.0008079219,0.00789719,0.000137214,0.0004133863,0.0008193729,0.00002981615,0.000009182502,0.0002572415],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.289787,"threshold_uncertainty_score":0.6174057,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2140654065","doi":"","title":"Formative Assessment and the Contemporary Classroom: Synergies and Tensions between Research and Practice.","year":2011,"lang":"en","type":"article","venue":"Canadian Journal of Education / Revue canadienne de l éducation","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":82,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"about_ca":true},"ca_institutions":"Brock University","funders":"","keywords":"Formative assessment; Variety (cybernetics); Professional development; Pedagogy; Mathematics education; Psychology; Faculty development; Teacher education; Medical education; Sociology; Medicine; Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.2594907877898358,"gpt":0.4333496664294458,"spread":0.17385887863961,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00523093,0.00008039937,0.0001617254,0.0003663796,0.0009871922,0.0002011871,0.00016855,0.00007290884,0.00003209898],"category_scores_gemma":[0.001993585,0.00006766112,0.00002127353,0.0002939814,0.0008056787,0.0007339992,0.00001565226,0.0003083482,9.212743e-7],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009576009,"about_ca_system_score_gemma":0.008864352,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.1288346,"about_ca_topic_score_gemma":0.3592528,"domain_scores_codex":[0.998451,0.0006847926,0.0002850686,0.0001218076,0.0001204879,0.0003368201],"domain_scores_gemma":[0.9966347,0.00112873,0.0002877412,0.0001139634,0.001024376,0.0008104439],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.00002515054,0.00003296807,0.1284289,0.00002177346,0.00007138892,0.000005324046,0.6919468,1.140411e-7,0.0000079647,0.162109,0.01212503,0.005225537],"study_design_scores_gemma":[0.0002875466,0.00009053537,0.3582227,0.00008587546,0.00004989496,0.00005733417,0.5891812,0.000003916492,0.00000175359,0.01567087,0.0362656,0.00008274681],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9315327,0.001308636,0.00002866259,0.03329591,0.0008119114,0.0003154929,0.00000531452,0.000002954953,0.0326984],"genre_scores_gemma":[0.9973254,0.0004077335,0.0008745736,0.0002827155,0.000362816,0.00001853948,0.000004804387,0.000007645081,0.0007157449],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2304182,"threshold_uncertainty_score":0.9967545,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2167507251","doi":"10.1111/medu.12517","title":"Automated essay scoring and the future of educational assessment in medical education","year":2014,"lang":"en","type":"article","venue":"Medical Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":80,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Medical Council of Canada; University of Alberta","funders":"","keywords":"Summative assessment; Formative assessment; Computer science; Process (computing); Context (archaeology); Scoring system; Writing assessment; Educational measurement; Artificial intelligence; Natural language processing; Machine learning; Mathematics education; Curriculum; Psychology; Medicine; Pedagogy","retraction":null,"screen_n_in":null,"score":{"opus":0.007292918176272418,"gpt":0.3889499880168408,"spread":0.3816570698405684,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003247858,0.00008300824,0.0001642869,0.0001018235,0.0001928185,0.00004446965,0.0003106954,0.0001560306,0.001711079],"category_scores_gemma":[0.002603784,0.00006068587,0.00003201485,0.0003606279,0.0004784511,0.0001384338,0.00004613607,0.0002516379,0.000008097481],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001578628,"about_ca_system_score_gemma":0.01241013,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001613262,"about_ca_topic_score_gemma":0.001806709,"domain_scores_codex":[0.9975402,0.0005262927,0.0003242319,0.0001807286,0.00125531,0.0001731988],"domain_scores_gemma":[0.9988843,0.0005535576,0.000132433,0.0001321625,0.000127712,0.0001698929],"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":[0.00001491421,0.0008687578,0.2090398,0.00003781899,0.00001194825,6.532783e-8,0.01104376,5.021541e-7,0.000002635624,0.614473,0.01724652,0.1472602],"study_design_scores_gemma":[0.001659379,0.00003038018,0.8698143,0.0004131703,0.00003246984,0.000003347403,0.02255609,0.005027284,0.000002854037,0.0167968,0.0834605,0.0002034565],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5630151,0.0009811503,0.00008898578,0.3599799,0.005178316,0.0005364445,4.120704e-7,0.00005643197,0.07016329],"genre_scores_gemma":[0.9942191,0.0003835559,0.0004066657,0.002277235,0.001793189,0.0001131998,0.00002266636,0.000006207894,0.0007781372],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6607745,"threshold_uncertainty_score":0.9992015,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2086922103","doi":"10.1002/tesq.105","title":"Motivation and Test Anxiety in Test Performance Across Three Testing Contexts: The <scp>CAEL</scp>,<scp> CET</scp>, and <scp>GEPT</scp>","year":2013,"lang":"en","type":"article","venue":"TESOL Quarterly","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":77,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"Mount Saint Vincent University; Carleton University; Queen's University","funders":"U.S. Department of Energy","keywords":"Test anxiety; Test (biology); Psychology; Context (archaeology); Anxiety; Social psychology; Language assessment; Developmental psychology; Mathematics education","retraction":null,"screen_n_in":null,"score":{"opus":0.02374035340395477,"gpt":0.2807221828600872,"spread":0.2569818294561324,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001715787,0.0004921216,0.0004921919,0.0001270654,0.001873445,0.001205294,0.0007001758,0.0003056634,0.00001497111],"category_scores_gemma":[0.005842639,0.0004015983,0.00008309764,0.0009956824,0.0009669386,0.001643264,0.0001580773,0.0006123004,0.0001578514],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001300289,"about_ca_system_score_gemma":0.0001300828,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002595366,"about_ca_topic_score_gemma":0.002937181,"domain_scores_codex":[0.9961533,0.00016827,0.0006820718,0.0007559219,0.0008085135,0.001431921],"domain_scores_gemma":[0.9858107,0.01268123,0.0004280162,0.000445592,0.0003517932,0.0002826562],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[3.988584e-7,0.0001538825,0.9138054,0.00003630797,0.00001951482,0.000002485138,0.06236891,0.000001959623,0.001536253,0.0002203746,0.00340258,0.0184519],"study_design_scores_gemma":[0.001020209,0.0006138945,0.9120818,0.0001215064,0.0000271479,0.00000653762,0.07990547,0.001413024,0.00007270964,0.0008289532,0.003836374,0.00007237762],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9808239,0.0006198175,0.00002983308,0.0003139183,0.0002408339,0.001420154,0.00002398222,0.0002404802,0.01628705],"genre_scores_gemma":[0.9957807,0.0001627754,0.0003048151,0.0003506505,0.0005389691,0.0002041772,0.0000136114,0.00005097037,0.002593315],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01837952,"threshold_uncertainty_score":0.9998436,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2108440479","doi":"10.1080/00131725.2011.577669","title":"Being Fair: Teachers’ Interpretations of Principles for Standards-Based Grading","year":2011,"lang":"en","type":"article","venue":"The Educational Forum","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":77,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"University of Ottawa","funders":"","keywords":"Grading (engineering); Mathematics education; Psychology; Academic standards; Set (abstract data type); Pedagogy; Higher education; Computer science; Engineering; Political science","retraction":null,"screen_n_in":null,"score":{"opus":0.07001771760809876,"gpt":0.3902159675238942,"spread":0.3201982499157954,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000741084,0.00004989009,0.00006523079,0.00004351317,0.0004725479,0.00002265695,0.0002590526,0.0000233915,0.0003344085],"category_scores_gemma":[0.0003040684,0.00003912626,0.00007374098,0.0001107938,0.0001701064,0.0001055401,0.00001821018,0.00004278769,0.000004059017],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001016835,"about_ca_system_score_gemma":0.000595751,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000224999,"about_ca_topic_score_gemma":0.0003996054,"domain_scores_codex":[0.9992958,0.00004815691,0.0001426075,0.00008257299,0.0002733914,0.0001574675],"domain_scores_gemma":[0.9992388,0.0003823306,0.00008816575,0.00009032337,0.0001685873,0.00003176313],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00001338286,0.0000697668,0.08611476,0.000004236524,0.00002560813,9.729662e-9,0.07770976,0.000003159206,0.00002855549,0.8329976,0.002432221,0.0006009235],"study_design_scores_gemma":[0.0008245112,0.000177566,0.2152953,0.000143387,0.0001552201,2.752481e-7,0.2366945,0.0003825849,0.00114744,0.3677661,0.1770284,0.0003848212],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6488358,0.0002188763,0.01339021,0.0422912,0.00228536,0.001458282,0.00009741794,0.0000817422,0.2913412],"genre_scores_gemma":[0.9934412,0.0000035507,0.004061677,0.0001133961,0.0001380557,0.00007504957,0.00001108122,0.000006040496,0.002149976],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4652316,"threshold_uncertainty_score":0.3661538,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2600733185","doi":"10.1080/0969594x.2017.1297010","title":"Developing assessment capable teachers in this age of accountability","year":2017,"lang":"en","type":"article","venue":"Assessment in Education Principles Policy and Practice","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":75,"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; Psychology; Medical education; Political science; Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.1225845974022681,"gpt":0.5148076355503635,"spread":0.3922230381480953,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005457025,0.0001511705,0.0002598889,0.0002510282,0.0006227701,0.0003924616,0.000512693,0.0001279713,0.0001255186],"category_scores_gemma":[0.003231292,0.0001624988,0.00003586689,0.0002870877,0.0003158816,0.002027341,0.000201889,0.0003605561,0.000003886596],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00124927,"about_ca_system_score_gemma":0.0057436,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.09320701,"about_ca_topic_score_gemma":0.01843984,"domain_scores_codex":[0.9975737,0.0007353768,0.0004992859,0.0003345431,0.0004962453,0.0003608429],"domain_scores_gemma":[0.9973277,0.001351779,0.000623671,0.0004520884,0.0001548377,0.00008987364],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00001524136,0.0005197534,0.5562643,0.00003339005,0.0000186363,0.000001585196,0.02971618,0.000005175718,0.00009025372,0.4065339,0.00007300705,0.006728579],"study_design_scores_gemma":[0.0003475698,0.00001998301,0.7810145,0.00007257796,0.00001658217,0.000001020581,0.05467653,0.00001478507,0.00001131535,0.003633609,0.1600303,0.0001612413],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5109373,0.00006620627,0.00006757063,0.02198634,0.0003839033,0.000487625,0.000002447362,0.0000147035,0.4660539],"genre_scores_gemma":[0.9771204,0.00136459,0.01853381,0.0004878001,0.0002106914,0.0001035273,0.00001239934,0.0000102076,0.002156608],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.466183,"threshold_uncertainty_score":0.9998929,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1996435010","doi":"10.1080/09695940701272773","title":"Did we take the same test? Differing accounts of the Ontario Secondary School Literacy Test by first and second language test‐takers","year":2007,"lang":"en","type":"article","venue":"Assessment in Education Principles Policy and Practice","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":74,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"Queen's University; Carleton University","funders":"","keywords":"Test (biology); Graduation (instrument); Psychology; Context (archaeology); Construct (python library); Literacy; Construct validity; Mathematics education; Fidelity; Test score; Standardized test; Pedagogy; Developmental psychology; Computer science; Psychometrics; Mathematics","retraction":null,"screen_n_in":null,"score":{"opus":0.02100229501179931,"gpt":0.3845813286896781,"spread":0.3635790336778789,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002388958,0.0001786905,0.0001731892,0.0001097142,0.0006577378,0.0003841227,0.0003783061,0.00009920697,0.0003271223],"category_scores_gemma":[0.004567929,0.0001313146,0.00003937975,0.0004546433,0.0002520351,0.001184283,0.000179183,0.0005769877,0.000004157873],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005247691,"about_ca_system_score_gemma":0.0020187,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.04493859,"about_ca_topic_score_gemma":0.1139421,"domain_scores_codex":[0.9983174,0.0002050183,0.0004182057,0.0002808006,0.0004265653,0.0003519708],"domain_scores_gemma":[0.9892814,0.009708045,0.0004543165,0.0003119002,0.0001122827,0.0001321193],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00001662022,0.0006631211,0.8745536,0.00004868594,0.00002720056,9.822992e-7,0.1114054,5.882509e-7,0.0006239841,0.003228653,0.001569173,0.007861994],"study_design_scores_gemma":[0.0002352006,0.00003407097,0.6397342,0.00005857932,0.00002670472,0.000005609869,0.04729789,0.000003764079,0.00004907619,0.0002276095,0.3122129,0.0001143526],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8785336,0.000717962,0.000005737945,0.03486021,0.0003170077,0.0005951427,0.00003316722,0.0000180155,0.08491918],"genre_scores_gemma":[0.9832307,0.0009199142,0.000621495,0.002271085,0.0003312866,0.00004199333,0.00001052814,0.00001383392,0.01255913],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3106437,"threshold_uncertainty_score":0.9614213,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4400440977","doi":"10.55016/ojs/ajer.v53i1.55195","title":"Factors Affecting Teachers’ Grading and Assessment Practices","year":2007,"lang":"en","type":"article","venue":"Alberta Journal of Educational Research","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":73,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Grading (engineering); Psychology; Mathematics education; Pedagogy; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.2729481972337564,"gpt":0.5720544857102489,"spread":0.2991062884764925,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.008342218,0.00007110175,0.0001223185,0.0003225982,0.0008482348,0.000247262,0.0002823558,0.00005823105,0.002052923],"category_scores_gemma":[0.01740982,0.00005798895,0.00005256108,0.0004196439,0.000223809,0.0006596246,0.00005154815,0.0005876735,0.00001200785],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003292327,"about_ca_system_score_gemma":0.001076689,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003883352,"about_ca_topic_score_gemma":0.00634469,"domain_scores_codex":[0.9976609,0.0004055412,0.0002734335,0.0001231235,0.001154295,0.0003826534],"domain_scores_gemma":[0.9573922,0.04145533,0.0004121119,0.00006298505,0.0004336997,0.0002436496],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00000985947,0.0001366429,0.9417267,0.000004814995,0.00005094221,4.791697e-7,0.03385338,2.320174e-7,0.0002776717,0.02073358,0.002206731,0.0009988941],"study_design_scores_gemma":[0.0001532461,0.00008527441,0.8581464,0.00003648162,0.00001634345,0.000004075446,0.1021244,0.000001112746,0.00004175077,0.0005896594,0.0387331,0.00006812252],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8045771,0.0002534752,0.000004930459,0.008473429,0.0003401281,0.00009421898,1.105157e-7,4.795263e-7,0.1862562],"genre_scores_gemma":[0.9860188,0.0001858058,0.0005858932,0.00002214539,0.0009093003,9.817772e-7,0.00000100462,0.000007187919,0.01226887],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1814417,"threshold_uncertainty_score":0.9988593,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2013464569","doi":"10.1080/0969594x.2013.776943","title":"Fair and equitable assessment practices for all students","year":2013,"lang":"en","type":"article","venue":"Assessment in Education Principles Policy and Practice","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":71,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Thompson Rivers University; University of Lethbridge; University of Alberta; University of Calgary","funders":"","keywords":"Intrusiveness; Equity (law); Psychology; Public relations; Best practice; Medical education; Applied psychology; Pedagogy; Social psychology; Political science; Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.1023168743994288,"gpt":0.5279200270248844,"spread":0.4256031526254556,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.004179651,0.0002085413,0.0002371054,0.0002521336,0.0006425898,0.001184108,0.0003592938,0.000132958,0.0001406804],"category_scores_gemma":[0.003173401,0.0002118671,0.0000362212,0.0003464833,0.0001532799,0.003488443,0.0002624991,0.0002812839,0.00001477248],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004633966,"about_ca_system_score_gemma":0.002181478,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0196238,"about_ca_topic_score_gemma":0.001214983,"domain_scores_codex":[0.997134,0.0006968656,0.0004453826,0.0004651367,0.000657997,0.0006006595],"domain_scores_gemma":[0.994364,0.004074993,0.0007698587,0.0002361321,0.0003138615,0.0002411873],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00004274996,0.001842809,0.2229104,0.00009676772,0.0001433305,8.524243e-7,0.01804011,0.000005288103,0.000235441,0.7311828,0.003819997,0.0216795],"study_design_scores_gemma":[0.0006782885,0.0001218495,0.2919045,0.00003538582,0.00008289351,0.000004646491,0.08186039,0.00009393153,0.000003673005,0.007085557,0.6178655,0.0002633843],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4649363,0.0006306556,0.0005220761,0.1363678,0.001022394,0.004128053,0.00001065014,0.0001004109,0.3922817],"genre_scores_gemma":[0.9457006,0.004114734,0.03419917,0.003967003,0.0007121699,0.001296294,0.00003454959,0.00002473072,0.009950678],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7240973,"threshold_uncertainty_score":0.9998528,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2923740196","doi":"10.1080/0969594x.2019.1593105","title":"Conceptualising fairness in classroom assessment: exploring the value of organisational justice theory","year":2019,"lang":"en","type":"article","venue":"Assessment in Education Principles Policy and Practice","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":71,"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":"Foundation (evidence); Economic Justice; Scholarship; Value (mathematics); Core (optical fiber); Sociology; Psychology; Social psychology; Epistemology; Political science; Computer science; Law","retraction":null,"screen_n_in":null,"score":{"opus":0.07905727411628827,"gpt":0.4421515498552321,"spread":0.3630942757389438,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005509842,0.0001531339,0.0002152979,0.0002652954,0.000302508,0.0001768171,0.0003539386,0.00008157531,0.000181437],"category_scores_gemma":[0.001945079,0.0001376627,0.00003591063,0.0008488765,0.0002238656,0.001742413,0.0001319266,0.0004014618,0.00001018672],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005734127,"about_ca_system_score_gemma":0.003732229,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003472368,"about_ca_topic_score_gemma":0.0003561579,"domain_scores_codex":[0.996267,0.001942137,0.0005124431,0.0003023901,0.0006499005,0.000326108],"domain_scores_gemma":[0.991627,0.007442335,0.0004194252,0.0002589938,0.0001827617,0.0000694409],"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":[0.00002865085,0.0003229735,0.1066119,0.0000401553,0.00002059672,4.183273e-7,0.03777248,0.0001840673,0.0001230797,0.8522458,0.00002172318,0.002628144],"study_design_scores_gemma":[0.0005097623,0.00003842234,0.563396,0.00009847654,0.00006077866,0.000002889843,0.3773915,0.0001447901,0.00001961376,0.01490691,0.04324486,0.0001859801],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7657065,0.0001308024,0.0003280732,0.01375263,0.001058244,0.0006923455,0.000003794297,0.00002087156,0.2183067],"genre_scores_gemma":[0.992701,0.0008593524,0.003746679,0.001014333,0.0003976421,0.0001081556,0.0000139136,0.00001486204,0.001144084],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8373389,"threshold_uncertainty_score":0.6620815,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1996477132","doi":"10.1177/0741088310371635","title":"Undergraduate Writing Assignments: An Analysis of Syllabi at One Canadian College","year":2010,"lang":"en","type":"article","venue":"Written Communication","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":69,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"Western University; University of Alberta","funders":"","keywords":"Syllabus; Mathematics education; Curriculum; Higher education; Task (project management); Academic writing; Psychology; Computer science; Pedagogy; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.03217846521966579,"gpt":0.3400945437894142,"spread":0.3079160785697485,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00110119,0.0000759697,0.000187508,0.0002580923,0.0009023706,0.00006274137,0.0007197179,0.0001029887,0.0004729163],"category_scores_gemma":[0.00007413554,0.00008854166,0.00007156444,0.0009009136,0.0002145229,0.0002573724,0.00009979092,0.0001657692,0.00002185787],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002714451,"about_ca_system_score_gemma":0.0001703081,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.2421239,"about_ca_topic_score_gemma":0.9324702,"domain_scores_codex":[0.9986742,0.0003081981,0.0002582853,0.0001467567,0.0003727103,0.000239827],"domain_scores_gemma":[0.9986197,0.0001758921,0.0001652319,0.0006813022,0.0001780167,0.0001798363],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00001067293,0.0002388295,0.7892851,0.000005363193,0.0005469159,8.179559e-7,0.00834503,0.00001590562,0.006556522,0.1918674,0.0008663748,0.002261118],"study_design_scores_gemma":[0.0004094799,0.0000369225,0.9530722,0.00002144313,0.0006829528,1.79003e-7,0.02001519,0.001673154,0.0001731513,0.001856149,0.02176725,0.0002918631],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8906112,0.00004657376,0.00001568984,0.006540043,0.00006730558,0.0002049918,0.00003573225,0.00003667664,0.1024418],"genre_scores_gemma":[0.9965639,0.0001438922,0.001668773,0.0001305339,0.00004011327,0.0000153009,0.0001651965,0.00000831409,0.001263949],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6903463,"threshold_uncertainty_score":0.7629229,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W4388945822","doi":"10.3389/feduc.2023.1270700","title":"Challenges and opportunities for classroom-based formative assessment and AI: a perspective article","year":2023,"lang":"en","type":"article","venue":"Frontiers in Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":65,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Kellogg's (Canada)","funders":"","keywords":"Formative assessment; Perspective (graphical); Computer science; Mathematics education; Engineering ethics; Psychology; Artificial intelligence; Engineering","retraction":null,"screen_n_in":null,"score":{"opus":0.08248159969855182,"gpt":0.404538068375617,"spread":0.3220564686770652,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005136054,0.00006277323,0.00009719751,0.0001685957,0.000196893,0.00006117883,0.00005349977,0.00004531327,0.000004902844],"category_scores_gemma":[0.0000483315,0.00006591071,0.00001670988,0.0001144876,0.0001303275,0.0003039717,0.00001480864,0.00005459287,7.216331e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002402484,"about_ca_system_score_gemma":0.0003782162,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007474604,"about_ca_topic_score_gemma":0.0002454042,"domain_scores_codex":[0.9993693,0.00008062852,0.00009416985,0.0001457701,0.000136657,0.0001734228],"domain_scores_gemma":[0.9996624,0.00009068137,0.00004389932,0.00005287314,0.00009417996,0.00005597831],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"qualitative","study_design_scores_codex":[0.00004349168,0.0002552772,0.0839034,0.00005825922,0.00004223479,6.784403e-7,0.2884889,0.000004581779,0.00001473194,0.216908,0.04825319,0.3620272],"study_design_scores_gemma":[0.0003486866,0.00005354726,0.2212113,0.00002393752,0.0000121801,6.125186e-8,0.7276303,0.001455833,0.000005692597,0.03734066,0.01182784,0.00008999347],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7789204,0.007082559,0.004343429,0.1351047,0.003416581,0.001937723,0.00001376603,0.0001859898,0.06899485],"genre_scores_gemma":[0.9905671,0.004205739,0.003783859,0.000321674,0.0001219254,0.0002554235,0.00001032878,0.000007091842,0.0007268942],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4391413,"threshold_uncertainty_score":0.2687761,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W1978294241","doi":"10.1108/02621710010322580","title":"Receptivity to assessment‐based feedback for management development","year":2000,"lang":"en","type":"article","venue":"Journal of Management Development","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":65,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Concordia University","funders":"","keywords":"Receptivity; Psychology; Congruence (geometry); Social psychology; Positive feedback","retraction":null,"screen_n_in":null,"score":{"opus":0.0340642683330416,"gpt":0.3544036209878689,"spread":0.3203393526548273,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003782463,0.0003579118,0.000486485,0.0005794473,0.0009242448,0.0003033818,0.001017751,0.00009477554,0.00208011],"category_scores_gemma":[0.00001812882,0.000344324,0.0002080265,0.0007081145,0.00006937423,0.0003689843,0.0001533566,0.0001869559,0.0002640634],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001288105,"about_ca_system_score_gemma":0.0004623858,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006627735,"about_ca_topic_score_gemma":0.0000727333,"domain_scores_codex":[0.9954661,0.0001645982,0.001179903,0.00044065,0.001906692,0.0008420605],"domain_scores_gemma":[0.9984845,0.0001183925,0.0004215584,0.0002647595,0.0002942192,0.0004165559],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0004753195,0.001149891,0.006831024,0.0002378605,0.001174904,0.00009451323,0.007923694,0.0004806218,0.00003010414,0.005302899,0.04455656,0.9317426],"study_design_scores_gemma":[0.001996177,0.0001085602,0.1292281,0.0002217303,0.00009518816,8.557128e-7,0.003446756,0.000011905,0.0001196672,0.0001512837,0.8641926,0.0004271927],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"other","genre_gemma":"methods","genre_scores_codex":[0.2877342,0.0001400973,0.07440869,0.009515555,0.003048972,0.006337141,0.000006309684,0.0002265575,0.6185825],"genre_scores_gemma":[0.1923853,0.0003028225,0.7340251,0.001899385,0.0004221408,0.0003442017,0.00001941137,0.00006161345,0.07054],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9313154,"threshold_uncertainty_score":0.9999009,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2147628522","doi":"","title":"Some drivers of test item difficulty in mathematics : an analysis of the competency rubric","year":2012,"lang":"en","type":"article","venue":"ACEReSearch (Australian Council for Educational Research)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":64,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true},"ca_institutions":"","funders":"","keywords":"Rubric; Test (biology); Inclusion (mineral); Mathematics education; Test preparation; Psychology; Pedagogy; Computer science; Medical education; Engineering; Social psychology; Medicine","retraction":null,"screen_n_in":null,"score":{"opus":0.35000712176952,"gpt":0.4785186624063204,"spread":0.1285115406368004,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.009152442,0.0001135985,0.0002860887,0.0004715073,0.0004816415,0.00007093784,0.001186869,0.0001057377,0.001525858],"category_scores_gemma":[0.00895057,0.0000894094,0.0002006029,0.002996424,0.001154669,0.0005722618,0.0001527094,0.0003362625,0.00002708121],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00153621,"about_ca_system_score_gemma":0.004147247,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005162846,"about_ca_topic_score_gemma":0.007404346,"domain_scores_codex":[0.9934162,0.0004569809,0.000413431,0.0002314196,0.004604148,0.0008778214],"domain_scores_gemma":[0.9912003,0.005345425,0.0001487045,0.0004213811,0.002595613,0.0002885777],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00001770966,0.001951914,0.813169,0.00008327176,0.0001733352,9.879776e-8,0.02695471,0.00001676349,0.001594415,0.1409698,0.01499944,0.00006946819],"study_design_scores_gemma":[0.0002828153,0.00008407081,0.9449779,0.00004157329,0.00007093918,1.038644e-7,0.04231956,0.0001357899,0.0001734502,0.00522829,0.00657298,0.0001125025],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9863477,0.0000884189,0.000001072387,0.005986522,0.0001549892,0.0009161863,0.0001743373,0.000006014037,0.006324804],"genre_scores_gemma":[0.9759531,0.0001142522,0.0003671285,0.000009034919,0.0002605894,0.00008703986,0.00004232479,0.00001280376,0.02315375],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1357416,"threshold_uncertainty_score":0.9993975,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2472075195","doi":"10.1017/s0261444815000233","title":"Review of washback research literature within Kane's argument-based validation framework","year":2015,"lang":"en","type":"article","venue":"Language Teaching","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":64,"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":"Empirical research; Argument (complex analysis); Maturity (psychological); Systematic review; English language; Psychology; Political science; Epistemology; Mathematics education; Medicine; Philosophy; Law; Developmental psychology","retraction":null,"screen_n_in":null,"score":{"opus":0.08897567591661655,"gpt":0.4676807480738409,"spread":0.3787050721572244,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008405294,0.00009677374,0.0001930687,0.0001076777,0.0002755386,0.0001413566,0.0003822704,0.0001173853,0.0001927444],"category_scores_gemma":[0.002783663,0.00008355034,0.00006624773,0.0005155813,0.0001002474,0.000237498,0.00006173008,0.0007020785,0.00005114832],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001297221,"about_ca_system_score_gemma":0.0001785059,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007269448,"about_ca_topic_score_gemma":0.00006574538,"domain_scores_codex":[0.9968656,0.001354676,0.0002524979,0.0002029523,0.001032305,0.0002919937],"domain_scores_gemma":[0.9989012,0.0003555972,0.0001327331,0.0002900443,0.0001928764,0.0001275712],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"qualitative","study_design_scores_codex":[0.00006070068,0.0004102897,0.02273194,0.002547823,0.00007092238,0.0000511237,0.8282193,0.00002511056,0.001215261,0.08848168,0.0392401,0.01694577],"study_design_scores_gemma":[0.003763122,0.0009055446,0.002045689,0.1229825,0.0003066562,0.000005826112,0.5872716,0.0005816926,0.005315928,0.01855049,0.2561239,0.002147038],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6932727,0.09987199,0.001739795,0.008966687,0.001415091,0.001836243,0.00002071576,0.0003516127,0.1925252],"genre_scores_gemma":[0.9798496,0.0007700308,0.0151538,0.001036793,0.0006753333,0.00002309469,0.00007431699,0.00002017043,0.002396829],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.286577,"threshold_uncertainty_score":0.3407084,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2063505651","doi":"10.3200/joeb.81.6.322-326","title":"Using Peer Review to Improve Student Writing in Business Courses","year":2006,"lang":"en","type":"article","venue":"Journal of Education for Business","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":62,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false},"ca_institutions":"Saint Mary's University","funders":"","keywords":"Peer feedback; Technical peer review; Peer review; Computer science; Peer-to-peer; Medical education; Psychology; Mathematics education; World Wide Web; Medicine; Political science","retraction":null,"screen_n_in":null,"score":{"opus":0.0662221502487459,"gpt":0.4615727496667562,"spread":0.3953505994180103,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002009784,0.00009934387,0.0002664287,0.0002296697,0.0001915909,0.0001637764,0.0002733864,0.00004537252,0.00005282672],"category_scores_gemma":[0.0007987818,0.00009179631,0.00006693453,0.001142783,0.00003608268,0.0004660786,0.00002440436,0.00007613109,0.000003329892],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003226585,"about_ca_system_score_gemma":0.001263247,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007981966,"about_ca_topic_score_gemma":0.0003192362,"domain_scores_codex":[0.9982461,0.00005594299,0.0006013245,0.0001181418,0.000755968,0.0002224622],"domain_scores_gemma":[0.9941015,0.0001008641,0.0004767154,0.00008214326,0.005173782,0.00006496864],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000179265,0.00534169,0.6548789,0.002183691,0.0001125653,0.0000132705,0.01142467,0.00137165,0.004714921,0.02432265,0.25081,0.04464677],"study_design_scores_gemma":[0.0006803165,0.00002980366,0.806959,0.002807345,0.000129078,0.000007804247,0.01223238,0.000007467899,0.00002952783,0.0006673987,0.1761816,0.0002683376],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9179365,0.006277052,0.002007012,0.05853179,0.006977318,0.001347702,0.000005811917,0.00001517456,0.006901613],"genre_scores_gemma":[0.9807703,0.0009648717,0.007509507,0.001084895,0.004978865,0.00004132864,0.0000121763,0.00002823733,0.004609834],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1520801,"threshold_uncertainty_score":0.3743345,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2061239388","doi":"10.3138/cmlr.67.3.377","title":"Working Smarter, Not Working Harder: Revisiting Teacher Feedback in the L2 Writing Classroom","year":2011,"lang":"en","type":"article","venue":"Canadian Modern Language Review/ La Revue canadienne des langues vivantes","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":62,"is_retracted":false,"has_abstract":true,"routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false},"ca_institutions":"","funders":"","keywords":"Formative assessment; Feeling; Confusion; Psychology; Value (mathematics); Mathematics education; Peer feedback; Pedagogy; Social psychology; Computer science","retraction":null,"screen_n_in":null,"score":{"opus":0.05312265572183805,"gpt":0.2858817771152325,"spread":0.2327591213933944,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.003435901,0.0003837841,0.000610598,0.0002904698,0.0007539063,0.0002768496,0.001171809,0.0001926438,0.0005252396],"category_scores_gemma":[0.000833842,0.0003434283,0.0002377473,0.0008379528,0.0003061082,0.000252675,0.000068327,0.0006247407,0.00005252121],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008165094,"about_ca_system_score_gemma":0.0002715526,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.2634419,"about_ca_topic_score_gemma":0.8664898,"domain_scores_codex":[0.9960514,0.0008842389,0.00063795,0.0005861002,0.0002631257,0.001577239],"domain_scores_gemma":[0.9980577,0.0004233826,0.0002568275,0.0005762067,0.00009605333,0.0005898447],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"qualitative","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001371211,0.00005081722,0.1695648,0.0008843634,0.0001136798,0.002444385,0.4733525,0.000001442706,0.0003299086,0.005385099,0.002030449,0.3458288],"study_design_scores_gemma":[0.001097074,0.00007803083,0.2588188,0.03217737,0.0004830666,0.0002499158,0.2775775,0.0004802652,0.00001957479,0.001179631,0.4253059,0.002532819],"study_design_candidate":"qualitative","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6892459,0.08902,0.00007583553,0.003657875,0.0005275119,0.001525538,0.00003152957,0.0001688917,0.2157469],"genre_scores_gemma":[0.9859936,0.007669674,0.0009444319,0.002333809,0.001028789,0.00008727409,0.00004502597,0.00006961344,0.001827844],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6030479,"threshold_uncertainty_score":0.9999018,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null},{"id":"W2770188235","doi":"10.1080/09585176.2017.1401550","title":"Student perspectives on assessment for learning","year":2017,"lang":"en","type":"article","venue":"The Curriculum Journal","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":62,"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":"Mathematics education; Thematic analysis; Terminology; Psychology; Portfolio; Coding (social sciences); Value (mathematics); Computer science; Qualitative research; Mathematics; Sociology","retraction":null,"screen_n_in":null,"score":{"opus":0.03844282093240321,"gpt":0.4392462300933151,"spread":0.4008034091609119,"validation_status":"score_only:v0-immature-baseline"},"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.002740597,0.00009967885,0.0001288172,0.00003627603,0.008379923,0.001278815,0.0009740979,0.00003894596,0.0002185651],"category_scores_gemma":[0.0002953215,0.00006155465,0.0001562816,0.00003841741,0.0002272979,0.0002544121,0.00008643037,0.000437949,0.00002747352],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002169047,"about_ca_system_score_gemma":0.0001149253,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009505637,"about_ca_topic_score_gemma":0.00005553564,"domain_scores_codex":[0.9984759,0.0002690849,0.0001452242,0.0001393622,0.000640918,0.0003295227],"domain_scores_gemma":[0.9990409,0.0001448236,0.0003277088,0.0001948382,0.000193337,0.00009837966],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"qualitative","study_design_scores_codex":[0.00002937562,0.0007969104,0.5256286,0.000004988092,0.0003159837,0.00001625337,0.1525251,0.0001302667,0.00009944267,0.2846466,0.01640124,0.01940526],"study_design_scores_gemma":[0.001054318,0.0003450904,0.4272619,0.00005214727,0.00007348917,0.00000526879,0.512233,0.000124623,0.000006199921,0.002823514,0.05580622,0.0002141558],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7969167,0.0002288781,0.001297582,0.01492643,0.002027703,0.0005322563,0.000001080779,0.00004420492,0.1840251],"genre_scores_gemma":[0.9930295,0.0004603261,0.0004257266,0.00004771433,0.002139793,0.00002049801,3.19473e-7,0.000009274701,0.003866902],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.359708,"threshold_uncertainty_score":0.9997579,"prediction_status":"machine_predicted_unvalidated"},"labels":[],"label_agreement":null}]}