{"meta":{"query_hash":"028605329201","filters":{"topic":"Student Assessment and Feedback"},"cohort_total":860,"direct_labels_cover":1,"predictions_cover":860,"exported":860,"export_cap":100000,"truncated":false,"label_status":"direct model label, unvalidated","prediction_status":"machine_predicted_unvalidated (Codex and Gemma teacher distillation)","score_status":"score_only:v0-immature-baseline","snapshot":{"source":"OpenAlex, pinned release, all 482 partitions","release":"2026-06-24","frame_built":"2026-07-12"},"permalink":"https://metacan.xera.ac/q/028605329201","api":"https://metacan.xera.ac/api/v1/cohort?topic=Student+Assessment+and+Feedback"},"results":[{"id":"W12634517","doi":"10.1097/00001756-200303030-00046","title":"Getting Feedback to Feed Forward: Incorporating revision into upper-year English papers","year":2011,"lang":"en","type":"article","venue":"Teaching Innovation Projects","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Mathematics education; Value (mathematics); Writing process; Academic writing; Scientific writing; Technical writing; Perception; Professional writing; Pedagogy; Computer science; Psychology; Higher education; Linguistics","score_opus":0.041823068904343834,"score_gpt":0.330857381163083,"score_spread":0.28903431225873916,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W12634517","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.648646,0.007303637,0.056528214,0.027953146,0.015393105,0.0010117637,0.0014012521,0.0073819575,0.23438093],"genre_scores_gemma":[0.9030475,0.0022845378,0.027586399,0.0013512415,0.0024987867,0.00018135033,0.0007157423,0.0010932006,0.061241213],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9928007,0.003074079,0.0008375513,0.00055873074,0.0023460032,0.00038295166],"domain_scores_gemma":[0.8802649,0.06452888,0.009385502,0.011860997,0.027925655,0.0060342574],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0100807985,0.0005176569,0.0003972089,0.0019083905,0.00085589255,0.004873884,0.0011012984,0.00079067325,0.021074658],"category_scores_gemma":[0.13701439,0.00020328638,0.00038827775,0.0011141187,0.0008321496,0.0045836787,0.0019608776,0.0009036422,0.005143921],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007591724,0.00058139005,0.011956668,0.0010593304,0.00004486122,0.0014916074,0.011055949,0.00050261087,0.008263362,0.005815282,0.0589607,0.89950913],"study_design_scores_gemma":[0.00037651273,0.0030855525,0.093567714,0.0021174005,0.00021888525,0.0037564782,0.012616126,0.006505138,0.03134167,0.03373059,0.8123595,0.00032445448],"about_ca_topic_score_codex":0.0010412545,"about_ca_topic_score_gemma":0.0014305892,"teacher_disagreement_score":0.021074658,"about_ca_system_score_codex":0.0010794094,"about_ca_system_score_gemma":0.0022739766,"threshold_uncertainty_score":0.070501745},"labels":[],"label_agreement":null},{"id":"W134909854","doi":"10.5206/cie-eci.v36i1.9088","title":"ESL/EFL Instructors’ Beliefs about Assessment and Evaluation","year":2007,"lang":"en","type":"article","venue":"Comparative and International Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Queen's University; University of Alberta","funders":"Beijing Foreign Studies University; Social Sciences and Humanities Research Council of Canada; Queen's University","keywords":"Psychology; Humanities; Philosophy","score_opus":0.14118637835775827,"score_gpt":0.5323399088658649,"score_spread":0.39115353050810664,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W134909854","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9989208,0.000037225513,0.00005703844,0.00006160678,0.0000021477933,0.000010528144,0.000016783222,0.0000025605016,0.00089127925],"genre_scores_gemma":[0.9969566,0.00009553983,0.000118825854,0.00006982654,0.000002464384,0.000015522315,0.00003531685,0.0000016744494,0.0027042357],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.99826247,0.00032442086,0.00015848225,0.0001282135,0.00069631275,0.00043016797],"domain_scores_gemma":[0.9898437,0.0024038453,0.0019192352,0.00027463812,0.003721487,0.0018371046],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0034508924,0.00028005714,0.0002647129,0.0010726439,0.0017425225,0.0017030484,0.000512919,0.00031941728,0.0023489257],"category_scores_gemma":[0.007217974,0.00024661724,0.00020122448,0.00071727816,0.002067475,0.0005297806,0.0010508667,0.0006974034,0.00033488017],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011256182,0.00011753279,0.937359,0.00004568335,0.000018785368,0.00036679048,0.038120996,0.0001580063,0.0016700581,0.0001980324,0.00041242372,0.021420185],"study_design_scores_gemma":[0.000015991176,0.00022974619,0.93886936,0.00007364758,0.000015759691,0.00009809639,0.05603243,0.0003180788,0.0009773627,0.00006717875,0.0032766254,0.000025773366],"about_ca_topic_score_codex":0.29830232,"about_ca_topic_score_gemma":0.32879302,"teacher_disagreement_score":0.29830232,"about_ca_system_score_codex":0.0052869935,"about_ca_system_score_gemma":0.0039854296,"threshold_uncertainty_score":0.593132},"labels":[],"label_agreement":null},{"id":"W134958124","doi":"10.55016/ojs/ajer.v50i3.55088","title":"Teachers' Attitudes Toward Government-Mandated Provincial Testing in Manitoba","year":2003,"lang":"en","type":"article","venue":"Alberta Journal of Educational Research","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Government (linguistics); Psychology; Educational research; Mathematics education; Public administration; Political science; Pedagogy","score_opus":0.15520904463095445,"score_gpt":0.4500630955999164,"score_spread":0.294854050968962,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W134958124","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9980186,0.000045508048,0.000030774587,0.0004081617,0.0000042945217,0.000008437843,0.000020175825,0.000004409481,0.0014596648],"genre_scores_gemma":[0.9981805,0.000116503164,0.00008042203,0.00013973942,0.000002123752,0.000008946149,0.000026346132,0.0000029321673,0.0014425857],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99841213,0.00037607836,0.000090724556,0.00010785239,0.000531697,0.00048153618],"domain_scores_gemma":[0.99362344,0.0010003521,0.0011410153,0.00019403448,0.0025064817,0.0015346851],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022525063,0.00015471557,0.00018942045,0.0006694114,0.0039615063,0.0015378892,0.0005464689,0.00033516382,0.0016036937],"category_scores_gemma":[0.0059475414,0.00034455088,0.00021130955,0.0010098043,0.0017031553,0.00026227307,0.0010792485,0.0010121443,0.00021887055],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012496595,0.00013884253,0.92660534,0.000040697614,0.00002010908,0.00039698763,0.054162025,0.0002156512,0.0029235014,0.00041276246,0.00089515245,0.014063896],"study_design_scores_gemma":[0.000010660365,0.00014374951,0.9537987,0.00005143267,0.000014849268,0.00009777385,0.041481294,0.00033562022,0.00057037047,0.000050952956,0.0034229704,0.000021538985],"about_ca_topic_score_codex":0.9170699,"about_ca_topic_score_gemma":0.9666236,"teacher_disagreement_score":0.98338324,"about_ca_system_score_codex":0.016616778,"about_ca_system_score_gemma":0.017960196,"threshold_uncertainty_score":0.16683692},"labels":[],"label_agreement":null},{"id":"W135797668","doi":"10.1007/978-1-4614-3178-7_12","title":"Assessment for Learning Using Digital Knowledge Maps","year":2013,"lang":"en","type":"book-chapter","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":22,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Formative assessment; Strengths and weaknesses; Computer science; Knowledge management; Knowledge survey; Mathematics education; Psychology; Summative assessment","score_opus":0.06704158551693114,"score_gpt":0.3793630614865653,"score_spread":0.31232147596963417,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W135797668","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009579314,0.01992163,0.40269423,0.004794448,0.001776888,0.00029951974,0.00023759628,0.0026978485,0.5579985],"genre_scores_gemma":[0.17204392,0.018815003,0.3629364,0.0007939956,0.0006361871,0.0004998834,0.0005468083,0.00050873903,0.44321907],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982439,0.00036360958,0.000072983916,0.00010526937,0.0011517372,0.000062633735],"domain_scores_gemma":[0.99808586,0.0010758785,0.00006603169,0.00013769142,0.00054817024,0.00008638996],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013806847,0.0007574524,0.00043355976,0.0015425883,0.00056592963,0.0030131268,0.0012803479,0.00088946073,0.011924288],"category_scores_gemma":[0.006583133,0.00021395647,0.00038971956,0.0013896364,0.0010951713,0.0029910624,0.0021151952,0.0014051434,0.0040107183],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010891666,0.000044439283,0.00035335086,0.0002270621,0.00000512703,0.000042672822,0.0006569997,0.0013349166,0.0005896461,0.052998777,0.038855318,0.9048807],"study_design_scores_gemma":[0.000011218406,0.00008378669,0.0032233289,0.0015356787,0.00002009922,0.0005397589,0.0014949696,0.015621118,0.0035081925,0.32958227,0.6443244,0.000055174347],"about_ca_topic_score_codex":0.0030671763,"about_ca_topic_score_gemma":0.0053953147,"teacher_disagreement_score":0.011924288,"about_ca_system_score_codex":0.0016242099,"about_ca_system_score_gemma":0.0018450482,"threshold_uncertainty_score":0.039890766},"labels":[],"label_agreement":null},{"id":"W1488794702","doi":"10.1002/9781118269558.app5","title":"Appendix 5: Student Survey Questionnaire","year":2007,"lang":"en","type":"other","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Mathematics education; Psychology; Computer science; Medical education; Medicine","score_opus":0.038295680706052666,"score_gpt":0.40104740344103096,"score_spread":0.3627517227349783,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1488794702","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06127954,0.00028832976,0.015817875,0.006471619,0.0012833417,0.09455939,0.637719,0.005476108,0.17710473],"genre_scores_gemma":[0.16309732,0.0013843694,0.054240756,0.0055249995,0.000382367,0.23554319,0.3668391,0.0008458301,0.17214207],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9947261,0.0019102016,0.0011602854,0.0002626233,0.001393873,0.0005468437],"domain_scores_gemma":[0.9711076,0.011376407,0.0018537198,0.0016837685,0.012240526,0.0017379428],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009096171,0.0008676035,0.0010685057,0.0039180457,0.0010153701,0.0018553785,0.0010829484,0.0014915499,0.26793677],"category_scores_gemma":[0.03173016,0.0005676464,0.0003447421,0.0040774914,0.00036102533,0.0014880373,0.0013565135,0.001656824,0.12083776],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025791264,0.0020530887,0.00927131,0.00060280703,0.000012342226,0.000068278365,0.00088173925,0.00054845604,0.00025099132,0.0017321203,0.8980486,0.0862724],"study_design_scores_gemma":[0.00070170825,0.0011535417,0.10763382,0.0009192964,0.000023968283,0.00027970196,0.006009546,0.0022070408,0.0012790279,0.0040868004,0.87556547,0.00014002225],"about_ca_topic_score_codex":0.0029281557,"about_ca_topic_score_gemma":0.0035818254,"teacher_disagreement_score":0.26793677,"about_ca_system_score_codex":0.002147553,"about_ca_system_score_gemma":0.0031477038,"threshold_uncertainty_score":0.89633775},"labels":[],"label_agreement":null},{"id":"W1489042430","doi":"10.1111/j.1365-2923.2011.04150.x","title":"Influences on medical students’ self‐regulated learning after test completion","year":2012,"lang":"en","type":"article","venue":"Medical Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":41,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; McMaster University","funders":"McMaster University","keywords":"Test (biology); Context (archaeology); Psychology; Multiple choice; Educational measurement; Medical education; Medicine; Social psychology; Curriculum; Pedagogy; Significant difference; Internal medicine","score_opus":0.015465468583563952,"score_gpt":0.39028454000698004,"score_spread":0.3748190714234161,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1489042430","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9996674,0.000029579007,0.000062545165,0.000018804089,0.0000015902056,0.000003506193,0.000005736728,0.0000037776185,0.00020712477],"genre_scores_gemma":[0.99973744,0.000019503497,0.00008489589,0.0000109939365,0.000002813204,0.0000048460797,0.000011207588,0.0000024580297,0.00012582027],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99829763,0.0007126714,0.00010191197,0.00016984397,0.000533911,0.00018418586],"domain_scores_gemma":[0.9849657,0.0074878396,0.0035901584,0.00048484243,0.001057835,0.0024136903],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012268551,0.00021675146,0.00019941058,0.0003592221,0.00021239082,0.000863619,0.00020173551,0.0003148015,0.0016384358],"category_scores_gemma":[0.01669602,0.00013799449,0.0002349805,0.00018652555,0.00035268397,0.00015203259,0.0005008882,0.0005414431,0.0003422848],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000766331,0.001660156,0.9352595,0.00006411053,0.00009706849,0.0002619872,0.0037325558,0.00032426053,0.016672984,0.000042261545,0.00017978647,0.04093898],"study_design_scores_gemma":[0.000012700779,0.0011763296,0.99493307,0.000009468114,0.000017230084,0.00013858295,0.0006304451,0.00046733764,0.0022756914,0.000031710628,0.00029402995,0.000013566547],"about_ca_topic_score_codex":0.0008851291,"about_ca_topic_score_gemma":0.00097372977,"teacher_disagreement_score":0.0016384358,"about_ca_system_score_codex":0.0002534991,"about_ca_system_score_gemma":0.00035655708,"threshold_uncertainty_score":0.006488323},"labels":[],"label_agreement":null},{"id":"W1503706910","doi":"10.22230/ijepl.2010v5n11a202","title":"Saudi National Assessment of Educational Progress (SNAEP)","year":2010,"lang":"en","type":"article","venue":"International Journal of Education Policy and Leadership","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Extant taxon; Curriculum; National curriculum; Political science; Quality (philosophy); Medical education; Educational assessment; Student achievement; Subject (documents); Mathematics education; Pedagogy; Psychology; Academic achievement; Computer science; Medicine; Library science","score_opus":0.10517672166806506,"score_gpt":0.4794197639325415,"score_spread":0.3742430422644764,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1503706910","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.55620444,0.004233121,0.030027855,0.0048672375,0.0016825352,0.0051371637,0.060525,0.0016359966,0.33568665],"genre_scores_gemma":[0.88558626,0.0030028485,0.056765307,0.00045592917,0.00007903503,0.003681336,0.01904472,0.000117618634,0.031266928],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9937192,0.0016014137,0.0011030545,0.0002491091,0.0030044524,0.00032277752],"domain_scores_gemma":[0.9721491,0.0019636366,0.0026574135,0.0010225553,0.021140682,0.0010665614],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0074597187,0.0006508593,0.00054033747,0.0049620736,0.0008136736,0.0014557233,0.0008904184,0.00041181827,0.006328043],"category_scores_gemma":[0.024343854,0.00015816466,0.0006071199,0.0033933194,0.00040729227,0.0015934858,0.0025345532,0.0007901231,0.0026925963],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00049152365,0.00063862564,0.28651276,0.0010890035,0.00015722284,0.000118405915,0.003238416,0.0013150657,0.0012021217,0.0068752714,0.0747376,0.6236241],"study_design_scores_gemma":[0.00010785214,0.0013599694,0.6612958,0.0010474848,0.000106350504,0.0003968527,0.008835832,0.004280058,0.0041857157,0.0036881135,0.31456247,0.00013365434],"about_ca_topic_score_codex":0.010884987,"about_ca_topic_score_gemma":0.015721526,"teacher_disagreement_score":0.010884987,"about_ca_system_score_codex":0.0021673022,"about_ca_system_score_gemma":0.0048316405,"threshold_uncertainty_score":0.03945124},"labels":[],"label_agreement":null},{"id":"W1503949343","doi":"10.22329/celt.v1i0.3171","title":"2. The Map to Curriculum Alignment and Improvement","year":2008,"lang":"en","type":"article","venue":"Collected Essays on Learning and Teaching","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Curriculum; Process (computing); Mathematics education; Computer science; Curriculum mapping; Curriculum development; Concept map; Pedagogy; Sociology; Psychology","score_opus":0.012278429191304119,"score_gpt":0.29870902779021175,"score_spread":0.2864305985989076,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1503949343","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.033541627,0.0009367131,0.5329577,0.017243205,0.0007841552,0.0009865599,0.0014262799,0.005443155,0.4066806],"genre_scores_gemma":[0.28276703,0.0011232531,0.6677125,0.0009464244,0.00018121142,0.0012132348,0.0009312531,0.00088130304,0.044243716],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9964645,0.0017599027,0.00010608015,0.00029826994,0.0011536508,0.00021752683],"domain_scores_gemma":[0.9970055,0.000979933,0.00033585835,0.00056707114,0.0009656725,0.00014594039],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0026310422,0.0005979266,0.00030188265,0.003754695,0.0018174864,0.006647981,0.0009492981,0.001773797,0.01927856],"category_scores_gemma":[0.011739221,0.00039084395,0.0004666125,0.003345383,0.002678242,0.0057183267,0.0036304248,0.0013590894,0.005796893],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000071092785,0.00010587088,0.004573727,0.00052642723,0.00001660073,0.00021373967,0.008392871,0.00409917,0.0015128491,0.27819782,0.041263565,0.6610262],"study_design_scores_gemma":[0.000051752355,0.00016848887,0.012751845,0.0007380296,0.000028480645,0.00048915064,0.010772809,0.018236985,0.007005931,0.26980782,0.6798602,0.000088497356],"about_ca_topic_score_codex":0.0055361777,"about_ca_topic_score_gemma":0.004362469,"teacher_disagreement_score":0.01927856,"about_ca_system_score_codex":0.0018693428,"about_ca_system_score_gemma":0.0047776317,"threshold_uncertainty_score":0.06449318},"labels":[],"label_agreement":null},{"id":"W1518941279","doi":"","title":"Assessment Around the World","year":2006,"lang":"en","type":"article","venue":"Educational leadership","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Standardized test; Psychology; Tracking (education); Mathematics education; Test (biology); Aptitude; Achievement test; Academic achievement; Advanced Placement; Norm-referenced test; Medical education; Pedagogy; Developmental psychology; Medicine","score_opus":0.1129451474931034,"score_gpt":0.39879403650871376,"score_spread":0.28584888901561034,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1518941279","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0017954776,0.012107724,0.007573451,0.03988275,0.0047027427,0.0002500445,0.0017595119,0.0013488169,0.93057954],"genre_scores_gemma":[0.058597736,0.026905626,0.023221575,0.03320054,0.002694732,0.00071842247,0.004939447,0.0011582245,0.84856373],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9935137,0.0017366639,0.00050248514,0.0007439018,0.003044139,0.0004589874],"domain_scores_gemma":[0.9811491,0.0014645994,0.0007272664,0.0012823972,0.012539145,0.0028374689],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00553966,0.0009310454,0.0006214485,0.0049472605,0.002438944,0.007773432,0.0016617001,0.0023423433,0.12166772],"category_scores_gemma":[0.022380065,0.00032548982,0.00031452818,0.0039250394,0.0018456085,0.005555204,0.0053827856,0.0026735908,0.08211274],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026620399,0.000039249462,0.0014441969,0.00016466701,0.000006530656,0.0001157709,0.00059422536,0.00010368308,0.000258899,0.030196656,0.55700856,0.41004094],"study_design_scores_gemma":[0.0000024180981,0.000007761904,0.00088224077,0.00028427833,0.0000015971666,0.00012310609,0.000256042,0.000039866234,0.000058309684,0.003419956,0.99491775,0.000006633305],"about_ca_topic_score_codex":0.011446064,"about_ca_topic_score_gemma":0.010393002,"teacher_disagreement_score":0.12166772,"about_ca_system_score_codex":0.0040699057,"about_ca_system_score_gemma":0.009475293,"threshold_uncertainty_score":0.40701902},"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,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_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","score_opus":0.15790322565992373,"score_gpt":0.5635018527575003,"score_spread":0.40559862709757655,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1520074575","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16104946,0.032886516,0.62156093,0.0074882293,0.004377466,0.00465818,0.0007238938,0.0048206323,0.1624347],"genre_scores_gemma":[0.7628887,0.0071798987,0.21061164,0.00035303814,0.0010102479,0.0017251348,0.0005947043,0.00045260193,0.01518388],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9479783,0.030034011,0.0016956726,0.002015815,0.017693482,0.0005826119],"domain_scores_gemma":[0.8876217,0.06727206,0.006905161,0.007554996,0.027776148,0.0028700128],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.029781897,0.00069805636,0.0011513354,0.0041540046,0.0017632188,0.004097313,0.0021911843,0.0011800656,0.007644879],"category_scores_gemma":[0.17008804,0.0003504959,0.00058348285,0.0029344507,0.0013979924,0.0037501904,0.0037414797,0.0014816745,0.0032359692],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026371473,0.00025415455,0.0057310653,0.0010236101,0.000077959725,0.000076539676,0.0013144311,0.0022829878,0.0010106519,0.012958478,0.009551789,0.9654546],"study_design_scores_gemma":[0.0008199272,0.006573712,0.13655055,0.0073301303,0.00067251595,0.0016823251,0.012848296,0.18198971,0.021617755,0.23929925,0.38981476,0.0008009856],"about_ca_topic_score_codex":0.003903937,"about_ca_topic_score_gemma":0.0038931726,"teacher_disagreement_score":0.9702181,"about_ca_system_score_codex":0.0015152791,"about_ca_system_score_gemma":0.0041873013,"threshold_uncertainty_score":0.1575036},"labels":[],"label_agreement":null},{"id":"W1521765823","doi":"10.55016/ojs/ajer.v47i3.54877","title":"An Examination of Preservice Teachers' Simulated Classroom Assessment Practices","year":2001,"lang":"en","type":"article","venue":"Alberta Journal of Educational Research","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Ministry of Education and Child Care; University of Victoria","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Psychology; Mathematics education; Pedagogy; Educational research","score_opus":0.14166078468908497,"score_gpt":0.536891958466766,"score_spread":0.395231173777681,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1521765823","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99859947,0.000055996683,0.00038312253,0.0000917223,0.0000052078126,0.00003551499,0.000042211075,0.000014190407,0.0007726084],"genre_scores_gemma":[0.997244,0.0001410433,0.0011232167,0.00007815894,0.000006427827,0.00008969499,0.00010365908,0.000009741348,0.0012041859],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.9880525,0.0068416367,0.000991874,0.0012438622,0.00229358,0.0005765402],"domain_scores_gemma":[0.92885447,0.047438413,0.007852552,0.004091317,0.008238844,0.0035245232],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007472149,0.0002991916,0.00044022925,0.0020570299,0.0019940236,0.0022884456,0.0012019159,0.0011587744,0.0014669012],"category_scores_gemma":[0.060866553,0.000554625,0.0002748108,0.0011211305,0.0012418258,0.0007340113,0.002592535,0.0010301592,0.0005811163],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00068988954,0.0011933554,0.3770815,0.00037311512,0.00008193267,0.0022515114,0.4779387,0.0011306389,0.013554576,0.00038654538,0.0016805729,0.123637624],"study_design_scores_gemma":[0.00008198662,0.0032867696,0.44907662,0.0003342055,0.000063088155,0.0033568637,0.51459646,0.0030762816,0.009282809,0.0005419453,0.016124817,0.00017815235],"about_ca_topic_score_codex":0.0033911495,"about_ca_topic_score_gemma":0.011439199,"teacher_disagreement_score":0.007472149,"about_ca_system_score_codex":0.0023740218,"about_ca_system_score_gemma":0.0016338316,"threshold_uncertainty_score":0.039516926},"labels":[],"label_agreement":null},{"id":"W1522083394","doi":"10.1007/978-94-6091-506-2_1","title":"Pacific Crystal Centre For Science, Mathematics, And Technology Literacy","year":2011,"lang":"en","type":"book-chapter","venue":"SensePublishers eBooks","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Victoria","funders":"","keywords":"Literacy; Engineering research; Mathematics education; Political science; Natural science; Scientific literacy; Engineering; Library science; Science education; Pedagogy; Mathematics; Computer science; Sociology; Physics","score_opus":0.022680609282771973,"score_gpt":0.28479047262353396,"score_spread":0.262109863340762,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1522083394","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001277679,0.007426452,0.0015274922,0.011271355,0.0010178261,0.00006685276,0.0012760722,0.0003662431,0.97577],"genre_scores_gemma":[0.009029131,0.0089227855,0.004339531,0.0007045215,0.00014111085,0.00006405666,0.0008794304,0.00023030212,0.9756891],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9994017,0.000031669308,0.000011041207,0.000064396496,0.00041170212,0.00007944114],"domain_scores_gemma":[0.99906045,0.000089864036,0.000018220771,0.00004536653,0.00048061387,0.00030551016],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005252363,0.00051102135,0.00037110352,0.0014312433,0.0035921414,0.0038814628,0.0007269495,0.0008930895,0.115203775],"category_scores_gemma":[0.0012569245,0.00028395833,0.0001870103,0.0021019334,0.0009964206,0.0026879357,0.0023401112,0.0020385736,0.024090901],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011350228,0.000020048039,0.00035963045,0.00014989084,0.0000010937034,0.000071464165,0.0009209447,0.000022711034,0.00018845436,0.0289063,0.7797266,0.18962151],"study_design_scores_gemma":[0.0000013575603,0.0000026827092,0.0006715334,0.00005471435,0.0000011204793,0.000063927124,0.0002607728,0.000022902868,0.00006314175,0.0009834961,0.9978714,0.0000029045896],"about_ca_topic_score_codex":0.40655914,"about_ca_topic_score_gemma":0.70102805,"teacher_disagreement_score":0.40655914,"about_ca_system_score_codex":0.0068888254,"about_ca_system_score_gemma":0.033681873,"threshold_uncertainty_score":0.8083854},"labels":[],"label_agreement":null},{"id":"W1523324611","doi":"10.3968/6313","title":"Application of Formative Assessment in College English Teaching","year":2015,"lang":"en","type":"article","venue":"Higher education of social science","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Formative assessment; Computer science; Quality (philosophy); College English; Mathematics education; Order (exchange); Key (lock); Psychology","score_opus":0.029651391863191708,"score_gpt":0.4108975659950856,"score_spread":0.3812461741318939,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1523324611","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15922529,0.006084599,0.77126855,0.0033355535,0.0010346521,0.003827852,0.0001490759,0.0009824907,0.0540921],"genre_scores_gemma":[0.52782387,0.0036066442,0.4624776,0.00046275172,0.00025880637,0.0016479698,0.000092634975,0.00007837267,0.003551353],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9329659,0.048040982,0.0037221042,0.001075665,0.01360628,0.00058904267],"domain_scores_gemma":[0.9046758,0.056838393,0.0054053864,0.003736251,0.02841953,0.00092474325],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0627171,0.0007584239,0.0005665902,0.0050017983,0.0010131206,0.0043575466,0.0012809101,0.0010243683,0.00083421223],"category_scores_gemma":[0.11696142,0.0003059247,0.00061295496,0.003174472,0.0018591965,0.00323517,0.0017559229,0.0013126677,0.00024510644],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017765531,0.0005167873,0.019103106,0.00094293506,0.00006954766,0.00017756993,0.013331025,0.0023911516,0.0046675666,0.015936062,0.0014245869,0.9412619],"study_design_scores_gemma":[0.00038664468,0.013823348,0.2853385,0.0128089385,0.00069177407,0.008979009,0.06431146,0.09884301,0.09787381,0.1398573,0.27581644,0.0012697757],"about_ca_topic_score_codex":0.0019103033,"about_ca_topic_score_gemma":0.0022849164,"teacher_disagreement_score":0.0627171,"about_ca_system_score_codex":0.0027984108,"about_ca_system_score_gemma":0.004858727,"threshold_uncertainty_score":0.33168364},"labels":[],"label_agreement":null},{"id":"W1524578401","doi":"10.1002/9781118411360.wbcla071","title":"Consequences, Impact, and Washback","year":2013,"lang":"en","type":"other","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Phenomenon; Context (archaeology); Test (biology); Psychology; Set (abstract data type); Empirical research; Scale (ratio); Mathematics education; Pedagogy; Computer science; Epistemology","score_opus":0.026173577142377853,"score_gpt":0.3635325425005921,"score_spread":0.33735896535821425,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1524578401","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.41561422,0.0050594932,0.036151454,0.046296116,0.0013049351,0.0006629924,0.00062859576,0.0006037559,0.4936784],"genre_scores_gemma":[0.9877666,0.0008184518,0.0022647113,0.002453861,0.00012558875,0.00018127618,0.000082504295,0.00009096173,0.006215905],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9690842,0.011709306,0.0018657782,0.0023943682,0.012658352,0.002287862],"domain_scores_gemma":[0.9172742,0.05048302,0.008792039,0.009804441,0.010060137,0.00358617],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.020263238,0.0009751195,0.00073038816,0.003599703,0.003966403,0.0074977856,0.001957545,0.002914033,0.015984422],"category_scores_gemma":[0.10268839,0.00046980983,0.0009284543,0.0021071394,0.016095985,0.009707679,0.009424059,0.005243229,0.0010515507],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000464758,0.0010430702,0.1188921,0.0012598397,0.00021398989,0.0049126986,0.035045885,0.003356594,0.0031596539,0.5076196,0.013459526,0.3105723],"study_design_scores_gemma":[0.0001282221,0.00080665445,0.14312781,0.002071258,0.00021262294,0.0037956336,0.054485776,0.002716068,0.007481302,0.6532379,0.13167776,0.00025895503],"about_ca_topic_score_codex":0.0024624635,"about_ca_topic_score_gemma":0.0018717893,"teacher_disagreement_score":0.020263238,"about_ca_system_score_codex":0.005235262,"about_ca_system_score_gemma":0.0044401386,"threshold_uncertainty_score":0.10716355},"labels":[],"label_agreement":null},{"id":"W152593044","doi":"10.1007/0-306-47642-8_21","title":"Teachers’ Sources and Uses of Assessment Information","year":2002,"lang":"en","type":"book-chapter","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Information retrieval; Environmental science","score_opus":0.03573563513499994,"score_gpt":0.3168163061912377,"score_spread":0.28108067105623774,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W152593044","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.110645145,0.023942968,0.053841326,0.0069823083,0.00021102991,0.00011483557,0.00083158223,0.00064057106,0.8027903],"genre_scores_gemma":[0.75637454,0.017224347,0.034186926,0.00039733798,0.00011870469,0.00012086102,0.0009306097,0.0005143804,0.19013225],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9958354,0.001481027,0.00025541737,0.00020192924,0.0020810256,0.00014512107],"domain_scores_gemma":[0.9819873,0.014016784,0.0006457018,0.00080517714,0.002358588,0.00018643888],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004789666,0.00029816732,0.00023992373,0.006714283,0.0009408197,0.008149955,0.0009836864,0.00071736047,0.0066414336],"category_scores_gemma":[0.024077317,0.0006886655,0.00025002676,0.006350285,0.0012797109,0.0063606193,0.0013466984,0.0013788595,0.0021112985],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000062937186,0.00010153754,0.012115227,0.0003820518,0.000021926848,0.0003779827,0.08983397,0.0006362213,0.0014308967,0.10321411,0.021776361,0.7700468],"study_design_scores_gemma":[0.000021879503,0.000074925614,0.03722202,0.0025433176,0.000064106105,0.0018246046,0.03333836,0.0035981692,0.008640335,0.08399202,0.8286017,0.00007855905],"about_ca_topic_score_codex":0.0044245827,"about_ca_topic_score_gemma":0.009781599,"teacher_disagreement_score":0.008149955,"about_ca_system_score_codex":0.0019840752,"about_ca_system_score_gemma":0.0021510494,"threshold_uncertainty_score":0.025330484},"labels":[],"label_agreement":null},{"id":"W1529042430","doi":"10.1177/160940691501400202","title":"Methodological Diversity in Language Assessment Research: The Role of Mixed Methods in Classroom-Based Language Assessment Studies","year":2015,"lang":"en","type":"article","venue":"International Journal of Qualitative Methods","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Context (archaeology); Diversity (politics); Multimethodology; Qualitative research; Educational research; Face (sociological concept); Computer science; Engineering ethics; Psychology; Sociology; Pedagogy; Social science","score_opus":0.8885844506479319,"score_gpt":0.7692516158840498,"score_spread":0.11933283476388212,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1529042430","genre_codex":"methods","genre_gemma":"methods","domain_codex":"methods","domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"methods","domain_consensus":"methods","prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03426087,0.13209057,0.717293,0.08866105,0.00524087,0.0057376483,0.00018696264,0.00026726944,0.016261768],"genre_scores_gemma":[0.2772366,0.02642801,0.66087174,0.016871812,0.002602045,0.014550301,0.00014636344,0.00030775106,0.0009854023],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.14593457,0.7612511,0.036123253,0.016030114,0.03936402,0.0012969429],"domain_scores_gemma":[0.14269468,0.76735145,0.024759552,0.037987422,0.024406018,0.002800826],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.6521932,0.0020259174,0.005366517,0.019455172,0.012709628,0.036434118,0.009574499,0.011177804,0.0017812483],"category_scores_gemma":[0.66736305,0.0028247624,0.0024518077,0.017763868,0.04071156,0.030604292,0.028952243,0.013010899,0.0005453224],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030442048,0.00038953318,0.019967517,0.014727145,0.0011446811,0.00069386786,0.19774045,0.0018711275,0.0012869408,0.4134806,0.0040439097,0.34434977],"study_design_scores_gemma":[0.0003911882,0.0013106876,0.008206839,0.06616045,0.0008507398,0.002567493,0.08791641,0.012038741,0.003915342,0.6913746,0.124554954,0.00071252964],"about_ca_topic_score_codex":0.0035079746,"about_ca_topic_score_gemma":0.005834222,"teacher_disagreement_score":0.3478068,"about_ca_system_score_codex":0.014741684,"about_ca_system_score_gemma":0.025695816,"threshold_uncertainty_score":0.42890775},"labels":[],"label_agreement":null},{"id":"W1531240630","doi":"10.58680/rte201424579","title":"A Framework for Using Consequential Validity Evidence in Evaluating Large-Scale Writing Assessments: A Canadian Study","year":2014,"lang":"en","type":"article","venue":"Research in the Teaching of English","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":49,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Ottawa; University of Lethbridge","funders":"","keywords":"Scale (ratio); Psychology; Test validity; Mathematics education; Pedagogy; Psychometrics; Developmental psychology; Geography","score_opus":0.50791354546036,"score_gpt":0.5991396042643354,"score_spread":0.09122605880397539,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1531240630","genre_codex":"methods","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15373278,0.03619197,0.41122812,0.09531116,0.0014217206,0.042496163,0.002015113,0.00034034165,0.2572626],"genre_scores_gemma":[0.6793953,0.0045685726,0.29607782,0.004822715,0.000103501574,0.012771108,0.00035688197,0.000115057104,0.0017890839],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.38026664,0.49248445,0.037352696,0.017963575,0.062491927,0.009440643],"domain_scores_gemma":[0.24636845,0.56456083,0.032773685,0.035614397,0.11462832,0.00605428],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.5714146,0.0026008661,0.0039799274,0.05165152,0.026161572,0.027730998,0.012841314,0.0055680657,0.0031792286],"category_scores_gemma":[0.66245747,0.002663023,0.0040727304,0.035035316,0.060853068,0.018667955,0.024450418,0.008102145,0.00037592478],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003226097,0.00030437284,0.048871078,0.006039891,0.0006939753,0.0012335391,0.15741272,0.0026821478,0.0007214453,0.6953988,0.003978986,0.082340516],"study_design_scores_gemma":[0.0014829384,0.0012752404,0.08026213,0.051262908,0.002768694,0.0013096725,0.17577392,0.025400603,0.0031370763,0.49433035,0.1620997,0.0008967958],"about_ca_topic_score_codex":0.7943796,"about_ca_topic_score_gemma":0.7955487,"teacher_disagreement_score":0.5714146,"about_ca_system_score_codex":0.18313807,"about_ca_system_score_gemma":0.3256985,"threshold_uncertainty_score":0.9474441},"labels":[],"label_agreement":null},{"id":"W1544944805","doi":"10.19173/irrodl.v14i1.1394","title":"Peer Portal: Quality enhancement in thesis writing using self-managed peer review on a mass scale","year":2013,"lang":"en","type":"review","venue":"The International Review of Research in Open and Distributed Learning","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":36,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Stockholms Universitet","keywords":"Peer review; Bachelor; Quality (philosophy); Peer feedback; Technical peer review; Computer science; Scale (ratio); Psychology; Medical education; Mathematics education; Multimedia; Medicine; Political science","score_opus":0.27905200290430215,"score_gpt":0.5703756518986821,"score_spread":0.29132364899437996,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1544944805","genre_codex":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.33702135,0.0049029826,0.46192816,0.0044734967,0.003872214,0.02119124,0.002658191,0.062749825,0.10120249],"genre_scores_gemma":[0.37587667,0.0022467528,0.56053066,0.0004524031,0.0023449569,0.0072396756,0.0023534154,0.0035944704,0.04536107],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9602861,0.022452796,0.003074801,0.0024140836,0.0110824555,0.00068979716],"domain_scores_gemma":[0.9256139,0.029248746,0.0074172216,0.013907735,0.019408917,0.004403608],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02961268,0.000749229,0.0011773967,0.0040882756,0.0016513161,0.0044419775,0.0017119121,0.00076992257,0.02576415],"category_scores_gemma":[0.06534458,0.0005786408,0.00093624485,0.002879413,0.0008909345,0.0033873646,0.005580349,0.00083264295,0.016394302],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009064562,0.0010217935,0.007711052,0.0015056306,0.00012896598,0.00029192213,0.002721692,0.00044550642,0.025694452,0.0016523158,0.049718898,0.9082012],"study_design_scores_gemma":[0.0026906685,0.013693805,0.15887602,0.0012519036,0.00082542904,0.0063797208,0.0046184645,0.024943165,0.12445016,0.008232742,0.65323263,0.00080524874],"about_ca_topic_score_codex":0.00029566692,"about_ca_topic_score_gemma":0.0005645663,"teacher_disagreement_score":0.97038734,"about_ca_system_score_codex":0.00052961777,"about_ca_system_score_gemma":0.0034568848,"threshold_uncertainty_score":0.15660864},"labels":[],"label_agreement":null},{"id":"W1546018842","doi":"10.7202/1000316ar","title":"La diversité ethnoculturelle dans les programmes français de sciences et technologie de l’Ontario : une analyse comparative entre le programme de 1998 et celui de 2007","year":2010,"lang":"fr","type":"article","venue":"Reflets Revue d’intervention sociale et communautaire","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université de Sherbrooke; University of Ottawa","funders":"","keywords":"Humanities; Political science; Art","score_opus":0.06546275745092044,"score_gpt":0.3931206413774599,"score_spread":0.32765788392653944,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1546018842","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.93926924,0.0014853574,0.000833235,0.0015047881,0.00003599225,0.00015992232,0.000520618,0.000012750963,0.056178153],"genre_scores_gemma":[0.97945845,0.0010162512,0.00056105835,0.00017028576,0.000014244368,0.00012927075,0.00025838532,0.000016934428,0.018375214],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9957008,0.00092014036,0.00012172058,0.00031711117,0.0016685767,0.0012717241],"domain_scores_gemma":[0.99275863,0.0020393045,0.0012892828,0.0003361469,0.0021340353,0.0014426634],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0030545243,0.0002957453,0.0003575953,0.0028706044,0.0056266915,0.004140257,0.00076904194,0.00054029375,0.0045968257],"category_scores_gemma":[0.006136108,0.0002880539,0.0002979207,0.007499858,0.004552497,0.0011382694,0.0028916646,0.00077845016,0.00024664967],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022408576,0.00010252009,0.16050477,0.00061240635,0.000056178353,0.0004830287,0.7103982,0.0004096193,0.0019059399,0.018663915,0.003734654,0.10290464],"study_design_scores_gemma":[0.000012678718,0.000055153312,0.6988343,0.0003408775,0.000029951641,0.000079146004,0.19604869,0.00022356551,0.0004465998,0.0005256366,0.10337429,0.000029019635],"about_ca_topic_score_codex":0.9093663,"about_ca_topic_score_gemma":0.9616827,"teacher_disagreement_score":0.09063369,"about_ca_system_score_codex":0.05254973,"about_ca_system_score_gemma":0.059107218,"threshold_uncertainty_score":0.3812768},"labels":[],"label_agreement":null},{"id":"W1549299204","doi":"10.1002/9781118411360.wbcla131","title":"Assessing Integrated Skills","year":2013,"lang":"en","type":"other","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Active listening; Reading (process); Relevance (law); Convention; Test (biology); Psychology; Vocational education; Literacy; Value (mathematics); Cognitive skill; Cognition; Mathematics education; Cognitive psychology; Pedagogy; Computer science; Linguistics; Sociology; Communication","score_opus":0.026527057152858826,"score_gpt":0.3790245025491448,"score_spread":0.352497445396286,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1549299204","genre_codex":"empirical","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8116511,0.0013449807,0.07305857,0.00048742548,0.00013403395,0.00091270293,0.0012493856,0.0012224566,0.1099394],"genre_scores_gemma":[0.8873479,0.0016198037,0.0845851,0.00023874201,0.000042016673,0.00068685674,0.0010721631,0.00015103394,0.02425647],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9968585,0.0004838537,0.00023003576,0.0003846531,0.0018973924,0.00014545147],"domain_scores_gemma":[0.9901838,0.0032356274,0.0010344276,0.00078006845,0.0040142424,0.0007518741],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002747847,0.00084058655,0.00059192185,0.0039293654,0.00042602487,0.0018745225,0.000750991,0.0005821216,0.008003607],"category_scores_gemma":[0.0139411,0.00022401445,0.0004306911,0.0016828817,0.0006844554,0.0018402955,0.0029659364,0.0008860011,0.0017038397],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028145153,0.0007420714,0.11055967,0.00055013114,0.0001302984,0.00021694036,0.005990524,0.0014776252,0.016407896,0.005236696,0.0038455687,0.85456115],"study_design_scores_gemma":[0.000097558805,0.0038230566,0.84295446,0.0011101643,0.00024346373,0.0028040963,0.008713277,0.013818438,0.0382594,0.03524742,0.052739564,0.00018913404],"about_ca_topic_score_codex":0.0016184641,"about_ca_topic_score_gemma":0.0037320147,"teacher_disagreement_score":0.008003607,"about_ca_system_score_codex":0.0005523323,"about_ca_system_score_gemma":0.0013778015,"threshold_uncertainty_score":0.026774764},"labels":[],"label_agreement":null},{"id":"W1557823848","doi":"","title":"The Evaluation of University Teaching: Exploring the Question of Resistance","year":2000,"lang":"en","type":"article","venue":"Resources for feminist research","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Ideology; Resistance (ecology); Humanities; Sociology; Context (archaeology); Curriculum; Politics; Documentation; Pedagogy; Political science; Philosophy; Law","score_opus":0.20262336338286807,"score_gpt":0.4708646831618238,"score_spread":0.2682413197789557,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1557823848","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.37335566,0.01207268,0.066443495,0.19366966,0.0009819593,0.0004702003,0.000057523266,0.0001709763,0.35277784],"genre_scores_gemma":[0.98925775,0.0011176115,0.003702513,0.0018974897,0.00014771373,0.00019013435,0.000007763923,0.000061411745,0.0036175512],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.6910661,0.27246752,0.005373263,0.0042442675,0.021778554,0.00507029],"domain_scores_gemma":[0.7584417,0.20402311,0.009264407,0.0076254983,0.016571512,0.0040738476],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.10347201,0.00060655654,0.0013460468,0.0047295294,0.010395342,0.029756885,0.0033580305,0.0075138556,0.0031841435],"category_scores_gemma":[0.16325238,0.0005091922,0.0008970504,0.003316463,0.06615057,0.022372019,0.015164452,0.008641858,0.00051705184],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000083549756,0.00016170228,0.005246089,0.00041901122,0.000040632043,0.00038874647,0.33526683,0.00064595963,0.0005194089,0.59687614,0.0033482653,0.057003625],"study_design_scores_gemma":[0.00009320973,0.0004633126,0.0080003375,0.002163176,0.00006658178,0.00073036057,0.49565822,0.0044532614,0.0029757218,0.37911403,0.10611664,0.0001651573],"about_ca_topic_score_codex":0.0045260508,"about_ca_topic_score_gemma":0.002674163,"teacher_disagreement_score":0.896528,"about_ca_system_score_codex":0.018059976,"about_ca_system_score_gemma":0.010136271,"threshold_uncertainty_score":0.5472188},"labels":[],"label_agreement":null},{"id":"W1558577420","doi":"","title":"Evaluation Methods: Learner Perceptions of Authentic Assessment Practices","year":2009,"lang":"en","type":"article","venue":"EdMedia: World Conference on Educational Media and Technology","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University; MacEwan University","funders":"","keywords":"Perception; Psychology; Computer science; Social psychology; Pedagogy; Mathematics education","score_opus":0.10760073386868232,"score_gpt":0.489301490347308,"score_spread":0.38170075647862567,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1558577420","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94902515,0.00047623026,0.032564767,0.00064845214,0.00015103888,0.0021343923,0.00014406432,0.00012523343,0.014730692],"genre_scores_gemma":[0.97505456,0.00022967764,0.01858321,0.0001870954,0.000041381638,0.002725816,0.000116859985,0.00004528529,0.0030161147],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.93453735,0.047361523,0.0040512746,0.0018776499,0.0114611685,0.0007110767],"domain_scores_gemma":[0.81421024,0.12915106,0.01581869,0.007625115,0.02899844,0.004196394],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.051465023,0.0005126897,0.0006350293,0.0016718825,0.0014903956,0.003610695,0.0009606882,0.0009785705,0.002866338],"category_scores_gemma":[0.17830206,0.00027018972,0.00065803796,0.0009902781,0.0010112349,0.0029355437,0.0032432075,0.0011450688,0.000584331],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004068144,0.009621223,0.20377396,0.0036758,0.00033963413,0.00022212234,0.19806914,0.0011896719,0.01390493,0.007256136,0.006322715,0.5515565],"study_design_scores_gemma":[0.0022024144,0.033048794,0.6031599,0.005259093,0.0014097844,0.0016384571,0.17436704,0.02036251,0.0679348,0.013788321,0.07602041,0.0008085052],"about_ca_topic_score_codex":0.0006163765,"about_ca_topic_score_gemma":0.00089633145,"teacher_disagreement_score":0.051465023,"about_ca_system_score_codex":0.0016544714,"about_ca_system_score_gemma":0.0028320558,"threshold_uncertainty_score":0.27217627},"labels":[],"label_agreement":null},{"id":"W1565883978","doi":"10.1002/9781118411360.wbcla022","title":"Large‐Scale Assessment","year":2013,"lang":"en","type":"other","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Accountability; Scale (ratio); Bureaucracy; Politics; Test (biology); Quality (philosophy); Language assessment; Political science; Public relations; Psychology; Computer science; Mathematics education; Epistemology; Geography; Law","score_opus":0.01975342632826853,"score_gpt":0.3682010653148333,"score_spread":0.3484476389865648,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1565883978","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05449145,0.0014457493,0.13227512,0.010795477,0.00081103406,0.0016795747,0.001166714,0.0019633314,0.79537165],"genre_scores_gemma":[0.7622144,0.0019996248,0.07898178,0.0024433287,0.00044039194,0.0014185928,0.0015072383,0.00093999883,0.1500546],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9861362,0.0057739187,0.0005097147,0.0012122192,0.005830937,0.0005369826],"domain_scores_gemma":[0.93580097,0.0262144,0.0035088933,0.010338869,0.0203676,0.003769262],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.017071301,0.00071516325,0.0005034848,0.002114705,0.0018624,0.0050561493,0.0020371946,0.0008713063,0.038068917],"category_scores_gemma":[0.07056222,0.00019595792,0.00038047438,0.0025568048,0.0018017937,0.0056781,0.008173919,0.001513261,0.0067244824],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016028254,0.00037224605,0.020383082,0.00044898596,0.000058069978,0.00025789332,0.0067518805,0.002301805,0.0013736212,0.16522361,0.11962212,0.6830464],"study_design_scores_gemma":[0.000068469664,0.00044221888,0.046865664,0.0008857756,0.000051402254,0.00052608905,0.011580733,0.010259716,0.0032237219,0.23731333,0.68866,0.00012274699],"about_ca_topic_score_codex":0.0042244666,"about_ca_topic_score_gemma":0.006908999,"teacher_disagreement_score":0.038068917,"about_ca_system_score_codex":0.00276768,"about_ca_system_score_gemma":0.007230689,"threshold_uncertainty_score":0.12735325},"labels":[],"label_agreement":null},{"id":"W1567910316","doi":"10.18806/tesl.v23i2.55","title":"Professionalism and High-Stakes Tests: Teachers’ Perspectives When Dealing With Educational Change Introduced Through Provincial Exams","year":2006,"lang":"en","type":"article","venue":"TESL Canada Journal","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Social Sciences and Humanities Research Council of Canada; University of Cambridge; McGill University; Yale University","keywords":"Curriculum; Perception; Mathematics education; Psychology; Pedagogy; Professional development; Element (criminal law); Political science","score_opus":0.037744421768051976,"score_gpt":0.3168132509451714,"score_spread":0.2790688291771194,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1567910316","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97319835,0.00042059465,0.0017611228,0.012074995,0.00007401915,0.00003594462,0.000012484312,0.00002187036,0.012400552],"genre_scores_gemma":[0.99820614,0.00013369057,0.000208042,0.0003455397,0.00001740594,0.000006764794,0.0000040712252,0.0000051612956,0.001073126],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9706364,0.01990577,0.0008610624,0.00068543607,0.0044051027,0.003506062],"domain_scores_gemma":[0.9439856,0.033222314,0.008179074,0.0014991531,0.0071899015,0.0059240484],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.019514877,0.00018319969,0.000357061,0.00118574,0.008660194,0.007155817,0.0012083609,0.0020033296,0.0013636228],"category_scores_gemma":[0.067306176,0.0004141163,0.00034934166,0.0007364692,0.009599718,0.0025327178,0.003951864,0.004300494,0.00017658899],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005306382,0.00009772131,0.04833402,0.00006929584,0.000010383662,0.001417766,0.9298882,0.000074698364,0.001222637,0.0019076526,0.0010077137,0.015916878],"study_design_scores_gemma":[0.00001213169,0.00014898936,0.037773713,0.000082238555,0.000011309144,0.0009946516,0.9429436,0.0002470176,0.0010892937,0.0008928243,0.015776442,0.000027864211],"about_ca_topic_score_codex":0.04265326,"about_ca_topic_score_gemma":0.065322496,"teacher_disagreement_score":0.04265326,"about_ca_system_score_codex":0.0086949365,"about_ca_system_score_gemma":0.010304195,"threshold_uncertainty_score":0.10320574},"labels":[],"label_agreement":null},{"id":"W1568000697","doi":"10.5489/cuaj.1007","title":"The importance of feedback","year":2013,"lang":"en","type":"article","venue":"Canadian Urological Association Journal","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Canadian Urological Association","funders":"","keywords":"Psychology","score_opus":0.015825444352469013,"score_gpt":0.26923113101737284,"score_spread":0.2534056866649038,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1568000697","genre_codex":"empirical","genre_gemma":"commentary","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5159362,0.008620044,0.023609903,0.09292814,0.0033093158,0.00028016538,0.0002394499,0.0006494786,0.35442725],"genre_scores_gemma":[0.99175054,0.0006331432,0.0015935247,0.0012172248,0.00024928417,0.000040241976,0.000025758203,0.00003238811,0.0044577746],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9536497,0.024717236,0.0017278189,0.0016744565,0.015640605,0.002590174],"domain_scores_gemma":[0.70446545,0.19017303,0.02158054,0.009097222,0.047701363,0.026982341],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.017445697,0.0003533535,0.0004501051,0.0020400118,0.0028886318,0.0065264865,0.0009596243,0.0022031458,0.007851304],"category_scores_gemma":[0.19125244,0.00029698398,0.000557559,0.0008489653,0.0028052242,0.00407158,0.0033656014,0.0029824064,0.0012313694],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008196727,0.0012324804,0.1603771,0.0007945628,0.00014726871,0.0004727183,0.028075915,0.00078896125,0.0024634157,0.032437727,0.02177935,0.7506109],"study_design_scores_gemma":[0.00029890594,0.002700443,0.6241317,0.0033162998,0.00035200722,0.0027987512,0.05127862,0.0071992753,0.0059686736,0.10273191,0.19884416,0.00037927096],"about_ca_topic_score_codex":0.00556611,"about_ca_topic_score_gemma":0.006527501,"teacher_disagreement_score":0.9825543,"about_ca_system_score_codex":0.003731357,"about_ca_system_score_gemma":0.010862662,"threshold_uncertainty_score":0.092262745},"labels":[],"label_agreement":null},{"id":"W1569132542","doi":"10.1186/s40468-015-0020-6","title":"Chinese university students’ perceptions of assessment tasks and classroom assessment environment","year":2015,"lang":"en","type":"article","venue":"Language Testing in Asia","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":29,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Psychology; Learning environment; Context (archaeology); Perception; Mathematics education; Formative assessment; Scale (ratio); Pedagogy","score_opus":0.028109092519047394,"score_gpt":0.3653477989662329,"score_spread":0.33723870644718545,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1569132542","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9992254,0.000031015512,0.00005200158,0.000042580254,0.000001964324,0.0000062824083,0.000015462221,0.0000017534907,0.0006237307],"genre_scores_gemma":[0.9994331,0.000056341603,0.000069894464,0.000025106781,0.0000020331574,0.000010398321,0.000031405092,8.021215e-7,0.00037086438],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9990977,0.00012350014,0.00011707957,0.00011187334,0.00034413583,0.00020583368],"domain_scores_gemma":[0.99745387,0.00049301283,0.0006858986,0.00012499053,0.0004686866,0.0007736095],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012087529,0.0003465667,0.0003127586,0.0008998459,0.0014709192,0.0015218019,0.00028987855,0.00039196853,0.0016907774],"category_scores_gemma":[0.0026465293,0.00016743116,0.0004249162,0.0013026189,0.00082095625,0.0006958864,0.0010455382,0.0004159662,0.00016486378],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006381631,0.00023657015,0.94005686,0.000086257045,0.000025026791,0.00024515958,0.029996242,0.00030554016,0.002576571,0.00044087984,0.0003867432,0.02558029],"study_design_scores_gemma":[0.0000046237187,0.00007906578,0.98559004,0.000018361749,0.000010637296,0.00005186734,0.012514851,0.00046541097,0.00035652696,0.00016490043,0.0007237588,0.000020090072],"about_ca_topic_score_codex":0.037828133,"about_ca_topic_score_gemma":0.050725877,"teacher_disagreement_score":0.037828133,"about_ca_system_score_codex":0.00151075,"about_ca_system_score_gemma":0.002411839,"threshold_uncertainty_score":0.075215936},"labels":[],"label_agreement":null},{"id":"W1570879941","doi":"10.22329/celt.v1i0.3191","title":"22. The Writing Development Initiative: A Pilot Project to Help Students Become Proficient Writers","year":2008,"lang":"en","type":"article","venue":"Collected Essays on Learning and Teaching","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Grading (engineering); Psychology; Medical education; Teaching assistant; Grant writing; Pedagogy; Mathematics education; Medicine; Library science; Engineering; Computer science","score_opus":0.06557763282669944,"score_gpt":0.37366961149807154,"score_spread":0.3080919786713721,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1570879941","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9629884,0.00013201055,0.010063913,0.0029307087,0.00022635999,0.013194757,0.0004037982,0.00076125626,0.0092988815],"genre_scores_gemma":[0.7871041,0.00039452547,0.16047391,0.0020521637,0.00013495813,0.02174602,0.0012640838,0.00033110532,0.026499096],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9917476,0.005003829,0.00041400242,0.0005651305,0.0012542165,0.001015191],"domain_scores_gemma":[0.971235,0.007990013,0.0014901145,0.0020959605,0.0046338844,0.012555115],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02326402,0.00072793907,0.00048580024,0.0010379674,0.0038338436,0.002350313,0.0021044712,0.0014136699,0.0031205025],"category_scores_gemma":[0.020928973,0.00081786036,0.000535635,0.000547787,0.0015514165,0.0018503888,0.0041758404,0.0033228383,0.001147066],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0021952987,0.045799967,0.039961584,0.0010070672,0.00006301647,0.0033656773,0.13832118,0.00092163455,0.032949187,0.0020657459,0.030312406,0.70303726],"study_design_scores_gemma":[0.011187432,0.10685818,0.24838494,0.00046545887,0.00031452652,0.0033351823,0.17724462,0.0063860645,0.077909306,0.0034116579,0.36408573,0.00041686514],"about_ca_topic_score_codex":0.0018624212,"about_ca_topic_score_gemma":0.005039137,"teacher_disagreement_score":0.02326402,"about_ca_system_score_codex":0.0012927584,"about_ca_system_score_gemma":0.009229375,"threshold_uncertainty_score":0.123033345},"labels":[],"label_agreement":null},{"id":"W1577833291","doi":"","title":"Diagnosing L2 Learners' Language Skills Based on the Use of a Web-Based Assessment Tool Called DIALANG","year":2014,"lang":"en","type":"article","venue":"International journal of e-learning & distance education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Active listening; Reading (process); Psychology; Significant difference; Mathematics education; English language; Foreign language; Ranking (information retrieval); English as a foreign language; Pedagogy; Computer science; Linguistics; Mathematics; Artificial intelligence; Communication","score_opus":0.017757784324462636,"score_gpt":0.3534006645869133,"score_spread":0.3356428802624507,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1577833291","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99797875,0.00005239264,0.00070726796,0.000027991708,0.000006205552,0.00007815181,0.000058516423,0.000028323557,0.0010624302],"genre_scores_gemma":[0.99400985,0.00012582523,0.0044276756,0.00003931146,0.000004194102,0.00012016248,0.0001100113,0.0000049218193,0.0011582138],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9993962,0.00021213017,0.00008141879,0.000073432464,0.00017206829,0.00006484757],"domain_scores_gemma":[0.99772745,0.0007341858,0.00039996306,0.000094521485,0.00073011126,0.00031366167],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014410815,0.00047582117,0.0003527536,0.0013251051,0.0003241644,0.00061082165,0.0002680736,0.00024437933,0.0014325271],"category_scores_gemma":[0.0043203556,0.00011213771,0.00028564507,0.00029742264,0.00018699729,0.00052327494,0.0009143074,0.0003837241,0.00046670632],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00036115936,0.0013952919,0.78031456,0.00019481692,0.000042850694,0.00026291044,0.006173039,0.00023107916,0.015440817,0.00006255805,0.00084947725,0.19467148],"study_design_scores_gemma":[0.000051264902,0.0033971327,0.9661284,0.000085890715,0.000054482018,0.001106509,0.01045256,0.0020001715,0.013956372,0.00022382088,0.0024831188,0.000060411385],"about_ca_topic_score_codex":0.0012066264,"about_ca_topic_score_gemma":0.0028149863,"teacher_disagreement_score":0.0014410815,"about_ca_system_score_codex":0.00022602691,"about_ca_system_score_gemma":0.00038442088,"threshold_uncertainty_score":0.0076212287},"labels":[],"label_agreement":null},{"id":"W1578913844","doi":"","title":"What Has Experience Got to Do with It? An Exploration of L1 and L2 Test Takers' Perceptions of Test Performance and Alignment to Classroom Literacy Activities.","year":2011,"lang":"en","type":"article","venue":"ePrints Soton (University of Southampton)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Carleton University; Queen's University","funders":"","keywords":"Test (biology); Graduation (instrument); Literacy; Psychology; Perception; Mathematics education; Scale (ratio); Pedagogy; Engineering","score_opus":0.05434605885297318,"score_gpt":0.29153421959941517,"score_spread":0.237188160746442,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1578913844","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9978011,0.00023790941,0.00012984099,0.0005952079,0.000014998242,0.000013899351,0.000034043853,0.0000054038173,0.0011676288],"genre_scores_gemma":[0.9987733,0.00022638973,0.00010419128,0.0002045013,0.000009547201,0.000013620547,0.00003415061,0.0000062995523,0.0006280174],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9931846,0.0036509663,0.0004325171,0.00028161606,0.0014535746,0.0009967122],"domain_scores_gemma":[0.97216,0.013785785,0.0045603057,0.0007097962,0.0038346364,0.004949542],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010214283,0.0004144812,0.00056868047,0.0015076768,0.002494152,0.0041950187,0.00090519426,0.0012356468,0.0018030703],"category_scores_gemma":[0.03840467,0.0004429551,0.0005966179,0.0011167614,0.003428136,0.002780478,0.0034297425,0.0020644187,0.00028330745],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010047849,0.00015482446,0.14545894,0.00014483648,0.000030538682,0.00086499454,0.8369657,0.000039007387,0.0013575804,0.0001999033,0.000563439,0.01411974],"study_design_scores_gemma":[0.0000076219253,0.00036862917,0.1366436,0.00012384077,0.000016848424,0.000559183,0.85761565,0.00009447851,0.00037901997,0.0000892721,0.004052283,0.000049448354],"about_ca_topic_score_codex":0.03184856,"about_ca_topic_score_gemma":0.038509354,"teacher_disagreement_score":0.03184856,"about_ca_system_score_codex":0.0025772855,"about_ca_system_score_gemma":0.0024959357,"threshold_uncertainty_score":0.06332636},"labels":[],"label_agreement":null},{"id":"W1583411474","doi":"10.18806/tesl.v31i1.1166","title":"The Effect of Self-Assessment on EFL Learners’ Self-Efficacy","year":2014,"lang":"en","type":"article","venue":"TESL Canada Journal","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":55,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology; Analysis of covariance; Formative assessment; Mathematics education; Humanities; Mathematics; Statistics; Philosophy","score_opus":0.008497245299180027,"score_gpt":0.3039366541429781,"score_spread":0.2954394088437981,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1583411474","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.998744,0.00008498682,0.00016367473,0.000019257817,0.0000050571675,0.000011925097,0.000010387465,0.0000046523096,0.0009560886],"genre_scores_gemma":[0.9993753,0.00004110939,0.00020996532,0.000007646958,0.000004475003,0.000013675707,0.000015105325,0.0000017655982,0.00033090828],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99726176,0.0013128279,0.00016219573,0.00027259105,0.0008219276,0.00016864833],"domain_scores_gemma":[0.9730324,0.017958755,0.003678528,0.001381926,0.0022219836,0.0017263175],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0033735477,0.000289894,0.00037156921,0.00057392777,0.0002472798,0.00076702447,0.00022731304,0.000238231,0.001347089],"category_scores_gemma":[0.013333846,0.00012351583,0.00039359863,0.00021512553,0.0004715217,0.0003514346,0.00050249544,0.00046460438,0.00020299877],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00097535976,0.0026802102,0.89612734,0.00013001397,0.00019461426,0.0001482729,0.005365164,0.00028719392,0.008406186,0.00014948499,0.00018320611,0.08535296],"study_design_scores_gemma":[0.000020041925,0.001398703,0.994337,0.000025707457,0.00004756928,0.00007325791,0.0011808183,0.0004155232,0.0019891278,0.00007505355,0.00042018495,0.000016982696],"about_ca_topic_score_codex":0.0005593933,"about_ca_topic_score_gemma":0.00074300764,"teacher_disagreement_score":0.0033735477,"about_ca_system_score_codex":0.00023412489,"about_ca_system_score_gemma":0.00033693272,"threshold_uncertainty_score":0.01784122},"labels":[],"label_agreement":null},{"id":"W1586317966","doi":"","title":"Accountability, Student Assessment, and the Need for a Comprehensive Approach.","year":2005,"lang":"en","type":"article","venue":"International electronic journal for leadership in learning","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":10,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Accountability; Psychology; Pedagogy; Sociology; Mathematics education; Political science","score_opus":0.15105256910987522,"score_gpt":0.44048664126366943,"score_spread":0.28943407215379424,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1586317966","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022055658,0.05021276,0.022831552,0.83760405,0.0044519952,0.000154679,0.000047670736,0.00029877867,0.06234284],"genre_scores_gemma":[0.8851613,0.01658555,0.034149427,0.054685313,0.002679761,0.00044486288,0.00005132191,0.00009454932,0.006147914],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9262768,0.04689402,0.0041159,0.0020669347,0.018068895,0.0025773633],"domain_scores_gemma":[0.79896235,0.12616421,0.01079257,0.007806985,0.03258306,0.02369082],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0884882,0.0003974218,0.00074675586,0.0034119438,0.006181748,0.012706236,0.0019094923,0.008172408,0.0019091761],"category_scores_gemma":[0.20204337,0.00047265162,0.00034328774,0.0014475279,0.017504217,0.013556014,0.011456391,0.013966673,0.0002674841],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000087435685,0.0004141505,0.025584714,0.00087739865,0.00011452961,0.0003548427,0.019033635,0.00090971513,0.00034101369,0.38978636,0.11364068,0.44885537],"study_design_scores_gemma":[0.00009291655,0.00025328642,0.039440177,0.0058799414,0.00008816984,0.0009819613,0.026199397,0.0025272483,0.0005798489,0.7557638,0.16799307,0.00020026191],"about_ca_topic_score_codex":0.010212061,"about_ca_topic_score_gemma":0.022786997,"teacher_disagreement_score":0.0884882,"about_ca_system_score_codex":0.0065453392,"about_ca_system_score_gemma":0.04067012,"threshold_uncertainty_score":0.4679759},"labels":[],"label_agreement":null},{"id":"W1587603569","doi":"","title":"The Handheld: A Useful Tool to Collect Information in the Process of Authentic Assessment.","year":2008,"lang":"en","type":"article","venue":"E-Learn: World Conference on E-Learning in Corporate, Government, Healthcare, and Higher Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Mobile device; Process (computing); Computer science; World Wide Web","score_opus":0.06382413120279898,"score_gpt":0.3529445154863502,"score_spread":0.28912038428355125,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1587603569","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16638125,0.006839722,0.6558937,0.0045988704,0.0027568773,0.010516068,0.023259973,0.04160658,0.08814697],"genre_scores_gemma":[0.28217077,0.0027635633,0.63656783,0.001789414,0.0005562893,0.005770325,0.0048289765,0.0021511307,0.06340169],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9965767,0.0016084374,0.00023971603,0.00028160188,0.0011955276,0.00009801226],"domain_scores_gemma":[0.9840261,0.009562854,0.0007533587,0.002254868,0.0026152688,0.0007874978],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004142951,0.000803989,0.0004938097,0.0021155705,0.00061228784,0.0012161117,0.0012491441,0.0010147764,0.021818038],"category_scores_gemma":[0.022455996,0.00036035944,0.00028658894,0.0011294015,0.00042762392,0.002217282,0.0021878486,0.0008743569,0.011555393],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015727084,0.0005004529,0.008523941,0.0015016135,0.00006648513,0.0009096206,0.0033226358,0.00022606229,0.05651867,0.0017117219,0.07907223,0.8460739],"study_design_scores_gemma":[0.00089806435,0.00413615,0.105618306,0.0044702,0.0003131626,0.006638478,0.0076650246,0.009810965,0.15884943,0.013479342,0.6872903,0.0008305484],"about_ca_topic_score_codex":0.00065483514,"about_ca_topic_score_gemma":0.0010753139,"teacher_disagreement_score":0.021818038,"about_ca_system_score_codex":0.00019541703,"about_ca_system_score_gemma":0.00096097897,"threshold_uncertainty_score":0.07298863},"labels":[],"label_agreement":null},{"id":"W1590091593","doi":"10.22329/il.v33i3.3774","title":"A Serious Flaw in the Collegiate Learning Assessment [CLA] Test","year":2013,"lang":"en","type":"article","venue":"Informal Logic","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Test (biology); Rendering (computer graphics); Logical reasoning; Psychology; Reliability (semiconductor); Mathematics education; Critical thinking; Test validity; Validity; Computer science; Applied psychology; Artificial intelligence; Psychometrics; Developmental psychology","score_opus":0.022408105744773383,"score_gpt":0.3322505504779639,"score_spread":0.30984244473319056,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1590091593","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16398837,0.008643495,0.26783603,0.4302262,0.019605892,0.0013307431,0.0015604503,0.0053881607,0.10142073],"genre_scores_gemma":[0.7050834,0.0033501661,0.13285844,0.11896579,0.003092506,0.0011782887,0.0010401694,0.00078707584,0.033644076],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9372035,0.01813234,0.006668051,0.0028191616,0.033926714,0.0012502016],"domain_scores_gemma":[0.79554,0.12863912,0.0118092,0.009650101,0.05053436,0.0038271314],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0406902,0.00061489403,0.0006789322,0.0017596051,0.0013781722,0.0032036984,0.0024330749,0.0047162133,0.0028103068],"category_scores_gemma":[0.2573174,0.00047780466,0.00082326453,0.0014214166,0.005645261,0.0031012224,0.0028604076,0.0064964695,0.00262291],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003790221,0.00053922384,0.07399078,0.0007788039,0.00017908194,0.0007400609,0.006576465,0.0013783318,0.0048710606,0.09618074,0.19066194,0.6237245],"study_design_scores_gemma":[0.0004235055,0.0032385704,0.12664531,0.0050797765,0.00055579736,0.0141645465,0.0054947482,0.014187868,0.021756737,0.23487815,0.57281643,0.00075851934],"about_ca_topic_score_codex":0.0054524983,"about_ca_topic_score_gemma":0.0069998302,"teacher_disagreement_score":0.0406902,"about_ca_system_score_codex":0.002208782,"about_ca_system_score_gemma":0.006763246,"threshold_uncertainty_score":0.21519291},"labels":[],"label_agreement":null},{"id":"W1590196413","doi":"","title":"Individual Assignments and Student Expectancies: Exploring the Learning Conundrum","year":2007,"lang":"en","type":"article","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Laurentian University","funders":"","keywords":"Psychology; Social psychology; Mathematics education; Cognitive psychology","score_opus":0.0968097770842884,"score_gpt":0.3817578029481843,"score_spread":0.2849480258638959,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1590196413","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99790895,0.00007188681,0.00045016696,0.00026831302,0.000005760197,0.000010038194,0.000027300359,0.000006393621,0.0012511716],"genre_scores_gemma":[0.99967325,0.000021550526,0.00011091807,0.000030189482,0.0000055136393,0.000009285417,0.000025228132,0.0000018939169,0.00012229108],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.995732,0.002663285,0.00020641489,0.0002541357,0.0007525686,0.00039164835],"domain_scores_gemma":[0.9060702,0.066649094,0.011405593,0.0022145105,0.0038737927,0.009786779],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009980272,0.00025579246,0.00049236324,0.0013103468,0.00059349486,0.0023951,0.0007569632,0.0008033093,0.0034229644],"category_scores_gemma":[0.056888506,0.00021357209,0.00035558708,0.0012341117,0.001300514,0.0018614552,0.0015902527,0.0014691645,0.00026910173],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023506653,0.00057768734,0.97284716,0.000032319538,0.000055128647,0.000052005056,0.004380044,0.00018441948,0.00021252579,0.00065763434,0.00017602464,0.020589938],"study_design_scores_gemma":[0.000020254745,0.0006279476,0.9884221,0.000019665113,0.000034011307,0.000053338805,0.0066535105,0.00204423,0.00019692091,0.0016214284,0.00028638,0.000020325662],"about_ca_topic_score_codex":0.001831912,"about_ca_topic_score_gemma":0.0029032642,"teacher_disagreement_score":0.009980272,"about_ca_system_score_codex":0.0007351891,"about_ca_system_score_gemma":0.0009074169,"threshold_uncertainty_score":0.052781403},"labels":[],"label_agreement":null},{"id":"W1599466273","doi":"","title":"The nature and impact of teachers’ formative assessment practices","year":2005,"lang":"en","type":"article","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":52,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Formative assessment; Accountability; Orchestration; Mathematics education; Psychology; Assessment for learning; Pedagogy; Action research; Process (computing); Medical education; Computer science; Political science; Medicine","score_opus":0.026829701479986,"score_gpt":0.45290406753436335,"score_spread":0.4260743660543774,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1599466273","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9018313,0.0049746293,0.051326636,0.0063863015,0.00040209314,0.0007156153,0.00017428683,0.00046029655,0.033728767],"genre_scores_gemma":[0.9823094,0.00076798623,0.014548948,0.0004215693,0.00012660788,0.00036158008,0.000044484506,0.00005876207,0.0013607625],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.7829983,0.12807319,0.012417368,0.011434092,0.06277486,0.0023021705],"domain_scores_gemma":[0.23075736,0.6546978,0.03876265,0.043821413,0.028631153,0.003329684],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.13966745,0.0008616692,0.0006421727,0.004175077,0.0023191848,0.009288794,0.0031334474,0.001780293,0.0017598573],"category_scores_gemma":[0.4940533,0.0010609986,0.0007403232,0.002428256,0.0040957085,0.009121327,0.004890441,0.003043969,0.0003459118],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000836412,0.0016392067,0.22506809,0.001593967,0.00046759954,0.0001588335,0.090944156,0.0024932448,0.006864441,0.010351736,0.0014757651,0.65810657],"study_design_scores_gemma":[0.0006124849,0.0098013235,0.78650856,0.0049127676,0.0007810028,0.0016631633,0.054871555,0.012576397,0.026749901,0.039417036,0.061586175,0.00051955367],"about_ca_topic_score_codex":0.0028684281,"about_ca_topic_score_gemma":0.003925912,"teacher_disagreement_score":0.13966745,"about_ca_system_score_codex":0.0057782386,"about_ca_system_score_gemma":0.0059427507,"threshold_uncertainty_score":0.7386409},"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,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_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","score_opus":0.015254767070093588,"score_gpt":0.284865287494137,"score_spread":0.2696105204240434,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1599897745","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9992812,0.000074436095,0.00015474377,0.00003093326,0.000006095781,0.000026823076,0.0000052997643,0.000008965833,0.00041139737],"genre_scores_gemma":[0.99877006,0.000089318506,0.0006620936,0.000023633756,0.000013571803,0.000039244354,0.000011706008,0.000005302148,0.00038506117],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98682714,0.009353414,0.00059493765,0.00068103784,0.0020642984,0.00047915857],"domain_scores_gemma":[0.92827404,0.049403436,0.00740787,0.002277199,0.0079431515,0.004694289],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0063291914,0.0006594701,0.00080555724,0.0008242865,0.0016071039,0.0011286094,0.00052088825,0.0007043291,0.0013375061],"category_scores_gemma":[0.06671613,0.00023856196,0.00028863532,0.00038461568,0.00079992274,0.00069702737,0.001739477,0.0005647016,0.00020287085],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.008158998,0.008970548,0.3985783,0.0011360686,0.0003789988,0.0030802235,0.16823667,0.0006582762,0.09218762,0.0002191898,0.000825502,0.31756958],"study_design_scores_gemma":[0.0006187594,0.03681539,0.8163277,0.0003012247,0.0005255767,0.0017450231,0.09663276,0.0020473513,0.039438624,0.00053270214,0.004847407,0.00016746903],"about_ca_topic_score_codex":0.001482534,"about_ca_topic_score_gemma":0.0026113195,"teacher_disagreement_score":0.0063291914,"about_ca_system_score_codex":0.00046822205,"about_ca_system_score_gemma":0.00082191394,"threshold_uncertainty_score":0.03347236},"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,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_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","score_opus":0.03360182513708301,"score_gpt":0.3962923616583372,"score_spread":0.36269053652125416,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1600384676","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00062435574,0.061380412,0.006763033,0.8903543,0.02435288,0.00017016324,0.0005668545,0.0006338034,0.015154268],"genre_scores_gemma":[0.027848016,0.19156922,0.05231432,0.64426225,0.046253577,0.0015697925,0.0025553433,0.0014070093,0.032220475],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.97946006,0.009183844,0.0019242322,0.0008506429,0.007462112,0.0011192159],"domain_scores_gemma":[0.8841751,0.03937459,0.0051854067,0.008082137,0.045382753,0.017799942],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03366942,0.0017182473,0.0021090403,0.0044864076,0.0032041871,0.00878798,0.0055561266,0.016058663,0.014944881],"category_scores_gemma":[0.12738723,0.00072852307,0.0010134561,0.0033029325,0.009310993,0.020679275,0.004837667,0.0153413,0.016632104],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000043740085,0.00014421923,0.0026644315,0.00066577917,0.000021511618,0.0002569167,0.00047575013,0.00012670406,0.00011979682,0.0060268026,0.6614284,0.32802585],"study_design_scores_gemma":[0.00005450557,0.00015457442,0.0048290854,0.012107574,0.000045351062,0.0015976345,0.0036988028,0.000363933,0.00031254638,0.05026188,0.92645174,0.00012243538],"about_ca_topic_score_codex":0.016083024,"about_ca_topic_score_gemma":0.01697704,"teacher_disagreement_score":0.03366942,"about_ca_system_score_codex":0.0049432786,"about_ca_system_score_gemma":0.02129801,"threshold_uncertainty_score":0.1780631},"labels":[],"label_agreement":null},{"id":"W1604800422","doi":"10.1002/9781118411360.wbcla142","title":"Mixed Methods Research","year":2013,"lang":"en","type":"other","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Positivism; Parallels; Context (archaeology); Construct (python library); Field (mathematics); Narrative; Epistemology; Sociology; Engineering ethics; Management science; Computer science; Linguistics; Engineering; Geography","score_opus":0.25637731550061194,"score_gpt":0.5739206860344149,"score_spread":0.317543370533803,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1604800422","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013440813,0.042681575,0.47476164,0.017556632,0.015230948,0.2082975,0.02174158,0.0026135554,0.20367575],"genre_scores_gemma":[0.057098474,0.028189791,0.4954152,0.016269207,0.0029326242,0.34375837,0.008902203,0.0014993486,0.045934767],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.81815565,0.1297692,0.015094709,0.01372097,0.02074653,0.002512892],"domain_scores_gemma":[0.80750555,0.102102086,0.011840821,0.028406966,0.046344943,0.0037997141],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.09943652,0.0022845143,0.003209458,0.008067507,0.005486001,0.011884314,0.006071833,0.004001099,0.08535766],"category_scores_gemma":[0.18570498,0.0014791673,0.0035098905,0.009836285,0.0037386406,0.0057143862,0.00906742,0.0052522304,0.022309544],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00088919944,0.0008092444,0.003489915,0.030104212,0.00095888856,0.00041275087,0.021114858,0.001559472,0.00091091456,0.12718575,0.13477363,0.67779124],"study_design_scores_gemma":[0.0005725458,0.000848184,0.002082353,0.024808215,0.00040892977,0.00041480377,0.008958343,0.0010341987,0.0011190212,0.06551293,0.8940921,0.00014844193],"about_ca_topic_score_codex":0.0033126776,"about_ca_topic_score_gemma":0.0065252096,"teacher_disagreement_score":0.09943652,"about_ca_system_score_codex":0.0084184455,"about_ca_system_score_gemma":0.032523453,"threshold_uncertainty_score":0.5258769},"labels":[],"label_agreement":null},{"id":"W16087079","doi":"10.1053/j.semtcvs.2005.04.002","title":"Assessing for Student Success and a Target Class Average: Balancing two grade-related goals facing university instructors and teaching assistants","year":2012,"lang":"en","type":"article","venue":"Seminars in Thoracic and Cardiovascular Surgery","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Grading (engineering); Mathematics education; The arts; Psychology; Medical education; Computer science; Engineering; Political science; Medicine","score_opus":0.02535534479289702,"score_gpt":0.3408351853130464,"score_spread":0.3154798405201494,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W16087079","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96890813,0.00045889843,0.0016913774,0.014051482,0.00028745653,0.000082531595,0.00014448448,0.00023254887,0.014142929],"genre_scores_gemma":[0.99629647,0.00016688499,0.0013900591,0.00033060816,0.00006778818,0.0000410857,0.00007211879,0.000023973123,0.0016109544],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.9942662,0.0017860564,0.00033064064,0.00035574063,0.002582677,0.0006785859],"domain_scores_gemma":[0.96959865,0.0046169404,0.0045526,0.0007812769,0.007023306,0.013427199],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008664896,0.00045515274,0.00069486117,0.0017823117,0.0018597133,0.004461597,0.00090141926,0.000891633,0.0031636474],"category_scores_gemma":[0.041066736,0.00019393189,0.00041341817,0.00079925306,0.00091542234,0.0018021566,0.0039611356,0.0012623112,0.0014595183],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031821633,0.0009660615,0.66611576,0.00013134036,0.00005471318,0.00018287836,0.008505643,0.00030993315,0.0007620252,0.000958214,0.019767696,0.30192757],"study_design_scores_gemma":[0.00006357936,0.0020945766,0.9300086,0.0002512558,0.000059861286,0.00040251896,0.041557662,0.0026062154,0.0015989667,0.004510155,0.016714191,0.00013233775],"about_ca_topic_score_codex":0.0018570925,"about_ca_topic_score_gemma":0.0028872092,"teacher_disagreement_score":0.008664896,"about_ca_system_score_codex":0.0016766199,"about_ca_system_score_gemma":0.002892128,"threshold_uncertainty_score":0.045824885},"labels":[],"label_agreement":null},{"id":"W1611061022","doi":"","title":"Att bedöma elevers läsförståelse : En jämförelse mellan svenska och kanadensiska bedömningsdiskurser i grundskolans mellanår","year":2013,"lang":"sv","type":"article","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Psychology","score_opus":0.016897596670021057,"score_gpt":0.2931017035423877,"score_spread":0.27620410687236663,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1611061022","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9906606,0.0002503766,0.00023537957,0.00034442,0.000011781353,0.00002125509,0.00014012516,0.00001819286,0.008317769],"genre_scores_gemma":[0.9903964,0.00031858197,0.0005699198,0.000046618305,0.0000030111828,0.00001292989,0.00016403229,0.00001661658,0.008471796],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99773127,0.0004191229,0.000117077434,0.00021160717,0.001128132,0.00039282977],"domain_scores_gemma":[0.99584216,0.0010996826,0.00047990293,0.00009491703,0.001795086,0.0006881711],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0022798174,0.0004174063,0.00040002796,0.001522107,0.0037365952,0.0037187273,0.0006396994,0.0004959033,0.004220547],"category_scores_gemma":[0.0069978447,0.00022529022,0.00016549852,0.0013193575,0.002110962,0.0008897438,0.0020709953,0.0009553773,0.00069086597],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005351175,0.00027530402,0.27081126,0.00042532844,0.000052248306,0.0013484341,0.57642984,0.0007677832,0.007411867,0.0020260385,0.005298505,0.13461828],"study_design_scores_gemma":[0.000014461776,0.00017749696,0.3791008,0.00024164931,0.00004302162,0.00040571994,0.5751459,0.00044941643,0.004170725,0.00064852816,0.039535206,0.000067051995],"about_ca_topic_score_codex":0.7000705,"about_ca_topic_score_gemma":0.818958,"teacher_disagreement_score":0.2999295,"about_ca_system_score_codex":0.0094362,"about_ca_system_score_gemma":0.014201802,"threshold_uncertainty_score":0.60339165},"labels":[],"label_agreement":null},{"id":"W1620918562","doi":"10.22329/jtl.v4i1.89","title":"An Alternative Vision for Large-scale Assessment in Canada","year":2006,"lang":"en","type":"article","venue":"Journal of Teaching and Learning","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Brock University","funders":"","keywords":"Scale (ratio); Test (biology); Set (abstract data type); Sample (material); Quality (philosophy); Achievement test; Educational assessment; Standardized test; Psychology; Mathematics education; Medical education; Computer science; Geography; Medicine; Cartography","score_opus":0.011930447431533972,"score_gpt":0.36058651399949543,"score_spread":0.34865606656796144,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1620918562","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10908392,0.008945931,0.15854172,0.29342508,0.0016030534,0.0023661405,0.0014816704,0.0017349448,0.4228175],"genre_scores_gemma":[0.8569042,0.0021116314,0.08863783,0.019033493,0.00029133665,0.0008546759,0.00033508523,0.00016049675,0.03167115],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9731169,0.006677255,0.0010972158,0.0027873893,0.012455287,0.0038659652],"domain_scores_gemma":[0.9546653,0.0069466247,0.0015293227,0.0036562516,0.026085475,0.007117042],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.018887836,0.00062616373,0.0007006814,0.0025453812,0.008888663,0.012190715,0.0037831313,0.003587497,0.003962082],"category_scores_gemma":[0.03334904,0.0006263846,0.0007106135,0.0039154817,0.00824027,0.006294776,0.0062910523,0.0053947847,0.0004798993],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001903329,0.00019257025,0.011890539,0.00036250835,0.000057009715,0.0003535057,0.0067321337,0.006386439,0.0012194905,0.74009883,0.04629724,0.18621936],"study_design_scores_gemma":[0.0004580677,0.000441064,0.06323928,0.0012701764,0.00014558248,0.0005267339,0.011953015,0.026537593,0.0016641248,0.35766047,0.53559065,0.0005132545],"about_ca_topic_score_codex":0.9715759,"about_ca_topic_score_gemma":0.9738174,"teacher_disagreement_score":0.111057095,"about_ca_system_score_codex":0.111057095,"about_ca_system_score_gemma":0.29344577,"threshold_uncertainty_score":0.8057794},"labels":[],"label_agreement":null},{"id":"W1626448709","doi":"10.18806/tesl.v26i1.129","title":"Teachers' Assessment of ESL Students in Mainstream Classes: Challenges, Strategies, and Decision-Making","year":2008,"lang":"en","type":"article","venue":"TESL Canada Journal","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Mainstream; Psychology; Mathematics education; Work (physics); Pedagogy","score_opus":0.035413551529769056,"score_gpt":0.3662058004315097,"score_spread":0.33079224890174064,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1626448709","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99646807,0.00008413096,0.00021308215,0.00013101372,0.000004610394,0.000022522912,0.000018281404,0.00000950503,0.0030487278],"genre_scores_gemma":[0.9955922,0.00018383708,0.0006114718,0.000059361246,0.0000029180226,0.000014030827,0.00003573588,0.000005097967,0.0034953032],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99740237,0.0006081744,0.00019990673,0.0002478667,0.0010919498,0.00044968165],"domain_scores_gemma":[0.9921461,0.0018514649,0.0011939582,0.00020282283,0.0033251366,0.0012805358],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027060877,0.00038278606,0.00038870386,0.001160796,0.0021983176,0.0027777636,0.00065057,0.00038406794,0.001696891],"category_scores_gemma":[0.009577212,0.0002719401,0.00022807418,0.00067411084,0.0017934273,0.0007238176,0.0021339252,0.0006847059,0.00061216444],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028084376,0.00076168054,0.39920565,0.00029847887,0.000027895454,0.00130692,0.42725724,0.00024015183,0.013947749,0.0004229955,0.0018432442,0.15440711],"study_design_scores_gemma":[0.000035027162,0.00042531407,0.41946018,0.00020713902,0.00002598025,0.00042345191,0.55876344,0.0006022014,0.004638615,0.000637449,0.014714205,0.000066951725],"about_ca_topic_score_codex":0.14252828,"about_ca_topic_score_gemma":0.32518372,"teacher_disagreement_score":0.14252828,"about_ca_system_score_codex":0.004071578,"about_ca_system_score_gemma":0.006219845,"threshold_uncertainty_score":0.28339738},"labels":[],"label_agreement":null},{"id":"W1628651023","doi":"","title":"Implementation of Peer Reviews: Online Learning","year":2015,"lang":"en","type":"article","venue":"International Journal of Learning Teaching and Educational Research","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Windsor; University of Ottawa","funders":"","keywords":"CLARITY; Peer review; Technical peer review; Peer feedback; Computer science; Online course; Online learning; Grammar; Subject (documents); Mathematics education; Psychology; World Wide Web; Political science","score_opus":0.2608650624116684,"score_gpt":0.5989500543172764,"score_spread":0.33808499190560803,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1628651023","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14263715,0.0028076072,0.5764384,0.020624515,0.0045544608,0.038904056,0.0004281882,0.013126114,0.20047957],"genre_scores_gemma":[0.43439826,0.0014920931,0.51416796,0.0026369742,0.0012387334,0.00943951,0.00037368463,0.0008006495,0.035452124],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.7434413,0.16198476,0.016342107,0.008798407,0.06607364,0.0033597532],"domain_scores_gemma":[0.6464007,0.12875168,0.037033148,0.056028776,0.1149532,0.01683251],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.105864614,0.0008991868,0.0011197836,0.0026781287,0.0027449578,0.008209022,0.0051446753,0.0022071651,0.008511206],"category_scores_gemma":[0.25810343,0.0008879788,0.0011281623,0.0019313865,0.0022549648,0.0058254446,0.006897051,0.0034688523,0.006309642],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024766568,0.0019139788,0.008074749,0.0021783647,0.00015848016,0.00021535794,0.007656675,0.0011503132,0.0053816135,0.007958445,0.022387572,0.94267684],"study_design_scores_gemma":[0.0008956686,0.007794416,0.060789913,0.004900577,0.00040412028,0.002430832,0.010450596,0.023788998,0.023622612,0.03949141,0.8246127,0.0008181317],"about_ca_topic_score_codex":0.0015436868,"about_ca_topic_score_gemma":0.0023838538,"teacher_disagreement_score":0.89413536,"about_ca_system_score_codex":0.002923568,"about_ca_system_score_gemma":0.020214248,"threshold_uncertainty_score":0.55987227},"labels":[],"label_agreement":null},{"id":"W1654600664","doi":"10.21432/t2j300","title":"Optional online quizzes: College student use and relationship to achievement","year":2006,"lang":"en","type":"article","venue":"Canadian Journal of Learning and Technology","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":44,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"MacEwan University","funders":"","keywords":"Academic achievement; Psychology; Mathematics education; Comprehension; Cognition; Class (philosophy); Student achievement; Computer science","score_opus":0.026190919804516488,"score_gpt":0.3202131937309054,"score_spread":0.2940222739263889,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1654600664","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99947053,0.00005247551,0.00003265187,0.000033154618,0.0000024874832,0.000005167883,0.000069483496,0.000006570417,0.00032751437],"genre_scores_gemma":[0.99947816,0.000042355325,0.0000573483,0.00000860229,0.000003098588,0.0000054418956,0.000097773205,0.000002638706,0.00030457816],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9989686,0.00022313128,0.00014101774,0.00016052565,0.0003586742,0.00014805899],"domain_scores_gemma":[0.9789757,0.0071471357,0.008079106,0.0006361078,0.0019530958,0.003208768],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009943604,0.0002549194,0.0002698036,0.0014757703,0.000459731,0.0012624946,0.00047135787,0.0005590146,0.0033342692],"category_scores_gemma":[0.018815009,0.00023087206,0.00024779665,0.0012581006,0.00042205642,0.0005479478,0.0007163767,0.00096510974,0.0004599123],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011058039,0.00020604223,0.99265164,0.000007967363,0.000025613223,0.000028850745,0.00020661205,0.000024393898,0.00015198484,0.0000112142225,0.000098011595,0.006477134],"study_design_scores_gemma":[0.0000027415422,0.00021005646,0.9989951,0.0000032206672,0.000011087828,0.000068680936,0.00028674182,0.00018095155,0.00011900763,0.000019707015,0.00009845326,0.0000041975304],"about_ca_topic_score_codex":0.0072924215,"about_ca_topic_score_gemma":0.009197708,"teacher_disagreement_score":0.0072924215,"about_ca_system_score_codex":0.00040022325,"about_ca_system_score_gemma":0.00041676295,"threshold_uncertainty_score":0.014499962},"labels":[],"label_agreement":null},{"id":"W1655149967","doi":"10.22329/jtl.v9i1.3540","title":"Student Washback from Tertiary Standardized English Proficiency Exit Requirements in Taiwan","year":2013,"lang":"en","type":"article","venue":"Journal of Teaching and Learning","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Mathematics education; sort; Tertiary level; Higher education; Psychology; Medical education; Political science; Computer science; Medicine","score_opus":0.0208192614809386,"score_gpt":0.34683071652552294,"score_spread":0.32601145504458434,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1655149967","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99939823,0.000024518715,0.0000605164,0.00011835638,0.0000044039907,0.000008158541,0.000008335797,0.000008452319,0.0003689467],"genre_scores_gemma":[0.9993007,0.000022247874,0.000069871414,0.000077835546,0.0000038276244,0.00000970528,0.000025363757,0.000003999989,0.0004864845],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99637765,0.0013196553,0.00039489128,0.00027156662,0.0010404198,0.0005957696],"domain_scores_gemma":[0.9848417,0.0042692567,0.0050290427,0.0012639351,0.0022005027,0.0023955535],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0047244416,0.0002608695,0.0005433153,0.00072976755,0.0008985868,0.0014994387,0.00055567425,0.00073171844,0.002364307],"category_scores_gemma":[0.025293065,0.00023777262,0.00039581905,0.000730202,0.0007994259,0.00069137383,0.0024957221,0.0012799607,0.00048047514],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011092642,0.0012581273,0.8093829,0.00014800123,0.000048484966,0.0018314943,0.04577765,0.00027982154,0.0063815312,0.00022820711,0.0016563612,0.13189808],"study_design_scores_gemma":[0.00004210736,0.002865416,0.9271651,0.00009728195,0.000026098867,0.0005816113,0.0595206,0.00065480993,0.005464251,0.00026908505,0.0032657504,0.00004786164],"about_ca_topic_score_codex":0.0022239264,"about_ca_topic_score_gemma":0.0037805857,"teacher_disagreement_score":0.0047244416,"about_ca_system_score_codex":0.001085358,"about_ca_system_score_gemma":0.0013126257,"threshold_uncertainty_score":0.024985552},"labels":[],"label_agreement":null},{"id":"W1757897301","doi":"10.29173/cmplct17993","title":"Enmeshing Interruption in Assessment of Teacher Education. Response to Bernard Ricca","year":2014,"lang":"en","type":"article","venue":"Complicity An International Journal of Complexity and Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"License; Publication; Permission; Statement (logic); World Wide Web; Library science; Computer science; Political science; Law","score_opus":0.08673746315053754,"score_gpt":0.4580667957143578,"score_spread":0.3713293325638203,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1757897301","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00040373005,0.004084899,0.00012816336,0.9693322,0.024997935,0.000035434332,0.00003743457,0.00003871167,0.0009414506],"genre_scores_gemma":[0.0059496784,0.004407225,0.00034521805,0.9569846,0.02185114,0.00016625527,0.000037451107,0.00006016757,0.010198331],"study_design_codex":"not_applicable","study_design_gemma":"qualitative","domain_scores_codex":[0.9959752,0.0014312562,0.0005556019,0.000529638,0.0011531204,0.0003551729],"domain_scores_gemma":[0.97325605,0.014774878,0.0011870011,0.00068321236,0.0062416755,0.0038571085],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006476008,0.0010740423,0.0011225434,0.00073738326,0.0036044165,0.002740125,0.0028967091,0.021520052,0.0104147205],"category_scores_gemma":[0.049532454,0.00079166994,0.00083828764,0.0007933707,0.0032384542,0.0036517077,0.0030756344,0.02906733,0.0039496743],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000060313596,0.000021379286,0.00029095146,0.00015325882,0.000009249135,0.00044585718,0.0006542951,0.000052105308,0.00014891458,0.00055264274,0.987773,0.009837976],"study_design_scores_gemma":[0.000044791475,0.0000805644,0.0023888035,0.00087210094,0.00001753203,0.0012554004,0.0050844294,0.0001573324,0.00020002197,0.0012043276,0.98862773,0.00006695815],"about_ca_topic_score_codex":0.019032663,"about_ca_topic_score_gemma":0.028955106,"teacher_disagreement_score":0.021520052,"about_ca_system_score_codex":0.0042490596,"about_ca_system_score_gemma":0.0057724034,"threshold_uncertainty_score":0.037843764},"labels":[],"label_agreement":null},{"id":"W1795761960","doi":"10.3968/j.ccc.1923670020110703.162","title":"The IELTS Preparation Washback on Learning and Teaching Outcomes","year":2011,"lang":"en","type":"article","venue":"Cross-cultural communication","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Mathematics education; Economic shortage; Test of English as a Foreign Language; Context (archaeology); Psychology; Language education; Linguistics; Geography","score_opus":0.06037046805975251,"score_gpt":0.43459134305866265,"score_spread":0.37422087499891016,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1795761960","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9961832,0.00023450067,0.00035417915,0.00024360805,0.00007122761,0.000113479,0.000082661165,0.000050153987,0.0026668713],"genre_scores_gemma":[0.99770314,0.000099366356,0.00050016196,0.00007603527,0.00002325327,0.00011236202,0.00007336555,0.000010456729,0.0014018803],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9976547,0.000724812,0.00022837975,0.00026258337,0.00072208606,0.00040740203],"domain_scores_gemma":[0.9863643,0.006548214,0.0023144525,0.000933151,0.0013758774,0.0024641592],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029584933,0.0003728582,0.00073904597,0.00047813886,0.00046774783,0.0014305646,0.0007311852,0.0005667193,0.011280354],"category_scores_gemma":[0.017055802,0.00012355564,0.0006695547,0.00043489842,0.00052155077,0.0007727709,0.0012272425,0.001477103,0.0009782619],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.014627705,0.02640918,0.1679155,0.0022249403,0.00026165784,0.00081166584,0.014035321,0.0010574127,0.025784671,0.0011391455,0.005222274,0.74051046],"study_design_scores_gemma":[0.0005760458,0.026548386,0.92274636,0.0006825516,0.0003372717,0.00021162337,0.012356427,0.0010621924,0.02198038,0.0013490185,0.012048953,0.0001007806],"about_ca_topic_score_codex":0.0006697655,"about_ca_topic_score_gemma":0.0006612839,"teacher_disagreement_score":0.011280354,"about_ca_system_score_codex":0.0007462842,"about_ca_system_score_gemma":0.0010470195,"threshold_uncertainty_score":0.037736535},"labels":[],"label_agreement":null},{"id":"W1797460826","doi":"","title":"Putting Rubrics to the Test: The Effect of Rubric-Referenced Peer Assessment on EFL Learners’ Evaluation of Speaking","year":2013,"lang":"en","type":"article","venue":"Journal of academic and applied studies","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Rubric; Formative assessment; Peer assessment; Psychology; Presupposition; Test (biology); Mathematics education; Peer feedback; Pedagogy; Computer science; Linguistics","score_opus":0.08647179667909898,"score_gpt":0.4307727206229517,"score_spread":0.3443009239438527,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1797460826","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98616993,0.00036138046,0.007884146,0.000171388,0.00008579438,0.00046956353,0.000022644834,0.00028983757,0.0045452383],"genre_scores_gemma":[0.9760582,0.00024670505,0.021669347,0.000094977484,0.000042922253,0.00028395443,0.00004507549,0.00005026118,0.0015085948],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9717748,0.018293826,0.0015958615,0.0015782946,0.0061887596,0.00056846894],"domain_scores_gemma":[0.90779054,0.060825944,0.009251787,0.006133833,0.013146801,0.0028511153],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01768866,0.0009872932,0.000996591,0.0014315944,0.0010347241,0.0014543933,0.0014685448,0.0006664571,0.001698517],"category_scores_gemma":[0.1298854,0.000320764,0.00071005564,0.000576479,0.0010719666,0.0014335669,0.002363052,0.0010538327,0.00049949315],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0026244004,0.0052686534,0.084208824,0.0013863305,0.0003276361,0.0007988261,0.064633705,0.0021935299,0.07218933,0.0007087936,0.0019116787,0.7637482],"study_design_scores_gemma":[0.00066211104,0.057946917,0.64927596,0.0018134956,0.0013487956,0.0047276383,0.09998529,0.026847402,0.12926441,0.0034147038,0.023529157,0.0011840774],"about_ca_topic_score_codex":0.00094481255,"about_ca_topic_score_gemma":0.0017123185,"teacher_disagreement_score":0.01768866,"about_ca_system_score_codex":0.000545755,"about_ca_system_score_gemma":0.0009656828,"threshold_uncertainty_score":0.0935477},"labels":[],"label_agreement":null},{"id":"W1838922808","doi":"10.22329/celt.v8i0.4256","title":"Performance, Feedback, and Revision: Metacognitive Approaches to Undergraduate Essay Writing","year":2015,"lang":"en","type":"article","venue":"Collected Essays on Learning and Teaching","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":39,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Bishop's University","funders":"Bishop's University","keywords":"Metacognition; Writing process; Mathematics education; Academic writing; Psychology; Plan (archaeology); Professional writing; Perception; Pedagogy; Scientific writing; Process (computing); Computer science; Cognition; Linguistics","score_opus":0.09045564680795112,"score_gpt":0.322857496550097,"score_spread":0.23240184974214587,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1838922808","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97493696,0.00039093802,0.016645396,0.00041209243,0.000028280509,0.00016643046,0.000012866655,0.00010588916,0.007301159],"genre_scores_gemma":[0.9873585,0.00009951649,0.011842025,0.000033833927,0.000013161186,0.000098781224,0.0000069669527,0.000007676911,0.0005395075],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.98377293,0.012569177,0.00052180473,0.000829239,0.0019845418,0.00032242888],"domain_scores_gemma":[0.88153094,0.09318608,0.011218587,0.0061519085,0.0051164776,0.002796002],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014131353,0.00048843387,0.00041400184,0.0014424415,0.0008315698,0.0033726017,0.0010706929,0.00055314286,0.0009771009],"category_scores_gemma":[0.07970879,0.00029481488,0.00028862103,0.00064032426,0.0015188169,0.001806387,0.0022265753,0.0010693591,0.00014050852],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00084845885,0.0030743494,0.10361166,0.0007061926,0.000118085525,0.00022882044,0.06862107,0.0022227746,0.01393659,0.0027963067,0.00076485524,0.80307084],"study_design_scores_gemma":[0.0007372355,0.011893856,0.7721776,0.002121387,0.000552217,0.0019141919,0.07424145,0.043639347,0.04126642,0.025761835,0.02521786,0.00047660543],"about_ca_topic_score_codex":0.00069826865,"about_ca_topic_score_gemma":0.0015997551,"teacher_disagreement_score":0.014131353,"about_ca_system_score_codex":0.0010915056,"about_ca_system_score_gemma":0.001608997,"threshold_uncertainty_score":0.07473463},"labels":[],"label_agreement":null},{"id":"W1855174569","doi":"10.55016/ojs/ajer.v60i2.55920","title":"Making the Invisible of Learning Visible: Pre-service Teachers Identify Connections between the Use of Literacy Strategies and their Content Area Assessment Practices","year":2015,"lang":"en","type":"article","venue":"Alberta Journal of Educational Research","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"St. Francis Xavier University","funders":"","keywords":"Literacy; Content (measure theory); Mathematics education; Psychology; Content analysis; Pedagogy; Service (business); Sociology; Social science; Business; Marketing; Mathematics","score_opus":0.5367516268674741,"score_gpt":0.5577969117049367,"score_spread":0.021045284837462597,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1855174569","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99069595,0.00013861018,0.0011521424,0.00040728314,0.000007839032,0.000027003802,0.000010853972,0.000015256623,0.0075450432],"genre_scores_gemma":[0.99761033,0.00013841927,0.00054043747,0.000060733062,0.0000018272983,0.000016285956,0.000009755675,0.000008697713,0.0016136136],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9981711,0.0006795227,0.00010406502,0.00018658818,0.0004639266,0.00039472705],"domain_scores_gemma":[0.9924224,0.0041640783,0.0010561425,0.00036448814,0.0012022272,0.0007906641],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023373133,0.0002687059,0.00032770267,0.0010464924,0.0025165754,0.003999731,0.00060834724,0.00088624604,0.0032158683],"category_scores_gemma":[0.012165069,0.00034139055,0.00018942116,0.0006075019,0.004159849,0.0026660261,0.003214806,0.0019101395,0.0005978166],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000035801866,0.00014015475,0.048036877,0.000103447856,0.000003984869,0.0007199606,0.9264098,0.000027220058,0.0026224388,0.00083133153,0.00030422476,0.020764869],"study_design_scores_gemma":[0.0000033903877,0.0001321955,0.04409525,0.000109002496,0.0000058117066,0.0005206881,0.94515365,0.00007652655,0.0011776896,0.0008439005,0.007865174,0.000016778074],"about_ca_topic_score_codex":0.0092254905,"about_ca_topic_score_gemma":0.0183141,"teacher_disagreement_score":0.0092254905,"about_ca_system_score_codex":0.0013951834,"about_ca_system_score_gemma":0.002758467,"threshold_uncertainty_score":0.018343568},"labels":[],"label_agreement":null},{"id":"W1858612200","doi":"","title":"The Effect of Self-assessment on Iranian EFL Learners` Reading Comprehension Skill","year":2015,"lang":"en","type":"article","venue":"Journal of academic and applied studies","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Learner autonomy; Reading comprehension; Autonomy; Test (biology); Psychology; Language assessment; Reading (process); Mathematics education; Comprehension; Self-assessment; Process (computing); Pedagogy; Language education; Computer science; Comprehension approach; Linguistics","score_opus":0.041729942879182816,"score_gpt":0.3929681490143589,"score_spread":0.3512382061351761,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1858612200","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99689144,0.0003263236,0.00018599813,0.00008163266,0.000025904299,0.00002273408,0.000035913727,0.000033107306,0.0023970061],"genre_scores_gemma":[0.9982039,0.00014283629,0.00037731408,0.000018520675,0.000012709205,0.000026758993,0.000041425345,0.0000037998461,0.0011726998],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99918526,0.00025711206,0.00006328883,0.00010871288,0.00032586115,0.000059813618],"domain_scores_gemma":[0.9909446,0.0053342455,0.0011737612,0.0003343988,0.0013284471,0.000884508],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016313181,0.00030498873,0.00032489334,0.00041657887,0.00017146001,0.00049914286,0.0003031089,0.00027431888,0.004534067],"category_scores_gemma":[0.009818714,0.00008541685,0.0004996946,0.0001973084,0.0003094064,0.000487603,0.00045993985,0.00041767437,0.00044273835],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.007770294,0.007181866,0.50343996,0.0008631107,0.00029548618,0.00022749742,0.008361982,0.0012489923,0.015502016,0.00055325835,0.003056795,0.4514987],"study_design_scores_gemma":[0.00014955473,0.011581724,0.97414637,0.000119357384,0.00023086368,0.00012268587,0.0020957857,0.0017548014,0.006699587,0.00030114118,0.0027596452,0.000038547907],"about_ca_topic_score_codex":0.0009115109,"about_ca_topic_score_gemma":0.00095504784,"teacher_disagreement_score":0.004534067,"about_ca_system_score_codex":0.0002781272,"about_ca_system_score_gemma":0.00041557892,"threshold_uncertainty_score":0.015167952},"labels":[],"label_agreement":null},{"id":"W1888282162","doi":"10.5539/ies.v8n11p193","title":"Teachers’ Knowledge and Readiness towards Implementation of School Based Assessment in Secondary Schools","year":2015,"lang":"en","type":"article","venue":"International Education Studies","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Likert scale; Knowledge level; Psychology; Mathematics education; School teachers; Perception; Situated; Scale (ratio); Class (philosophy); Pedagogy; Computer science; Developmental psychology; Geography","score_opus":0.12709263475145594,"score_gpt":0.5309250401396273,"score_spread":0.40383240538817133,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1888282162","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99900657,0.000066006614,0.00004349369,0.00010773892,0.0000023273956,0.000017929055,0.000018041832,0.0000034157038,0.0007344823],"genre_scores_gemma":[0.99944013,0.00009686756,0.0001451155,0.000018589084,0.0000013479583,0.000013573203,0.000026359206,7.1046236e-7,0.00025738592],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.998094,0.0004911778,0.00024454386,0.0001568408,0.0007042886,0.00030918102],"domain_scores_gemma":[0.9931591,0.0017123801,0.0022021264,0.0003117491,0.0012949844,0.0013197035],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003152374,0.00016231225,0.00032019845,0.0009637687,0.0005403774,0.0012327495,0.00045068702,0.0005887395,0.0015325921],"category_scores_gemma":[0.007682506,0.0003637806,0.0005315188,0.0006169851,0.0004165731,0.0009792388,0.0010204318,0.0008639173,0.00039315427],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005567,0.0005250885,0.95651644,0.00015289444,0.000027829361,0.00022907107,0.013240194,0.00022188698,0.0013200949,0.000093753966,0.0002934945,0.02732364],"study_design_scores_gemma":[0.0000064435844,0.00046195288,0.9838934,0.00013650315,0.000020334362,0.00013788624,0.0133455945,0.00037038265,0.0005645456,0.000059103473,0.0009865367,0.000017272958],"about_ca_topic_score_codex":0.009179249,"about_ca_topic_score_gemma":0.015575077,"teacher_disagreement_score":0.009179249,"about_ca_system_score_codex":0.00061134377,"about_ca_system_score_gemma":0.002180357,"threshold_uncertainty_score":0.018251598},"labels":[],"label_agreement":null},{"id":"W1892621048","doi":"10.5539/hes.v5n5p50","title":"Multiple-Choice Testing Using Immediate Feedback—Assessment Technique (IF AT®) Forms: Second-Chance Guessing vs. Second-Chance Learning?","year":2015,"lang":"en","type":"article","venue":"Higher Education Studies","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Southern Connecticut State University","keywords":"Multiple choice; Reading (process); Mathematics education; Order (exchange); Computer science; Psychology; Cognitive psychology; Artificial intelligence; Linguistics","score_opus":0.1349722425459681,"score_gpt":0.4323272447495154,"score_spread":0.29735500220354727,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1892621048","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.89369076,0.0050034113,0.08211849,0.0018081167,0.0010625827,0.0008737384,0.0003782419,0.00080643606,0.014258136],"genre_scores_gemma":[0.96824855,0.000822396,0.027826391,0.00040350395,0.00019542914,0.00033066282,0.00013446515,0.000091541566,0.0019470835],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.97459704,0.015360552,0.0020461436,0.0016594506,0.005805429,0.0005313015],"domain_scores_gemma":[0.8892609,0.09154294,0.008312281,0.0030482518,0.0063117896,0.001523796],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03094546,0.0007692523,0.0014508946,0.0016998888,0.00031322622,0.0014507344,0.00096962537,0.0013292966,0.0029799305],"category_scores_gemma":[0.108525656,0.00024559183,0.00058126694,0.0013665499,0.00090671907,0.0020094365,0.0006002363,0.00080759055,0.0010742408],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.009197362,0.0018295193,0.16390972,0.0015206854,0.00036961623,0.0002939671,0.0028966297,0.00088736956,0.013474653,0.0027811595,0.0050188666,0.7978205],"study_design_scores_gemma":[0.0010604807,0.040269844,0.7905315,0.002406723,0.0005619492,0.0062158736,0.0037808872,0.0457337,0.07312786,0.009667111,0.025983093,0.000660911],"about_ca_topic_score_codex":0.0007529043,"about_ca_topic_score_gemma":0.0012122917,"teacher_disagreement_score":0.03094546,"about_ca_system_score_codex":0.0004089916,"about_ca_system_score_gemma":0.00046260888,"threshold_uncertainty_score":0.16365719},"labels":[],"label_agreement":null},{"id":"W1893911515","doi":"10.1017/cbo9780511611186.006","title":"Verbal Reports as Data for Cognitive Diagnostic Assessment","year":2007,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":50,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Psychology; Strengths and weaknesses; Cognition; Distributive property; Test (biology); Cognitive psychology; Cognitive skill; Subject (documents); Scale (ratio); Mathematics education; Social psychology; Computer science; Mathematics","score_opus":0.0876519378095488,"score_gpt":0.3478663010064851,"score_spread":0.26021436319693625,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1893911515","genre_codex":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1319117,0.013316959,0.13493182,0.00678822,0.009951809,0.014820481,0.19523136,0.005162416,0.48788524],"genre_scores_gemma":[0.32841036,0.018012442,0.2667715,0.0054408265,0.0022728096,0.045181304,0.15478083,0.0030575306,0.17607246],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9817946,0.007320345,0.003641304,0.00087286346,0.006002636,0.00036832446],"domain_scores_gemma":[0.9057008,0.04445247,0.010215266,0.009054277,0.029263474,0.0013136152],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013290904,0.000874037,0.0009180803,0.013953657,0.0006527832,0.0025011934,0.0016507965,0.00097597926,0.037377827],"category_scores_gemma":[0.095673,0.00025716747,0.00045440387,0.0070606354,0.0011273994,0.0019097951,0.0023012508,0.0024405431,0.019010996],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00072523707,0.00077388104,0.037822362,0.003028786,0.000108834596,0.0008879429,0.00849218,0.00068661454,0.003089743,0.041713208,0.2638215,0.6388497],"study_design_scores_gemma":[0.00011861662,0.00058802904,0.03481278,0.0033454658,0.000054385837,0.0016686844,0.007824167,0.0009217538,0.0055738124,0.017031215,0.92791075,0.00015028904],"about_ca_topic_score_codex":0.0015468929,"about_ca_topic_score_gemma":0.0015398588,"teacher_disagreement_score":0.037377827,"about_ca_system_score_codex":0.0011426705,"about_ca_system_score_gemma":0.0017734051,"threshold_uncertainty_score":0.1250413},"labels":[],"label_agreement":null},{"id":"W1893952289","doi":"10.18296/am.0079","title":"Assessment for learning as a participative pedagogy","year":2010,"lang":"en","type":"article","venue":"Assessment Matters","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":37,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Victoria Park","funders":"","keywords":"Computer science; Psychology; Pedagogy; Mathematics education","score_opus":0.0329168317974783,"score_gpt":0.46042971779549835,"score_spread":0.42751288599802006,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1893952289","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.46481556,0.0012550934,0.2181073,0.00799115,0.0003647352,0.0053414493,0.00015287062,0.0012605621,0.30071136],"genre_scores_gemma":[0.892601,0.00034691053,0.08027428,0.00027850756,0.00003448175,0.0010805328,0.00003805416,0.000107118634,0.025239127],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.96876556,0.022796225,0.0008527603,0.0011801934,0.005695879,0.00070941984],"domain_scores_gemma":[0.9674421,0.022222938,0.0020831274,0.0034097193,0.0030877085,0.0017544066],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.021282881,0.000596772,0.00071695045,0.002052499,0.0036455,0.007954428,0.0020566043,0.0010559588,0.0058836285],"category_scores_gemma":[0.046123333,0.00038502584,0.00028319133,0.0014290205,0.007072694,0.00355084,0.007033152,0.0019214427,0.0011885298],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013492521,0.001036574,0.014220452,0.0008622648,0.000020554999,0.0009251307,0.350764,0.0019104893,0.008259444,0.09287367,0.0072159343,0.52177656],"study_design_scores_gemma":[0.00017992566,0.0021162722,0.0380281,0.0021368128,0.000038973787,0.0037318957,0.23416792,0.014347894,0.008831401,0.17918423,0.5170324,0.00020426569],"about_ca_topic_score_codex":0.001984111,"about_ca_topic_score_gemma":0.0039174818,"teacher_disagreement_score":0.021282881,"about_ca_system_score_codex":0.0030203103,"about_ca_system_score_gemma":0.005541352,"threshold_uncertainty_score":0.11255598},"labels":[],"label_agreement":null},{"id":"W1916237854","doi":"10.24908/pceea.v0i0.5778","title":"Using Student Focus Groups to Support the Validation of Rubrics for Large Scale Undergraduate Independent Research Projects","year":2015,"lang":"en","type":"article","venue":"Proceedings of the Canadian Engineering Education Association (CEEA)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"University of Toronto","keywords":"Rubric; Capstone; Focus group; Scale (ratio); Psychology; Focus (optics); Medical education; Computer science; Mathematics education; Sociology; Medicine","score_opus":0.0932519063745481,"score_gpt":0.39171820876125646,"score_spread":0.29846630238670835,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1916237854","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.34216487,0.00035534185,0.5985408,0.0018654215,0.00066203374,0.036629956,0.0005714004,0.0028052665,0.016404923],"genre_scores_gemma":[0.3604806,0.00035922797,0.5506314,0.0011513842,0.00024780558,0.07691489,0.00087649596,0.0007307205,0.008607472],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.800462,0.15567674,0.01078746,0.007179014,0.022146834,0.0037479843],"domain_scores_gemma":[0.486318,0.32586727,0.023914816,0.05825046,0.1007415,0.00490794],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.2269284,0.002661248,0.0013453793,0.0075720935,0.006467953,0.0037709468,0.0049710353,0.001650255,0.008494748],"category_scores_gemma":[0.34478524,0.0012236597,0.001277803,0.0026960236,0.0029635474,0.005162385,0.008071015,0.0030468993,0.0032376663],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00089642516,0.0041531255,0.019008584,0.0025378978,0.00014618876,0.00047798603,0.3561144,0.0016719747,0.040150937,0.0069702896,0.012287275,0.5555849],"study_design_scores_gemma":[0.0020627694,0.015972838,0.10178239,0.005072929,0.00037562204,0.0016013163,0.28162313,0.02765126,0.20967305,0.034762137,0.31821635,0.0012062542],"about_ca_topic_score_codex":0.0015753891,"about_ca_topic_score_gemma":0.0036896383,"teacher_disagreement_score":0.2269284,"about_ca_system_score_codex":0.003696597,"about_ca_system_score_gemma":0.0070192725,"threshold_uncertainty_score":0.9533349},"labels":[],"label_agreement":null},{"id":"W1928825815","doi":"10.22329/celt.v5i0.3423","title":"12. Undergraduate Essay Writing: Online and Face-to-Face Peer Reviews","year":2012,"lang":"en","type":"article","venue":"Collected Essays on Learning and Teaching","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Peer review; Peer feedback; Face-to-face; Peer evaluation; Face (sociological concept); Computer science; Psychology; Mathematics education; Online discussion; Peer instruction; Web application; Medical education; Multimedia; World Wide Web; Higher education; Sociology; Chemistry; Medicine; Social science","score_opus":0.03992110082034801,"score_gpt":0.36285928733884043,"score_spread":0.32293818651849243,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1928825815","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6156603,0.00074742606,0.22851309,0.002227629,0.0011263522,0.020704098,0.003164264,0.026683943,0.1011729],"genre_scores_gemma":[0.41868985,0.00038053188,0.5171287,0.0005301903,0.0005038193,0.012407836,0.0015918037,0.0014916772,0.0472757],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.96120214,0.02103178,0.0057549733,0.0037705489,0.007054538,0.0011860768],"domain_scores_gemma":[0.89707994,0.042409394,0.006795654,0.017955719,0.030212212,0.005547052],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.029118635,0.00082264893,0.0007405815,0.0023940848,0.0011474704,0.0025692228,0.0017735241,0.0010324828,0.017670972],"category_scores_gemma":[0.068779685,0.0005168784,0.0005335583,0.0012789438,0.0007045446,0.0017504476,0.0031217441,0.0007415236,0.011240998],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011780994,0.00348942,0.012119168,0.0013048234,0.00005169055,0.00051858556,0.011446984,0.0006654485,0.04017443,0.0010707129,0.018030996,0.90994954],"study_design_scores_gemma":[0.0022914738,0.011827847,0.15417251,0.0011721731,0.00028613213,0.0036614223,0.012421648,0.03228188,0.21467678,0.0069992756,0.5592297,0.0009793093],"about_ca_topic_score_codex":0.00049357256,"about_ca_topic_score_gemma":0.0017379423,"teacher_disagreement_score":0.97088134,"about_ca_system_score_codex":0.0007185308,"about_ca_system_score_gemma":0.002083162,"threshold_uncertainty_score":0.15399593},"labels":[],"label_agreement":null},{"id":"W1929426705","doi":"10.26522/brocked.v15i2.74","title":"Principles for Effective ClassroomAssessment","year":2006,"lang":"en","type":"article","venue":"Brock Education Journal","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Brock University","funders":"","keywords":"Variety (cybernetics); Zeitgeist; Service (business); Psychology; Mathematics education; Computer science; Engineering ethics; Political science; Engineering; Artificial intelligence","score_opus":0.022251610050161026,"score_gpt":0.3689551073058239,"score_spread":0.3467034972556629,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1929426705","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0037391097,0.006522806,0.79285663,0.0440063,0.0014424181,0.0030873232,0.0001830893,0.0014174657,0.14674492],"genre_scores_gemma":[0.08588432,0.003364308,0.8801024,0.0061894,0.00056167465,0.006156782,0.00015289472,0.00029609242,0.017292159],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.93848324,0.02593607,0.0053719804,0.0037846575,0.024685523,0.0017385691],"domain_scores_gemma":[0.931262,0.030594744,0.0029948244,0.00721699,0.025112523,0.0028188895],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.05498841,0.0012169911,0.0011902562,0.004230619,0.0050259647,0.010983136,0.0037627174,0.0060665607,0.00604533],"category_scores_gemma":[0.08003431,0.0011116152,0.0010702437,0.0019145748,0.014796462,0.007983163,0.009304442,0.009904515,0.006380589],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003615211,0.00025851955,0.0014194128,0.0009795999,0.00002342813,0.00012109029,0.009876475,0.0015041941,0.00071024196,0.65938467,0.026011314,0.2996749],"study_design_scores_gemma":[0.00005505235,0.00012279558,0.0013285007,0.00205008,0.000018902925,0.00044435522,0.0026189885,0.0016037029,0.0012420651,0.64378077,0.34667155,0.00006338076],"about_ca_topic_score_codex":0.0030145827,"about_ca_topic_score_gemma":0.003434309,"teacher_disagreement_score":0.05498841,"about_ca_system_score_codex":0.004945885,"about_ca_system_score_gemma":0.020196734,"threshold_uncertainty_score":0.29081},"labels":[],"label_agreement":null},{"id":"W1951727650","doi":"10.3968/j.hess.1927024020110102.010","title":"Alternative Assessment in the Post-Method Era: Pedagogic Implications","year":2011,"lang":"en","type":"article","venue":"Higher education of social science","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Formative assessment; Operationalization; Context (archaeology); Mathematics education; Process (computing); Summative assessment; Psychology; Engineering ethics; Computer science; Pedagogy; Epistemology; Engineering","score_opus":0.10639265693083012,"score_gpt":0.48971712777315773,"score_spread":0.3833244708423276,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1951727650","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.059854288,0.03983642,0.54510754,0.107553214,0.005798883,0.0007336398,0.00008886868,0.0008595419,0.24016765],"genre_scores_gemma":[0.6466033,0.015015451,0.29117236,0.0065159225,0.0021425302,0.0016334787,0.000056138437,0.0003014077,0.036559455],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.95762247,0.030701688,0.0017488655,0.0012981112,0.0081632,0.00046565128],"domain_scores_gemma":[0.84533733,0.12929584,0.0031740426,0.009004474,0.011314689,0.001873666],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.05112614,0.0009909568,0.00072151225,0.0036240644,0.00241738,0.009927889,0.0031109198,0.0030120842,0.008502137],"category_scores_gemma":[0.098751664,0.00044334037,0.00069782493,0.002103474,0.015705522,0.012395266,0.007038622,0.005328408,0.0013786283],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014442284,0.00044149195,0.004210217,0.001017682,0.000026713447,0.0005307755,0.033204548,0.0006863513,0.0009362509,0.49690834,0.0044437977,0.45744947],"study_design_scores_gemma":[0.000100212535,0.0005543454,0.0054655364,0.0046691224,0.000027119553,0.002235399,0.019921,0.0067574126,0.0045429966,0.63995755,0.31564826,0.000121075995],"about_ca_topic_score_codex":0.0012238404,"about_ca_topic_score_gemma":0.0016314354,"teacher_disagreement_score":0.05112614,"about_ca_system_score_codex":0.0052965865,"about_ca_system_score_gemma":0.0056375363,"threshold_uncertainty_score":0.27038407},"labels":[],"label_agreement":null},{"id":"W1953748391","doi":"10.5539/elt.v8n12p27","title":"Toward Differentiated Assessment in a Public College in Oman","year":2015,"lang":"en","type":"article","venue":"English Language Teaching","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Context (archaeology); Differentiated instruction; Psychology; Alternative assessment; Mathematics education; Pedagogy; Medical education","score_opus":0.05231859139052725,"score_gpt":0.3578362767086905,"score_spread":0.30551768531816326,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1953748391","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9971167,0.000035009627,0.00020751174,0.0007705634,0.000011590157,0.000037655605,0.0000064660207,0.000011973975,0.0018024454],"genre_scores_gemma":[0.99622786,0.0000652756,0.0010037866,0.00021381522,0.0000034325417,0.0000205323,0.000013234278,0.0000034457266,0.0024485334],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.9971034,0.0012802636,0.00015296886,0.00025383415,0.0005369346,0.00067265675],"domain_scores_gemma":[0.99327385,0.0013513514,0.0007399341,0.00022054609,0.0015594313,0.0028549389],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004950329,0.00021828162,0.0002459398,0.0008160092,0.0052231625,0.0031769155,0.00067268615,0.0009334338,0.0026439377],"category_scores_gemma":[0.009574427,0.00025571857,0.000170373,0.0010590133,0.0016456532,0.0015672841,0.003850274,0.0014831016,0.00038216836],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005147778,0.005755668,0.3448375,0.0002641675,0.000019931405,0.004160804,0.40472057,0.00064857624,0.013026676,0.00442206,0.005202987,0.21642621],"study_design_scores_gemma":[0.000054386666,0.001752028,0.31551057,0.00022684765,0.00001764537,0.00073944667,0.63617224,0.0014081701,0.0047833505,0.0016714779,0.03756192,0.00010193757],"about_ca_topic_score_codex":0.014470928,"about_ca_topic_score_gemma":0.040895212,"teacher_disagreement_score":0.014470928,"about_ca_system_score_codex":0.004184556,"about_ca_system_score_gemma":0.0065864637,"threshold_uncertainty_score":0.030361235},"labels":[],"label_agreement":null},{"id":"W1961884281","doi":"10.24908/pceea.v0i0.5908","title":"Peer Review as an Active Learning Strategy in a Large First Year Course","year":2015,"lang":"en","type":"article","venue":"Proceedings of the Canadian Engineering Education Association (CEEA)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"McGill University","funders":"McGill University","keywords":"Rubric; CLARITY; Peer feedback; Mathematics education; Critical thinking; Presentation (obstetrics); Competence (human resources); Class (philosophy); Discipline; Peer assessment; Psychology; Constructive criticism; Active learning (machine learning); Computer science; Criticism; Pedagogy; Medicine; Sociology","score_opus":0.0216094110134129,"score_gpt":0.3225431984446856,"score_spread":0.3009337874312727,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1961884281","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9404166,0.0003835662,0.031866293,0.001537985,0.0004761762,0.006363046,0.00012953127,0.0017255098,0.017101252],"genre_scores_gemma":[0.8066098,0.0005293512,0.17456464,0.000767506,0.0004165232,0.0035084654,0.00028532016,0.00018309454,0.0131352395],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.97947305,0.008617262,0.0009820426,0.0023560137,0.0075031715,0.0010684063],"domain_scores_gemma":[0.9286937,0.031049205,0.0075709047,0.006626673,0.013670179,0.012389214],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.022449438,0.0012478604,0.0013303263,0.0021634426,0.0032752187,0.0034851658,0.0034864547,0.0012618342,0.005419043],"category_scores_gemma":[0.06694364,0.00061267515,0.00052089395,0.0010748125,0.0011069677,0.0017486488,0.0038852685,0.0016218502,0.0025771398],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014639734,0.024670595,0.02189569,0.00092977565,0.00009061891,0.0013302471,0.027753655,0.0013772496,0.037758686,0.001148642,0.031643834,0.849937],"study_design_scores_gemma":[0.0029360722,0.10110666,0.38393214,0.0023302098,0.00041867085,0.0076877642,0.04878011,0.032700747,0.10977921,0.015887437,0.2929727,0.0014681908],"about_ca_topic_score_codex":0.0004936605,"about_ca_topic_score_gemma":0.0027111138,"teacher_disagreement_score":0.97755057,"about_ca_system_score_codex":0.0020242166,"about_ca_system_score_gemma":0.005528318,"threshold_uncertainty_score":0.11872536},"labels":[],"label_agreement":null},{"id":"W1963737077","doi":"10.3138/cmlr.1705.415","title":"Adapting the CEFR for the Classroom Assessment of Young Learners’ Writing","year":2013,"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":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Literacy; Assessment for learning; Mathematics education; Scale (ratio); Psychology; Pedagogy; Computer science; Formative assessment; Geography","score_opus":0.027825998353215798,"score_gpt":0.309119495218328,"score_spread":0.2812934968651122,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1963737077","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8662157,0.0024194047,0.07589472,0.0022244263,0.0009100029,0.0044234917,0.0011196522,0.0010386534,0.045753937],"genre_scores_gemma":[0.83316,0.0015360895,0.15365116,0.0003244142,0.000080524675,0.0030791394,0.0006941002,0.0001189694,0.0073555517],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98449856,0.008504671,0.0013843835,0.00057506695,0.0046107983,0.0004265912],"domain_scores_gemma":[0.96918285,0.0120037235,0.0021153186,0.0017305394,0.013947629,0.0010199347],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.020481264,0.0005593062,0.0006523501,0.0029933597,0.0007548012,0.001551426,0.0011274135,0.0008896214,0.0013531962],"category_scores_gemma":[0.052561317,0.00016887112,0.0005273123,0.0010439826,0.0008752742,0.0011108102,0.0021278458,0.0010116402,0.00076008803],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00040522427,0.0008028558,0.09008078,0.0010293497,0.000027885473,0.00040406387,0.022507278,0.0008924309,0.009766171,0.0024272832,0.005748947,0.86590767],"study_design_scores_gemma":[0.00037332234,0.005747277,0.68327725,0.003922597,0.0001329981,0.0043894127,0.041002944,0.008407106,0.03559629,0.004981278,0.21172199,0.00044757212],"about_ca_topic_score_codex":0.012957524,"about_ca_topic_score_gemma":0.026979052,"teacher_disagreement_score":0.020481264,"about_ca_system_score_codex":0.002131723,"about_ca_system_score_gemma":0.005780367,"threshold_uncertainty_score":0.10831654},"labels":[],"label_agreement":null},{"id":"W1965935538","doi":"10.1021/ed8000107","title":"Constructing the Components of a Lab Report Using Peer Review","year":2009,"lang":"en","type":"article","venue":"Journal of Chemical Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":45,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vancouver Island University; University of Victoria","funders":"","keywords":"Protocol (science); Workload; Class (philosophy); Style (visual arts); Computer science; Process (computing); Mathematics education; Peer evaluation; Quality (philosophy); Multimedia; Psychology; Higher education; Programming language; Medicine; Artificial intelligence; Operating system; Physics","score_opus":0.07177206871327357,"score_gpt":0.44168495173929634,"score_spread":0.36991288302602277,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1965935538","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.015640179,0.0003488506,0.72123265,0.0026255264,0.0032357434,0.22094297,0.00325375,0.011165668,0.021554627],"genre_scores_gemma":[0.016132342,0.0002990599,0.85111135,0.0004187842,0.0006166235,0.11527758,0.0014644088,0.0012912398,0.013388577],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.8543622,0.07826525,0.018977562,0.007377163,0.039021023,0.001996916],"domain_scores_gemma":[0.5926114,0.078964226,0.019420791,0.12858957,0.16947803,0.010936059],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.120597035,0.0021530993,0.0021457665,0.0064280992,0.0040950296,0.006077977,0.0048862984,0.0017493629,0.036536578],"category_scores_gemma":[0.233781,0.0020810934,0.0017097123,0.0026029488,0.0022639008,0.0029093758,0.0045296745,0.0044892863,0.026383271],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0022947337,0.0028712964,0.0024467518,0.0027598653,0.00012875591,0.0006713454,0.008917607,0.0023158954,0.04038255,0.0107039455,0.1440384,0.7824688],"study_design_scores_gemma":[0.0011552181,0.0054705446,0.009202269,0.0023846822,0.0001624592,0.00066928106,0.0052707586,0.0132905,0.05346261,0.017525328,0.8907348,0.0006715498],"about_ca_topic_score_codex":0.0010651347,"about_ca_topic_score_gemma":0.0019587202,"teacher_disagreement_score":0.879403,"about_ca_system_score_codex":0.0024105774,"about_ca_system_score_gemma":0.018915089,"threshold_uncertainty_score":0.6377857},"labels":[],"label_agreement":null},{"id":"W1969883013","doi":"10.1145/2676723.2677278","title":"Mechanical TA","year":2015,"lang":"en","type":"article","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":47,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Class (philosophy); Computer science; Process (computing); Mechanical design; Quality (philosophy); Human–computer interaction; Mathematics education; Multimedia; Psychology; Artificial intelligence; Engineering; Mechanical engineering; Programming language; Physics","score_opus":0.0998424434789948,"score_gpt":0.4038429837962849,"score_spread":0.3040005403172901,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1969883013","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01282381,0.0017965565,0.87219876,0.0015704292,0.0021085218,0.00227001,0.0015287948,0.052954536,0.05274856],"genre_scores_gemma":[0.09344024,0.0013684201,0.7812651,0.0021449348,0.00209578,0.0020570764,0.004247569,0.007046647,0.106334284],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9885416,0.0025887785,0.000980885,0.0018599066,0.0054961042,0.00053270755],"domain_scores_gemma":[0.971854,0.0064303344,0.0018762554,0.009518085,0.009065769,0.0012555936],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005397815,0.001127487,0.0008403695,0.0025099288,0.001484827,0.0045979666,0.0036280195,0.0015996037,0.06389952],"category_scores_gemma":[0.021669118,0.00071399094,0.0009108077,0.0024620395,0.00076682057,0.004370033,0.0034794027,0.0014827183,0.046879992],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025181466,0.00029464313,0.002713505,0.0007176255,0.000090382906,0.00046578477,0.0006836082,0.0012994886,0.02426349,0.007778045,0.17451987,0.78692174],"study_design_scores_gemma":[0.00012339419,0.00085344416,0.005094195,0.00020221742,0.00007390189,0.0032688382,0.0002675106,0.021390207,0.016371766,0.0063520498,0.945804,0.00019835726],"about_ca_topic_score_codex":0.0015950303,"about_ca_topic_score_gemma":0.0026223399,"teacher_disagreement_score":0.06389952,"about_ca_system_score_codex":0.00051847147,"about_ca_system_score_gemma":0.0016968369,"threshold_uncertainty_score":0.2137652},"labels":[],"label_agreement":null},{"id":"W1975230259","doi":"10.1080/1360144042000277900","title":"A Learning‐centred Faculty Certificate Programme on University Teaching","year":2003,"lang":"en","type":"article","venue":"The International Journal for Academic Development","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Pedagogy; Certificate; Higher education; Sociology; Faculty development; Mathematics education; Professional development; Psychology; Political science; Computer science","score_opus":0.19423080715050173,"score_gpt":0.39890678247484423,"score_spread":0.2046759753243425,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1975230259","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.817718,0.0002821023,0.018472658,0.0035560008,0.0016791464,0.009406043,0.0014335952,0.0018184293,0.14563398],"genre_scores_gemma":[0.90747184,0.00023036353,0.022553757,0.00083042076,0.00038106425,0.0036956777,0.0007685855,0.0001077231,0.06396058],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99744886,0.0008507707,0.000073412986,0.00023305824,0.00049009884,0.00090374856],"domain_scores_gemma":[0.9813364,0.0024252417,0.000887254,0.0013772117,0.0012981346,0.012675768],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004883468,0.0004642358,0.0005320548,0.0012456024,0.0026614012,0.0015146731,0.002079283,0.0007572525,0.029606834],"category_scores_gemma":[0.012035089,0.0002996472,0.00048744484,0.0010571581,0.0014708064,0.00079814525,0.0072520766,0.0015387858,0.005521475],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0021433022,0.016018461,0.020226749,0.0006418038,0.000021347305,0.0010459578,0.008006787,0.003801733,0.007311401,0.0073586316,0.057141785,0.876282],"study_design_scores_gemma":[0.0029799126,0.03010573,0.4177915,0.0009061218,0.00005710967,0.0022707193,0.016291592,0.007862758,0.019363293,0.011475734,0.49044228,0.00045333427],"about_ca_topic_score_codex":0.0020117096,"about_ca_topic_score_gemma":0.0064100986,"teacher_disagreement_score":0.029606834,"about_ca_system_score_codex":0.002309529,"about_ca_system_score_gemma":0.010528794,"threshold_uncertainty_score":0.0990448},"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,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Assessment for learning; Mathematics education; Writing assessment; Pedagogy; Psychology; Computer science; Formative assessment","score_opus":0.02022232402502297,"score_gpt":0.33829144772885,"score_spread":0.318069123703827,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1975314479","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.27801,0.12631656,0.21169715,0.08280223,0.002714295,0.0022177326,0.0002317632,0.0022464022,0.2937638],"genre_scores_gemma":[0.81413853,0.017110793,0.1572776,0.0017586421,0.00025995864,0.0006010736,0.00007220733,0.000075826574,0.008705395],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9829616,0.011843234,0.0005841579,0.00046000778,0.003820014,0.00033103031],"domain_scores_gemma":[0.9830284,0.009968736,0.0012139241,0.00059848506,0.00416334,0.0010270231],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0234808,0.00041432894,0.00069873524,0.0027404898,0.0015286257,0.004809333,0.0013795872,0.00092441984,0.0013728504],"category_scores_gemma":[0.03528127,0.00019622906,0.00025685676,0.0025882735,0.0037779573,0.003171573,0.0036440666,0.0017736971,0.00025679066],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004931093,0.00019594238,0.0064328946,0.0012679781,0.000019712836,0.00018850407,0.014606871,0.00043744242,0.00090963393,0.026961068,0.008010125,0.9409206],"study_design_scores_gemma":[0.00029165787,0.0014070692,0.10936882,0.011379335,0.00018841102,0.0025034358,0.058550715,0.01051132,0.007850726,0.13379486,0.6638736,0.0002800551],"about_ca_topic_score_codex":0.03631164,"about_ca_topic_score_gemma":0.04681213,"teacher_disagreement_score":0.03631164,"about_ca_system_score_codex":0.008201598,"about_ca_system_score_gemma":0.025155045,"threshold_uncertainty_score":0.12417984},"labels":[],"label_agreement":null},{"id":"W1975403746","doi":"10.3138/cmlr.64.1.181","title":"<i>Auto-évaluation</i> : Daily Self-Assessment in the FSL 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":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Valuation (finance); Mathematics education; Computer science; Psychology; Economics","score_opus":0.020349828938382594,"score_gpt":0.30909300046608384,"score_spread":0.28874317152770124,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1975403746","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8628959,0.0009883884,0.027473323,0.0034064974,0.00028261333,0.0008890411,0.0003061007,0.0020461355,0.101711944],"genre_scores_gemma":[0.96225697,0.00038396817,0.021337844,0.00033167604,0.000068490306,0.00036108226,0.0001818788,0.000095868265,0.014982218],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99220663,0.005703433,0.00029630883,0.00030066486,0.0012616945,0.0002313038],"domain_scores_gemma":[0.9892691,0.004970208,0.00082684297,0.0010843198,0.0030124192,0.0008372321],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009412425,0.00027212087,0.00040382188,0.0012906817,0.00084284873,0.0018351715,0.0006867138,0.0004565789,0.004060566],"category_scores_gemma":[0.0138310585,0.00011862994,0.00015806186,0.000775962,0.0010756734,0.00087850564,0.0015729662,0.0005697669,0.0014602204],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017837557,0.0008959452,0.044943094,0.0004642169,0.000013582002,0.00019549031,0.032529622,0.0003518923,0.00579992,0.0019766788,0.022275997,0.89037514],"study_design_scores_gemma":[0.00018382444,0.0055596554,0.46502358,0.0018853624,0.000087119755,0.0031752882,0.089112066,0.012006054,0.058237556,0.008846596,0.35532054,0.00056236493],"about_ca_topic_score_codex":0.003977565,"about_ca_topic_score_gemma":0.008295857,"teacher_disagreement_score":0.009412425,"about_ca_system_score_codex":0.0015527989,"about_ca_system_score_gemma":0.0020592804,"threshold_uncertainty_score":0.049778223},"labels":[],"label_agreement":null},{"id":"W1975472233","doi":"10.5539/ies.v7n9p69","title":"Exploring Primary School Teachers’ Conceptions of “Assessment for Learning”","year":2014,"lang":"en","type":"article","venue":"International Education Studies","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Universiti Brunei Darussalam","keywords":"Assessment for learning; Government (linguistics); Mathematics education; Pedagogy; Psychology; Educational assessment; Primary education; Qualitative research; Data collection; Christian ministry; Qualitative property; Semi-structured interview; Formative assessment; Sociology; Political science; Social science","score_opus":0.22290386212218646,"score_gpt":0.49012126253713956,"score_spread":0.2672174004149531,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1975472233","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.937502,0.0028273587,0.00571003,0.008777178,0.00007714578,0.00011930058,0.000031392377,0.000036491583,0.04491914],"genre_scores_gemma":[0.99756634,0.00029178843,0.0005720709,0.0002478552,0.0000038291887,0.000021173155,0.000006457195,0.0000065360086,0.0012839346],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9878918,0.0075716255,0.00047455347,0.000752312,0.0018985624,0.0014111563],"domain_scores_gemma":[0.9868146,0.007628555,0.0014114241,0.0006383602,0.002113509,0.0013936375],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011544947,0.00038515596,0.0005862025,0.0026782153,0.008482897,0.009703824,0.0016265218,0.0020713038,0.0011511984],"category_scores_gemma":[0.017519765,0.00062797044,0.0002998212,0.0023665754,0.0236088,0.004292021,0.0058631455,0.004320893,0.0001550591],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000073397896,0.000015156866,0.00354081,0.000045170622,0.000001984227,0.00016942159,0.98555654,0.000035799112,0.00031750315,0.0070716348,0.00014651258,0.0030920403],"study_design_scores_gemma":[0.000007188107,0.000037418104,0.008342917,0.00020423916,0.000006047852,0.00023860493,0.9598936,0.00015864379,0.00019061052,0.0035820277,0.027315771,0.000022993674],"about_ca_topic_score_codex":0.09757386,"about_ca_topic_score_gemma":0.08893594,"teacher_disagreement_score":0.09757386,"about_ca_system_score_codex":0.017475072,"about_ca_system_score_gemma":0.014065499,"threshold_uncertainty_score":0.19401187},"labels":[],"label_agreement":null},{"id":"W1975565019","doi":"10.1002/bmb.20592","title":"Peer review in class: Metrics and variations in a senior course","year":2012,"lang":"en","type":"article","venue":"Biochemistry and Molecular Biology Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Guelph","funders":"","keywords":"Class (philosophy); Peer review; Peer assessment; Peer evaluation; Technical peer review; Peer feedback; Psychology; Medical education; Peer group; Quality (philosophy); Mathematics education; Computer science; Higher education; Social psychology; Medicine; Biology; Artificial intelligence; Political science","score_opus":0.019947783361024384,"score_gpt":0.3982574906643874,"score_spread":0.37830970730336305,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1975565019","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9305052,0.00034830187,0.052749995,0.0013756006,0.00013250859,0.0004550288,0.00055649836,0.0011700866,0.012706683],"genre_scores_gemma":[0.98665214,0.000031308864,0.01141488,0.000042854546,0.000020515101,0.00014084738,0.00023370437,0.00008752371,0.0013763394],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.95989907,0.019971108,0.0024639738,0.003373979,0.013075826,0.0012160782],"domain_scores_gemma":[0.6996648,0.19295073,0.029625915,0.01919552,0.049212605,0.009350386],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.03875978,0.0004982739,0.00091469253,0.0036878686,0.0013859293,0.0040953485,0.0017268314,0.0014286014,0.0024904392],"category_scores_gemma":[0.24928448,0.00023576462,0.00047421668,0.0036659162,0.0015091893,0.002714669,0.0024662695,0.0013573298,0.0007620353],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000989349,0.0011428428,0.6020433,0.00031674368,0.00027543848,0.00039527996,0.0065461514,0.045068864,0.004632958,0.012187875,0.011164838,0.3152364],"study_design_scores_gemma":[0.0001088806,0.0036900337,0.6055186,0.0001872528,0.00012331271,0.0008015592,0.0048391935,0.32918307,0.01103559,0.024930233,0.019262534,0.0003197863],"about_ca_topic_score_codex":0.0027049154,"about_ca_topic_score_gemma":0.002619777,"teacher_disagreement_score":0.96124023,"about_ca_system_score_codex":0.0034945484,"about_ca_system_score_gemma":0.0016838353,"threshold_uncertainty_score":0.20498377},"labels":[],"label_agreement":null},{"id":"W1976878455","doi":"10.5206/cjsotl-rcacea.2013.1.5","title":"Enhancing Assessment in Teacher Education Courses","year":2013,"lang":"en","type":"article","venue":"The Canadian Journal for the Scholarship of Teaching and Learning","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Lethbridge","funders":"University of Lethbridge","keywords":"Pedagogy; Valuation (finance); Higher education; Teacher education; Sociology; Political science; Library science; Psychology; Computer science","score_opus":0.033269992751195306,"score_gpt":0.37327392627960093,"score_spread":0.34000393352840563,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1976878455","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8892278,0.0008828914,0.05379951,0.004019401,0.00024981852,0.0018825544,0.000069174894,0.0010722973,0.048796456],"genre_scores_gemma":[0.88030726,0.00045960658,0.10638324,0.00046004597,0.000056891993,0.0005287538,0.00006875258,0.0000846269,0.011650791],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.97464716,0.014371541,0.0013708582,0.0019622457,0.005589523,0.002058586],"domain_scores_gemma":[0.963111,0.01640504,0.0028520264,0.0028257514,0.010417873,0.0043882704],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.019724723,0.00054924825,0.0005447286,0.0014015724,0.00292386,0.006944555,0.0017250592,0.0009747326,0.004010223],"category_scores_gemma":[0.04998355,0.00040447604,0.0003827149,0.0013131034,0.0011727605,0.00261516,0.005898859,0.0013614867,0.0014284104],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025340277,0.0020256927,0.02985969,0.000426639,0.000021199457,0.00023847162,0.042935148,0.001378463,0.010271454,0.0029085153,0.0043843808,0.9052969],"study_design_scores_gemma":[0.0007460838,0.00887247,0.25465536,0.0026966569,0.00024461825,0.0015320986,0.107265174,0.018581292,0.09308675,0.022850344,0.48878145,0.0006877888],"about_ca_topic_score_codex":0.0070048803,"about_ca_topic_score_gemma":0.01515433,"teacher_disagreement_score":0.019724723,"about_ca_system_score_codex":0.0056363842,"about_ca_system_score_gemma":0.0132550765,"threshold_uncertainty_score":0.10431558},"labels":[],"label_agreement":null},{"id":"W1978227392","doi":"10.1080/09695940903565362","title":"Teacher beliefs about the cognitive diagnostic information of classroom‐ versus large‐scale tests: implications for assessment literacy","year":2010,"lang":"en","type":"article","venue":"Assessment in Education Principles Policy and Practice","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":58,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Smiths Detection (Canada); University of Alberta","funders":"","keywords":"Test (biology); Mathematics education; Scale (ratio); Psychology; Literacy; Pedagogy","score_opus":0.05055241862711323,"score_gpt":0.48032179247732004,"score_spread":0.4297693738502068,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1978227392","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99188614,0.00024301311,0.0011651815,0.0019535585,0.000009878112,0.000032793072,0.00001531575,0.000005557,0.0046885805],"genre_scores_gemma":[0.9993843,0.00008268609,0.00025888154,0.000109025896,0.000004612682,0.000013857664,0.0000060101356,0.0000014053752,0.00013923016],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98628485,0.009205063,0.0006611623,0.00053826824,0.0027811956,0.0005295246],"domain_scores_gemma":[0.84626615,0.12573156,0.014900184,0.0026642012,0.0075896927,0.0028482473],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.018061748,0.00013510532,0.00031527245,0.00089983945,0.0007124273,0.0021008593,0.00038190634,0.0005893644,0.0016410751],"category_scores_gemma":[0.099560484,0.00018641462,0.00023702162,0.0005637105,0.0026847508,0.0016724197,0.0011950225,0.0012352631,0.00020267752],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003199617,0.000556424,0.8799813,0.00017500063,0.000044236538,0.00020928221,0.051796883,0.00017874126,0.0012654676,0.002176912,0.00043723694,0.06285856],"study_design_scores_gemma":[0.00005866946,0.00097214413,0.91199565,0.00046277975,0.000072134186,0.0003476619,0.07655937,0.0013056658,0.0018964044,0.0032486925,0.0030447752,0.000036115744],"about_ca_topic_score_codex":0.004040514,"about_ca_topic_score_gemma":0.0056788507,"teacher_disagreement_score":0.018061748,"about_ca_system_score_codex":0.0014630883,"about_ca_system_score_gemma":0.0020025526,"threshold_uncertainty_score":0.095520735},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Receptivity; Psychology; Congruence (geometry); Social psychology; Positive feedback","score_opus":0.0340642683330416,"score_gpt":0.35440362098786893,"score_spread":0.3203393526548273,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1978294241","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9912571,0.00027194456,0.0022673407,0.0005808711,0.00006512586,0.00011535752,0.00005238178,0.000054176042,0.005335729],"genre_scores_gemma":[0.99751747,0.00014271724,0.0013233344,0.00010343299,0.00002253857,0.00006848249,0.000032428095,0.000011536314,0.0007780795],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9840013,0.010149443,0.00071528467,0.00047579894,0.004038933,0.0006192538],"domain_scores_gemma":[0.90773827,0.063714385,0.010591079,0.0043460354,0.010045489,0.0035647412],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.022883192,0.000337284,0.00041758458,0.0008956374,0.0005515334,0.001995642,0.00037526255,0.0005507095,0.0032528515],"category_scores_gemma":[0.12681888,0.0002428482,0.00051428657,0.00022256932,0.00040984282,0.0008226979,0.0012954084,0.0015978295,0.0005864875],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008637729,0.0015711888,0.7675112,0.00031698064,0.00013712277,0.00031794098,0.019085031,0.00047105597,0.010663536,0.0010479097,0.0009543193,0.19706],"study_design_scores_gemma":[0.000092658054,0.005279714,0.9462428,0.0006791727,0.00016513391,0.0012409292,0.016081745,0.004419352,0.015467655,0.0019598145,0.008217125,0.00015394052],"about_ca_topic_score_codex":0.00079026463,"about_ca_topic_score_gemma":0.00080654956,"teacher_disagreement_score":0.022883192,"about_ca_system_score_codex":0.0005539984,"about_ca_system_score_gemma":0.0013084313,"threshold_uncertainty_score":0.121019304},"labels":[],"label_agreement":null},{"id":"W1982497397","doi":"10.1016/s0191-491x(02)00014-7","title":"Matching the grade 8 TIMSS item pool to the Ontario curriculum","year":2002,"lang":"en","type":"article","venue":"Studies In Educational Evaluation","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Toronto; Lakehead University","funders":"","keywords":"Mathematics education; Curriculum; Matching (statistics); Secondary education; Psychology; Pedagogy; Mathematics; Statistics","score_opus":0.1656116291663467,"score_gpt":0.46858849052707463,"score_spread":0.30297686136072793,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1982497397","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8653688,0.00028221757,0.008903453,0.0009755732,0.00026292226,0.010193389,0.01556348,0.00047175394,0.09797835],"genre_scores_gemma":[0.8571397,0.0004773014,0.023602365,0.00054757274,0.00007735432,0.019713577,0.024123287,0.00027405508,0.074044734],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99457586,0.0010798334,0.0008775836,0.0004309253,0.0022610568,0.00077460957],"domain_scores_gemma":[0.98238695,0.0018775178,0.0013449743,0.0016088217,0.011788719,0.0009930335],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006091932,0.00045520285,0.00087595836,0.00277918,0.0016319698,0.0013194004,0.0010017052,0.0005862346,0.015324642],"category_scores_gemma":[0.02805678,0.00035272838,0.0011925163,0.0031187374,0.0006877443,0.00051318377,0.0016168247,0.00055141206,0.005923534],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0020997983,0.0014681094,0.6317484,0.0006047713,0.00024538164,0.00022016288,0.0063142935,0.0016011576,0.0107468255,0.0025860693,0.0780332,0.26433188],"study_design_scores_gemma":[0.00015866513,0.00038370848,0.95599735,0.0001328983,0.00007836178,0.00004161184,0.001492595,0.000821356,0.0018499247,0.0003503727,0.038662747,0.00003048803],"about_ca_topic_score_codex":0.48082414,"about_ca_topic_score_gemma":0.7813034,"teacher_disagreement_score":0.9921031,"about_ca_system_score_codex":0.007896907,"about_ca_system_score_gemma":0.024597902,"threshold_uncertainty_score":0.9560509},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; McMaster University","funders":"","keywords":"Formative assessment; Test (biology); Curriculum; Psychology; Medicine; Medical education; Mathematics education; Pedagogy","score_opus":0.02780155950402934,"score_gpt":0.3811736229013911,"score_spread":0.35337206339736177,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1986967177","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99152595,0.0007314097,0.0009144827,0.00096497755,0.00010382186,0.00009139469,0.000044616016,0.00016411509,0.0054592276],"genre_scores_gemma":[0.99776995,0.00019377517,0.0008546276,0.000068144844,0.000035856698,0.000020709165,0.00003115403,0.000012282091,0.0010136176],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98696125,0.008533501,0.00043376908,0.00047760582,0.003132275,0.00046154181],"domain_scores_gemma":[0.9398135,0.043918133,0.0063951286,0.0019585644,0.0025918656,0.005322757],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007991611,0.0004973412,0.00058312755,0.00054870907,0.000367403,0.0008742223,0.0005972525,0.00067041157,0.0029110985],"category_scores_gemma":[0.07465793,0.00018741193,0.0005346778,0.00035503847,0.00054837595,0.0008385214,0.0011749035,0.001257822,0.00054604246],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0125194285,0.014835335,0.13481946,0.00043973004,0.0002945124,0.000347228,0.0014739432,0.004221201,0.007969149,0.00037534488,0.0027809555,0.81992376],"study_design_scores_gemma":[0.0007951513,0.073497616,0.90487856,0.00024871834,0.00029985278,0.00051098695,0.0009529607,0.005608432,0.0091471225,0.000582253,0.0033826544,0.00009567889],"about_ca_topic_score_codex":0.0022487019,"about_ca_topic_score_gemma":0.002345902,"teacher_disagreement_score":0.007991611,"about_ca_system_score_codex":0.0005115114,"about_ca_system_score_gemma":0.00132378,"threshold_uncertainty_score":0.042264163},"labels":[],"label_agreement":null},{"id":"W198737285","doi":"10.1007/978-94-007-1727-5_5","title":"Fair and Ethical Student Assessment Practices","year":2011,"lang":"en","type":"book-chapter","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":18,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Engineering ethics; Best practice; Process (computing); Ethical issues; Pedagogy; Psychology; Political science; Public relations; Sociology; Computer science; Engineering; Law","score_opus":0.11087441878626461,"score_gpt":0.44903393319752816,"score_spread":0.3381595144112636,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W198737285","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01183916,0.00632099,0.13269521,0.06129597,0.002040499,0.0002434276,0.000041685445,0.00029640665,0.7852266],"genre_scores_gemma":[0.5266413,0.00330428,0.07502692,0.010062312,0.00090365566,0.00057989464,0.000057341742,0.00028431247,0.38313994],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.94794405,0.02872255,0.00155992,0.0021468385,0.017802535,0.0018241662],"domain_scores_gemma":[0.9663694,0.01717708,0.0014489401,0.005218394,0.007931387,0.0018547061],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03248956,0.0006442622,0.0005669557,0.0017813703,0.0063493582,0.011805169,0.0020853004,0.0040605464,0.0057693995],"category_scores_gemma":[0.059497252,0.0004141116,0.00040082404,0.0010936408,0.021117266,0.007897505,0.006552034,0.008074379,0.0015927684],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00000590958,0.000041267853,0.00039022558,0.000042512875,0.0000055903947,0.00003907009,0.008816547,0.00042970158,0.00009372553,0.9113625,0.02187666,0.05689621],"study_design_scores_gemma":[0.0000045095003,0.000017116958,0.0005801534,0.0003085678,0.0000048871284,0.0001312248,0.004312578,0.000845756,0.0004037975,0.8567889,0.1365825,0.00002003757],"about_ca_topic_score_codex":0.003661817,"about_ca_topic_score_gemma":0.01048685,"teacher_disagreement_score":0.03248956,"about_ca_system_score_codex":0.0057436884,"about_ca_system_score_gemma":0.011384136,"threshold_uncertainty_score":0.1718232},"labels":[],"label_agreement":null},{"id":"W1994264241","doi":"10.24908/eoe-ese-rse.v11i0.2526","title":"The Capacity of Assessment in Arts Education","year":2010,"lang":"en","type":"article","venue":"Encounters in Theory and History of Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Cognitive reframing; Creativity; The arts; Accountability; Psychology; Standards-based assessment; Pedagogy; Educational assessment; Engineering ethics; Political science; Engineering; Social psychology","score_opus":0.018926907092902484,"score_gpt":0.3412857423962693,"score_spread":0.32235883530336684,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1994264241","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14801334,0.007844034,0.18910365,0.031809147,0.0006517538,0.00037064488,0.00008146065,0.0005437512,0.62158215],"genre_scores_gemma":[0.9680368,0.0012578964,0.02490432,0.00062134716,0.00013781634,0.00018478393,0.000019082723,0.000055312717,0.004782714],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.93990576,0.037587557,0.0031095105,0.00349584,0.014309539,0.0015917952],"domain_scores_gemma":[0.84638584,0.12109556,0.005822952,0.012336903,0.01110146,0.0032572376],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.043946594,0.0005638403,0.00073180563,0.003749401,0.0032128675,0.014070293,0.0019005836,0.0029093262,0.004927645],"category_scores_gemma":[0.15054426,0.00054601545,0.00048129816,0.0023391508,0.033412907,0.023228645,0.015172581,0.00490353,0.0009158354],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006447417,0.00012241116,0.008327135,0.0005058539,0.000025739626,0.00016270133,0.04809404,0.0023009242,0.0011162919,0.75138956,0.0022452795,0.18564557],"study_design_scores_gemma":[0.000024103232,0.00014423922,0.005988959,0.0011889517,0.000016385953,0.0005174527,0.011938174,0.004548115,0.0014980902,0.9041391,0.069907635,0.00008889305],"about_ca_topic_score_codex":0.0023161815,"about_ca_topic_score_gemma":0.0014390703,"teacher_disagreement_score":0.043946594,"about_ca_system_score_codex":0.00395153,"about_ca_system_score_gemma":0.009824209,"threshold_uncertainty_score":0.2324146},"labels":[],"label_agreement":null},{"id":"W1995272993","doi":"10.4018/jicthd.2010100104","title":"Leveraging Technology to Promote Assessment for Learning in Higher Education","year":2010,"lang":"en","type":"article","venue":"International Journal of Information Communication Technologies and Human Development","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Queen's University","funders":"","keywords":"Peer assessment; Higher education; Computer science; Medical education; Institution; Process (computing); Service (business); Mathematics education; Engineering management; Knowledge management; Psychology; Sociology; Engineering; Political science; Business; Marketing; Medicine","score_opus":0.03263258367176606,"score_gpt":0.38530118750130593,"score_spread":0.35266860382953985,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1995272993","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.62599504,0.002688581,0.22418623,0.008820336,0.00043432938,0.0021495586,0.00009268216,0.0020128659,0.13362034],"genre_scores_gemma":[0.7868243,0.0015280888,0.20370118,0.00055089634,0.00014113593,0.00067595206,0.00005305211,0.0000862027,0.0064392635],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9872273,0.008062107,0.00046751846,0.000664287,0.0030042785,0.0005743759],"domain_scores_gemma":[0.97109115,0.0214484,0.0018184375,0.0026117398,0.0017455608,0.0012847277],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011974376,0.0005377126,0.00040225452,0.0024552974,0.0014837598,0.0054999893,0.0010741727,0.0010190911,0.0031924725],"category_scores_gemma":[0.041777927,0.00024326022,0.00037026126,0.0015747083,0.0015194172,0.0049974644,0.0046302127,0.0014031903,0.0010997447],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010622812,0.0021289028,0.025647912,0.00063384214,0.000030215595,0.0002766649,0.013184018,0.00084573764,0.007353094,0.01281348,0.0038921135,0.9330878],"study_design_scores_gemma":[0.0005139516,0.011283222,0.23529485,0.005839989,0.00032962268,0.0045610364,0.048819058,0.01958191,0.05594503,0.117302984,0.49992543,0.000602965],"about_ca_topic_score_codex":0.001249115,"about_ca_topic_score_gemma":0.003052225,"teacher_disagreement_score":0.011974376,"about_ca_system_score_codex":0.0016028717,"about_ca_system_score_gemma":0.0035932544,"threshold_uncertainty_score":0.06332731},"labels":[],"label_agreement":null},{"id":"W1996030827","doi":"10.1016/j.asw.2010.05.003","title":"Assessing and providing feedback for student writing in Canadian classrooms","year":2010,"lang":"en","type":"article","venue":"Assessing Writing","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":38,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Alberta Advanced Education; University of Toronto","funders":"","keywords":"Mathematics education; Peer feedback; Psychology; Pedagogy; Medical education; Computer science; Medicine","score_opus":0.04316665126083148,"score_gpt":0.410534152827318,"score_spread":0.3673675015664865,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1996030827","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9674705,0.0005759599,0.0023372069,0.0019319905,0.00019914686,0.00038103768,0.00036005068,0.00037960845,0.026364453],"genre_scores_gemma":[0.9769736,0.0007029112,0.009466717,0.00018567247,0.000017358587,0.000113619615,0.00020815541,0.000050295457,0.012281603],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9886972,0.0029672312,0.000845814,0.0007093388,0.005324439,0.0014561212],"domain_scores_gemma":[0.9304844,0.008906381,0.0025814823,0.0011115011,0.047724884,0.009191277],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012930151,0.0007578669,0.0007143513,0.0029607,0.008852537,0.004414516,0.0022617725,0.0010683587,0.0034578324],"category_scores_gemma":[0.07978678,0.0004919982,0.00037514252,0.0024701052,0.00125643,0.0010714864,0.0028744026,0.0020440172,0.0009207627],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008958091,0.0021053413,0.15699245,0.00072597875,0.000059781258,0.0011076977,0.1248802,0.0033061942,0.008449247,0.002061323,0.03633699,0.6630791],"study_design_scores_gemma":[0.00028812126,0.0023119194,0.6288214,0.0017358842,0.00021539378,0.00078483747,0.16212985,0.010954947,0.034577943,0.00201441,0.15536685,0.0007984634],"about_ca_topic_score_codex":0.92787933,"about_ca_topic_score_gemma":0.9749292,"teacher_disagreement_score":0.07212067,"about_ca_system_score_codex":0.039937414,"about_ca_system_score_gemma":0.14163186,"threshold_uncertainty_score":0.28976756},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.02100229501179931,"score_gpt":0.38458132868967815,"score_spread":0.36357903367787886,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1996435010","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92587674,0.0020341796,0.0040572467,0.018252725,0.00013749169,0.00015667506,0.00035459912,0.000055695153,0.04907459],"genre_scores_gemma":[0.9910364,0.0006404976,0.0012047127,0.0014264357,0.000035411642,0.000058786205,0.00014571958,0.00005185678,0.0054000383],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9688408,0.011459429,0.0014289977,0.0017972499,0.014397805,0.0020757301],"domain_scores_gemma":[0.9702678,0.011937295,0.005158749,0.0027809558,0.0078006326,0.002054555],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015241263,0.00048024894,0.0004578446,0.0030776924,0.006924826,0.006276983,0.002250515,0.0016822041,0.0013975379],"category_scores_gemma":[0.062726915,0.00045078286,0.0006178707,0.002554065,0.016923836,0.0039197095,0.004454658,0.0024452854,0.00029282848],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008083533,0.00004395532,0.09512686,0.000111550624,0.000033325407,0.00063555536,0.86300915,0.00010999236,0.0010131459,0.015320596,0.0025560982,0.02195892],"study_design_scores_gemma":[0.000029515004,0.0001821476,0.3444324,0.0006555044,0.00007416746,0.0010197924,0.5689775,0.0011145981,0.0015667365,0.009352142,0.07239216,0.0002033274],"about_ca_topic_score_codex":0.72565645,"about_ca_topic_score_gemma":0.7678544,"teacher_disagreement_score":0.72565645,"about_ca_system_score_codex":0.03391194,"about_ca_system_score_gemma":0.01786655,"threshold_uncertainty_score":0.5519184},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.03217846521966579,"score_gpt":0.3400945437894142,"score_spread":0.30791607856974845,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1996477132","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9963057,0.000077197175,0.00026970427,0.000048948925,0.000008505333,0.00009287864,0.0004212201,0.000024286883,0.002751575],"genre_scores_gemma":[0.9936825,0.00016830479,0.001427342,0.000036831414,0.000008053629,0.000051143943,0.0010095779,0.000021272119,0.0035949787],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.99696004,0.00031895138,0.00018824631,0.00029149486,0.0017088006,0.00053248473],"domain_scores_gemma":[0.97843325,0.0037228975,0.0027495688,0.00051610667,0.011389052,0.003189171],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018517148,0.0003466083,0.00027973103,0.007493525,0.003223037,0.0013549319,0.00059768726,0.0002571035,0.0016911896],"category_scores_gemma":[0.020254217,0.00024137588,0.00019061133,0.006624245,0.00077108527,0.0003160977,0.0010437752,0.00041860028,0.00044489853],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00039088906,0.0003860544,0.6916221,0.0002450222,0.00003330124,0.0007819294,0.054799818,0.00031747142,0.010638733,0.0005373938,0.0029240632,0.23732316],"study_design_scores_gemma":[0.000004335132,0.000073949035,0.98595864,0.00002624987,0.0000073911838,0.000102028935,0.0071004145,0.00042468536,0.0012687261,0.000054707547,0.0049546147,0.000024280216],"about_ca_topic_score_codex":0.4844484,"about_ca_topic_score_gemma":0.70010626,"teacher_disagreement_score":0.51555157,"about_ca_system_score_codex":0.0067871152,"about_ca_system_score_gemma":0.011988912,"threshold_uncertainty_score":0.9632572},"labels":[],"label_agreement":null},{"id":"W1996479287","doi":"10.1080/09585176.2014.964276","title":"System leaders using assessment for learning as both the change and the change process: developing theory from practice","year":2014,"lang":"en","type":"article","venue":"The Curriculum Journal","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Fredericton; University of New Brunswick","funders":"","keywords":"Process (computing); Theory of change; Political science; Qualitative property; Qualitative research; Public relations; Pedagogy; Psychology; Sociology; Computer science; Social science","score_opus":0.0998659927114753,"score_gpt":0.40928048173368875,"score_spread":0.30941448902221347,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1996479287","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5032291,0.010736545,0.2567275,0.08618179,0.000637672,0.0022694413,0.000057359073,0.00038249447,0.13977814],"genre_scores_gemma":[0.93973273,0.0030334028,0.05450621,0.0011637879,0.00003695157,0.00053699984,0.000016008813,0.000031658088,0.00094222685],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.95048577,0.041669767,0.0011161811,0.0015270035,0.003453644,0.0017477504],"domain_scores_gemma":[0.9107238,0.079224676,0.0022040585,0.00234566,0.00363873,0.0018630879],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.053303152,0.00094262726,0.00071718247,0.004523295,0.0062091844,0.015394911,0.0033475235,0.0043714647,0.0011670297],"category_scores_gemma":[0.045747582,0.0009355538,0.0005625973,0.0029415567,0.038117524,0.014868691,0.008142585,0.005475376,0.0003601477],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000061811355,0.0006610425,0.019051947,0.0015512374,0.00005129965,0.00054535514,0.58188146,0.0015865647,0.0006264533,0.21766636,0.0028068905,0.17350954],"study_design_scores_gemma":[0.00010034036,0.00069954165,0.0066986494,0.007134835,0.00007079595,0.0005700423,0.7412323,0.0068319384,0.0023104865,0.17351858,0.060720332,0.00011216302],"about_ca_topic_score_codex":0.0050815195,"about_ca_topic_score_gemma":0.008688015,"teacher_disagreement_score":0.053303152,"about_ca_system_score_codex":0.010874524,"about_ca_system_score_gemma":0.021683164,"threshold_uncertainty_score":0.28189737},"labels":[],"label_agreement":null},{"id":"W1996719374","doi":"10.3138/jvme.0714-067r1","title":"Assessment Literacy: Definition, Implementation, and Implications","year":2014,"lang":"en","type":"article","venue":"Journal of Veterinary Medical Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Higher Education Academy","keywords":"Preparedness; Medical education; Curriculum; Cohort; Psychology; Session (web analytics); Literacy; Intervention (counseling); Formative assessment; Mathematics education; Pedagogy; Medicine; Computer science; Political science","score_opus":0.07582813055538377,"score_gpt":0.4954959922101246,"score_spread":0.4196678616547408,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1996719374","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7962796,0.00994845,0.04568341,0.09571933,0.00041807813,0.0024395238,0.00009116052,0.00033628236,0.049084194],"genre_scores_gemma":[0.97072864,0.0021119805,0.022984507,0.0019658084,0.00006045962,0.0011260941,0.000028334474,0.000034651064,0.0009595687],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.916202,0.06355352,0.0039357804,0.002953335,0.009742093,0.003613349],"domain_scores_gemma":[0.88583463,0.0812112,0.008403174,0.004470495,0.01347582,0.0066046827],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.07844728,0.00043998132,0.0005230852,0.0019221086,0.0023980949,0.007020576,0.0027853346,0.00209221,0.0018752553],"category_scores_gemma":[0.1108672,0.00046413162,0.0004820854,0.0014594746,0.006422958,0.0067731314,0.0076654507,0.0031065072,0.00028226245],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000291536,0.002460668,0.1240305,0.0023220403,0.000035595975,0.0003492032,0.07823374,0.0005725436,0.0019947244,0.02018832,0.0018524928,0.76766866],"study_design_scores_gemma":[0.00036196207,0.009647392,0.45880464,0.017194372,0.00021259424,0.0024578937,0.36208045,0.0080178045,0.01274872,0.04449946,0.08357309,0.00040167046],"about_ca_topic_score_codex":0.004709286,"about_ca_topic_score_gemma":0.005208908,"teacher_disagreement_score":0.07844728,"about_ca_system_score_codex":0.007948342,"about_ca_system_score_gemma":0.022382345,"threshold_uncertainty_score":0.41487384},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Praxis; Accountability; Teacher education; Literacy; Pedagogy; Psychology; Mathematics education; Perspective (graphical); Political science","score_opus":0.038888458072460504,"score_gpt":0.44715132300627947,"score_spread":0.40826286493381897,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1996728665","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8770329,0.0013101066,0.040413376,0.018629838,0.0002545872,0.001125317,0.000057163834,0.0007775932,0.060399093],"genre_scores_gemma":[0.956622,0.0006136704,0.03640751,0.00050362496,0.000045157718,0.0005525515,0.000034080724,0.000028558074,0.0051928507],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9946302,0.0036656598,0.00022692262,0.00023216972,0.000854563,0.0003904557],"domain_scores_gemma":[0.9848215,0.0068573137,0.002279341,0.0007831948,0.001697649,0.00356109],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008363344,0.00034853182,0.00030435115,0.0011506007,0.0027851225,0.0033325253,0.0009027171,0.00084221124,0.0030765424],"category_scores_gemma":[0.024639329,0.00025101035,0.0002543079,0.0005563675,0.0012022102,0.0014888977,0.0044808276,0.0019334806,0.0010015549],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001223903,0.0029748785,0.07727726,0.00086982735,0.000013843696,0.0010853459,0.19186383,0.00054550474,0.008623611,0.009879582,0.012185213,0.69455886],"study_design_scores_gemma":[0.00020123231,0.004513059,0.22113015,0.0038645833,0.00010460336,0.005087996,0.42611554,0.005016373,0.02126547,0.0267928,0.285707,0.00020112957],"about_ca_topic_score_codex":0.0007618944,"about_ca_topic_score_gemma":0.00362513,"teacher_disagreement_score":0.008363344,"about_ca_system_score_codex":0.0013960586,"about_ca_system_score_gemma":0.009341176,"threshold_uncertainty_score":0.044230163},"labels":[],"label_agreement":null},{"id":"W1997129769","doi":"10.7202/019859ar","title":"Plan-based Translation Assessment An Alternative to the Standard-based cut-the-feet-to-fit-the-shoes Style of Assessment","year":2009,"lang":"en","type":"article","venue":"Meta Journal des traducteurs","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Plan (archaeology); Computer science; Style (visual arts); Process (computing); sort; Mathematics education; Psychology","score_opus":0.09318539283418599,"score_gpt":0.39662914757635004,"score_spread":0.30344375474216406,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1997129769","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.051093303,0.00043929007,0.8529985,0.0021265626,0.00059747836,0.0018430141,0.00046273533,0.0034342788,0.08700479],"genre_scores_gemma":[0.39036036,0.00053216604,0.58128977,0.0007250702,0.00012848523,0.0012366431,0.0005170859,0.00035071265,0.024859786],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.985564,0.0076696994,0.0008445525,0.0009656486,0.004644343,0.0003118649],"domain_scores_gemma":[0.9782412,0.008581586,0.0016443931,0.003173607,0.0076397173,0.00071947125],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008606238,0.00090699043,0.00058037846,0.0027528482,0.00088770594,0.0044673006,0.0016584015,0.0014323422,0.009042219],"category_scores_gemma":[0.028170658,0.00031740498,0.0007708718,0.0023002832,0.0022997907,0.0041154856,0.002645193,0.0026327192,0.0017215229],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00054167036,0.0005742879,0.0098370295,0.0010836315,0.0001217736,0.0002856803,0.0065133865,0.0075978944,0.015990874,0.12228663,0.012493262,0.82267386],"study_design_scores_gemma":[0.00072358636,0.0060650613,0.04514002,0.0015053591,0.00040433084,0.003918371,0.007914046,0.18162316,0.059072945,0.3320474,0.36080128,0.00078456145],"about_ca_topic_score_codex":0.0020452042,"about_ca_topic_score_gemma":0.0041251807,"teacher_disagreement_score":0.009042219,"about_ca_system_score_codex":0.0013459681,"about_ca_system_score_gemma":0.0038997945,"threshold_uncertainty_score":0.045514703},"labels":[],"label_agreement":null},{"id":"W1999929076","doi":"10.1080/10627197.2011.584042","title":"Voices From Test-Takers: Further Evidence for Language Assessment Validation and Use","year":2011,"lang":"en","type":"article","venue":"Educational Assessment","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":56,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Guangdong University of Foreign Studies; Ministry of Education, India; Ministry of Earth Sciences","keywords":"Test (biology); Language assessment; Psychology; Test validity; Scale (ratio); Coding (social sciences); Test score; Computer science; Psychometrics; Mathematics education; Standardized test; Developmental psychology","score_opus":0.14416238535195033,"score_gpt":0.4552257976525222,"score_spread":0.3110634123005719,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1999929076","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97812563,0.0029714415,0.0061020222,0.007367013,0.00018267517,0.00011528806,0.00010727189,0.000046955684,0.004981703],"genre_scores_gemma":[0.99455243,0.0007247289,0.0018305904,0.001846136,0.000110603796,0.00012430765,0.00008408133,0.00006191035,0.00066523167],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.6754895,0.23173456,0.02039349,0.008941623,0.05831548,0.0051253242],"domain_scores_gemma":[0.29655135,0.58150554,0.04345421,0.025133682,0.047002777,0.006352395],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.16795583,0.0006862718,0.001460696,0.003745166,0.0050467476,0.007357724,0.0030838372,0.0028186003,0.0026675428],"category_scores_gemma":[0.5089094,0.0008900915,0.001389184,0.0020104637,0.009811517,0.00712669,0.01106563,0.0049013714,0.00060939963],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034389884,0.00013000949,0.078418285,0.0005830973,0.00011875083,0.000871143,0.8657131,0.000051525996,0.0025173414,0.0010073405,0.00075333146,0.049492124],"study_design_scores_gemma":[0.00011419213,0.0011644597,0.14296308,0.0027134626,0.00016570723,0.0031433324,0.8113228,0.0010015107,0.0071906666,0.0033458078,0.026594765,0.00028021532],"about_ca_topic_score_codex":0.004104786,"about_ca_topic_score_gemma":0.0037134096,"teacher_disagreement_score":0.16795583,"about_ca_system_score_codex":0.002931892,"about_ca_system_score_gemma":0.0038026855,"threshold_uncertainty_score":0.88824594},"labels":[],"label_agreement":null},{"id":"W2000242929","doi":"10.1007/s11092-014-9195-0","title":"Navigating dilemmas in transforming assessment practices: experiences of mathematics teachers in Ontario, Canada","year":2014,"lang":"en","type":"article","venue":"Educational Assessment Evaluation and Accountability","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":34,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Manitoba; University of Ottawa","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Situated; Accountability; Judgement; Pedagogy; Assessment for learning; Curriculum; Best practice; Mathematics education; Faculty development; Professional development; Psychology; Formative assessment; Political science; Computer science","score_opus":0.0639113308409666,"score_gpt":0.4511814897350099,"score_spread":0.38727015889404326,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2000242929","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96347135,0.0006880422,0.00056971825,0.016314968,0.00012096397,0.00015913216,0.00012218926,0.000033529417,0.018520137],"genre_scores_gemma":[0.981501,0.00046888995,0.0007866142,0.0014511197,0.000017132876,0.00003706638,0.000045527035,0.000038961363,0.015653748],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.986188,0.004560778,0.0004456162,0.00081982894,0.0033544935,0.0046312725],"domain_scores_gemma":[0.9657706,0.006701896,0.0022727014,0.00054160575,0.010554418,0.01415869],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007283135,0.00038643565,0.00059162657,0.0011619146,0.04574479,0.011248453,0.0031051964,0.0030321274,0.0036721984],"category_scores_gemma":[0.019882271,0.00079895335,0.00041944935,0.0031912997,0.012098179,0.0027212366,0.007363375,0.004539494,0.0004474468],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000072787705,0.00010285064,0.026113959,0.000086024054,0.000011776628,0.0012046669,0.9481727,0.0001998083,0.0005432122,0.001508758,0.006378561,0.015604891],"study_design_scores_gemma":[0.0000116285255,0.00004664168,0.022897903,0.000120703655,0.00001039913,0.00011146795,0.9361263,0.00017533194,0.00015424634,0.0003128931,0.039988443,0.000044045264],"about_ca_topic_score_codex":0.9924852,"about_ca_topic_score_gemma":0.99853444,"teacher_disagreement_score":0.14255129,"about_ca_system_score_codex":0.14255129,"about_ca_system_score_gemma":0.29116982,"threshold_uncertainty_score":0.994519},"labels":[],"label_agreement":null},{"id":"W2001609584","doi":"10.3138/jvme.0912-081r","title":"Experiences with Audio Feedback in a Veterinary Curriculum","year":2013,"lang":"en","type":"article","venue":"Journal of Veterinary Medical Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"University of Edinburgh","keywords":"Helpfulness; Peer feedback; Curriculum; Class (philosophy); Medical education; Psychology; Audio feedback; Test (biology); Multimedia; Computer science; Medicine; Pedagogy; Social psychology","score_opus":0.04294143203618296,"score_gpt":0.39723376888913586,"score_spread":0.3542923368529529,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2001609584","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99607027,0.00028693888,0.0012523131,0.0005457788,0.000045657456,0.00007397267,0.00001970028,0.00005886821,0.0016463881],"genre_scores_gemma":[0.9958689,0.00033947887,0.0018005256,0.00029563598,0.000063001884,0.00005979576,0.000025634483,0.00002702629,0.0015200804],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9726782,0.019914746,0.0010507697,0.00072243356,0.003939588,0.0016943312],"domain_scores_gemma":[0.94183123,0.038953144,0.0066570193,0.0016751065,0.0058029457,0.005080633],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013267269,0.0009255401,0.000675507,0.0010661818,0.0025931168,0.0027675824,0.0010986421,0.0018075085,0.0022792958],"category_scores_gemma":[0.06152064,0.00047570735,0.0006818807,0.0007194898,0.0020502391,0.001545245,0.0033670464,0.0016766136,0.00048879854],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001538782,0.003849948,0.08328515,0.0013956521,0.00012376807,0.0038656208,0.62551177,0.0012756063,0.022641242,0.0004911273,0.0044587324,0.25156265],"study_design_scores_gemma":[0.0002185439,0.030996548,0.16059785,0.0013731574,0.0003200625,0.014041988,0.68520844,0.004001329,0.027166994,0.00086653186,0.07468832,0.0005201728],"about_ca_topic_score_codex":0.001500382,"about_ca_topic_score_gemma":0.0029384885,"teacher_disagreement_score":0.013267269,"about_ca_system_score_codex":0.0014722666,"about_ca_system_score_gemma":0.0014485657,"threshold_uncertainty_score":0.07016486},"labels":[],"label_agreement":null},{"id":"W2005092513","doi":"10.5539/ies.v3n3p126","title":"Business Students' Views of Peer Assessment on Class Participation","year":2010,"lang":"en","type":"article","venue":"International Education Studies","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Peer assessment; Class (philosophy); Psychology; Peer evaluation; Peer feedback; Sample (material); Student engagement; Mathematics education; Process (computing); Self-assessment; Medical education; Pedagogy; Higher education; Computer science","score_opus":0.12892178434258825,"score_gpt":0.5537282949083048,"score_spread":0.4248065105657165,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2005092513","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9891544,0.00010827295,0.00041003956,0.0011262596,0.000063892374,0.000044767537,0.000011518172,0.000024781855,0.009056135],"genre_scores_gemma":[0.9982309,0.00006711519,0.00015190977,0.00009707661,0.000027097987,0.000031206015,0.000007827445,0.00000841942,0.0013785341],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.964234,0.02282079,0.001095024,0.0007882417,0.008472639,0.0025894325],"domain_scores_gemma":[0.9370287,0.027763994,0.008423837,0.002476933,0.013455201,0.010851265],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014357786,0.00036778094,0.00052044954,0.0010479859,0.002850705,0.005083516,0.00078195194,0.0009640487,0.0036889215],"category_scores_gemma":[0.06821945,0.00021241978,0.0004948515,0.00048923603,0.0020148377,0.0013038794,0.0038468777,0.0023112218,0.0007024455],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011602817,0.0037026445,0.31144395,0.00033047513,0.00013550249,0.0017943265,0.4339818,0.0004778463,0.0114153735,0.0026334827,0.007996759,0.22492751],"study_design_scores_gemma":[0.00013490782,0.005095934,0.3770878,0.0004672757,0.00012559057,0.0014165217,0.55655754,0.0017336233,0.008699537,0.0017619805,0.046675686,0.00024371651],"about_ca_topic_score_codex":0.0020869581,"about_ca_topic_score_gemma":0.0025367239,"teacher_disagreement_score":0.014357786,"about_ca_system_score_codex":0.0013573917,"about_ca_system_score_gemma":0.0018784228,"threshold_uncertainty_score":0.075932145},"labels":[],"label_agreement":null},{"id":"W2006092868","doi":"10.1016/j.asw.2008.10.004","title":"Harming not helping: The impact of a Canadian standardized writing assessment on curriculum and pedagogy","year":2008,"lang":"en","type":"article","venue":"Assessing Writing","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":29,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Curriculum; Writing assessment; Pedagogy; Sociology; Psychology; Political science","score_opus":0.06685673604162803,"score_gpt":0.43576278137128316,"score_spread":0.3689060453296551,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2006092868","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.935818,0.0013869978,0.0018912759,0.022278637,0.000985869,0.0009433042,0.0007581332,0.000295671,0.035642162],"genre_scores_gemma":[0.98086286,0.0009780753,0.005853062,0.0019800616,0.00006555349,0.00029358565,0.00037730896,0.00009888442,0.009490527],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9565125,0.009224327,0.0018828937,0.0021447623,0.02649369,0.0037419023],"domain_scores_gemma":[0.8897952,0.021339323,0.0047493563,0.0036075108,0.062355757,0.018152913],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02868051,0.00066892576,0.0007417193,0.0028943634,0.0142964935,0.0053797485,0.0041485694,0.002022182,0.0028800499],"category_scores_gemma":[0.106558256,0.0007579998,0.0009896208,0.0042778854,0.0039731753,0.0021268053,0.005276759,0.0034659556,0.00038736535],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0033144038,0.0044947085,0.20339964,0.00086852285,0.0002073908,0.0014871454,0.058361527,0.0058751567,0.0044216583,0.009043525,0.09436773,0.6141586],"study_design_scores_gemma":[0.0010395512,0.0033385442,0.8184913,0.0011077274,0.00039297316,0.00060168945,0.045318283,0.007647132,0.00663537,0.0023383927,0.11228661,0.00080250925],"about_ca_topic_score_codex":0.9913543,"about_ca_topic_score_gemma":0.9975184,"teacher_disagreement_score":0.16351937,"about_ca_system_score_codex":0.16351937,"about_ca_system_score_gemma":0.4270814,"threshold_uncertainty_score":0.970199},"labels":[],"label_agreement":null},{"id":"W2006287358","doi":"10.1111/medu.12111","title":"Standardised versus individualised assessment: related problems divided by a common language","year":2013,"lang":"en","type":"article","venue":"Medical Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"National Board of Medical Examiners","keywords":"Presentation (obstetrics); Population; Representation (politics); Psychology; Sample (material); Medical education; Politics; Medicine; Law; Political science","score_opus":0.013357299823821727,"score_gpt":0.3821863485403805,"score_spread":0.3688290487165588,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2006287358","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020982381,0.21700582,0.15202588,0.54291236,0.03635334,0.0011671982,0.00029025652,0.00056719943,0.028695589],"genre_scores_gemma":[0.46489385,0.07766837,0.17827688,0.22912636,0.034739234,0.0076399827,0.0004358059,0.0023226643,0.0048968056],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.33986655,0.51788723,0.056018516,0.01783278,0.06481105,0.0035838783],"domain_scores_gemma":[0.21888988,0.7202846,0.015697394,0.019558806,0.022988535,0.0025807112],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.39015165,0.001872617,0.0056467066,0.012730533,0.005436227,0.018851656,0.009953217,0.014202116,0.003297214],"category_scores_gemma":[0.64402694,0.00202886,0.0021689765,0.011844869,0.070567556,0.033948455,0.025193539,0.021204092,0.0012126686],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009086536,0.00014242173,0.0056214826,0.0100608,0.00045764807,0.00072970986,0.09137546,0.0006985534,0.00045660723,0.51507026,0.04874048,0.32573798],"study_design_scores_gemma":[0.00041007597,0.00046879964,0.008952801,0.037487756,0.0003539566,0.0043361615,0.06518413,0.0040450976,0.0007936472,0.7348712,0.14252532,0.0005710713],"about_ca_topic_score_codex":0.005152598,"about_ca_topic_score_gemma":0.0043218187,"teacher_disagreement_score":0.39015165,"about_ca_system_score_codex":0.016278027,"about_ca_system_score_gemma":0.014142297,"threshold_uncertainty_score":0.7520516},"labels":[],"label_agreement":null},{"id":"W2009280762","doi":"10.1007/s11135-011-9457-6","title":"The need for documenting validation transactions: a qualitative component of the testing validation process","year":2011,"lang":"en","type":"article","venue":"Quality & Quantity","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Champlain Regional College","funders":"","keywords":"Validator; Computer science; Documentation; Test (biology); Process (computing); Component (thermodynamics); Argument (complex analysis); Data science; Process management; Knowledge management; Software engineering; World Wide Web; Programming language; Business","score_opus":0.27900089821310037,"score_gpt":0.4818244700823256,"score_spread":0.20282357186922523,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2009280762","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.41643775,0.00037545335,0.52540565,0.024600647,0.00024059901,0.0058838115,0.0003280317,0.001096245,0.025631774],"genre_scores_gemma":[0.8307344,0.00009832526,0.16146949,0.0014207335,0.000045094184,0.0038516847,0.00012366459,0.0002039312,0.002052717],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.68560225,0.23841082,0.019447146,0.005897535,0.046495102,0.004147203],"domain_scores_gemma":[0.14852458,0.70363396,0.027920906,0.03645804,0.07970805,0.0037544393],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.27527,0.00072718813,0.0009880173,0.00386615,0.0072612027,0.009487151,0.004098847,0.0035366658,0.0026108664],"category_scores_gemma":[0.563074,0.0013596889,0.0006752367,0.0021827444,0.009164317,0.014465237,0.005301754,0.0061591393,0.0006631315],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00046648105,0.0009638333,0.05996855,0.0028887049,0.000097483105,0.0007648009,0.63557976,0.00200917,0.029960727,0.07448122,0.0058756005,0.18694359],"study_design_scores_gemma":[0.0003864144,0.0036037785,0.092578106,0.007261492,0.00020010557,0.002808374,0.60380495,0.033382628,0.058875505,0.10629678,0.09004163,0.00076023873],"about_ca_topic_score_codex":0.0038104248,"about_ca_topic_score_gemma":0.0053663976,"teacher_disagreement_score":0.72473,"about_ca_system_score_codex":0.010439494,"about_ca_system_score_gemma":0.029247435,"threshold_uncertainty_score":0.89372116},"labels":[],"label_agreement":null},{"id":"W2011625643","doi":"10.5430/wjel.v3n4p11","title":"In Search for Implementing Learning-Oriented Assessment in an EFL Setting","year":2013,"lang":"en","type":"article","venue":"World Journal of English Language","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Portfolio; Peer assessment; Computer science; Curriculum; Mathematics education; Assessment for learning; Psychology; Pedagogy; Formative assessment","score_opus":0.019598698348010837,"score_gpt":0.3814233614119601,"score_spread":0.3618246630639493,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2011625643","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.799346,0.001384545,0.13527638,0.012457394,0.00027757342,0.0037690771,0.00012299005,0.001939963,0.045426026],"genre_scores_gemma":[0.7839482,0.0004335047,0.2098384,0.0010392861,0.000044524684,0.000852056,0.00007666099,0.000053218017,0.0037142178],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.97620744,0.017095516,0.0010989152,0.0012642395,0.0030289968,0.0013049095],"domain_scores_gemma":[0.9595867,0.0193416,0.004240059,0.0036528537,0.008449025,0.00472977],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.031026917,0.0004844617,0.0005251116,0.001511584,0.0016297386,0.0045080697,0.0015211471,0.001575464,0.0025412221],"category_scores_gemma":[0.07117867,0.00036180211,0.00034300328,0.0008637629,0.0011505669,0.003876422,0.0033115821,0.0017435298,0.0013275595],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019730114,0.0050255563,0.09337885,0.0016572367,0.00003792704,0.0005305409,0.022730581,0.0016054389,0.008137742,0.0042854515,0.0033291937,0.85908425],"study_design_scores_gemma":[0.0013615179,0.015023741,0.44963703,0.014053353,0.00026794296,0.004854255,0.14097458,0.033086993,0.04666404,0.032429617,0.26082206,0.0008250147],"about_ca_topic_score_codex":0.002198529,"about_ca_topic_score_gemma":0.0039306474,"teacher_disagreement_score":0.031026917,"about_ca_system_score_codex":0.0018558634,"about_ca_system_score_gemma":0.010489898,"threshold_uncertainty_score":0.16408795},"labels":[],"label_agreement":null},{"id":"W2012525493","doi":"10.1016/j.jmathb.2015.01.004","title":"The assessment of mathematical literacy of linguistic minority students: Results of a multi-method investigation","year":2015,"lang":"en","type":"article","venue":"The Journal of Mathematical Behavior","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":13,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; University of British Columbia; University of Victoria","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Differential item functioning; Psychology; Test (biology); Mathematics education; Literacy; Think aloud protocol; Language proficiency; Language assessment; Pedagogy; Item response theory; Developmental psychology; Computer science; Psychometrics","score_opus":0.10903136226057507,"score_gpt":0.4817575674014773,"score_spread":0.3727262051409022,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2012525493","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9988926,0.000024747887,0.0005037317,0.00001594238,0.000005205249,0.00015445438,0.00001741532,0.000004633854,0.0003811425],"genre_scores_gemma":[0.99559635,0.000060206436,0.0029136874,0.000035321882,0.000006789761,0.00035366087,0.000032188495,0.000009445439,0.0009924602],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.9900607,0.006211377,0.0007189633,0.0007630225,0.0018797466,0.0003660888],"domain_scores_gemma":[0.969535,0.018214274,0.0021637662,0.0019744267,0.0069514303,0.0011610781],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014666956,0.0006200839,0.0008859691,0.0017853472,0.0016405337,0.0014364237,0.00087708957,0.00080528593,0.0012533517],"category_scores_gemma":[0.03743289,0.0005511627,0.00067831425,0.000747754,0.0008902454,0.0011487845,0.0023670709,0.00083687896,0.00043767956],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.013789066,0.024248617,0.69213265,0.00046405446,0.0004911469,0.0005700849,0.11237173,0.0005738185,0.026112024,0.00040543373,0.00043555192,0.1284058],"study_design_scores_gemma":[0.0008878202,0.028852934,0.8803834,0.00017560985,0.0004954884,0.0010110555,0.05625758,0.0045623095,0.023437118,0.00059265277,0.0031286369,0.000215444],"about_ca_topic_score_codex":0.0034952695,"about_ca_topic_score_gemma":0.0060925963,"teacher_disagreement_score":0.014666956,"about_ca_system_score_codex":0.0008474256,"about_ca_system_score_gemma":0.001560248,"threshold_uncertainty_score":0.07756722},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.10231687439942877,"score_gpt":0.5279200270248844,"score_spread":0.4256031526254556,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2013464569","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.65144926,0.001850122,0.11632229,0.07695903,0.00066359184,0.002417034,0.0001831516,0.001277564,0.14887792],"genre_scores_gemma":[0.9596473,0.00028479268,0.03225647,0.001603969,0.00006321611,0.0003984181,0.000043947326,0.00004973496,0.005652059],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.86074704,0.09396933,0.00852835,0.0043170634,0.02781846,0.0046198033],"domain_scores_gemma":[0.84342015,0.048043232,0.016955202,0.031935066,0.04756581,0.012080552],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.06826248,0.0004899547,0.000748409,0.0030492682,0.007909843,0.008764635,0.0029354065,0.0029372398,0.0034946383],"category_scores_gemma":[0.18625376,0.0003797446,0.00048840616,0.0021531917,0.003962099,0.007811042,0.012702419,0.0039201877,0.001094227],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015906732,0.0012634157,0.07330026,0.00034779502,0.00004293047,0.00028758988,0.08340397,0.0021184923,0.0028594097,0.045729678,0.015377735,0.7751097],"study_design_scores_gemma":[0.0001616588,0.0022520528,0.17419362,0.004081983,0.0000940471,0.0020195965,0.18448268,0.010308879,0.015773902,0.2698782,0.33609122,0.00066211587],"about_ca_topic_score_codex":0.0038677263,"about_ca_topic_score_gemma":0.008385749,"teacher_disagreement_score":0.06826248,"about_ca_system_score_codex":0.0049416954,"about_ca_system_score_gemma":0.018133085,"threshold_uncertainty_score":0.3610108},"labels":[],"label_agreement":null},{"id":"W2013836468","doi":"10.1080/09500790.2010.490875","title":"Assessment use, self-efficacy and mathematics achievement: comparative analysis of PISA 2003 data of Finland, Canada and the USA","year":2010,"lang":"en","type":"article","venue":"Evaluation & Research in Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Division of Mathematical Sciences","keywords":"Student achievement; Mathematics education; Academic achievement; Psychology; Test (biology); Achievement test; Standardized test; Pedagogy","score_opus":0.27445317848692796,"score_gpt":0.5499734689545585,"score_spread":0.2755202904676305,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2013836468","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9904974,0.00039815166,0.00010538469,0.00013182587,0.000008447061,0.000035557823,0.0065359105,0.000011903396,0.0022753533],"genre_scores_gemma":[0.9880618,0.00041028328,0.00028637282,0.00006359304,0.000003899208,0.00004849207,0.010185365,0.000011219157,0.0009289892],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.997855,0.00018968977,0.00016766922,0.00020418999,0.001115291,0.0004680566],"domain_scores_gemma":[0.98949194,0.001269028,0.001314155,0.00024575577,0.006507714,0.0011714874],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021132554,0.0003519271,0.0008006709,0.006217508,0.002848005,0.0020750673,0.001208403,0.00041862746,0.001391959],"category_scores_gemma":[0.007020174,0.0002859271,0.0007803359,0.016930534,0.0007723185,0.0004596009,0.0013874652,0.0005855896,0.00023902116],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008815424,0.000045905937,0.9904759,0.00006229076,0.00011708213,0.000098231234,0.0019853895,0.00013792068,0.00014909795,0.00015119495,0.0009880317,0.005700716],"study_design_scores_gemma":[0.0000035877551,0.000013404654,0.99636567,0.000023889885,0.000029117231,0.000034974615,0.0024082563,0.00011791096,0.000100891724,0.0000093116205,0.00088322145,0.000009625251],"about_ca_topic_score_codex":0.9870164,"about_ca_topic_score_gemma":0.9909203,"teacher_disagreement_score":0.015376339,"about_ca_system_score_codex":0.015376339,"about_ca_system_score_gemma":0.027251944,"threshold_uncertainty_score":0.11156368},"labels":[],"label_agreement":null},{"id":"W2015223621","doi":"10.1080/15434303.2014.981334","title":"Interpreting the Impact of the Ontario Secondary School Literacy Test on Second Language Students Within an Argument-Based Validation Framework","year":2015,"lang":"en","type":"article","venue":"Language Assessment Quarterly","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Queen's University","funders":"","keywords":"Argument (complex analysis); Literacy; Context (archaeology); Mathematics education; Test (biology); Curriculum; Reading (process); Ell; Language proficiency; Empirical research; Psychology; Pedagogy; Language assessment; Linguistics; Teaching method; Mathematics","score_opus":0.016460365348475472,"score_gpt":0.3890332495887422,"score_spread":0.37257288424026674,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2015223621","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.87345415,0.0069315084,0.014462142,0.033461295,0.0005854814,0.0012062998,0.0015701172,0.00006345061,0.06826553],"genre_scores_gemma":[0.992042,0.0004945359,0.004812666,0.00092674297,0.00004284059,0.0005099642,0.0002940349,0.00001919496,0.0008579599],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.8053914,0.13100895,0.0076246806,0.004572826,0.04813973,0.0032623992],"domain_scores_gemma":[0.35160136,0.5002401,0.06280159,0.012803408,0.07066703,0.001886627],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.17836873,0.0008130009,0.0010102672,0.0067225182,0.00523628,0.009038216,0.0048267064,0.002168444,0.0024857516],"category_scores_gemma":[0.5317957,0.0006734873,0.0016412156,0.0061114575,0.01809934,0.0041334443,0.008799448,0.002775795,0.000191719],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010975422,0.00033355367,0.64067364,0.0028158524,0.0009401556,0.0008947505,0.1903153,0.002683178,0.00074478285,0.0645788,0.006554093,0.08836835],"study_design_scores_gemma":[0.00036641525,0.00092820055,0.7094768,0.011494198,0.0013893165,0.00019027981,0.19120882,0.01114879,0.004854373,0.030235814,0.0384125,0.00029437154],"about_ca_topic_score_codex":0.45774013,"about_ca_topic_score_gemma":0.44409764,"teacher_disagreement_score":0.5422599,"about_ca_system_score_codex":0.045906212,"about_ca_system_score_gemma":0.04270188,"threshold_uncertainty_score":0.94331527},"labels":[],"label_agreement":null},{"id":"W2015457266","doi":"10.1016/j.system.2013.07.010","title":"Putting testing researchers to the test: An exploratory study on the TOEFL iBT","year":2013,"lang":"en","type":"article","venue":"System","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":14,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Mount Saint Vincent University; Carleton University; Queen's University","funders":"","keywords":"Test of English as a Foreign Language; Computer science; Context (archaeology); Construct (python library); Test (biology); Exploratory research; Variance (accounting); Focus group; Psychology; Construct validity; Language assessment; Mathematics education; Psychometrics; Sociology; Developmental psychology; Programming language","score_opus":0.24683390530327248,"score_gpt":0.4152035437005829,"score_spread":0.1683696383973104,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2015457266","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9924656,0.000020056279,0.004570937,0.00014963774,0.000016453394,0.00042401624,0.00008806133,0.00019780816,0.0020675445],"genre_scores_gemma":[0.98065305,0.00003638857,0.015080083,0.0002115626,0.00001739489,0.0005488663,0.00024061985,0.00019297065,0.0030190095],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.9724743,0.020024044,0.0014053878,0.0014361781,0.0033087682,0.0013512286],"domain_scores_gemma":[0.74209285,0.21102725,0.0063784365,0.01311728,0.02180824,0.0055759544],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02996378,0.0007863044,0.0009599343,0.0019055788,0.0031603738,0.0047042496,0.0029395826,0.0018612613,0.0026712941],"category_scores_gemma":[0.16813003,0.0006860668,0.0004515925,0.0014658322,0.0020492112,0.0043466557,0.004134938,0.0030254808,0.0010304472],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0038873688,0.02391551,0.27937675,0.0010689159,0.00018410472,0.0031134116,0.35354486,0.0032670356,0.02675684,0.0023868429,0.0050119297,0.29748636],"study_design_scores_gemma":[0.0012522592,0.05513493,0.38917342,0.0010006768,0.00055994134,0.0026873418,0.381825,0.04979213,0.063381344,0.0046420926,0.049824987,0.0007258906],"about_ca_topic_score_codex":0.0063436744,"about_ca_topic_score_gemma":0.011010149,"teacher_disagreement_score":0.9700362,"about_ca_system_score_codex":0.0027250785,"about_ca_system_score_gemma":0.0035256157,"threshold_uncertainty_score":0.1584655},"labels":[],"label_agreement":null},{"id":"W2017217841","doi":"10.1080/00220973.2013.795127","title":"The “None of the Above” Option in Multiple-Choice Testing: An Experimental Study","year":2013,"lang":"en","type":"article","venue":"The Journal of Experimental Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brock University","funders":"","keywords":"Multiple choice; Test (biology); Incentive; Actuarial science; Psychology; Social psychology; Economics; Statistics; Mathematics; Significant difference; Microeconomics","score_opus":0.06713802323590551,"score_gpt":0.41460810319018354,"score_spread":0.34747007995427803,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2017217841","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9976235,0.000038404298,0.0006998392,0.000067663896,0.000050793213,0.00074679777,0.000029461044,0.000018387891,0.0007251596],"genre_scores_gemma":[0.984576,0.00011395895,0.00964837,0.00031647962,0.00011596901,0.0036516823,0.00008669532,0.00002669412,0.0014642363],"study_design_codex":"nonrandomized_trial","study_design_gemma":"randomized_trial","domain_scores_codex":[0.9749902,0.015004867,0.0022422909,0.0023949507,0.004647901,0.0007197148],"domain_scores_gemma":[0.64643115,0.3192126,0.013917478,0.010900444,0.0046586,0.0048797433],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.026733566,0.0017798761,0.0016588254,0.0008708614,0.0014900671,0.0022597527,0.0027754635,0.0025335841,0.0073317303],"category_scores_gemma":[0.14855951,0.0016486399,0.0008901915,0.0006915771,0.002279067,0.0038597742,0.0015083302,0.0037851266,0.0010114445],"study_design_candidate":"randomized_trial","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.10264303,0.7064082,0.02591401,0.0013084013,0.00040619393,0.00044672473,0.015358669,0.0024495472,0.025686396,0.002279012,0.0015889059,0.11551095],"study_design_scores_gemma":[0.081444554,0.78139293,0.07189746,0.00051568676,0.00063556025,0.00059221126,0.0032570332,0.022345334,0.02803987,0.005285885,0.004099333,0.0004941531],"about_ca_topic_score_codex":0.00085434725,"about_ca_topic_score_gemma":0.0010856382,"teacher_disagreement_score":0.026733566,"about_ca_system_score_codex":0.0010115659,"about_ca_system_score_gemma":0.0015731758,"threshold_uncertainty_score":0.14138228},"labels":[],"label_agreement":null},{"id":"W2021788015","doi":"10.1080/14926150409556629","title":"Between student observation and student assessment: A critical reflection","year":2004,"lang":"en","type":"article","venue":"Canadian Journal of Science Mathematics and Technology Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":16,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Active listening; Mathematics education; Psychology; Reflection (computer programming); Pedagogy; Computer science; Communication","score_opus":0.043190057674966746,"score_gpt":0.42379406979282436,"score_spread":0.3806040121178576,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2021788015","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23244238,0.012290932,0.3857726,0.291783,0.01987235,0.0054340684,0.00016746538,0.0013040607,0.050933167],"genre_scores_gemma":[0.8881877,0.0023081452,0.08012951,0.016597541,0.0020367464,0.0026568638,0.000053007076,0.00044993966,0.007580476],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.6830553,0.2658623,0.007535436,0.009416179,0.029055921,0.0050748372],"domain_scores_gemma":[0.40154937,0.51386094,0.011680476,0.020967621,0.04449315,0.0074485163],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.18436658,0.0015888527,0.0014563377,0.0023959556,0.010997575,0.021035833,0.0077220406,0.011436395,0.0019976327],"category_scores_gemma":[0.40232477,0.0022390436,0.0014374522,0.0010539417,0.026836336,0.018829059,0.026087059,0.036364455,0.0006770116],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004457837,0.0007599376,0.0037757137,0.0009441814,0.00015095195,0.0015495691,0.8372468,0.0005973648,0.0043560937,0.025593774,0.016074074,0.108505726],"study_design_scores_gemma":[0.00038563702,0.001270714,0.007815674,0.0069541684,0.0002820731,0.004179357,0.68695277,0.006170925,0.01174279,0.078924365,0.19463547,0.00068611687],"about_ca_topic_score_codex":0.003490841,"about_ca_topic_score_gemma":0.0056776963,"teacher_disagreement_score":0.8156334,"about_ca_system_score_codex":0.013677766,"about_ca_system_score_gemma":0.021595007,"threshold_uncertainty_score":0.97503537},"labels":[],"label_agreement":null},{"id":"W2023466828","doi":"10.1111/j.0965-075x.2005.00307.x","title":"Who Will Evaluate Me? Rater Selection in Multi‐Source Assessment Contexts","year":2005,"lang":"en","type":"article","venue":"International Journal of Selection and Assessment","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Montreal Clinical Research Institute; Concordia University","funders":"","keywords":"Psychology; Preference; Affect (linguistics); Selection (genetic algorithm); Inter-rater reliability; Social psychology; Performance appraisal; Applied psychology; Developmental psychology; Rating scale; Statistics; Computer science; Communication","score_opus":0.03028675750328179,"score_gpt":0.4241642399649722,"score_spread":0.3938774824616904,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2023466828","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9841942,0.00023357815,0.008307587,0.00054901734,0.000083152954,0.00009490979,0.000025160225,0.000059466704,0.00645285],"genre_scores_gemma":[0.99167025,0.0002508137,0.005487033,0.00015946354,0.00007794583,0.00007084376,0.000030355359,0.000025427325,0.0022278759],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9793139,0.014282582,0.0008197637,0.0010605137,0.0039769113,0.0005463434],"domain_scores_gemma":[0.93519056,0.042043246,0.0078091677,0.0027742423,0.008756368,0.0034264377],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.019723238,0.0004033923,0.0006054614,0.0009890104,0.0009221103,0.0020971957,0.00057949626,0.00056141615,0.0022571825],"category_scores_gemma":[0.10818049,0.00020169203,0.0002898321,0.00035305723,0.0004737017,0.0011876136,0.0009783384,0.00076435023,0.0013043222],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0031596061,0.00079912954,0.44711176,0.00046773124,0.00019963345,0.0025797375,0.082629874,0.00071929995,0.038051892,0.002137705,0.004929818,0.41721386],"study_design_scores_gemma":[0.0003924695,0.004835311,0.7549363,0.00060334353,0.00034611803,0.0098642595,0.13008691,0.02408502,0.029153867,0.007873971,0.03728785,0.0005345613],"about_ca_topic_score_codex":0.0007313765,"about_ca_topic_score_gemma":0.0016696102,"teacher_disagreement_score":0.019723238,"about_ca_system_score_codex":0.0003478218,"about_ca_system_score_gemma":0.0004087895,"threshold_uncertainty_score":0.10430771},"labels":[],"label_agreement":null},{"id":"W2024930517","doi":"10.5430/ijhe.v1n1p2","title":"Multi-disciplinary Peer-mark Moderation of Group Work","year":2012,"lang":"en","type":"article","venue":"International Journal of Higher Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Loughborough University; Joint Information Systems Committee; Higher Education Academy","keywords":"Moderation; Transparency (behavior); Peer review; Psychology; Computer science; Peer assessment; World Wide Web; Social psychology; Mathematics education; Political science; Computer security","score_opus":0.04742055874931791,"score_gpt":0.4274911673045354,"score_spread":0.3800706085552175,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2024930517","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25395405,0.001078933,0.6781958,0.002651072,0.0014438434,0.0052355547,0.00023084648,0.0072650155,0.04994501],"genre_scores_gemma":[0.7323258,0.00033433814,0.24612524,0.00033784076,0.0006516614,0.0030366622,0.0002226446,0.00073807174,0.016227746],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9363648,0.046937678,0.0030152388,0.004072617,0.00858086,0.0010287362],"domain_scores_gemma":[0.77311635,0.13192755,0.01860618,0.049938574,0.020450898,0.005960464],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.045445222,0.00074997556,0.00096875045,0.0023558629,0.0028513502,0.0030805317,0.0025897496,0.0010014566,0.009758339],"category_scores_gemma":[0.133894,0.0004725825,0.00059627736,0.0013867941,0.0019177116,0.00395263,0.008479665,0.0013181951,0.003572372],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012335969,0.00084106677,0.020905327,0.0018951927,0.00019903436,0.00024977195,0.03646627,0.0018358731,0.031022847,0.010739864,0.008938483,0.88567275],"study_design_scores_gemma":[0.000977119,0.006971554,0.10718285,0.002503816,0.0004239462,0.0019561008,0.02852689,0.050236363,0.112553515,0.07193085,0.61581576,0.0009212756],"about_ca_topic_score_codex":0.0003402934,"about_ca_topic_score_gemma":0.0010152952,"teacher_disagreement_score":0.045445222,"about_ca_system_score_codex":0.00088525517,"about_ca_system_score_gemma":0.001876623,"threshold_uncertainty_score":0.24034017},"labels":[],"label_agreement":null},{"id":"W2025703093","doi":"10.1007/s10459-004-8740-x","title":"Does Blueprint Publication Affect Students’ Perception of Validity of the Evaluation Process?","year":2005,"lang":"en","type":"article","venue":"Advances in Health Sciences Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":19,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Foothills Medical Centre; University of Calgary","funders":"","keywords":"Affect (linguistics); Blueprint; Perception; Psychology; Process (computing); Medical education; Computer science; Applied psychology; Medicine; Engineering; Communication","score_opus":0.06317850139397954,"score_gpt":0.5164379696194489,"score_spread":0.45325946822546936,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2025703093","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9747853,0.00080217177,0.0043117157,0.008423782,0.0006025393,0.00026357028,0.00014766154,0.00023600276,0.01042719],"genre_scores_gemma":[0.99511564,0.00024303338,0.0021483193,0.0007556406,0.00015784756,0.00009948459,0.000085441556,0.000082178376,0.0013123691],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.8640518,0.065650344,0.014177528,0.0036275126,0.049073428,0.0034193548],"domain_scores_gemma":[0.17667677,0.6348672,0.08102526,0.020197723,0.07368123,0.013551836],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.12569298,0.00044844853,0.0011928157,0.0033954745,0.0014947042,0.0075292718,0.0014187301,0.0030483855,0.0065662893],"category_scores_gemma":[0.57713836,0.00057898724,0.0014597205,0.001896819,0.0019293432,0.0056690397,0.0028362721,0.003087253,0.0016857025],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004694818,0.0034297043,0.70596343,0.00074831117,0.000419329,0.0002568176,0.01568985,0.0008029524,0.003868504,0.0013080366,0.0053112954,0.25750697],"study_design_scores_gemma":[0.000613006,0.005157771,0.9457774,0.0010831045,0.0003390856,0.0005448721,0.012440879,0.006674213,0.011534888,0.003678187,0.011882966,0.00027359245],"about_ca_topic_score_codex":0.0018466234,"about_ca_topic_score_gemma":0.0019024016,"teacher_disagreement_score":0.12569298,"about_ca_system_score_codex":0.0033099505,"about_ca_system_score_gemma":0.006163048,"threshold_uncertainty_score":0.6647359},"labels":[],"label_agreement":null},{"id":"W2026630819","doi":"10.1080/14926150609556699","title":"Junior secondary science teachers’ understanding and practice of alternative assessment in Hong Kong: Implications for teacher professional development","year":2006,"lang":"en","type":"article","venue":"Canadian Journal of Science Mathematics and Technology Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":41,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Summative assessment; Professional development; Mathematics education; Alternative assessment; Science education; Medical education; Science learning; Pedagogy; Psychology; Formative assessment; Medicine","score_opus":0.04644577135039397,"score_gpt":0.393949517339641,"score_spread":0.34750374598924705,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2026630819","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99948287,0.000042574615,0.00002943014,0.00003294561,0.0000018737351,0.000004631051,0.0000066779667,6.299673e-7,0.00039833112],"genre_scores_gemma":[0.99907327,0.00010522488,0.000096039155,0.000019620378,5.837659e-7,0.0000086087175,0.000015082812,7.9951604e-7,0.000680742],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.99903476,0.00032551767,0.00016640632,0.00011491581,0.00016315798,0.00019530156],"domain_scores_gemma":[0.9948783,0.0017036645,0.00086108764,0.00020565852,0.0012738818,0.0010774015],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027445494,0.00022395936,0.00036879283,0.0006333744,0.0021249945,0.0019238702,0.00045656104,0.00033827938,0.0013304917],"category_scores_gemma":[0.005863865,0.00027181802,0.00028674034,0.0010804418,0.00092930655,0.0010029834,0.0011830211,0.0007294633,0.0001646379],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027923548,0.0003401919,0.66468686,0.0001446672,0.000028370705,0.000700367,0.3018143,0.00023768164,0.0017199016,0.00046476972,0.0005681971,0.029015504],"study_design_scores_gemma":[0.000017396169,0.00036779765,0.75294477,0.00013870448,0.000026424945,0.00018384928,0.2425912,0.00071518036,0.00070578564,0.00017474128,0.0020958749,0.000038290793],"about_ca_topic_score_codex":0.32247868,"about_ca_topic_score_gemma":0.41709086,"teacher_disagreement_score":0.32247868,"about_ca_system_score_codex":0.0035371615,"about_ca_system_score_gemma":0.007614487,"threshold_uncertainty_score":0.6412033},"labels":[],"label_agreement":null},{"id":"W2036552474","doi":"10.1007/s10459-005-2327-z","title":"Using a Sampling Strategy to Address Psychometric Challenges in Tutorial-Based Assessments","year":2006,"lang":"en","type":"article","venue":"Advances in Health Sciences Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":19,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Sampling (signal processing); Medical education; Computer science; Educational measurement; Medical physics; Psychology; Data science; Medicine; Curriculum; Pedagogy","score_opus":0.22663524795726642,"score_gpt":0.5530907750885159,"score_spread":0.3264555271312495,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2036552474","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20923685,0.00051328493,0.64087063,0.0011422557,0.0022544812,0.13425766,0.0008897801,0.00070230535,0.0101328],"genre_scores_gemma":[0.34897602,0.00033657416,0.46135128,0.0032723981,0.00043153967,0.17907856,0.001117766,0.00023551674,0.005200306],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.6871928,0.23705941,0.027277334,0.009168977,0.036802545,0.002498912],"domain_scores_gemma":[0.65291,0.19434954,0.013033536,0.05152665,0.085339844,0.00284045],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.22051963,0.0021829128,0.0017276322,0.004357683,0.004190004,0.0033285206,0.0030920852,0.0036854218,0.0042626145],"category_scores_gemma":[0.46364477,0.0013687244,0.0019319545,0.0035425825,0.0023907106,0.002357807,0.0047400296,0.0033523825,0.002453133],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0054164664,0.014713998,0.29468623,0.002831347,0.001964796,0.0014520037,0.041851252,0.0074529285,0.022026045,0.053293355,0.029624376,0.52468723],"study_design_scores_gemma":[0.008964125,0.046892818,0.377074,0.0031280434,0.003706351,0.0052279416,0.025419561,0.1946565,0.09095602,0.075995296,0.16714126,0.0008380184],"about_ca_topic_score_codex":0.0035554036,"about_ca_topic_score_gemma":0.005453062,"teacher_disagreement_score":0.77948034,"about_ca_system_score_codex":0.0023562126,"about_ca_system_score_gemma":0.005554256,"threshold_uncertainty_score":0.9612381},"labels":[],"label_agreement":null},{"id":"W2038816208","doi":"10.5539/hes.v1n2p107","title":"Fairness of IELTS Test Scores in University Admission","year":2011,"lang":"en","type":"article","venue":"Higher Education Studies","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Test (biology); Context (archaeology); Language proficiency; Psychology; Language assessment; Interpretation (philosophy); Empirical research; Medical education; Mathematics education; Applied psychology; Medicine; Computer science; Statistics","score_opus":0.11572440948171929,"score_gpt":0.3958591156896718,"score_spread":0.2801347062079525,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2038816208","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9654029,0.000666131,0.006040947,0.0044647646,0.00036612322,0.00021286808,0.00016890622,0.00010341132,0.022573974],"genre_scores_gemma":[0.9982666,0.000042211974,0.00065637607,0.00012194817,0.00004784206,0.000033756798,0.000030469802,0.000009275058,0.00079144095],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.8803708,0.07100375,0.009837171,0.0046675983,0.030394256,0.0037263627],"domain_scores_gemma":[0.65467584,0.17840731,0.063272454,0.024232628,0.06828411,0.011127688],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.13474715,0.00026103796,0.00073287275,0.003503164,0.002186707,0.0043194736,0.001477027,0.00097043224,0.002934508],"category_scores_gemma":[0.4027041,0.00022344064,0.0005175149,0.0027903072,0.0035182675,0.0027036786,0.0045171585,0.0018697218,0.00053023605],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012531758,0.0004247863,0.8370126,0.00009655071,0.00008974319,0.00017158205,0.016431894,0.00070057565,0.000587415,0.0045165517,0.0026364995,0.13607861],"study_design_scores_gemma":[0.000038781604,0.00077213015,0.96654963,0.0002270994,0.000027597825,0.00017724156,0.01403624,0.0033993789,0.0024526569,0.007759092,0.004449198,0.000110944864],"about_ca_topic_score_codex":0.0056533883,"about_ca_topic_score_gemma":0.0048676208,"teacher_disagreement_score":0.13474715,"about_ca_system_score_codex":0.004917426,"about_ca_system_score_gemma":0.0044074804,"threshold_uncertainty_score":0.71261954},"labels":[],"label_agreement":null},{"id":"W2039255653","doi":"10.7202/039179ar","title":"Student Choice between Computer and Traditional Paper-and-Pencil University Tests: What Predicts Preference and Performance?","year":2009,"lang":"en","type":"article","venue":"Revue internationale des technologies en pédagogie universitaire","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Saint Mary's University","funders":"","keywords":"Pencil (optics); Multiple choice; Preference; Test (biology); Psychology; Significant difference; Mathematics education; Cognition; Computer science; Statistics; Mathematics; Engineering","score_opus":0.0694845535592559,"score_gpt":0.290109193583946,"score_spread":0.2206246400246901,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2039255653","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9922808,0.004641319,0.0021086105,0.00018325445,0.00003389107,0.00005702091,0.00019140814,0.000022631095,0.00048094627],"genre_scores_gemma":[0.99701095,0.0010318245,0.0013953457,0.00009268114,0.000026372943,0.00005240771,0.0002225766,0.0000065876366,0.00016119744],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9894521,0.006900831,0.0012650185,0.0008662679,0.0013585743,0.00015719203],"domain_scores_gemma":[0.7859971,0.17851098,0.021884564,0.007998203,0.0038703626,0.0017387349],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.032826826,0.00060799305,0.0016706302,0.002476637,0.0004026314,0.0026380534,0.00072443835,0.0011918651,0.0012849536],"category_scores_gemma":[0.10104896,0.00033649022,0.0026613746,0.0028400456,0.00077440817,0.0014938881,0.0006168252,0.00096315274,0.00020150136],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003572092,0.0006065888,0.92404187,0.0012034633,0.009098541,0.0000816084,0.0018790994,0.0010281607,0.000602193,0.0002954777,0.00030739678,0.05728352],"study_design_scores_gemma":[0.001285358,0.009390549,0.9410211,0.0010461134,0.010826943,0.000668675,0.0040843566,0.01601238,0.005444986,0.007227633,0.002732373,0.00025964138],"about_ca_topic_score_codex":0.0011592264,"about_ca_topic_score_gemma":0.0015922422,"teacher_disagreement_score":0.032826826,"about_ca_system_score_codex":0.0004549729,"about_ca_system_score_gemma":0.0004769951,"threshold_uncertainty_score":0.17360693},"labels":[],"label_agreement":null},{"id":"W2043035035","doi":"10.3200/jexe.77.4.311-338","title":"Grading Scheme, Test Difficulty, and the Immediate Feedback Assessment Technique","year":2009,"lang":"en","type":"article","venue":"The Journal of Experimental Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brock University","funders":"Brock University","keywords":"Grading (engineering); Scheme (mathematics); Multiple choice; Test (biology); Classification scheme; Mathematics education; Psychology; Machine learning; Computer science; Significant difference; Mathematics; Statistics; Engineering","score_opus":0.015571283466485277,"score_gpt":0.3774555524268169,"score_spread":0.3618842689603316,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2043035035","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9814317,0.00035904767,0.012382049,0.0002269353,0.00021483547,0.0009707708,0.00013076689,0.00013102731,0.004152927],"genre_scores_gemma":[0.9792644,0.00011314038,0.017153643,0.00008158083,0.0000491687,0.0009108941,0.00012979627,0.000035784877,0.0022616978],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9871423,0.006973521,0.0014072203,0.00082949863,0.0033548686,0.00029270182],"domain_scores_gemma":[0.8722,0.09255017,0.015169561,0.007162328,0.010512203,0.0024057385],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0141557,0.0006292165,0.0007881322,0.001039521,0.0002742441,0.0008055811,0.00078957516,0.00066684367,0.0029401304],"category_scores_gemma":[0.12803268,0.00024826606,0.00047229204,0.0005650567,0.0004671087,0.00084130134,0.0006222237,0.0008706719,0.0005867799],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.01787244,0.005847201,0.3760779,0.0007765743,0.00043899784,0.00018270299,0.0024477208,0.0020434044,0.032501765,0.0011063172,0.0023768328,0.5583282],"study_design_scores_gemma":[0.0012093631,0.036610007,0.9208923,0.00023395279,0.00039101127,0.0006499619,0.0009704332,0.012267068,0.017953731,0.0024049429,0.006187886,0.00022920466],"about_ca_topic_score_codex":0.000309366,"about_ca_topic_score_gemma":0.00059946446,"teacher_disagreement_score":0.0141557,"about_ca_system_score_codex":0.0003478404,"about_ca_system_score_gemma":0.00032659734,"threshold_uncertainty_score":0.074863374},"labels":[],"label_agreement":null},{"id":"W2043393508","doi":"10.5296/ije.v2i2.490","title":"Pre-service Teachers’ Thinking about Student Assessment Issues","year":2010,"lang":"en","type":"article","venue":"International Journal of Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Context (archaeology); Psychology; Critical thinking; Introspection; Think aloud protocol; Pedagogy; Computer science","score_opus":0.022617865469250563,"score_gpt":0.4615424663876334,"score_spread":0.43892460091838287,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2043393508","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9584879,0.0012316755,0.009872574,0.010225533,0.00014196256,0.000107594075,0.000022366916,0.000109109315,0.019801294],"genre_scores_gemma":[0.98850787,0.0008516907,0.0028156189,0.0006016158,0.000020953657,0.000044721895,0.000018395185,0.000021518008,0.0071176086],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99479795,0.0023878678,0.00041962028,0.0003958004,0.0013935722,0.0006052022],"domain_scores_gemma":[0.9799973,0.010783326,0.0020578012,0.00079444936,0.004360613,0.0020066637],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0073974067,0.0002813602,0.00032802744,0.0013371552,0.003796484,0.006328355,0.0011274628,0.0015747583,0.0019487751],"category_scores_gemma":[0.024748541,0.00047423638,0.00041412737,0.0007294717,0.0045244913,0.0035938143,0.0025800169,0.005252238,0.00057608413],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000040390034,0.0002274887,0.05566066,0.0001972515,0.000011810746,0.001724431,0.861812,0.0003450681,0.002832659,0.004902819,0.003718815,0.06852673],"study_design_scores_gemma":[0.000010201588,0.00021528419,0.02526094,0.00034119704,0.000018035033,0.0015815168,0.91280437,0.00070271536,0.002536161,0.006449497,0.0500266,0.000053487685],"about_ca_topic_score_codex":0.0068364893,"about_ca_topic_score_gemma":0.0095860455,"teacher_disagreement_score":0.0073974067,"about_ca_system_score_codex":0.0036332565,"about_ca_system_score_gemma":0.005079497,"threshold_uncertainty_score":0.039121747},"labels":[],"label_agreement":null},{"id":"W2044712612","doi":"10.5539/ies.v7n5p68","title":"EFL Primary School Teachers’ Attitudes, Knowledge and Skills in Alternative Assessment","year":2014,"lang":"en","type":"article","venue":"International Education Studies","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":36,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology; Mathematics education; Christian ministry; Test (biology); Alternative assessment; School teachers; Descriptive statistics; Focus group; Knowledge level; Preference; Medical education; Qualitative property; Pedagogy","score_opus":0.042832997362448305,"score_gpt":0.47056223708406836,"score_spread":0.42772923972162,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2044712612","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99924326,0.00003557438,0.00003303234,0.00002978238,0.0000010817703,0.0000044156577,0.000008285978,9.857299e-7,0.0006435686],"genre_scores_gemma":[0.9987287,0.000089532354,0.000083464234,0.0000397744,0.0000040138175,0.000012002716,0.00001521772,7.0940837e-7,0.0010265082],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99912506,0.00020601353,0.00007544668,0.0000991377,0.0003120454,0.00018229728],"domain_scores_gemma":[0.9959806,0.0018110859,0.0010404803,0.00014123022,0.0005908323,0.00043582282],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018854181,0.00019736502,0.0004013268,0.0010335841,0.00073507946,0.0010284083,0.00016981183,0.00036581175,0.0027072087],"category_scores_gemma":[0.0034971002,0.00024351802,0.00017501379,0.0006353874,0.00063090207,0.0007451806,0.0005539522,0.00046477138,0.0005415445],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010405578,0.0009226694,0.89948595,0.00010549402,0.000011099271,0.0007694006,0.061218943,0.00006968315,0.0028822976,0.00010702499,0.00024972876,0.034073677],"study_design_scores_gemma":[0.000009549647,0.00081050716,0.95511305,0.000046098758,0.000009933937,0.0006537006,0.041209817,0.00009883915,0.0005077065,0.000078722944,0.0014498739,0.000012246016],"about_ca_topic_score_codex":0.0025689884,"about_ca_topic_score_gemma":0.005958484,"teacher_disagreement_score":0.0027072087,"about_ca_system_score_codex":0.00043353415,"about_ca_system_score_gemma":0.00042254513,"threshold_uncertainty_score":0.009971142},"labels":[],"label_agreement":null},{"id":"W2049433997","doi":"10.3200/joeb.79.3.176-178","title":"Using Professional Teaching Assistants to Support Large Group Business Communication Classes","year":2004,"lang":"en","type":"article","venue":"Journal of Education for Business","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Saint Mary's University","funders":"","keywords":"Grading (engineering); Mathematics education; Business communication; Computer science; Teaching method; Teaching assistant; Pedagogy; Psychology; Engineering","score_opus":0.07617504651563431,"score_gpt":0.45510638266963066,"score_spread":0.3789313361539963,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2049433997","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92095983,0.00038410738,0.054049425,0.00064729137,0.000455847,0.0019516685,0.00012517371,0.0055407127,0.015885979],"genre_scores_gemma":[0.89458495,0.00024932207,0.087347746,0.00022540403,0.00019866925,0.000798411,0.00017981954,0.00029072637,0.016124994],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9942782,0.003352405,0.00032264172,0.0005916674,0.0010777978,0.00037733212],"domain_scores_gemma":[0.9534402,0.027081018,0.003532241,0.0038536107,0.0064664506,0.005626536],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0056947586,0.0007466509,0.00056393,0.0009418901,0.0009797959,0.0014958477,0.001980859,0.0006044334,0.0073506953],"category_scores_gemma":[0.041801184,0.0003472508,0.000283241,0.00033018546,0.0003088382,0.00088997744,0.0014302187,0.00090372574,0.0043323473],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014253482,0.011559688,0.015812565,0.00041639208,0.000043742864,0.0010550852,0.010794324,0.0010861547,0.01842528,0.00040640164,0.011518124,0.927457],"study_design_scores_gemma":[0.008411545,0.092346214,0.1177823,0.0012531925,0.00084510347,0.010242872,0.045239683,0.05994663,0.21979941,0.006545892,0.43686736,0.0007197996],"about_ca_topic_score_codex":0.00050028577,"about_ca_topic_score_gemma":0.00093586184,"teacher_disagreement_score":0.0073506953,"about_ca_system_score_codex":0.00048023998,"about_ca_system_score_gemma":0.0016044658,"threshold_uncertainty_score":0.030117154},"labels":[],"label_agreement":null},{"id":"W20496686","doi":"","title":"ASSESSING CANADA’S STUDENT AID NEED ASSESSMENT POLICIES","year":2003,"lang":"en","type":"article","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Political science","score_opus":0.04076856405110143,"score_gpt":0.4061012720258114,"score_spread":0.36533270797471,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W20496686","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6376702,0.0017021955,0.0050075934,0.028942715,0.00030194139,0.0012565011,0.018454826,0.0011143442,0.3055497],"genre_scores_gemma":[0.93901336,0.0011771845,0.0071989573,0.0016848292,0.000048716058,0.00028315908,0.0036176092,0.000084970256,0.04689126],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.99107087,0.0011224916,0.00027427383,0.0004146604,0.0052677174,0.0018499249],"domain_scores_gemma":[0.967261,0.0032298302,0.0012102972,0.0006003829,0.021510754,0.006187689],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005844736,0.00035729204,0.00036110243,0.005726235,0.0040908703,0.005375999,0.0025001338,0.0011612943,0.018316323],"category_scores_gemma":[0.024843125,0.00022515663,0.00029827963,0.0052881395,0.00090838154,0.0017464868,0.0022887788,0.00094542676,0.0019986967],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022923778,0.0005517817,0.42156553,0.0003165049,0.000072087685,0.00030064967,0.00438057,0.006024005,0.0008386289,0.025087645,0.22019918,0.32043412],"study_design_scores_gemma":[0.000055281937,0.00031209073,0.5267294,0.00065799797,0.00009770697,0.00015877823,0.044406578,0.025995888,0.0018612241,0.005643845,0.393897,0.00018423692],"about_ca_topic_score_codex":0.9179608,"about_ca_topic_score_gemma":0.9511578,"teacher_disagreement_score":0.94259065,"about_ca_system_score_codex":0.057409324,"about_ca_system_score_gemma":0.12862785,"threshold_uncertainty_score":0.41653574},"labels":[],"label_agreement":null},{"id":"W2049720960","doi":"10.3115/1149293.1149385","title":"Exploring collaborative aspects of knowledge building through collaborative summary notes","year":2005,"lang":"en","type":"article","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Capital Regional District; Simon Fraser University","funders":"","keywords":"Knowledge building; Unit (ring theory); Computer science; Knowledge management; Mathematics education; Psychology","score_opus":0.10550017795597491,"score_gpt":0.38699772474706895,"score_spread":0.28149754679109407,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2049720960","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.88260335,0.00055010454,0.100034185,0.00085260137,0.00004303532,0.00042413038,0.0002210753,0.00030329084,0.014968244],"genre_scores_gemma":[0.9469744,0.00028293167,0.050589688,0.000035932153,0.000024451287,0.000152437,0.00012184857,0.000024969144,0.0017932912],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.98817503,0.007991125,0.0005421797,0.00075824145,0.002110638,0.00042272182],"domain_scores_gemma":[0.8792375,0.10211873,0.007679559,0.0051876437,0.004538638,0.0012379355],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012006027,0.000691622,0.0004739097,0.002668586,0.0014342511,0.0050798613,0.001330223,0.000969104,0.0024819956],"category_scores_gemma":[0.057176333,0.0003130638,0.00038766547,0.0021493286,0.0019155516,0.005409126,0.0024289559,0.00093078683,0.00036774678],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008116351,0.0006630036,0.045021728,0.0019499864,0.0001878467,0.0018239738,0.477273,0.0051392335,0.033455234,0.014379445,0.0016631229,0.41763186],"study_design_scores_gemma":[0.00047537338,0.0052971127,0.17150252,0.0019278822,0.0005730935,0.0040922025,0.4849343,0.055080168,0.07073293,0.0627899,0.14187184,0.00072272593],"about_ca_topic_score_codex":0.0013667652,"about_ca_topic_score_gemma":0.002580962,"teacher_disagreement_score":0.012006027,"about_ca_system_score_codex":0.0010182268,"about_ca_system_score_gemma":0.0009802697,"threshold_uncertainty_score":0.06349468},"labels":[],"label_agreement":null},{"id":"W2050121974","doi":"10.1152/advan.00020.2004","title":"<i>The Art of Evaluation: A Handbook for Educators and Trainers.</i> T. Fenwick and J. Parson. Toronto, Canada: Thompson Educational Press, 2000. ISBN 1-55077-104-3 (US$29.95)","year":2004,"lang":"en","type":"article","venue":"AJP Advances in Physiology Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Wonder; Economic Justice; Autonomy; Psychology; Sociology; Law; Political science; Social psychology","score_opus":0.011543846979011734,"score_gpt":0.34221257467796906,"score_spread":0.33066872769895733,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2050121974","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010504968,0.7459465,0.11158943,0.050544202,0.008248869,0.0008044406,0.0010023814,0.004354371,0.0764593],"genre_scores_gemma":[0.025896227,0.58900815,0.23855187,0.014689499,0.0070349495,0.003961464,0.0015167469,0.0025541107,0.11678699],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98168725,0.008817226,0.0021563498,0.00050974806,0.006522122,0.00030728863],"domain_scores_gemma":[0.9462542,0.04053617,0.0016524554,0.0019084393,0.008609613,0.0010391125],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02170691,0.002211703,0.0022650096,0.0072248243,0.0012508396,0.0059558805,0.0025853822,0.0034218794,0.016290506],"category_scores_gemma":[0.035739016,0.0015830692,0.0007813735,0.005159988,0.0059930705,0.0075256703,0.0024737301,0.005418883,0.016345616],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030858402,0.000051537532,0.00020438597,0.0017176952,0.000015617694,0.00006249903,0.0011145679,0.00024985595,0.00042272886,0.005354476,0.49662912,0.49414665],"study_design_scores_gemma":[0.000017871353,0.00008297008,0.0014140228,0.0049928566,0.000016721788,0.0009769304,0.0013085689,0.00042228895,0.000499818,0.02660127,0.9636098,0.0000567593],"about_ca_topic_score_codex":0.0075189383,"about_ca_topic_score_gemma":0.017982438,"teacher_disagreement_score":0.02170691,"about_ca_system_score_codex":0.0029107484,"about_ca_system_score_gemma":0.008474134,"threshold_uncertainty_score":0.114798486},"labels":[],"label_agreement":null},{"id":"W2053410856","doi":"10.5054/tj.2011.269751","title":"Generalizability Theory as Evidence of Concerns About Fairness in Large‐Scale ESL Writing Assessments","year":2011,"lang":"en","type":"article","venue":"TESOL Journal","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Generalizability theory; Rating scale; Reliability (semiconductor); Psychology; Variation (astronomy); Scale (ratio); Inter-rater reliability; Mathematics education; Developmental psychology; Geography","score_opus":0.11265739958471804,"score_gpt":0.4387508983425095,"score_spread":0.3260934987577915,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2053410856","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.47807953,0.0022313243,0.43814534,0.0093087675,0.0008296572,0.0032373578,0.0003823948,0.0005141868,0.0672715],"genre_scores_gemma":[0.9799396,0.00010898817,0.017400438,0.0009715423,0.00014700787,0.0007589685,0.00007912635,0.00006184834,0.0005326284],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.716629,0.19236796,0.013810841,0.022917444,0.051688794,0.0025859359],"domain_scores_gemma":[0.2270143,0.6487939,0.033944126,0.06338106,0.025616622,0.0012500384],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.26579344,0.000770367,0.0012106253,0.0037138578,0.0023902855,0.0033575085,0.0021364845,0.0026211855,0.0036516278],"category_scores_gemma":[0.53842944,0.0006637615,0.0024350572,0.0023538768,0.011276856,0.006421719,0.0048455684,0.004199011,0.00032456114],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0021531198,0.0011707114,0.58365947,0.0025982843,0.0029454085,0.0011577045,0.06349207,0.0102963075,0.0060498887,0.17017318,0.0038856263,0.15241817],"study_design_scores_gemma":[0.0007245232,0.006900851,0.4830637,0.0020136598,0.0013831547,0.0031304522,0.023454448,0.056258485,0.014976727,0.38803545,0.019664217,0.00039429267],"about_ca_topic_score_codex":0.0036730464,"about_ca_topic_score_gemma":0.002012534,"teacher_disagreement_score":0.26579344,"about_ca_system_score_codex":0.0037930948,"about_ca_system_score_gemma":0.0027078344,"threshold_uncertainty_score":0.9054074},"labels":[],"label_agreement":null},{"id":"W2055314676","doi":"10.1080/02602930601122555","title":"Assessment purposes and procedures in ESL/EFL classrooms","year":2007,"lang":"en","type":"article","venue":"Assessment & Evaluation in Higher Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":61,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Alberta; Queen's University","funders":"Beijing Foreign Studies University","keywords":"Psychology; Mathematics education; Pedagogy; Teaching method; Linguistics","score_opus":0.07152919239186825,"score_gpt":0.4767516717717072,"score_spread":0.4052224793798389,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2055314676","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7340542,0.0022913131,0.17155014,0.0021367734,0.000321618,0.0060861814,0.00029418038,0.0008930839,0.08237242],"genre_scores_gemma":[0.8168532,0.0008789748,0.16849758,0.0003793776,0.000086047694,0.0044279117,0.00012039537,0.00017791586,0.008578503],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.8990082,0.07590421,0.009162639,0.0035131138,0.01066196,0.001749868],"domain_scores_gemma":[0.80585366,0.12706976,0.017322032,0.01595708,0.03042322,0.0033742662],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.07390258,0.00053462636,0.00055692403,0.003641465,0.0034283265,0.004079118,0.0017394074,0.00093676196,0.0021133088],"category_scores_gemma":[0.1822176,0.0004837739,0.0003194828,0.0031108682,0.004800101,0.002627232,0.0043897848,0.0015128583,0.0012964723],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003039135,0.0009308084,0.036065508,0.00085216365,0.000013756824,0.0005559638,0.27743787,0.0010944429,0.01587763,0.014626498,0.0034115764,0.6488298],"study_design_scores_gemma":[0.00019033387,0.0018236799,0.25547874,0.0032886243,0.000052831205,0.0023845036,0.30281848,0.009109317,0.051701117,0.047663327,0.3248994,0.00058959593],"about_ca_topic_score_codex":0.0025021501,"about_ca_topic_score_gemma":0.004457325,"teacher_disagreement_score":0.07390258,"about_ca_system_score_codex":0.0036176902,"about_ca_system_score_gemma":0.0068014283,"threshold_uncertainty_score":0.39083886},"labels":[],"label_agreement":null},{"id":"W2055895965","doi":"10.1080/17439880802324061","title":"Electronic assessment issues and practices in Pakistan: a case study","year":2008,"lang":"en","type":"article","venue":"Learning Media and Technology","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"International Development Research Centre; Kent State University","keywords":"Scope (computer science); Political science; Institution; Resource (disambiguation); Quantitative assessment; Needs assessment; Higher education; Knowledge management; Public relations; Business; Computer science; Risk analysis (engineering)","score_opus":0.030134497116153357,"score_gpt":0.42456706770363806,"score_spread":0.3944325705874847,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2055895965","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9939109,0.00014810413,0.0003804403,0.00070089224,0.000013179633,0.00007732955,0.00003221498,0.0000056977406,0.004731321],"genre_scores_gemma":[0.99641126,0.0007043623,0.00057923404,0.00022115833,0.000013207133,0.000031664415,0.000016346361,0.000004303225,0.002018486],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99656916,0.0016206321,0.00022489578,0.00020108989,0.0006312124,0.00075307913],"domain_scores_gemma":[0.9928606,0.0038482419,0.0010920678,0.00024754458,0.0009489742,0.0010025002],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0037518744,0.00041489038,0.00036722617,0.0015492463,0.00884682,0.0033084971,0.0009953813,0.0022452457,0.003646096],"category_scores_gemma":[0.007980117,0.00039374465,0.00029162408,0.0030349568,0.0030716835,0.0018638986,0.00251904,0.001587863,0.00043316363],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033100994,0.0045626843,0.22762445,0.0005696563,0.000027574679,0.105191536,0.5378398,0.0010646378,0.0016046311,0.005362297,0.003685996,0.11213578],"study_design_scores_gemma":[0.00003173166,0.0016479101,0.074546576,0.00025553323,0.00003655065,0.0230103,0.87379795,0.0012750857,0.001390175,0.0008315535,0.023106122,0.000070593116],"about_ca_topic_score_codex":0.023207571,"about_ca_topic_score_gemma":0.036644038,"teacher_disagreement_score":0.023207571,"about_ca_system_score_codex":0.0047050416,"about_ca_system_score_gemma":0.0038900843,"threshold_uncertainty_score":0.046144962},"labels":[],"label_agreement":null},{"id":"W2059151369","doi":"10.5539/ies.v7n5p116","title":"Educational Assessment Profile of Teachers in the Sultanate of Oman","year":2014,"lang":"en","type":"article","venue":"International Education Studies","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Competence (human resources); Grading (engineering); Psychology; Medical education; Mathematics education; Pedagogy; Medicine; Engineering","score_opus":0.057268269989033824,"score_gpt":0.4822276099051725,"score_spread":0.42495933991613866,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2059151369","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99931514,0.000036977865,0.0000218783,0.00006044423,0.0000015404004,0.0000071936465,0.000045082015,0.000001809282,0.00050998706],"genre_scores_gemma":[0.9989178,0.00015097065,0.00009970959,0.000040632192,0.0000029200542,0.000018410748,0.00012585975,0.0000013112241,0.00064230815],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.999777,0.000029863522,0.00002830041,0.00001915382,0.000068529305,0.0000771414],"domain_scores_gemma":[0.99925405,0.00008081238,0.00026285867,0.000024590363,0.0002322865,0.00014535285],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00035818305,0.00016015669,0.00019098846,0.0011026117,0.0008377108,0.0006198301,0.0001485202,0.0002268973,0.0014137169],"category_scores_gemma":[0.0013728942,0.00013594271,0.00012700912,0.0011798644,0.00021374952,0.00048000473,0.0004113084,0.00021386736,0.00035905963],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000033920278,0.00008323544,0.9690981,0.00005445107,0.000005790024,0.00047209617,0.015642313,0.00003290097,0.0015376994,0.000059069058,0.00037622478,0.012604259],"study_design_scores_gemma":[0.0000025284505,0.00010285546,0.96315587,0.000032163858,0.000005006218,0.00045437238,0.033444837,0.00009217961,0.00023650136,0.000028697683,0.0024380216,0.0000070124174],"about_ca_topic_score_codex":0.01292947,"about_ca_topic_score_gemma":0.029252712,"teacher_disagreement_score":0.01292947,"about_ca_system_score_codex":0.00070391607,"about_ca_system_score_gemma":0.00083079835,"threshold_uncertainty_score":0.025708437},"labels":[],"label_agreement":null},{"id":"W2060254942","doi":"10.1007/s10780-008-9041-8","title":"Equitable Classroom Assessment: Promoting Self-Development and Self-Determination","year":2008,"lang":"en","type":"article","venue":"Interchange","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":15,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Social Sciences and Humanities Research Council of Canada; University of British Columbia; Government of Canada","keywords":"Oppression; Pedagogy; Nature versus nurture; Curriculum; Psychology; Sociology; Political science","score_opus":0.05951707463431537,"score_gpt":0.3543729971544347,"score_spread":0.29485592252011933,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2060254942","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7354355,0.0012326124,0.15505874,0.007816315,0.00021868985,0.0006475539,0.000048488557,0.00064954045,0.09889256],"genre_scores_gemma":[0.9238377,0.00041921213,0.06756077,0.00039933994,0.00005381214,0.00035405092,0.00004391219,0.00009162426,0.0072395685],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98169935,0.012220882,0.0005878854,0.0006354595,0.004453507,0.00040296442],"domain_scores_gemma":[0.9734257,0.013159599,0.002365961,0.0038850207,0.004491214,0.002672469],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015435714,0.00029943185,0.00047718568,0.001423401,0.0015929526,0.0031338644,0.0009188955,0.0007270094,0.0035310544],"category_scores_gemma":[0.061705567,0.0002238983,0.00021476341,0.0005441622,0.0009553582,0.002474654,0.0058686035,0.0012213505,0.0005915767],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002691842,0.0033089279,0.04834824,0.00014944069,0.000027426246,0.00009820217,0.012745544,0.0008862428,0.0030651095,0.021075064,0.004252665,0.90577394],"study_design_scores_gemma":[0.0008029595,0.0058768247,0.36289588,0.0028035208,0.00033807615,0.003403662,0.053608444,0.03563266,0.045582462,0.29512656,0.19359913,0.00032981296],"about_ca_topic_score_codex":0.00076262705,"about_ca_topic_score_gemma":0.0019990876,"teacher_disagreement_score":0.015435714,"about_ca_system_score_codex":0.0012682478,"about_ca_system_score_gemma":0.004124276,"threshold_uncertainty_score":0.08163279},"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,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Formative assessment; Feeling; Confusion; Psychology; Value (mathematics); Mathematics education; Peer feedback; Pedagogy; Social psychology; Computer science","score_opus":0.05312265572183805,"score_gpt":0.2858817771152325,"score_spread":0.23275912139339444,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2061239388","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9887427,0.0011948387,0.0026077062,0.0019951703,0.000058702746,0.00012524947,0.000021206739,0.00005168271,0.005202673],"genre_scores_gemma":[0.9949896,0.0007329203,0.0027264855,0.00022325983,0.000014240017,0.00007654982,0.000014351415,0.000016658192,0.0012059769],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.953249,0.03938608,0.001254169,0.0009989314,0.0041524633,0.0009593294],"domain_scores_gemma":[0.8794365,0.09654596,0.008680123,0.0035834133,0.009589012,0.0021650272],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03226363,0.00046990303,0.000768245,0.001505684,0.0025686987,0.004854318,0.0012436036,0.0012592964,0.00090348034],"category_scores_gemma":[0.118595675,0.00044798624,0.00022258075,0.0013149994,0.0033095446,0.002744817,0.0027553535,0.0016533904,0.00027220132],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024582358,0.000543773,0.057590365,0.0008169867,0.00003262709,0.0009876268,0.7173811,0.0002618135,0.0035935368,0.0011213553,0.0016780883,0.21574685],"study_design_scores_gemma":[0.0001554044,0.0022751666,0.17860113,0.0018544769,0.00012523014,0.0010753595,0.7704825,0.0022013427,0.007889927,0.003503577,0.031681664,0.00015428005],"about_ca_topic_score_codex":0.015595715,"about_ca_topic_score_gemma":0.029956209,"teacher_disagreement_score":0.03226363,"about_ca_system_score_codex":0.0032647962,"about_ca_system_score_gemma":0.007345907,"threshold_uncertainty_score":0.17062837},"labels":[],"label_agreement":null},{"id":"W2062042622","doi":"10.7202/1024956ar","title":"Assessment for Learning","year":2009,"lang":"fr","type":"article","venue":"Mesure et évaluation en éducation","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":39,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Computer science; Psychology","score_opus":0.08600414387348224,"score_gpt":0.46872927147305815,"score_spread":0.3827251275995759,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2062042622","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011273726,0.010534225,0.12602252,0.021437837,0.0044292053,0.0013265989,0.0020822189,0.004491663,0.818402],"genre_scores_gemma":[0.20398358,0.0056237085,0.18109198,0.0038660492,0.0011287928,0.0015406676,0.0031003093,0.0011959428,0.59846896],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9832267,0.006060338,0.0011612534,0.0013707287,0.007494671,0.00068641355],"domain_scores_gemma":[0.9825659,0.0039756037,0.0008916538,0.003466284,0.007872693,0.0012279103],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010410977,0.0008525638,0.00081794214,0.0043325513,0.0027449175,0.010294018,0.0020729613,0.0019611556,0.05529949],"category_scores_gemma":[0.039484672,0.00032867075,0.0008006296,0.0025079395,0.0027711818,0.0067221676,0.007310809,0.0025060126,0.027886273],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008668066,0.00010284212,0.001407923,0.00037615717,0.00001629371,0.000055440974,0.0016743498,0.00018480359,0.00068069756,0.14075603,0.09429327,0.76036555],"study_design_scores_gemma":[0.000022331868,0.00010162656,0.0035034493,0.0006679768,0.000018438917,0.0003067859,0.0012784014,0.0007399306,0.0015272157,0.084864594,0.90693015,0.00003904729],"about_ca_topic_score_codex":0.004963043,"about_ca_topic_score_gemma":0.0061022253,"teacher_disagreement_score":0.05529949,"about_ca_system_score_codex":0.004327999,"about_ca_system_score_gemma":0.008930077,"threshold_uncertainty_score":0.18499523},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.0662221502487459,"score_gpt":0.4615727496667562,"score_spread":0.3953505994180103,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2063505651","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7951857,0.0039829714,0.07782498,0.017428108,0.0048478814,0.0019245306,0.00013886983,0.004461546,0.09420542],"genre_scores_gemma":[0.8450234,0.0030835117,0.12584448,0.0018593721,0.0013216584,0.00072455447,0.0001701864,0.0006024756,0.021370355],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9532444,0.029787501,0.0022251196,0.00093907304,0.012769888,0.0010340486],"domain_scores_gemma":[0.83695674,0.107701905,0.009027643,0.0075250953,0.032291424,0.006497179],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.026895814,0.00072942296,0.0010893175,0.0023140514,0.0020106866,0.003634717,0.0014875967,0.0011535222,0.004951826],"category_scores_gemma":[0.17216152,0.0002954288,0.00052884145,0.0013597291,0.0010372294,0.0024652362,0.003254514,0.0019177035,0.0026266836],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028582863,0.0024790901,0.0076553263,0.0007289488,0.000045773766,0.00035768317,0.01340934,0.00052974606,0.00804319,0.0012791248,0.035725933,0.92946],"study_design_scores_gemma":[0.001145734,0.01917218,0.19593236,0.004216717,0.0005181161,0.007322373,0.0692514,0.019552657,0.10819729,0.033108935,0.54059243,0.0009897631],"about_ca_topic_score_codex":0.0002695033,"about_ca_topic_score_gemma":0.0006912832,"teacher_disagreement_score":0.026895814,"about_ca_system_score_codex":0.00063096586,"about_ca_system_score_gemma":0.0021997257,"threshold_uncertainty_score":0.14224035},"labels":[],"label_agreement":null},{"id":"W2063726363","doi":"10.1007/s10984-014-9170-1","title":"SWDYT: So What Do You Think? Canadian students’ attitudes about peerScholar, an online peer-assessment tool","year":2014,"lang":"en","type":"article","venue":"Learning Environments Research","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":18,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"The Scarborough Hospital; University of Toronto","funders":"","keywords":"Sociology of Education; Peer review; Peer evaluation; Psychology; Peer assessment; Educational technology; Higher education; Medical education; Pedagogy; Political science; Medicine","score_opus":0.06964661344691153,"score_gpt":0.44059494710350894,"score_spread":0.3709483336565974,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2063726363","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9662356,0.0004887552,0.00095362833,0.0040177405,0.00022104337,0.00040246567,0.000793594,0.00022613813,0.026661003],"genre_scores_gemma":[0.97551167,0.00074224855,0.0038728816,0.00068608223,0.000035961202,0.00025374853,0.00060250703,0.00008986113,0.018205095],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.9951108,0.0009994586,0.00025820115,0.00029429657,0.0026713999,0.0006658921],"domain_scores_gemma":[0.9747712,0.005158843,0.001691801,0.00073953165,0.01148556,0.0061530326],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008743838,0.00042987673,0.00048983586,0.0018046707,0.003956862,0.004836712,0.0012679773,0.00076968566,0.005375892],"category_scores_gemma":[0.035415895,0.00026886014,0.00057152344,0.0012311138,0.0017167071,0.002315234,0.0025226204,0.0019734886,0.00094945496],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005631127,0.00173421,0.5360007,0.00040758992,0.00010302667,0.00027836906,0.12354826,0.00038998984,0.0026283364,0.002003064,0.051116157,0.28122702],"study_design_scores_gemma":[0.00017081863,0.0010428152,0.7566426,0.00081125693,0.00019106145,0.00021525011,0.13733035,0.0015586884,0.0027815844,0.00075390853,0.09816283,0.00033894132],"about_ca_topic_score_codex":0.85852,"about_ca_topic_score_gemma":0.9372824,"teacher_disagreement_score":0.9912562,"about_ca_system_score_codex":0.015488269,"about_ca_system_score_gemma":0.039791856,"threshold_uncertainty_score":0.28462642},"labels":[],"label_agreement":null},{"id":"W2067457676","doi":"10.1136/bmj.38993.466678.be","title":"Putting the cart before the horse: testing to improve learning","year":2007,"lang":"en","type":"article","venue":"BMJ","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Worry; Psychology; Context (archaeology); Social psychology; Test (biology); Cognitive psychology; Applied psychology; Mathematics education; History","score_opus":0.03700351524578259,"score_gpt":0.383076420799716,"score_spread":0.3460729055539334,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2067457676","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.075853124,0.048582584,0.073153466,0.6562179,0.0076281014,0.00059157034,0.00018197771,0.0024015205,0.13538985],"genre_scores_gemma":[0.5810359,0.06003256,0.2489649,0.07917421,0.0048437524,0.00078032154,0.00019096397,0.00048093454,0.024496512],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9845473,0.011204421,0.00049591594,0.0002959454,0.0031289663,0.00032743363],"domain_scores_gemma":[0.9683317,0.025099207,0.001708426,0.0011769062,0.0020039026,0.0016798282],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.019292139,0.00070071116,0.0005656203,0.001422842,0.0008809684,0.0029637998,0.0014520054,0.003306358,0.011056972],"category_scores_gemma":[0.07304708,0.00020474124,0.00041904964,0.0009522539,0.004833296,0.0059601255,0.0020763613,0.0025474716,0.0021654437],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023778496,0.0005311099,0.004771209,0.0015031721,0.000037084294,0.00031465947,0.0028976125,0.00035589718,0.0010177699,0.017259981,0.080044515,0.8910291],"study_design_scores_gemma":[0.00040063306,0.003411957,0.0610208,0.012037333,0.00023806252,0.0038911612,0.02274527,0.0053618294,0.007893776,0.34335762,0.53921336,0.0004281408],"about_ca_topic_score_codex":0.002062454,"about_ca_topic_score_gemma":0.0042784503,"teacher_disagreement_score":0.019292139,"about_ca_system_score_codex":0.00096626714,"about_ca_system_score_gemma":0.0030529103,"threshold_uncertainty_score":0.102027774},"labels":[],"label_agreement":null},{"id":"W2071179638","doi":"10.1007/s11423-015-9375-8","title":"Developing an adaptive tool to select, plan, and scaffold oral assessment tasks for undergraduate courses","year":2015,"lang":"en","type":"article","venue":"Educational Technology Research and Development","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Scaffold; Plan (archaeology); Computer science; Educational technology; Instructional design; Computer-Assisted Instruction; Mathematics education; Multimedia; Engineering management; Psychology; Engineering","score_opus":0.22200173344247034,"score_gpt":0.4938688766434834,"score_spread":0.271867143201013,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2071179638","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15593089,0.00017003946,0.76746005,0.00041500418,0.00017605891,0.0026504854,0.0009676824,0.06808251,0.004147304],"genre_scores_gemma":[0.11327277,0.00008397957,0.88100547,0.00011508965,0.000021545204,0.0011780584,0.0006655313,0.0006371452,0.0030204288],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9975782,0.00068676495,0.0003101491,0.0006562517,0.00063850684,0.00013015114],"domain_scores_gemma":[0.98277825,0.011603624,0.0008315302,0.0014991845,0.0026359137,0.0006515083],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0052066897,0.0015579485,0.0007079408,0.0019109433,0.00039212138,0.0016795195,0.002499538,0.001338412,0.0052089207],"category_scores_gemma":[0.024972139,0.00082847144,0.0006340415,0.0007315574,0.00029327188,0.0021452438,0.0017153746,0.00097137754,0.0025573594],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005114744,0.0013082678,0.0102017615,0.00027620714,0.00006878539,0.00020487365,0.0016637647,0.0019253525,0.02628702,0.00052875414,0.00824044,0.94878334],"study_design_scores_gemma":[0.0027812656,0.0078923395,0.12177719,0.0015113902,0.0013509431,0.003837799,0.005999618,0.42958406,0.2658243,0.0099580195,0.14840272,0.0010803026],"about_ca_topic_score_codex":0.0018533205,"about_ca_topic_score_gemma":0.0031274285,"teacher_disagreement_score":0.0052089207,"about_ca_system_score_codex":0.00048332175,"about_ca_system_score_gemma":0.0015167913,"threshold_uncertainty_score":0.027535915},"labels":[],"label_agreement":null},{"id":"W2072017158","doi":"10.1378/chest.128.4_meetingabstracts.344s","title":"PUBLICATION OF RESEARCH UNDERTAKEN IN A CANADIAN TEACHING CENTRE: A REVIEW BY A RESEARCH ETHICS BOARD","year":2005,"lang":"en","type":"review","venue":"CHEST Journal","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Queen Elizabeth II Health Sciences Centre","funders":"","keywords":"Medicine; Institutional review board; Research ethics; Engineering ethics; Medical education; Ethics committee; Clinical research; Editorial board; Family medicine; Library science; Pathology; Surgery; Public administration; Engineering; Political science","score_opus":0.5068319885516277,"score_gpt":0.6176119719025462,"score_spread":0.11077998335091854,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2072017158","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0066550677,0.9315295,0.0011991438,0.03513679,0.0056332196,0.009078654,0.0017011596,0.000059952094,0.009006428],"genre_scores_gemma":[0.07444109,0.883532,0.014559909,0.013441163,0.0019191788,0.0077437116,0.0010463506,0.000080416416,0.0032361755],"study_design_codex":"systematic_review","study_design_gemma":"not_applicable","domain_scores_codex":[0.6675354,0.12302868,0.08349699,0.0060981777,0.113011315,0.006829371],"domain_scores_gemma":[0.31188738,0.2620246,0.09668339,0.016495429,0.2943852,0.01852399],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.27823257,0.0013686208,0.0044000503,0.03181473,0.005149463,0.00878531,0.0050412435,0.005346653,0.0022236006],"category_scores_gemma":[0.4840958,0.001780932,0.0026690112,0.03976692,0.0075640897,0.0031210987,0.0041462434,0.0038324124,0.00052626536],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017853837,0.00016127828,0.017789206,0.42888808,0.0021784606,0.0012264842,0.010929963,0.00015103057,0.0018019889,0.0033651767,0.11708692,0.41463602],"study_design_scores_gemma":[0.00080125814,0.00036094303,0.08139421,0.55524725,0.005182782,0.0007458358,0.0060514933,0.00011969468,0.0010975195,0.00069375813,0.3481198,0.0001854543],"about_ca_topic_score_codex":0.35368687,"about_ca_topic_score_gemma":0.67524695,"teacher_disagreement_score":0.99465334,"about_ca_system_score_codex":0.067187935,"about_ca_system_score_gemma":0.37220556,"threshold_uncertainty_score":0.89006776},"labels":[],"label_agreement":null},{"id":"W2072764341","doi":"10.1080/09695940600563611","title":"Differential effects of global modifications to large‐scale high stakes examination programmes","year":2006,"lang":"en","type":"article","venue":"Assessment in Education Principles Policy and Practice","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta; Queen's University","funders":"","keywords":"Scholarship; Accountability; Scale (ratio); Session (web analytics); Test (biology); Empirical examination; Identification (biology); Psychology; Political science; Medical education; Medicine; Geography; Law; Actuarial science; Business; Advertising","score_opus":0.02697556704776101,"score_gpt":0.41688929703418975,"score_spread":0.38991372998642876,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2072764341","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9905674,0.00027148725,0.00065994717,0.0005236309,0.00009257206,0.0002329693,0.00015488954,0.00010919885,0.007387961],"genre_scores_gemma":[0.996357,0.000100101126,0.00067292363,0.00023870674,0.00003626014,0.00010449759,0.00011856779,0.0000397402,0.0023321856],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98720586,0.006351449,0.00092829915,0.0014912084,0.0025000253,0.0015231473],"domain_scores_gemma":[0.9452789,0.03262029,0.0071814563,0.0065671536,0.0033437875,0.0050085257],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008889036,0.0006268205,0.00087824237,0.001015656,0.0007086614,0.0018573365,0.0012813318,0.0010813521,0.009779217],"category_scores_gemma":[0.07017854,0.00031757326,0.00087923213,0.001295103,0.0020312094,0.0013574059,0.0040929434,0.0012944186,0.0008612818],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.019845316,0.008258079,0.32675573,0.0012312583,0.0011573995,0.0013797089,0.008124097,0.015740296,0.029159168,0.0052903136,0.0043976163,0.5786612],"study_design_scores_gemma":[0.0003380403,0.01041602,0.9727098,0.00013828657,0.00027367167,0.00017459168,0.0025893876,0.0011938802,0.005266742,0.0010610058,0.005779342,0.000059150265],"about_ca_topic_score_codex":0.003920957,"about_ca_topic_score_gemma":0.0072783376,"teacher_disagreement_score":0.009779217,"about_ca_system_score_codex":0.0021736068,"about_ca_system_score_gemma":0.0012492482,"threshold_uncertainty_score":0.047010243},"labels":[],"label_agreement":null},{"id":"W2073067066","doi":"10.1080/14926150209556514","title":"New drivers for new science education highways","year":2002,"lang":"en","type":"article","venue":"Canadian Journal of Science Mathematics and Technology Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Curriculum; Argument (complex analysis); Science education; Mathematics education; Focus (optics); Engineering ethics; Sociology; Pedagogy; Engineering; Psychology","score_opus":0.024484998501149383,"score_gpt":0.3155274204900703,"score_spread":0.29104242198892094,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2073067066","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09863276,0.0073125483,0.0066592586,0.64241993,0.0070949495,0.00015097622,0.0024285861,0.0011827273,0.23411831],"genre_scores_gemma":[0.7208684,0.009699038,0.0062819063,0.036238693,0.003300845,0.00015778023,0.001307975,0.00057484384,0.22157054],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.996807,0.0005001175,0.0001096523,0.00035281578,0.0013110047,0.0009194196],"domain_scores_gemma":[0.9850621,0.0015503814,0.00085669284,0.00046527857,0.007501135,0.0045644687],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003285985,0.00038889662,0.00041761823,0.0019095142,0.004625244,0.011589542,0.0014547831,0.0047987727,0.11101048],"category_scores_gemma":[0.012111414,0.0003414768,0.0005715219,0.0021294847,0.0026041649,0.011693417,0.0033641416,0.0056121224,0.007938208],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018997978,0.00019672484,0.021874169,0.00044754276,0.000027231974,0.00030926822,0.004055808,0.0012937576,0.00082623353,0.26635346,0.579177,0.12524883],"study_design_scores_gemma":[0.000022311304,0.0000650892,0.011402686,0.00024966765,0.000016362184,0.00009101107,0.0115300305,0.00076410396,0.00025262317,0.030791102,0.9447604,0.00005473341],"about_ca_topic_score_codex":0.09480842,"about_ca_topic_score_gemma":0.23700368,"teacher_disagreement_score":0.9910795,"about_ca_system_score_codex":0.008920519,"about_ca_system_score_gemma":0.022335898,"threshold_uncertainty_score":0.37136704},"labels":[],"label_agreement":null},{"id":"W2073387991","doi":"10.1080/02602938.2014.911244","title":"Record of assessment moderation practice (RAMP): survey software as a mechanism of continuous quality improvement","year":2014,"lang":"en","type":"article","venue":"Assessment & Evaluation in Higher Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"University of Alberta","keywords":"Moderation; Quality (philosophy); Identification (biology); Quality management; Process (computing); Unit (ring theory); Psychology; Computer science; Process management; Applied psychology; Operations management; Engineering; Mathematics education; Social psychology","score_opus":0.10712062213460302,"score_gpt":0.49623219056414075,"score_spread":0.38911156842953776,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2073387991","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16108085,0.00054280297,0.7719773,0.0021279692,0.00050700165,0.037354104,0.0017491058,0.016517205,0.008143772],"genre_scores_gemma":[0.2946717,0.00027316407,0.6512524,0.00049316336,0.00020875338,0.049280796,0.0007678836,0.0010235197,0.002028637],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.6395755,0.2974971,0.031256977,0.010744131,0.019059563,0.0018668267],"domain_scores_gemma":[0.33253536,0.43073654,0.053372733,0.12533693,0.05509734,0.0029211384],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2989586,0.0015029294,0.001459765,0.006451234,0.0018427899,0.0033348429,0.0026732297,0.0013066,0.0029490944],"category_scores_gemma":[0.4011781,0.0018766015,0.00118601,0.0057967063,0.0023232498,0.004671071,0.004910965,0.0030668993,0.001676952],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0025990661,0.0013582302,0.06364758,0.0036968351,0.0005302697,0.0001126037,0.034516305,0.0017210683,0.014510771,0.0053438097,0.009341357,0.8626221],"study_design_scores_gemma":[0.0059219664,0.030442797,0.4064899,0.007720744,0.0022870877,0.0011475128,0.02336656,0.11413062,0.15723011,0.030979013,0.21837427,0.0019093931],"about_ca_topic_score_codex":0.0008848627,"about_ca_topic_score_gemma":0.0014385434,"teacher_disagreement_score":0.7010414,"about_ca_system_score_codex":0.0016225344,"about_ca_system_score_gemma":0.005080401,"threshold_uncertainty_score":0.86450887},"labels":[],"label_agreement":null},{"id":"W2078247355","doi":"10.7202/1024798ar","title":"Le savoir-évaluer comme politique éducative","year":2014,"lang":"fr","type":"article","venue":"Mesure et évaluation en éducation","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Valuation (finance); Humanities; Philosophy; Political science; Economics","score_opus":0.1337467839041888,"score_gpt":0.43082348753831096,"score_spread":0.2970767036341222,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2078247355","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22429113,0.016052905,0.09394439,0.07098969,0.001347754,0.000881797,0.00070051075,0.00073253794,0.5910592],"genre_scores_gemma":[0.89280015,0.005329762,0.0368176,0.0048670205,0.0002852397,0.0007052537,0.00026167402,0.00028466657,0.05864871],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9533134,0.03233343,0.0016024628,0.00232343,0.009257073,0.001170107],"domain_scores_gemma":[0.93914044,0.030622857,0.0037467096,0.0041351207,0.02030915,0.002045722],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.033738483,0.00070952676,0.00064307003,0.0038091487,0.0031342113,0.011268821,0.0008175412,0.0016895529,0.012352786],"category_scores_gemma":[0.04901269,0.00029551642,0.00049159135,0.004687663,0.0063849827,0.008148899,0.0034352066,0.0027526072,0.0018816288],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00036478823,0.0005916751,0.047848146,0.0021918179,0.00015763225,0.00017094707,0.033867218,0.0024084293,0.0050042574,0.25617447,0.02252197,0.6286987],"study_design_scores_gemma":[0.00008551345,0.0013980767,0.14858258,0.0040374557,0.00017561838,0.00041202942,0.058384042,0.004031711,0.013219179,0.07774392,0.6917125,0.00021734509],"about_ca_topic_score_codex":0.016759744,"about_ca_topic_score_gemma":0.025137898,"teacher_disagreement_score":0.033738483,"about_ca_system_score_codex":0.009423614,"about_ca_system_score_gemma":0.014625796,"threshold_uncertainty_score":0.17842829},"labels":[],"label_agreement":null},{"id":"W2082333579","doi":"10.1017/s0958344000001014","title":"<i>Can computerised testing be authentic?</i>","year":2000,"lang":"en","type":"article","venue":"ReCALL","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Authentic assessment; Computer science; Field (mathematics); Process (computing); Portfolio; Context (archaeology); Computerized adaptive testing; Test (biology); Software testing; Multimedia; Software engineering; Software; Psychology; Pedagogy; Programming language; Psychometrics","score_opus":0.048368330273280864,"score_gpt":0.33047910175775025,"score_spread":0.2821107714844694,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2082333579","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06086471,0.044293903,0.202416,0.4365586,0.009349105,0.00037657123,0.00029078143,0.0015018147,0.24434844],"genre_scores_gemma":[0.8903748,0.011155239,0.04776008,0.029838953,0.0031877619,0.00052112585,0.0002918577,0.00016697931,0.016703265],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.97452873,0.018670585,0.0013882119,0.0011269884,0.0036272274,0.0006582043],"domain_scores_gemma":[0.8947385,0.06898447,0.010211833,0.011740304,0.011845526,0.0024793854],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.022003489,0.00050747936,0.00058304914,0.001239937,0.0012606423,0.008312287,0.0017138851,0.0068584685,0.007765641],"category_scores_gemma":[0.15920123,0.00023554779,0.00051069754,0.0012724422,0.0139156105,0.013447156,0.0039932416,0.0023982113,0.00312213],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005025006,0.00019230117,0.011573314,0.001640352,0.000044428634,0.0006280883,0.007916719,0.0013066456,0.0010406539,0.37389928,0.071775526,0.52948034],"study_design_scores_gemma":[0.000098599005,0.000611426,0.014073176,0.004501973,0.000053489228,0.004073869,0.010110376,0.004250779,0.004577594,0.49871957,0.45868304,0.0002460746],"about_ca_topic_score_codex":0.002128653,"about_ca_topic_score_gemma":0.001551163,"teacher_disagreement_score":0.022003489,"about_ca_system_score_codex":0.0019780018,"about_ca_system_score_gemma":0.002152281,"threshold_uncertainty_score":0.11636692},"labels":[],"label_agreement":null},{"id":"W2085095437","doi":"10.3109/0142159x.2014.956059","title":"Deliberate practice as a framework for evaluating feedback in residency training","year":2014,"lang":"en","type":"article","venue":"Medical Teacher","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":50,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University; St. Michael's Hospital; Hamilton General Hospital; Toronto Western Hospital; Centre for Excellence in Mining Innovation; Hamilton Health Sciences; University of Toronto","funders":"","keywords":"Residency training; Medical education; Training (meteorology); MEDLINE; Psychology; Medicine; Continuing education; Political science","score_opus":0.11777648371752797,"score_gpt":0.4901809480145839,"score_spread":0.3724044642970559,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2085095437","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.38025713,0.0025402596,0.5732401,0.00353768,0.00033290064,0.0057541006,0.00018609907,0.00085106463,0.03330069],"genre_scores_gemma":[0.7224549,0.0003805528,0.2727296,0.00022155892,0.00003714384,0.0033665006,0.000078125966,0.00005160542,0.0006800132],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.7185149,0.23076612,0.0135153085,0.0034457066,0.031972278,0.0017856532],"domain_scores_gemma":[0.646798,0.2701821,0.029091178,0.011726654,0.038663454,0.003538623],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.12893677,0.0010499641,0.0012011318,0.00823796,0.0022243974,0.0052902093,0.001544205,0.0013428847,0.0013192269],"category_scores_gemma":[0.32226703,0.0005566523,0.0011078523,0.0030428432,0.008928781,0.004638292,0.006542788,0.0016929705,0.00024177067],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016063217,0.0008468959,0.10052354,0.0041058213,0.00034626568,0.0004011272,0.11867746,0.01143826,0.0048583797,0.05359531,0.0029843634,0.7006163],"study_design_scores_gemma":[0.0012349786,0.016791563,0.2805987,0.017610993,0.00086408795,0.004047607,0.17497158,0.12916066,0.03292156,0.24216278,0.097872056,0.0017633816],"about_ca_topic_score_codex":0.002575046,"about_ca_topic_score_gemma":0.0034351968,"teacher_disagreement_score":0.12893677,"about_ca_system_score_codex":0.005792003,"about_ca_system_score_gemma":0.008429689,"threshold_uncertainty_score":0.68189096},"labels":[],"label_agreement":null},{"id":"W2086620040","doi":"10.1080/01443410.2014.946890","title":"Exploring plausible causes of differential item functioning in the PISA science assessment: language, curriculum or culture","year":2014,"lang":"en","type":"article","venue":"Educational Psychology","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":45,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Differential item functioning; Curriculum; Psychology; Scientific literacy; Literacy; Mainland China; Cross-cultural studies; Cultural diversity; Scale (ratio); Measurement invariance; Cross-cultural; China; Item response theory; Item analysis; Language proficiency; Variance (accounting); Mathematics education; Psychometrics; Developmental psychology; Pedagogy; Science education; Social psychology; Geography; Sociology; Confirmatory factor analysis","score_opus":0.10948053512327983,"score_gpt":0.46128240685700556,"score_spread":0.35180187173372574,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2086620040","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97038794,0.0003377303,0.020382654,0.00077432377,0.0001195347,0.00024967783,0.000160821,0.000053247455,0.0075341184],"genre_scores_gemma":[0.99431556,0.000054837306,0.004823813,0.0001541135,0.000014348918,0.00022612639,0.000119933095,0.000025855728,0.00026533665],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9338647,0.0418472,0.008290452,0.0039256,0.010318501,0.0017535302],"domain_scores_gemma":[0.81278163,0.1338195,0.018323433,0.01555776,0.017913893,0.0016037266],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.07430344,0.0008927176,0.0009164136,0.0034486498,0.0015484839,0.0026320869,0.0013531916,0.0006525397,0.0020760975],"category_scores_gemma":[0.18994191,0.0005357808,0.0013043464,0.0033865082,0.004274826,0.0025597163,0.0040158606,0.0014680485,0.0003674475],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003563903,0.00015317998,0.90052205,0.00031269583,0.00040767828,0.00017893924,0.026251439,0.00061692897,0.0023910499,0.004543534,0.00055858365,0.06370756],"study_design_scores_gemma":[0.00008410593,0.0006473677,0.95225215,0.00047535397,0.0002181879,0.00059145706,0.019756757,0.006445002,0.006370705,0.009871946,0.0031734877,0.00011345875],"about_ca_topic_score_codex":0.0033218598,"about_ca_topic_score_gemma":0.0043633557,"teacher_disagreement_score":0.92569655,"about_ca_system_score_codex":0.0016070587,"about_ca_system_score_gemma":0.0018837837,"threshold_uncertainty_score":0.39295888},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.02374035340395477,"score_gpt":0.28072218286008715,"score_spread":0.2569818294561324,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2086922103","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.999671,0.000024107165,0.00002587814,0.000021043512,0.0000011347204,0.0000029064277,0.000005977541,9.931804e-7,0.0002469325],"genre_scores_gemma":[0.9998809,0.000014349502,0.000030999505,0.000008856715,0.0000013811703,0.0000037431769,0.000013887867,6.3172797e-7,0.000045205124],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99694854,0.001050869,0.00017900202,0.0002326798,0.0011650522,0.00042395666],"domain_scores_gemma":[0.9883909,0.0038258212,0.0042904206,0.0003146394,0.0012542992,0.0019240611],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002809433,0.00027071266,0.00024112863,0.0011850123,0.00081420364,0.0017182318,0.0003532097,0.00034660913,0.00058331573],"category_scores_gemma":[0.0149024995,0.00014999737,0.00038774125,0.0007387298,0.0009554401,0.0005271804,0.0014846801,0.00079168583,0.00007873195],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004681199,0.00024140716,0.9902817,0.000009878059,0.000034788314,0.000043462096,0.0026023993,0.000050590304,0.00034730887,0.00007044752,0.000055982233,0.0062151877],"study_design_scores_gemma":[0.000001450096,0.00008405945,0.9979073,0.0000049984887,0.000006651118,0.000022985154,0.0016814906,0.00008841397,0.00010113093,0.000022823364,0.000073446936,0.000005379879],"about_ca_topic_score_codex":0.02078827,"about_ca_topic_score_gemma":0.036722746,"teacher_disagreement_score":0.02078827,"about_ca_system_score_codex":0.0013510669,"about_ca_system_score_gemma":0.0013030284,"threshold_uncertainty_score":0.04133457},"labels":[],"label_agreement":null},{"id":"W2087537317","doi":"10.1111/j.1365-2923.2008.03060.x","title":"Use of retrospective pre/post assessments in faculty development","year":2008,"lang":"en","type":"article","venue":"Medical Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Intervention (counseling); Context (archaeology); Medical education; Psychology; Retrospective cohort study; Scale (ratio); Perception; Medicine; Applied psychology; Nursing; Surgery","score_opus":0.06656884565472843,"score_gpt":0.4372180617800095,"score_spread":0.37064921612528107,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2087537317","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8056458,0.0021506853,0.1052188,0.0009792373,0.0015346673,0.0530201,0.003097012,0.0013375424,0.027016213],"genre_scores_gemma":[0.78877544,0.00065141334,0.11831065,0.0007509361,0.00034441956,0.086354434,0.0016512121,0.00023792093,0.002923525],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.8071216,0.13325182,0.02177539,0.011216431,0.023883775,0.0027509653],"domain_scores_gemma":[0.5753434,0.19139563,0.07502398,0.043810748,0.10855042,0.0058757868],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.15272708,0.0023313265,0.001539839,0.004742354,0.0019478293,0.0034155403,0.0028699997,0.0013870524,0.0034687682],"category_scores_gemma":[0.29781437,0.0015775152,0.0017966203,0.0038051845,0.002488167,0.0044738394,0.0037151177,0.0030033546,0.0015119626],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.009444803,0.008264086,0.30818817,0.0071598156,0.0010628357,0.0007115539,0.047320656,0.0029253163,0.011044393,0.0034281807,0.011759177,0.588691],"study_design_scores_gemma":[0.0013641377,0.03298473,0.84933245,0.0033379141,0.0006385216,0.00065159454,0.02371308,0.008575082,0.02557636,0.005927503,0.047289032,0.0006095704],"about_ca_topic_score_codex":0.002016544,"about_ca_topic_score_gemma":0.0042049466,"teacher_disagreement_score":0.15272708,"about_ca_system_score_codex":0.0020790484,"about_ca_system_score_gemma":0.0042108246,"threshold_uncertainty_score":0.80770767},"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,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Formative assessment; Assessment for learning; Mathematics education; Psychology; Curriculum; Pedagogy; Bridge (graph theory)","score_opus":0.1996400635777524,"score_gpt":0.42204256722631234,"score_spread":0.22240250364855993,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2090290510","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97334945,0.0028475288,0.005606914,0.0023303418,0.00009514637,0.00030491094,0.000111118425,0.00008875979,0.015265823],"genre_scores_gemma":[0.9946741,0.00067066925,0.0033433773,0.00027639503,0.00003907026,0.00015286679,0.00003803537,0.000017650143,0.0007878719],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9259647,0.053906396,0.0039327983,0.0022901073,0.012665985,0.0012401054],"domain_scores_gemma":[0.70306545,0.2110507,0.020250367,0.012007223,0.05020304,0.0034231907],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.09745892,0.00061683456,0.0008266872,0.0041934117,0.001897469,0.0059595574,0.0017900994,0.0009516652,0.0017827326],"category_scores_gemma":[0.20594028,0.00029668288,0.0003552806,0.0032625517,0.0038561677,0.005079907,0.0039789993,0.0014659405,0.00041242072],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004230235,0.0010712952,0.33108312,0.0019304814,0.00012058505,0.00048682585,0.25208795,0.0003687867,0.004233129,0.00268626,0.0020714914,0.40343702],"study_design_scores_gemma":[0.00017442848,0.008042185,0.6474378,0.0059319767,0.00021993983,0.0021051303,0.25923786,0.0031930807,0.020971417,0.0104774935,0.04187443,0.0003342583],"about_ca_topic_score_codex":0.007812535,"about_ca_topic_score_gemma":0.010197945,"teacher_disagreement_score":0.09745892,"about_ca_system_score_codex":0.0031345093,"about_ca_system_score_gemma":0.0045695826,"threshold_uncertainty_score":0.5154182},"labels":[],"label_agreement":null},{"id":"W2091897869","doi":"10.1515/1548-923x.2487","title":"High Time for a Change: Psychometric Analysis of Multiple-Choice Questions in Nursing","year":2012,"lang":"en","type":"article","venue":"International Journal of Nursing Education Scholarship","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Multiple choice; Test (biology); Psychology; Cognition; Educational measurement; MEDLINE; Nursing; Medical education; Medicine; Curriculum; Pedagogy","score_opus":0.13924153834215616,"score_gpt":0.5151177927329297,"score_spread":0.37587625439077355,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2091897869","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98787075,0.00028637532,0.008277191,0.00025225268,0.00009283389,0.00091298117,0.00013009421,0.000043476397,0.0021341485],"genre_scores_gemma":[0.9893722,0.00009173104,0.009034175,0.00009857394,0.000029095001,0.00093802914,0.00014197125,0.000019810816,0.00027438454],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.95683426,0.027318316,0.0041104164,0.001325338,0.009868195,0.00054351916],"domain_scores_gemma":[0.7012893,0.2580992,0.01484899,0.007911776,0.015494956,0.0023558277],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.064394936,0.00044252718,0.000622264,0.0020938702,0.00081461226,0.0013576155,0.0010915643,0.0010534939,0.0016607771],"category_scores_gemma":[0.22203955,0.00038107226,0.0019338138,0.0018793537,0.0011445361,0.0030815015,0.0017322123,0.0015087202,0.00028830036],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0031033494,0.0022444,0.7430353,0.000500907,0.00084135385,0.00010150276,0.012043486,0.002253021,0.0019415997,0.0012116744,0.0010558524,0.23166752],"study_design_scores_gemma":[0.00019833482,0.006660456,0.9715837,0.00029065053,0.00016400545,0.00021178999,0.0045558405,0.009995096,0.0021996722,0.0014569389,0.0025780618,0.00010548491],"about_ca_topic_score_codex":0.0009648381,"about_ca_topic_score_gemma":0.0012014993,"teacher_disagreement_score":0.93560505,"about_ca_system_score_codex":0.0011155222,"about_ca_system_score_gemma":0.0012627796,"threshold_uncertainty_score":0.34055704},"labels":[],"label_agreement":null},{"id":"W2094237702","doi":"10.1119/1.4820241","title":"Integrated testlets and the immediate feedback assessment technique","year":2013,"lang":"en","type":"article","venue":"American Journal of Physics","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Trent University","funders":"","keywords":"Context (archaeology); Multiple choice; Set (abstract data type); Test (biology); Reliability (semiconductor); Standard deviation; Computer science; Mathematics education; Statistics; Physics; Psychology; Mathematics; Programming language; Significant difference","score_opus":0.012545079734105244,"score_gpt":0.314171238454659,"score_spread":0.30162615872055376,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2094237702","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07620105,0.0005327561,0.8907543,0.00067011866,0.00035547622,0.0022673379,0.00065497414,0.0046948264,0.023869192],"genre_scores_gemma":[0.23024665,0.00027105463,0.75628716,0.0005773728,0.00028076622,0.0022943767,0.0010719222,0.00039394497,0.008576756],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9835616,0.0076390686,0.0008500791,0.0017360757,0.005671698,0.00054150773],"domain_scores_gemma":[0.9543226,0.027951242,0.0031385932,0.0066167116,0.006738453,0.0012324207],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009211964,0.0009524939,0.0007129935,0.0020949873,0.00035002024,0.0021194194,0.0022634044,0.0012677334,0.011548261],"category_scores_gemma":[0.057587247,0.00060386705,0.0007265042,0.0015068157,0.0008384455,0.0023646194,0.0032363306,0.0022080285,0.004022092],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012619774,0.0011287894,0.008967131,0.00059305446,0.000076659795,0.00041017006,0.0016738713,0.002798203,0.01674055,0.015908945,0.0087580625,0.9416826],"study_design_scores_gemma":[0.0016453045,0.029211666,0.16662642,0.0028156152,0.00059811457,0.018851925,0.0019008339,0.13908273,0.11318753,0.1563474,0.36883897,0.0008935151],"about_ca_topic_score_codex":0.00047054823,"about_ca_topic_score_gemma":0.00054359715,"teacher_disagreement_score":0.011548261,"about_ca_system_score_codex":0.00056701,"about_ca_system_score_gemma":0.0014083701,"threshold_uncertainty_score":0.048718095},"labels":[],"label_agreement":null},{"id":"W2094397051","doi":"10.7202/031735ar","title":"Liens entre anticipation, autoévaluation et le résultat à un examen de rendement scolaire","year":2007,"lang":"fr","type":"article","venue":"Revue des sciences de l éducation","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Humanities; Political science; Anticipation (artificial intelligence); Art; Psychology; Computer science; Artificial intelligence","score_opus":0.31819851517802966,"score_gpt":0.4749758471214142,"score_spread":0.15677733194338456,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2094397051","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9855398,0.000270593,0.0040199184,0.00026217045,0.000081195016,0.00006683297,0.000073961266,0.00009510654,0.009590406],"genre_scores_gemma":[0.9910104,0.00020232519,0.0018683625,0.00008828697,0.00003983396,0.000068281464,0.00007460859,0.000025680873,0.006622256],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.994568,0.0024851253,0.0002238277,0.0004595231,0.001964419,0.00029909782],"domain_scores_gemma":[0.919788,0.06258079,0.0055296617,0.0015713378,0.007959543,0.002570791],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004808995,0.0005325147,0.0004323064,0.0009828373,0.00053455733,0.0018259316,0.0003504406,0.0010691544,0.00599598],"category_scores_gemma":[0.06492824,0.00019959036,0.00035687862,0.00036714197,0.0006803851,0.00090269087,0.0014286246,0.0012491083,0.0007702187],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0062914584,0.0022657618,0.507266,0.0010004044,0.000311956,0.0012065675,0.083452344,0.002266244,0.061664708,0.0034266028,0.0032765546,0.3275715],"study_design_scores_gemma":[0.000072913295,0.0056037693,0.9298774,0.00028033112,0.0001490359,0.00089059584,0.03021809,0.0042523947,0.015821803,0.0024324176,0.010165929,0.00023539842],"about_ca_topic_score_codex":0.0018627439,"about_ca_topic_score_gemma":0.0016450656,"teacher_disagreement_score":0.00599598,"about_ca_system_score_codex":0.0006010512,"about_ca_system_score_gemma":0.0007510279,"threshold_uncertainty_score":0.025432706},"labels":[],"label_agreement":null},{"id":"W2095178943","doi":"10.3200/jexe.76.3.243-258","title":"Subset Testing: Prevalence and Implications for Study Behaviors","year":2008,"lang":"en","type":"article","venue":"The Journal of Experimental Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Mount Allison University","funders":"","keywords":"Psychology; Set (abstract data type); Clinical psychology; Computer science","score_opus":0.1021623673174721,"score_gpt":0.45205098407033967,"score_spread":0.3498886167528676,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2095178943","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99253875,0.0012832424,0.0026633176,0.00067492167,0.00004150004,0.00015174816,0.000086562664,0.000034780827,0.002525223],"genre_scores_gemma":[0.99846846,0.0002111815,0.0009559287,0.00009889009,0.000022804687,0.00009872217,0.000050801198,0.0000105316185,0.00008259117],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.93725055,0.03261997,0.008453901,0.0059855306,0.014330676,0.0013593908],"domain_scores_gemma":[0.6079253,0.2920294,0.06633477,0.017702721,0.012272583,0.0037352878],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.055102997,0.00039659787,0.0005966429,0.0038368097,0.0011065049,0.001711718,0.001407504,0.0012727403,0.0017258478],"category_scores_gemma":[0.23269159,0.00061397755,0.0007775064,0.0016787596,0.0032267987,0.0034243618,0.0027709247,0.001393162,0.00022424056],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017979521,0.00021490308,0.9812491,0.0001028341,0.00006969346,0.00008261226,0.002918707,0.0000320911,0.000362632,0.0002015386,0.0001128546,0.014473174],"study_design_scores_gemma":[0.00001443413,0.0004292411,0.9925891,0.00021975162,0.00008305231,0.0009121221,0.0036112443,0.0005395629,0.0005003671,0.0006344689,0.00044747832,0.00001912022],"about_ca_topic_score_codex":0.001884641,"about_ca_topic_score_gemma":0.0023303097,"teacher_disagreement_score":0.944897,"about_ca_system_score_codex":0.0006703786,"about_ca_system_score_gemma":0.00097497646,"threshold_uncertainty_score":0.29141593},"labels":[],"label_agreement":null},{"id":"W2101512152","doi":"10.26522/brocked.v16i1.77","title":"The Conundrum of Classroom Writing Assessment","year":2007,"lang":"en","type":"article","venue":"Brock Education Journal","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Brock University","funders":"","keywords":"Rubric; Writing assessment; Grading (engineering); Literacy; Mathematics education; Pedagogy; Standards-based assessment; Authentic assessment; Scale (ratio); Psychology; Professional writing; Reflective writing; Educational assessment; Curriculum; Engineering","score_opus":0.02209598557387845,"score_gpt":0.3989192757158156,"score_spread":0.37682329014193716,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2101512152","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.081201084,0.08609097,0.25173035,0.4382356,0.010967446,0.0007819072,0.00053880503,0.0020150663,0.12843883],"genre_scores_gemma":[0.7782285,0.022929955,0.15242909,0.02468896,0.0049542133,0.0010640742,0.00021735764,0.000594408,0.014893409],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.83314353,0.08511772,0.010508859,0.009944564,0.05963633,0.0016489751],"domain_scores_gemma":[0.7136997,0.1530207,0.011847969,0.023957329,0.089721166,0.007753178],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.109348066,0.0007349797,0.0018150692,0.0040549734,0.0032791,0.01020641,0.0044781053,0.0029394177,0.0018275647],"category_scores_gemma":[0.24205077,0.0006297967,0.00057705183,0.002018667,0.011849457,0.009091422,0.007983605,0.008279864,0.0013877176],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013337567,0.0002167996,0.020320622,0.0015888687,0.000104275154,0.000115961375,0.012557771,0.0012722337,0.0008881809,0.094013184,0.03371262,0.83507615],"study_design_scores_gemma":[0.0002015485,0.0011945801,0.06133777,0.015388345,0.00015153903,0.002140681,0.02899236,0.01164064,0.0049566575,0.38699153,0.4865628,0.00044164265],"about_ca_topic_score_codex":0.019472219,"about_ca_topic_score_gemma":0.022540534,"teacher_disagreement_score":0.109348066,"about_ca_system_score_codex":0.006173829,"about_ca_system_score_gemma":0.017465005,"threshold_uncertainty_score":0.57829475},"labels":[],"label_agreement":null},{"id":"W2101528453","doi":"10.55016/ojs/ajer.v52i3.55156","title":"Initial Use of the Perceptions of Assessment Tasks Inventory (PATI) in English Secondary Schools","year":2006,"lang":"en","type":"article","venue":"Alberta Journal of Educational Research","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Perception; Psychology; Mathematics education; Applied psychology; Pedagogy; Medical education","score_opus":0.10069139079290024,"score_gpt":0.4659886682713977,"score_spread":0.36529727747849744,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2101528453","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9975987,0.000063491454,0.0003429793,0.00010006199,0.000013276663,0.0003932922,0.00011029916,0.000007997583,0.0013698012],"genre_scores_gemma":[0.9966292,0.00012490661,0.0010975258,0.00011296399,0.000007457657,0.0007051771,0.00016345001,0.000010750051,0.0011485333],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9931538,0.001973944,0.0010163581,0.0005850566,0.0024104307,0.00086027576],"domain_scores_gemma":[0.98176885,0.0038899072,0.0025784401,0.00081438496,0.008495519,0.002452868],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.017119987,0.00048799498,0.001041641,0.0024943515,0.0019836728,0.0021754724,0.0005521591,0.0006515929,0.0015410425],"category_scores_gemma":[0.025040288,0.0010457804,0.0010789478,0.0016310666,0.0015940147,0.0021170136,0.00364786,0.0024337266,0.000701172],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00042427157,0.002801858,0.7382997,0.00036372556,0.000037540583,0.0006038407,0.19949834,0.00015617226,0.0042119334,0.00063135475,0.0017401444,0.051231068],"study_design_scores_gemma":[0.00004008054,0.0025487144,0.90146154,0.00016558163,0.000025792004,0.0001741833,0.08606199,0.00039928223,0.002128569,0.00022846277,0.006702706,0.00006309717],"about_ca_topic_score_codex":0.009086445,"about_ca_topic_score_gemma":0.018269239,"teacher_disagreement_score":0.017119987,"about_ca_system_score_codex":0.0027836438,"about_ca_system_score_gemma":0.0042755646,"threshold_uncertainty_score":0.09054023},"labels":[],"label_agreement":null},{"id":"W2104009022","doi":"10.5539/ijel.v3n1p41","title":"An Overview of Studies on Diagnostic Testing and its Implications for the Development of Diagnostic Speaking Test","year":2013,"lang":"en","type":"article","venue":"International Journal of English Linguistics","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Diagnostic test; Test (biology); Empirical research; Psychology; Computer science; Medicine; Epistemology","score_opus":0.14929342317387875,"score_gpt":0.44034623423027014,"score_spread":0.29105281105639136,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2104009022","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0114418715,0.9587443,0.0082980385,0.0048692157,0.00064547086,0.00020585432,0.00024038636,0.000035168487,0.015519721],"genre_scores_gemma":[0.112361655,0.8637651,0.019547665,0.001887123,0.00048662274,0.00053227553,0.00032773332,0.00004033363,0.0010514616],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98352456,0.008951818,0.0028457171,0.0009204236,0.0034362487,0.0003212727],"domain_scores_gemma":[0.8314282,0.1479858,0.0057467264,0.0018430748,0.012299598,0.0006965625],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.017552815,0.00071065413,0.0012032333,0.011698918,0.0013394195,0.004194093,0.0015578052,0.0016477039,0.0041776155],"category_scores_gemma":[0.09756416,0.0006450757,0.0011966462,0.014876922,0.002084845,0.0052617057,0.0018627873,0.0017028741,0.0006853218],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020352575,0.00019165681,0.014487221,0.0576449,0.0003275719,0.0004550816,0.007977404,0.0003798364,0.00062134955,0.04260591,0.008088507,0.8670171],"study_design_scores_gemma":[0.00008647823,0.0005660258,0.06294555,0.31333897,0.0022028997,0.004628034,0.028950384,0.0011557655,0.003500365,0.043276206,0.53912765,0.00022169376],"about_ca_topic_score_codex":0.007026652,"about_ca_topic_score_gemma":0.0063385135,"teacher_disagreement_score":0.017552815,"about_ca_system_score_codex":0.0052802493,"about_ca_system_score_gemma":0.008207275,"threshold_uncertainty_score":0.09282923},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.030320027060730614,"score_gpt":0.42869087904920095,"score_spread":0.39837085198847033,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2105451781","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5576613,0.010088329,0.35316706,0.0066699083,0.00032928615,0.0008942871,0.00017751243,0.00038709395,0.070625216],"genre_scores_gemma":[0.95153934,0.001755937,0.043193083,0.00017051023,0.00008937758,0.00065605034,0.00004003309,0.000050146988,0.0025054733],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.95229363,0.038467374,0.0016987859,0.0012080843,0.005936554,0.00039564478],"domain_scores_gemma":[0.9081358,0.07414794,0.007252437,0.00433499,0.004460025,0.0016688736],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.034785565,0.000617564,0.0007696394,0.005578764,0.0014768598,0.01191711,0.0016777656,0.0014989567,0.0016222023],"category_scores_gemma":[0.10054566,0.00035868637,0.00035311715,0.0036866933,0.013881913,0.009962572,0.0053009973,0.0023104127,0.00028052373],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019708356,0.00047035806,0.051817276,0.0014294807,0.00009859348,0.000492739,0.4369698,0.0021914595,0.0061090277,0.12878841,0.0010665038,0.37036923],"study_design_scores_gemma":[0.00012887265,0.0018416012,0.16395037,0.0035380274,0.00015519871,0.004283031,0.3164106,0.020575251,0.01895963,0.40266913,0.06704799,0.00044031028],"about_ca_topic_score_codex":0.0015557848,"about_ca_topic_score_gemma":0.002265697,"teacher_disagreement_score":0.034785565,"about_ca_system_score_codex":0.0022964398,"about_ca_system_score_gemma":0.0033879909,"threshold_uncertainty_score":0.18396586},"labels":[],"label_agreement":null},{"id":"W2106405220","doi":"10.1017/s0261444813000244","title":"Review of doctoral research in language assessment in Canada (2006–2011)","year":2013,"lang":"en","type":"article","venue":"Language Teaching","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Carleton University; Queen's University","funders":"","keywords":"Categorization; Psychology; Vocabulary; Test (biology); Language assessment; Linguistics; Mathematics education","score_opus":0.05336805665149192,"score_gpt":0.4393119507525629,"score_spread":0.385943894101071,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2106405220","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0061204927,0.9712426,0.00017122508,0.008777608,0.0017112272,0.00008910479,0.0012455578,0.000018271654,0.010623793],"genre_scores_gemma":[0.04547351,0.9465874,0.0005981437,0.002888035,0.0005562887,0.00012586227,0.0009921137,0.00002545592,0.002753297],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98632425,0.0020376332,0.0019424317,0.0009903908,0.00727812,0.0014271695],"domain_scores_gemma":[0.86916304,0.023410846,0.007860043,0.001351552,0.08937463,0.008839859],"candidate_categories":["metaresearch","bibliometrics"],"consensus_categories":[],"category_scores_codex":[0.020166155,0.0007459945,0.0020118284,0.028608873,0.006865771,0.009118888,0.0023604487,0.0015937294,0.0052705854],"category_scores_gemma":[0.08084478,0.0007738852,0.0009200387,0.064196736,0.0039007675,0.002195394,0.0026427824,0.0020675547,0.00078041956],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033204758,0.000088096735,0.015098436,0.09688228,0.00035950067,0.00076852937,0.030323537,0.00048284518,0.0007389483,0.010090376,0.18189651,0.6629389],"study_design_scores_gemma":[0.000029998117,0.000057207468,0.06828039,0.07232481,0.00030418998,0.00048850564,0.017714335,0.000060442206,0.00036691828,0.00047454683,0.8398176,0.00008102667],"about_ca_topic_score_codex":0.9371114,"about_ca_topic_score_gemma":0.9678886,"teacher_disagreement_score":0.97983384,"about_ca_system_score_codex":0.1220348,"about_ca_system_score_gemma":0.38819507,"threshold_uncertainty_score":0.8854286},"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,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Test (biology); Psychology; Quarter (Canadian coin); Mathematics education; Medical education; Pedagogy; Medicine; Geography","score_opus":0.02948544944097654,"score_gpt":0.42166555008289597,"score_spread":0.39218010064191944,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2107226435","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24112289,0.15404318,0.2685151,0.047814146,0.0066870404,0.0014026151,0.00017150244,0.0023529497,0.2778906],"genre_scores_gemma":[0.7940065,0.029257894,0.11671379,0.010203653,0.0010047016,0.0010048501,0.0001437557,0.0006390071,0.047025897],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9686812,0.020686403,0.0014526079,0.0013253975,0.007129975,0.0007244766],"domain_scores_gemma":[0.9403295,0.045741986,0.0026065873,0.003546007,0.0066678827,0.0011080067],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.022269933,0.0007997573,0.0010494776,0.002515795,0.0017841578,0.0059665754,0.0020691305,0.0026577674,0.009900821],"category_scores_gemma":[0.08076338,0.00045465212,0.00050135225,0.0013818383,0.0045907665,0.010107724,0.0081630405,0.0033703987,0.0024374954],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003682147,0.00037324644,0.003637181,0.0015427598,0.000028412713,0.00026698897,0.016558636,0.00037555175,0.0018509659,0.029072957,0.0058167293,0.9401084],"study_design_scores_gemma":[0.00024281998,0.0033691921,0.022286441,0.0133410655,0.00017609182,0.0045618177,0.044792213,0.0036554732,0.014211837,0.22305445,0.66992193,0.0003865726],"about_ca_topic_score_codex":0.0013540424,"about_ca_topic_score_gemma":0.0016613615,"teacher_disagreement_score":0.022269933,"about_ca_system_score_codex":0.0028222667,"about_ca_system_score_gemma":0.0026399235,"threshold_uncertainty_score":0.117776096},"labels":[],"label_agreement":null},{"id":"W2107492014","doi":"10.3138/jvme.36.1.100","title":"Getting Started with Curriculum Mapping in a Veterinary Degree Program","year":2009,"lang":"en","type":"review","venue":"Journal of Veterinary Medical Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Curriculum; CLARITY; Process (computing); Curriculum mapping; Curriculum development; Medical education; Resource (disambiguation); Engineering management; Computer science; Medicine; Engineering; Pedagogy; Sociology","score_opus":0.18214046913442627,"score_gpt":0.4915750064036833,"score_spread":0.309434537269257,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2107492014","genre_codex":"empirical","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9160343,0.00060009677,0.01785984,0.020876069,0.0012550799,0.0043099187,0.00023299885,0.0014624209,0.037369218],"genre_scores_gemma":[0.9050998,0.0010501387,0.072245054,0.0030534414,0.00023543245,0.0018581988,0.00036896433,0.00030139246,0.015787598],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9764574,0.012804546,0.001053654,0.0010081866,0.005674283,0.0030018268],"domain_scores_gemma":[0.9266325,0.013116191,0.0044335485,0.0023475613,0.017856086,0.035614144],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.033518963,0.00058185734,0.0007236452,0.0022253925,0.0043482035,0.005879722,0.0020679543,0.0015982615,0.0089800125],"category_scores_gemma":[0.10168358,0.000682672,0.0007766588,0.0018237324,0.0014315343,0.004231537,0.009810465,0.0037812197,0.0029628922],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00037258904,0.006333371,0.046898775,0.0012324854,0.0000490322,0.0015742261,0.13017018,0.0010429792,0.007328885,0.0019690404,0.052368693,0.75065976],"study_design_scores_gemma":[0.00032090966,0.010001461,0.22961989,0.0023238228,0.00010784367,0.0019591155,0.3696677,0.003925622,0.01876643,0.0073295515,0.3554935,0.0004842346],"about_ca_topic_score_codex":0.0016813138,"about_ca_topic_score_gemma":0.0041820016,"teacher_disagreement_score":0.033518963,"about_ca_system_score_codex":0.003289646,"about_ca_system_score_gemma":0.01265515,"threshold_uncertainty_score":0.17726731},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.07001771760809876,"score_gpt":0.3902159675238942,"score_spread":0.32019824991579543,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2108440479","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.54650295,0.0015101499,0.2734479,0.07963615,0.0016385254,0.00049333705,0.00010684465,0.00036953078,0.09629463],"genre_scores_gemma":[0.9840046,0.00008894556,0.014249929,0.0007320755,0.00005536276,0.00008371798,0.0000119417455,0.00003839704,0.000735063],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.82093364,0.13136242,0.010041252,0.0050316,0.029340126,0.0032909808],"domain_scores_gemma":[0.6819415,0.21875693,0.026836384,0.023971943,0.042684034,0.005809252],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.13890614,0.0004608569,0.0007692131,0.003779833,0.005635107,0.012733367,0.0030432497,0.0039338525,0.0011592552],"category_scores_gemma":[0.2755595,0.0007734571,0.0008264262,0.0016601882,0.033663306,0.00790163,0.0074138874,0.011009807,0.00022065306],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017600758,0.0002725214,0.020423952,0.0003215596,0.00006809943,0.0003377488,0.46602207,0.0021816487,0.0019304336,0.4616282,0.0051981965,0.04143958],"study_design_scores_gemma":[0.00012961836,0.00024914925,0.022080366,0.0010306882,0.00007268671,0.00038857802,0.12268746,0.014438343,0.0041883676,0.7757692,0.05868952,0.00027609966],"about_ca_topic_score_codex":0.0042963885,"about_ca_topic_score_gemma":0.005411205,"teacher_disagreement_score":0.13890614,"about_ca_system_score_codex":0.007445518,"about_ca_system_score_gemma":0.0074802767,"threshold_uncertainty_score":0.7346146},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.0812123857192674,"score_gpt":0.5733258516846382,"score_spread":0.49211346596537087,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2108604890","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.047126263,0.05032902,0.005721544,0.8226156,0.0020965163,0.000110226654,0.00041085965,0.00013578839,0.07145417],"genre_scores_gemma":[0.85060185,0.06431985,0.015209504,0.05997874,0.0015233324,0.00026530892,0.00053214806,0.00015411986,0.007415115],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.974506,0.0109554,0.0032436738,0.0027862485,0.005466879,0.003041816],"domain_scores_gemma":[0.84844697,0.08177641,0.01767701,0.0054556443,0.03640116,0.010242785],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.053512078,0.00031045717,0.0005905159,0.0034893318,0.0023405054,0.012473619,0.0022206954,0.0044592516,0.007039082],"category_scores_gemma":[0.0930329,0.0003343809,0.00058302894,0.00878365,0.008317293,0.013693296,0.006555142,0.008501506,0.00081970356],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014796996,0.0003864718,0.04241535,0.002450489,0.00003762682,0.00015532857,0.015313644,0.001295037,0.0005368834,0.41343388,0.03244552,0.49138182],"study_design_scores_gemma":[0.000055966753,0.00042628634,0.14681901,0.013497523,0.000040229537,0.0005637968,0.07023889,0.0017552716,0.0012449285,0.10801927,0.6571845,0.00015423265],"about_ca_topic_score_codex":0.03544124,"about_ca_topic_score_gemma":0.02222487,"teacher_disagreement_score":0.053512078,"about_ca_system_score_codex":0.018089512,"about_ca_system_score_gemma":0.032396883,"threshold_uncertainty_score":0.28300232},"labels":[],"label_agreement":null},{"id":"W2109561464","doi":"10.1002/nur.20104","title":"Nurse editors' views on the peer review process","year":2005,"lang":"en","type":"article","venue":"Research in Nursing & Health","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":43,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Women's Health Research Institute","funders":"","keywords":"Blinding; Peer review; Objectivity (philosophy); Workload; Transparency (behavior); Nursing; Medicine; Medical education; Psychology; Clinical trial; Computer science","score_opus":0.237411425472713,"score_gpt":0.6024689466926302,"score_spread":0.3650575212199172,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2109561464","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013630974,0.030060736,0.008873511,0.6753246,0.24341072,0.00033616895,0.0002421989,0.00048389338,0.027637202],"genre_scores_gemma":[0.29139626,0.07218469,0.047871,0.2138748,0.2974093,0.0016375568,0.0005825693,0.0016602051,0.07338355],"study_design_codex":"not_applicable","study_design_gemma":"qualitative","domain_scores_codex":[0.55734926,0.23116827,0.045653947,0.008598361,0.15157759,0.005652635],"domain_scores_gemma":[0.20469266,0.2687031,0.065616265,0.029728241,0.40814948,0.023110237],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.26097113,0.0012034717,0.0017858478,0.0028138782,0.0059972876,0.021373505,0.0035792736,0.007832354,0.004419601],"category_scores_gemma":[0.672726,0.0010499526,0.0012440248,0.0025756056,0.0061034453,0.008515883,0.005388349,0.01272493,0.003800735],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000403538,0.000099914665,0.0052847727,0.002727366,0.00016428212,0.0010793646,0.017985532,0.000546215,0.0017559963,0.006776761,0.78364277,0.17953335],"study_design_scores_gemma":[0.00004860112,0.00012302751,0.003819693,0.0029442557,0.00006953415,0.000977916,0.005803533,0.0007849263,0.0016360783,0.004679667,0.97892946,0.00018333475],"about_ca_topic_score_codex":0.0026555462,"about_ca_topic_score_gemma":0.0038806556,"teacher_disagreement_score":0.7390289,"about_ca_system_score_codex":0.007720565,"about_ca_system_score_gemma":0.040872496,"threshold_uncertainty_score":0.9113542},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Grading (engineering); Psychology; Mathematics education; English language; Multivariate analysis of variance; Statistics; Engineering; Mathematics","score_opus":0.04392888403571169,"score_gpt":0.44262896175885824,"score_spread":0.39870007772314653,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2112485328","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9835622,0.00042026726,0.009157084,0.0002548019,0.0000371652,0.000571558,0.00013652789,0.000074985175,0.0057854746],"genre_scores_gemma":[0.99441236,0.00008485719,0.0046064835,0.00002219572,0.000011508457,0.00013744262,0.00006755045,0.000014287144,0.00064328156],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.97926325,0.008851162,0.00219875,0.0022471333,0.0062029515,0.0012366921],"domain_scores_gemma":[0.9174977,0.052410282,0.015219703,0.0032044644,0.008862635,0.002805194],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.016898522,0.0009483484,0.00083015655,0.0033329576,0.0017018814,0.0039618863,0.0009623157,0.00049513887,0.0028090216],"category_scores_gemma":[0.049344543,0.0005961421,0.0011446865,0.002893308,0.0011635238,0.0011623224,0.0013402426,0.00072215544,0.00025820525],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001997072,0.00021418264,0.9457048,0.00016802973,0.00021292889,0.0002285701,0.012216184,0.00047802617,0.0007314763,0.00048748698,0.00031785245,0.039040763],"study_design_scores_gemma":[0.00003721968,0.0002177043,0.97367686,0.00015583588,0.00034590953,0.00027309285,0.011679246,0.008557175,0.0013823548,0.0012701555,0.0023108406,0.000093682764],"about_ca_topic_score_codex":0.012489276,"about_ca_topic_score_gemma":0.015998064,"teacher_disagreement_score":0.016898522,"about_ca_system_score_codex":0.002369377,"about_ca_system_score_gemma":0.004415166,"threshold_uncertainty_score":0.089369},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.29237641940546794,"score_gpt":0.5510859877479262,"score_spread":0.25870956834245823,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2116070328","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.89397186,0.00041844405,0.09813229,0.00019223375,0.00012734091,0.0013186177,0.00013550199,0.00023610612,0.005467661],"genre_scores_gemma":[0.913073,0.00052427937,0.07989421,0.00026898735,0.000116369105,0.0036343818,0.00019491986,0.0001571192,0.0021368158],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9395154,0.047427915,0.0033638806,0.0029153635,0.006367211,0.00041019727],"domain_scores_gemma":[0.6944738,0.2487216,0.022762796,0.017106093,0.015704732,0.001230987],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.037438773,0.00073611207,0.00049278885,0.0012075497,0.00091735413,0.0016428737,0.0011022746,0.00094669766,0.00116799],"category_scores_gemma":[0.21999006,0.000555056,0.00032053198,0.0010708567,0.001426186,0.0015625042,0.0019572917,0.0012809291,0.00066098967],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0029120299,0.001885879,0.11458012,0.0022114736,0.00035529106,0.0007919685,0.22303063,0.001853537,0.11902476,0.0054787006,0.0017866923,0.526089],"study_design_scores_gemma":[0.00074646063,0.020407619,0.5165713,0.0025433183,0.00057559216,0.007781459,0.123501666,0.027272105,0.2092096,0.0289061,0.06154568,0.00093917776],"about_ca_topic_score_codex":0.00019331435,"about_ca_topic_score_gemma":0.00026656708,"teacher_disagreement_score":0.96256125,"about_ca_system_score_codex":0.0004902453,"about_ca_system_score_gemma":0.0006471811,"threshold_uncertainty_score":0.19799751},"labels":[],"label_agreement":null},{"id":"W2118761841","doi":"10.7202/000126ar","title":"Enseignement et apprentissage des sciences: résultats de la troisième enquête internationale","year":2002,"lang":"fr","type":"article","venue":"Revue des sciences de l éducation","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Humanities; Political science; Sociology; Art","score_opus":0.31913840906530266,"score_gpt":0.443301512179905,"score_spread":0.12416310311460232,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2118761841","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9786164,0.00868612,0.0011349722,0.0006604737,0.00009984927,0.00012151313,0.00063895877,0.00005731603,0.009984418],"genre_scores_gemma":[0.9620642,0.009874858,0.0029941038,0.0002607951,0.000109926914,0.00020224227,0.0013642499,0.00007688567,0.023052905],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99245465,0.002044149,0.0011088615,0.000823278,0.0024408067,0.0011281447],"domain_scores_gemma":[0.95370936,0.017608419,0.005499605,0.0014772133,0.018006459,0.0036989846],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015823632,0.0006344791,0.0010063411,0.0052640396,0.0025404696,0.0026358678,0.000665682,0.00097023207,0.0045585493],"category_scores_gemma":[0.02559772,0.00028042612,0.00069815316,0.0078710485,0.0013423107,0.0015646107,0.003169983,0.0009586602,0.00089482754],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008607616,0.0005026532,0.50263673,0.0021648637,0.00023422226,0.00048280045,0.14748974,0.0005914828,0.0034376918,0.0010424159,0.0054372326,0.3351194],"study_design_scores_gemma":[0.000017440583,0.001061464,0.8791689,0.00044340236,0.00012249593,0.00033552715,0.05576138,0.00017844005,0.0016082588,0.00016829751,0.061063364,0.00007112247],"about_ca_topic_score_codex":0.068632886,"about_ca_topic_score_gemma":0.13106745,"teacher_disagreement_score":0.068632886,"about_ca_system_score_codex":0.0033152134,"about_ca_system_score_gemma":0.0062923315,"threshold_uncertainty_score":0.1364668},"labels":[],"label_agreement":null},{"id":"W2120301971","doi":"10.3138/jvme.0512-043r","title":"Peer Generation of Multiple-Choice Questions: Student Engagement and Experiences","year":2012,"lang":"en","type":"article","venue":"Journal of Veterinary Medical Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Thematic analysis; Medical education; Psychology; Multiple choice; Student engagement; Resource (disambiguation); Mathematics education; Peer feedback; Process (computing); Significant difference; Qualitative research; Computer science; Medicine; Sociology","score_opus":0.18695066046439923,"score_gpt":0.4902408693508604,"score_spread":0.3032902088864612,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2120301971","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9951704,0.000060940903,0.0029495356,0.00031000687,0.000017902312,0.00019139977,0.000026895426,0.00007680295,0.0011960233],"genre_scores_gemma":[0.9931733,0.000085439795,0.0043451358,0.00015607767,0.00002177945,0.0002555465,0.0000541575,0.000040228213,0.0018682583],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.97182703,0.022144342,0.000898089,0.0012206767,0.002370667,0.0015391433],"domain_scores_gemma":[0.92474717,0.056611545,0.00453965,0.003520566,0.004633457,0.005947713],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.021363603,0.0008617616,0.0011248951,0.0016429056,0.0023374879,0.0031102381,0.0019246212,0.0020415278,0.0026903704],"category_scores_gemma":[0.072417215,0.00060111965,0.000851448,0.000867406,0.0017361599,0.0023121862,0.006712524,0.0021175202,0.0007981951],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007972441,0.0069297417,0.09623557,0.00052523834,0.00008776499,0.0018963775,0.69223416,0.0006825137,0.008062583,0.0006948264,0.0033076154,0.18854636],"study_design_scores_gemma":[0.0003897614,0.016911017,0.14146519,0.0005560556,0.00016598124,0.0068516354,0.7431436,0.0118228085,0.024098778,0.0032015836,0.050799005,0.0005946015],"about_ca_topic_score_codex":0.00050826627,"about_ca_topic_score_gemma":0.0009348499,"teacher_disagreement_score":0.021363603,"about_ca_system_score_codex":0.0009150709,"about_ca_system_score_gemma":0.0012489378,"threshold_uncertainty_score":0.11298287},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université Laval","funders":"","keywords":"Test (biology); Psychology; Language proficiency; Process (computing); Mathematics education; Empirical research; Computer science","score_opus":0.05418180584152639,"score_gpt":0.417552964658704,"score_spread":0.36337115881717763,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2122362059","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9960716,0.00008090044,0.001216433,0.0005325318,0.00001895767,0.00013888397,0.000011370151,0.000016232561,0.0019131047],"genre_scores_gemma":[0.99296796,0.00025939735,0.0033303946,0.0003558495,0.000033881788,0.00014890042,0.00001667783,0.000019655314,0.002867276],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99234456,0.0044353264,0.0003190832,0.00044943244,0.000847509,0.0016041644],"domain_scores_gemma":[0.98438764,0.008667849,0.0017862826,0.00075169635,0.0010980531,0.0033084718],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007090907,0.0009132704,0.0006940333,0.0011775739,0.0074764076,0.002904533,0.0025957774,0.003783207,0.00242489],"category_scores_gemma":[0.026065875,0.0007124443,0.0006381013,0.0009941871,0.0026886323,0.0016174798,0.003125132,0.0041075842,0.00054787344],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006586729,0.015612577,0.09269043,0.0005907764,0.00008675403,0.09080338,0.6864872,0.001088879,0.006645918,0.002685027,0.001792372,0.100858055],"study_design_scores_gemma":[0.00017531101,0.006551826,0.04126441,0.00032412398,0.00007951962,0.033497617,0.8831282,0.0023797809,0.008789723,0.0016023105,0.022056464,0.00015069722],"about_ca_topic_score_codex":0.004929525,"about_ca_topic_score_gemma":0.013003497,"teacher_disagreement_score":0.0074764076,"about_ca_system_score_codex":0.0024064893,"about_ca_system_score_gemma":0.0027270336,"threshold_uncertainty_score":0.0375008},"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,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_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","score_opus":0.0368983349792774,"score_gpt":0.392057273630894,"score_spread":0.3551589386516166,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2122826394","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9968521,0.00011786249,0.00037774813,0.0004045533,0.000020813886,0.000025692627,0.00003889555,0.000014347747,0.002148049],"genre_scores_gemma":[0.9987238,0.00009610568,0.00025435002,0.00011375918,0.0000126035575,0.000019086878,0.00003162345,0.0000050128897,0.00074357167],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.99199694,0.0033728706,0.0006739202,0.00037044514,0.00271547,0.00087032036],"domain_scores_gemma":[0.9602551,0.020910356,0.00562533,0.00083204283,0.007279055,0.0050981785],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006881215,0.00028251042,0.00046119903,0.0011164959,0.0007879096,0.0024060728,0.00039795955,0.0009437928,0.0033906247],"category_scores_gemma":[0.049361054,0.00017270078,0.00059551146,0.0006476321,0.0006184676,0.0007241374,0.0010306686,0.0010596354,0.0005469775],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014967921,0.0014742203,0.75124794,0.0004242794,0.0001807339,0.0009681128,0.09319429,0.0005883319,0.0086819185,0.000548968,0.0024715944,0.13872288],"study_design_scores_gemma":[0.00012900062,0.005507839,0.7857044,0.00028463174,0.000121177356,0.0024612877,0.18580392,0.002059967,0.0039703343,0.00084739283,0.01292187,0.00018828409],"about_ca_topic_score_codex":0.001615206,"about_ca_topic_score_gemma":0.0014604992,"teacher_disagreement_score":0.006881215,"about_ca_system_score_codex":0.0007197597,"about_ca_system_score_gemma":0.00081775355,"threshold_uncertainty_score":0.036391795},"labels":[],"label_agreement":null},{"id":"W2122914175","doi":"10.5206/cjsotl-rcacea.2012.1.3","title":"Students’ Perceptions of the Effectiveness of Assessment Feedback as a Learning Tool in an Introductory Problem-solving Course","year":2012,"lang":"en","type":"article","venue":"The Canadian Journal for the Scholarship of Teaching and Learning","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Sudbury; University of New Brunswick","funders":"","keywords":"Formative assessment; Summative assessment; Pedagogy; Mathematics education; Documentation; Psychology; Computer science","score_opus":0.027510770007052206,"score_gpt":0.3742973487248409,"score_spread":0.3467865787177887,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2122914175","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99791545,0.000084215644,0.0002278685,0.00016323978,0.000010815973,0.000031371466,0.000008858657,0.000009687612,0.0015485411],"genre_scores_gemma":[0.99834526,0.00014505803,0.00038188792,0.00010007281,0.000009116317,0.00004679836,0.000017556216,0.000006399943,0.000947854],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.9885888,0.004853967,0.0010693051,0.000655514,0.0038236727,0.0010086152],"domain_scores_gemma":[0.94322413,0.03705059,0.0076654465,0.0011392137,0.0066625294,0.0042580576],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015824866,0.0004657886,0.00066888373,0.0014639678,0.001435742,0.0060617095,0.0009704655,0.001654651,0.0026071426],"category_scores_gemma":[0.07349587,0.00039368795,0.00079964806,0.0006621823,0.0019794719,0.0027260222,0.002002975,0.002854761,0.0007591958],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0022521473,0.009077494,0.4303839,0.0008447792,0.00024331776,0.0010715369,0.36748064,0.0014164873,0.012080824,0.0011471983,0.002213177,0.17178859],"study_design_scores_gemma":[0.00022461408,0.014562671,0.6536214,0.00067788456,0.00017602208,0.0008531977,0.30861717,0.0031501737,0.007112681,0.0010941493,0.0095500965,0.00036001732],"about_ca_topic_score_codex":0.0026882438,"about_ca_topic_score_gemma":0.0024101702,"teacher_disagreement_score":0.015824866,"about_ca_system_score_codex":0.0017275597,"about_ca_system_score_gemma":0.0013612729,"threshold_uncertainty_score":0.08369088},"labels":[],"label_agreement":null},{"id":"W2124002552","doi":"10.1080/0969594x.2014.967168","title":"Instructional Rounds as a professional learning model for systemic implementation of Assessment for Learning","year":2014,"lang":"en","type":"article","venue":"Assessment in Education Principles Policy and Practice","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":52,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Queen's University","funders":"","keywords":"Professional learning community; Professional development; Psychology; Value (mathematics); Pedagogy; Mathematics education; Session (web analytics); Medical education; Medicine; Computer science","score_opus":0.058823989514014775,"score_gpt":0.5102705274787012,"score_spread":0.45144653796468637,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2124002552","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.23667203,0.0005523081,0.47967136,0.017342234,0.00020435324,0.00394096,0.000091902584,0.0011005884,0.26042435],"genre_scores_gemma":[0.8017721,0.00020082905,0.18455575,0.0005642489,0.000027053004,0.0011399777,0.000038010377,0.000057641402,0.01164435],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.95770925,0.033728816,0.00089190016,0.0015697442,0.004691265,0.0014089942],"domain_scores_gemma":[0.9696437,0.014655311,0.0028472417,0.0046707257,0.005223579,0.0029595057],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.023705699,0.0004270737,0.00023211294,0.0011358649,0.002888883,0.005527039,0.0018150407,0.00089778745,0.0031825032],"category_scores_gemma":[0.02983303,0.00049740664,0.00035759207,0.00068775704,0.007585511,0.003834024,0.0044706226,0.0022351854,0.0008174926],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018421977,0.0016521158,0.03238274,0.00093822833,0.000044196007,0.0005284951,0.11242345,0.009633849,0.005130688,0.40580192,0.008707254,0.42257282],"study_design_scores_gemma":[0.0004405592,0.0047594467,0.057692725,0.0017869486,0.000114737064,0.0018018124,0.09455261,0.0730367,0.011325941,0.28623784,0.46786663,0.00038408232],"about_ca_topic_score_codex":0.013454142,"about_ca_topic_score_gemma":0.033154868,"teacher_disagreement_score":0.023705699,"about_ca_system_score_codex":0.010910666,"about_ca_system_score_gemma":0.029850464,"threshold_uncertainty_score":0.12536925},"labels":[],"label_agreement":null},{"id":"W2124140652","doi":"10.2308/iace-50754","title":"The Power of Giving Feedback: Outcomes from Implementing an Online Peer Assessment System","year":2014,"lang":"en","type":"article","venue":"Issues in Accounting Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":34,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Peer feedback; Peer assessment; Peer review; Work (physics); Quality (philosophy); Psychology; Peer-to-peer; Peer evaluation; Computer science; Medical education; Accounting; Mathematics education; Higher education; Political science; World Wide Web; Business","score_opus":0.030205319576389736,"score_gpt":0.4144605637323217,"score_spread":0.384255244155932,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2124140652","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99385214,0.000033108456,0.0030889534,0.00018338262,0.000016788726,0.0002124162,0.000018875928,0.00013095634,0.002463264],"genre_scores_gemma":[0.9955701,0.000030237235,0.0034673065,0.00006109033,0.0000137342595,0.00011369592,0.000026254336,0.000034448494,0.00068304065],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9500576,0.03820659,0.0022116657,0.0014631902,0.006502651,0.0015582931],"domain_scores_gemma":[0.61741155,0.3208344,0.016667796,0.016897544,0.021336528,0.0068520918],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.032368083,0.00052797364,0.0005894823,0.0012995333,0.0014828079,0.0034147452,0.0017807598,0.0017377505,0.0026410827],"category_scores_gemma":[0.26702073,0.0003477237,0.00054996024,0.0008905113,0.0013695719,0.0026266326,0.004193912,0.0015769769,0.00059707696],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.005192736,0.022706237,0.18215778,0.00082282996,0.00031629668,0.0013762828,0.06282742,0.008588897,0.011794355,0.0012211524,0.0020745567,0.7009213],"study_design_scores_gemma":[0.002767005,0.08120466,0.6034417,0.0012883436,0.0011153199,0.0022481575,0.10020343,0.11989055,0.056075606,0.0082987,0.02267656,0.0007899181],"about_ca_topic_score_codex":0.0019747815,"about_ca_topic_score_gemma":0.0013068408,"teacher_disagreement_score":0.032368083,"about_ca_system_score_codex":0.00094424427,"about_ca_system_score_gemma":0.0018279194,"threshold_uncertainty_score":0.17118078},"labels":[],"label_agreement":null},{"id":"W2126217100","doi":"10.5539/ass.v8n16p192","title":"A Case Study on Peer Review and Lecturer Evaluations in an Academic Setting","year":2012,"lang":"en","type":"article","venue":"Asian Social Science","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Universiti Kebangsaan Malaysia","keywords":"Peer assessment; Presentation (obstetrics); Strengths and weaknesses; Psychology; Medical education; Mathematics education; Peer evaluation; Peer feedback; Higher education; Social psychology; Medicine","score_opus":0.12513150999267597,"score_gpt":0.509895470399519,"score_spread":0.384763960406843,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2126217100","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9797544,0.00052089983,0.006145206,0.0015341442,0.000121022385,0.00042277557,0.00003369126,0.00005090611,0.0114170695],"genre_scores_gemma":[0.98705274,0.00046106018,0.0046923957,0.00026122294,0.00014569449,0.00016763432,0.00002362843,0.000034294775,0.007161217],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.95779127,0.031555865,0.0010759336,0.0017077656,0.005298396,0.0025707304],"domain_scores_gemma":[0.9623403,0.020118078,0.004734936,0.0025323597,0.004521578,0.0057526794],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.014770418,0.0008298015,0.0007191419,0.002131353,0.006127341,0.002940842,0.0024252695,0.0036946905,0.0024865249],"category_scores_gemma":[0.043911662,0.0004594329,0.0008360855,0.001397611,0.002194026,0.0019687805,0.0022955767,0.0023690995,0.0007518561],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00088239275,0.011942287,0.14351031,0.001333731,0.00021437954,0.21848865,0.34124053,0.0033407747,0.013383177,0.008337662,0.009737334,0.24758881],"study_design_scores_gemma":[0.00023680768,0.013635083,0.14528891,0.0009022637,0.0002237954,0.2107805,0.495261,0.01104756,0.018256588,0.0035733797,0.100328304,0.00046582552],"about_ca_topic_score_codex":0.003586599,"about_ca_topic_score_gemma":0.008378563,"teacher_disagreement_score":0.9852296,"about_ca_system_score_codex":0.0030986774,"about_ca_system_score_gemma":0.002677417,"threshold_uncertainty_score":0.07811439},"labels":[],"label_agreement":null},{"id":"W2127042235","doi":"10.37119/ojs2012.v18i2.63","title":"Walking Our Talk About Assessment With Preservice Teachers","year":2013,"lang":"en","type":"article","venue":"in education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"St. Francis Xavier University","funders":"","keywords":"Bachelor; Curriculum; Mathematics education; Psychology; Medical education; Best practice; Peer assessment; Test (biology); Pedagogy; Medicine; Political science","score_opus":0.01818101799266665,"score_gpt":0.3767391790240238,"score_spread":0.3585581610313572,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2127042235","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15210627,0.02070597,0.048737448,0.6720329,0.03171896,0.000336875,0.0001274922,0.00093095464,0.073303126],"genre_scores_gemma":[0.7365234,0.0069583887,0.020304177,0.15858047,0.0061195926,0.00038824507,0.0000811744,0.00049413444,0.070550494],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.9812649,0.014568135,0.00037161852,0.0011275798,0.0017261613,0.0009415497],"domain_scores_gemma":[0.9798151,0.009979279,0.0016915216,0.0017251009,0.002973442,0.0038154523],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011306129,0.0006097866,0.0005208582,0.00091909425,0.010840275,0.008894247,0.0013628632,0.004836609,0.0064323097],"category_scores_gemma":[0.040075082,0.0004747873,0.00054094376,0.0007387425,0.008594017,0.009642108,0.0051356773,0.0140465535,0.0019951009],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010630012,0.0004497257,0.011726817,0.00055522856,0.000051752762,0.0011947866,0.6437151,0.00021681337,0.0045963842,0.031388894,0.13719165,0.16880655],"study_design_scores_gemma":[0.000014405908,0.00025478163,0.0031912872,0.0007684315,0.000022610222,0.001899693,0.26219803,0.00018879598,0.0017896601,0.012481932,0.7171016,0.00008896938],"about_ca_topic_score_codex":0.0024874678,"about_ca_topic_score_gemma":0.0043785516,"teacher_disagreement_score":0.011306129,"about_ca_system_score_codex":0.0020989517,"about_ca_system_score_gemma":0.0033468509,"threshold_uncertainty_score":0.059793174},"labels":[],"label_agreement":null},{"id":"W2127785047","doi":"10.5539/elt.v8n2p109","title":"An Investigation of Saudi English-Major Learners’ Perceptions of Formative Assessment Tasks and Their Learning","year":2015,"lang":"en","type":"article","venue":"English Language Teaching","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Formative assessment; Summative assessment; Psychology; Scope (computer science); Syllabus; Knowledge survey; Mathematics education; Curriculum; Assessment for learning; Perception; Pedagogy; Medical education; Computer science","score_opus":0.01928969685329423,"score_gpt":0.3350048161152735,"score_spread":0.31571511926197926,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2127785047","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9993297,0.00004034296,0.00014557141,0.000042776777,0.0000025298675,0.000012633858,0.0000075060584,0.0000024216165,0.00041659107],"genre_scores_gemma":[0.9992048,0.0000867663,0.00025891553,0.000032313816,0.0000027467447,0.000014349347,0.000013935413,0.0000020164648,0.00038413098],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.9968831,0.0013364363,0.00033937857,0.00014247056,0.0010681757,0.00023031824],"domain_scores_gemma":[0.97215277,0.012994047,0.0048345015,0.000872699,0.0070975,0.0020485332],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007973781,0.00033574537,0.0003014757,0.00074319134,0.00070318126,0.0018353489,0.0003632729,0.0004657717,0.0011826318],"category_scores_gemma":[0.027111845,0.00017150432,0.0003665513,0.00037946447,0.0007132626,0.00081387174,0.0008159434,0.00065799506,0.00030970332],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00067174085,0.0012744836,0.5984371,0.0004489159,0.0000826396,0.00054637674,0.3049669,0.00034749464,0.01630041,0.00040003558,0.0004918453,0.07603218],"study_design_scores_gemma":[0.000051078343,0.0040644333,0.70674247,0.0002475148,0.00008128195,0.00070582423,0.27043766,0.0021906816,0.0068098325,0.00031266938,0.008217008,0.0001396072],"about_ca_topic_score_codex":0.004611671,"about_ca_topic_score_gemma":0.005045776,"teacher_disagreement_score":0.007973781,"about_ca_system_score_codex":0.0009490932,"about_ca_system_score_gemma":0.0010286366,"threshold_uncertainty_score":0.04216987},"labels":[],"label_agreement":null},{"id":"W2128292660","doi":"10.3138/jvme.36.4.403","title":"Value and Benefits of Open-Book Examinations as Assessment for Deep Learning in a Post-graduate Animal Health Course","year":2009,"lang":"en","type":"article","venue":"Journal of Veterinary Medical Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Medical education; Psychology; Perception; Value (mathematics); Graduate students; Medicine; Computer science","score_opus":0.11069069268048912,"score_gpt":0.5007805023999512,"score_spread":0.39008980971946206,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2128292660","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9974044,0.000078615,0.00033774198,0.0002230104,0.000021366703,0.00004941838,0.00000897157,0.000018702302,0.0018576891],"genre_scores_gemma":[0.9974806,0.00007851131,0.0014393453,0.00008199027,0.000020110308,0.00002547589,0.000013716095,0.0000037210484,0.0008566729],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9951526,0.0023773771,0.00023150566,0.00022363102,0.0016470798,0.00036786264],"domain_scores_gemma":[0.97503984,0.014098919,0.002307086,0.0007858703,0.0029039627,0.004864252],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0055982084,0.00032720662,0.00032890486,0.0006363234,0.00080162706,0.0015910706,0.00039365777,0.0005204597,0.0021398582],"category_scores_gemma":[0.035502966,0.0001774016,0.00026312188,0.000278302,0.00043990478,0.00078160135,0.0015380372,0.00091269845,0.00028009826],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0027871807,0.013100269,0.30914873,0.0003833302,0.0000619237,0.00080035825,0.03660877,0.00055363856,0.012767098,0.00042284335,0.0021602707,0.6212056],"study_design_scores_gemma":[0.0001880664,0.039004724,0.85049826,0.00047700247,0.00016201829,0.0011027014,0.08253899,0.0028394596,0.011362318,0.00083500426,0.010799669,0.00019181942],"about_ca_topic_score_codex":0.00077020656,"about_ca_topic_score_gemma":0.0026712676,"teacher_disagreement_score":0.0055982084,"about_ca_system_score_codex":0.00067620946,"about_ca_system_score_gemma":0.0011858495,"threshold_uncertainty_score":0.029606462},"labels":[],"label_agreement":null},{"id":"W2130719536","doi":"","title":"ADMISSION TO TEACHER EDUCATION PROGRAMS: THE PROBLEM AND TWO APPROACHES TO ADDRESSING IT","year":2010,"lang":"en","type":"article","venue":"Canadian Journal of Educational Administration and Policy","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Selection (genetic algorithm); Order (exchange); Face (sociological concept); Mathematics education; Computer science; Psychology; Teacher education; Pedagogy; Sociology; Artificial intelligence; Business","score_opus":0.12291906803968555,"score_gpt":0.41341670323016827,"score_spread":0.2904976351904827,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2130719536","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08427074,0.0043214494,0.23585637,0.6242426,0.0016328022,0.0013188157,0.00020356075,0.00020441125,0.04794932],"genre_scores_gemma":[0.8469371,0.00204931,0.11719105,0.01699806,0.0024733522,0.0019860812,0.00008495336,0.00011805061,0.012161931],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.8586639,0.08836033,0.0070821354,0.008547388,0.029874416,0.007471828],"domain_scores_gemma":[0.7514292,0.17919442,0.020938061,0.013544363,0.02441686,0.010476998],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.08960187,0.001397013,0.002810593,0.008101819,0.0105690975,0.016055914,0.007424039,0.020136986,0.006955685],"category_scores_gemma":[0.20593259,0.0011599787,0.0025050533,0.010067208,0.05429897,0.022492189,0.01617336,0.017012855,0.00075143564],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017729965,0.0004169718,0.013971151,0.000358301,0.00005892005,0.00028302695,0.016731318,0.0014376544,0.00023994978,0.87617415,0.0069547454,0.083196506],"study_design_scores_gemma":[0.00020060895,0.00039589836,0.009951731,0.0007684658,0.00004491255,0.00076408917,0.02859017,0.0077751605,0.00046606298,0.9245301,0.026300725,0.00021210303],"about_ca_topic_score_codex":0.016924407,"about_ca_topic_score_gemma":0.010589787,"teacher_disagreement_score":0.98416096,"about_ca_system_score_codex":0.015839042,"about_ca_system_score_gemma":0.030078128,"threshold_uncertainty_score":0.47386563},"labels":[],"label_agreement":null},{"id":"W2130803473","doi":"10.47678/cjhe.v44i2.183858","title":"When intentions meet reality: Consonance and dissonance in teacher approaches to peer assessment","year":2014,"lang":"en","type":"article","venue":"Canadian Journal of Higher Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Higher Education Research and Development Society of Australasia; Universitetet i Tromsø","keywords":"Consonance and dissonance; Cognitive dissonance; Peer assessment; Psychology; Peer evaluation; Mathematics education; Peer feedback; Teaching method; Pedagogy; Higher education; Social psychology","score_opus":0.10557192750967995,"score_gpt":0.36962017448641865,"score_spread":0.2640482469767387,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2130803473","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8794484,0.0012205279,0.0337043,0.012369649,0.00032508944,0.00021450318,0.000013422081,0.0001225108,0.07258167],"genre_scores_gemma":[0.99522567,0.00014957966,0.0022191335,0.00046703857,0.000027043217,0.00008754677,0.000007098092,0.00004334648,0.0017734453],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.8456526,0.123153366,0.0027028702,0.004619308,0.019396132,0.004475637],"domain_scores_gemma":[0.9116033,0.07048612,0.0055159642,0.0038157792,0.0054452014,0.0031336374],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.05021307,0.0006811396,0.0007607503,0.003066654,0.011502965,0.015844833,0.0034968243,0.003911603,0.0014574579],"category_scores_gemma":[0.14247705,0.0010904159,0.00063071033,0.0012100812,0.04752582,0.0120854145,0.019233944,0.0090488745,0.0003391823],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017840603,0.00001619916,0.0009834442,0.000025823849,0.0000056483573,0.00018115011,0.98382896,0.00003569436,0.00045731413,0.010537874,0.00014599696,0.0037640461],"study_design_scores_gemma":[0.000019797162,0.00007295166,0.0027373773,0.00014974877,0.000011135288,0.0005561635,0.9588978,0.00060001784,0.0006847259,0.020119414,0.016096985,0.00005386505],"about_ca_topic_score_codex":0.0055831014,"about_ca_topic_score_gemma":0.0058162166,"teacher_disagreement_score":0.05021307,"about_ca_system_score_codex":0.004658492,"about_ca_system_score_gemma":0.005884775,"threshold_uncertainty_score":0.26555526},"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,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.019308866200619203,"score_gpt":0.36926440630244384,"score_spread":0.3499555401018246,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2131806896","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8553696,0.003959606,0.015119097,0.044993464,0.0003419201,0.00054666563,0.00060858065,0.0003954977,0.07866564],"genre_scores_gemma":[0.98979133,0.00087594683,0.00392047,0.001027199,0.000014459251,0.000056776888,0.000097316144,0.000049852195,0.004166703],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.96634066,0.008796901,0.0015899892,0.003010779,0.017037626,0.0032241608],"domain_scores_gemma":[0.91618216,0.019471528,0.0055539156,0.0041853166,0.03866137,0.015945746],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.025415948,0.00037949398,0.00044560203,0.0037688427,0.020243084,0.014453441,0.0032385758,0.0010117004,0.0014388353],"category_scores_gemma":[0.03550963,0.00054767524,0.00031710707,0.0071642366,0.021221368,0.0023744453,0.0058537447,0.0032469153,0.0001732277],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.000114211456,0.00021900145,0.108589455,0.0004656782,0.000080667225,0.0008188799,0.61554563,0.002069137,0.0039558606,0.034349434,0.018590285,0.21520174],"study_design_scores_gemma":[0.00002317451,0.00011044654,0.28485215,0.0007936919,0.000045446373,0.0004115462,0.47797215,0.0022372273,0.0014466904,0.0069641555,0.22474541,0.00039794383],"about_ca_topic_score_codex":0.98570627,"about_ca_topic_score_gemma":0.9907783,"teacher_disagreement_score":0.97458404,"about_ca_system_score_codex":0.1637492,"about_ca_system_score_gemma":0.27957034,"threshold_uncertainty_score":0.9699324},"labels":[],"label_agreement":null},{"id":"W2133368865","doi":"10.5539/elt.v6n8p1","title":"Malaysian Primary School ESL Teachers’ Questions during Assessment for Learning","year":2013,"lang":"en","type":"article","venue":"English Language Teaching","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology; Class (philosophy); Mathematics education; Pedagogy; Teaching method; Kuala lumpur; Qualitative research; Cognition","score_opus":0.008446958120055175,"score_gpt":0.3179391097802562,"score_spread":0.309492151660201,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2133368865","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9795828,0.0005140665,0.0072681764,0.0008771589,0.000031895637,0.0004332413,0.00025432027,0.00009262303,0.01094575],"genre_scores_gemma":[0.98076576,0.00037108464,0.010601445,0.00028971626,0.00000946346,0.00034799773,0.00015029738,0.000021065138,0.007443141],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.99580234,0.0020876771,0.00044125476,0.0005872676,0.0007172692,0.00036424128],"domain_scores_gemma":[0.99227023,0.003913092,0.0010021534,0.00045660182,0.0018353496,0.00052260014],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004894462,0.00024461755,0.00030492304,0.0007971765,0.0013042508,0.0016369575,0.00050722784,0.000849603,0.0022548663],"category_scores_gemma":[0.009097732,0.00034604786,0.00021998482,0.0005722051,0.0012460005,0.0014546515,0.0015985903,0.000696299,0.00094706076],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015962662,0.00035406,0.07643279,0.0009870199,0.000009842778,0.0024577386,0.7337306,0.00033940977,0.021531595,0.001563406,0.006322357,0.15611157],"study_design_scores_gemma":[0.000045093035,0.0005944705,0.23311271,0.0012934412,0.00003032833,0.0029700005,0.52455866,0.0015150887,0.018195348,0.0026568635,0.21490033,0.0001276919],"about_ca_topic_score_codex":0.0030714513,"about_ca_topic_score_gemma":0.007504484,"teacher_disagreement_score":0.004894462,"about_ca_system_score_codex":0.001615558,"about_ca_system_score_gemma":0.0022135,"threshold_uncertainty_score":0.025884688},"labels":[],"label_agreement":null},{"id":"W2134230384","doi":"10.26522/brocked.v16i1.29","title":"Assessment - A Powerful Lever for Learning","year":2007,"lang":"en","type":"article","venue":"Brock Education Journal","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":51,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Lever; Assessment for learning; Psychology; Alternative assessment; Pedagogy; Mathematics education; Formative assessment; Engineering","score_opus":0.02843135377807545,"score_gpt":0.41798267199760963,"score_spread":0.3895513182195342,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2134230384","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012935219,0.014637791,0.2038716,0.13758337,0.0013223644,0.00019942195,0.00022804258,0.0014927684,0.6277294],"genre_scores_gemma":[0.7592287,0.012298647,0.12818837,0.015829856,0.002598184,0.0006838882,0.00020504762,0.00074752735,0.08021981],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.982386,0.008399334,0.00082366087,0.002215412,0.0052565075,0.00091918703],"domain_scores_gemma":[0.9591264,0.022668704,0.002020768,0.010797377,0.00293147,0.0024552026],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.021201054,0.0010832874,0.0012332639,0.002814965,0.0041021844,0.019727623,0.0025605967,0.0046678646,0.013222256],"category_scores_gemma":[0.048230477,0.00092049775,0.0007988,0.0023098346,0.03727054,0.035113942,0.021396037,0.009007177,0.0058366866],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000270281,0.000027842378,0.0007008173,0.00013381468,0.000024997049,0.000051878586,0.0024185588,0.00042924346,0.0003549947,0.9193171,0.0067618056,0.06975189],"study_design_scores_gemma":[0.00001934427,0.000038861435,0.0003792161,0.0003288841,0.000010767427,0.00007669722,0.00062343397,0.0005162353,0.0003204597,0.85231864,0.14533104,0.000036404],"about_ca_topic_score_codex":0.0030646126,"about_ca_topic_score_gemma":0.0019984867,"teacher_disagreement_score":0.021201054,"about_ca_system_score_codex":0.0039944155,"about_ca_system_score_gemma":0.006551584,"threshold_uncertainty_score":0.11212325},"labels":[],"label_agreement":null},{"id":"W2135920839","doi":"10.18733/c3qc71","title":"Teaching For Understanding: Spotlighting the Blythe and Associates Pedagogical Model","year":2015,"lang":"en","type":"article","venue":"Cultural and Pedagogical Inquiry","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Curriculum; Field (mathematics); Order (exchange); Computer science; Mathematics education; Deep learning; Engineering ethics; Management science; Pedagogy; Psychology; Artificial intelligence; Engineering","score_opus":0.8727235814564107,"score_gpt":0.5610861116109416,"score_spread":0.31163746984546914,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2135920839","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.029972168,0.012158278,0.26054397,0.4667693,0.0040711286,0.00033986257,0.00004555258,0.00043941173,0.22566041],"genre_scores_gemma":[0.7375196,0.011387782,0.17452979,0.042083606,0.0014571677,0.0014198318,0.000044129858,0.0004675968,0.031090457],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9529682,0.030752417,0.0013260406,0.0027627358,0.0109171355,0.0012734736],"domain_scores_gemma":[0.9552953,0.032085393,0.0019068714,0.003183347,0.0043153944,0.0032135658],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.036028396,0.0009830615,0.0010462197,0.0043452773,0.0055446876,0.01656515,0.0035299016,0.006842724,0.0021276707],"category_scores_gemma":[0.036804188,0.0006862957,0.00083181116,0.0018328932,0.0720941,0.02720103,0.014424548,0.01872822,0.0011855729],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017132643,0.00009427727,0.0006696835,0.00021698282,0.000007039871,0.000084237305,0.050409213,0.00025548472,0.00019307727,0.9086207,0.0073705385,0.032061663],"study_design_scores_gemma":[0.000028804841,0.00009442023,0.00046822318,0.00078182714,0.000015633776,0.000366431,0.022216635,0.001817494,0.000501646,0.8322131,0.14144704,0.000048702062],"about_ca_topic_score_codex":0.0046620704,"about_ca_topic_score_gemma":0.0059274663,"teacher_disagreement_score":0.036028396,"about_ca_system_score_codex":0.009396233,"about_ca_system_score_gemma":0.01726028,"threshold_uncertainty_score":0.19053864},"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,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Test (biology); Mathematics education; Context (archaeology); Psychology; English as a foreign language; Pedagogy; Geography","score_opus":0.024228455206167343,"score_gpt":0.31234216665668124,"score_spread":0.2881137114505139,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2136543334","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.78581476,0.00047870082,0.12903719,0.0030831515,0.00012070544,0.00093750097,0.00025486847,0.0012457072,0.07902728],"genre_scores_gemma":[0.9835218,0.000054717264,0.01281274,0.00010383047,0.000008790301,0.0002342928,0.000054233544,0.000042965487,0.003166637],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9917897,0.003318833,0.00035072555,0.0011186784,0.0029102997,0.0005119099],"domain_scores_gemma":[0.98288983,0.00816076,0.0018774329,0.0027083524,0.0036136652,0.0007500549],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007589388,0.00096048653,0.0007037085,0.003069831,0.0011014548,0.0038095163,0.0031448684,0.0019443717,0.008910361],"category_scores_gemma":[0.031730767,0.0006420445,0.00092838,0.0012553254,0.0038071137,0.007226914,0.0032377525,0.001851499,0.0012821711],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015571383,0.004058977,0.22874852,0.00083785376,0.00024220425,0.0016049065,0.08747581,0.016021729,0.016520908,0.16967756,0.0042266254,0.46902785],"study_design_scores_gemma":[0.00041575055,0.007213834,0.28198656,0.00077461684,0.00033966178,0.0023530703,0.06681259,0.33638874,0.019294394,0.25773498,0.026321001,0.00036478322],"about_ca_topic_score_codex":0.005673409,"about_ca_topic_score_gemma":0.0025357218,"teacher_disagreement_score":0.008910361,"about_ca_system_score_codex":0.004749323,"about_ca_system_score_gemma":0.0031055047,"threshold_uncertainty_score":0.040136993},"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,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Peer feedback; Coaching; Psychology; Peer review; Training (meteorology); Consciousness; Pedagogy; Medical education; Mathematics education; Political science","score_opus":0.14475727150004924,"score_gpt":0.46145459967225444,"score_spread":0.3166973281722052,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2138588257","genre_codex":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11966465,0.17194277,0.4207239,0.07823939,0.032092623,0.068557344,0.00052116835,0.006673516,0.10158471],"genre_scores_gemma":[0.26173317,0.118637726,0.5475936,0.009429468,0.00788373,0.03229143,0.00048738613,0.000345561,0.02159802],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.95064473,0.03364304,0.0032827402,0.0015150117,0.010250403,0.0006640361],"domain_scores_gemma":[0.91374314,0.045441855,0.008969618,0.004948833,0.021880165,0.005016357],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.052730456,0.001061499,0.0016117786,0.0028081147,0.0021563023,0.0016371235,0.0035056686,0.0024439646,0.003564148],"category_scores_gemma":[0.0845205,0.000621153,0.00092130504,0.0011906787,0.0014434996,0.0016424553,0.0027609223,0.002532561,0.003244256],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004227665,0.0009900694,0.0013680676,0.005858953,0.00019284246,0.00058949605,0.0049708784,0.00035230778,0.007774157,0.0011034304,0.057366516,0.91901046],"study_design_scores_gemma":[0.0017402311,0.007786678,0.026984252,0.012292475,0.0005474478,0.0075155436,0.0071777445,0.002843565,0.016326036,0.0055930195,0.9107158,0.00047721044],"about_ca_topic_score_codex":0.0011350862,"about_ca_topic_score_gemma":0.0040508215,"teacher_disagreement_score":0.94726956,"about_ca_system_score_codex":0.00084639475,"about_ca_system_score_gemma":0.0065461425,"threshold_uncertainty_score":0.27886862},"labels":[],"label_agreement":null},{"id":"W2138788260","doi":"","title":"A ROLE FOR RESEARCH IN INITIAL TEACHER EDUCATION ADMISSIONS: A CASE STUDY FROM ONE CANADIAN UNIVERSITY","year":2011,"lang":"en","type":"article","venue":"Canadian Journal of Educational Administration and Policy","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Confidentiality; Identity (music); Teacher education; Pedagogy; Service (business); Psychology; Medical education; Sociology; Political science; Medicine; Business","score_opus":0.19502835079680142,"score_gpt":0.4716467493462753,"score_spread":0.2766183985494739,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2138788260","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9164924,0.0019866633,0.0022724746,0.041120056,0.00043849632,0.0012454093,0.00009938946,0.00008473775,0.03626035],"genre_scores_gemma":[0.98091507,0.0015802021,0.0034072443,0.003316785,0.00007488228,0.00031767823,0.00004186929,0.000047001206,0.010299359],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9453352,0.03118004,0.0017287901,0.0016971892,0.0068630315,0.013195726],"domain_scores_gemma":[0.8988701,0.046172995,0.004443915,0.003458552,0.014721868,0.03233262],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03164966,0.0008472916,0.0012996516,0.0037926228,0.075691946,0.016086157,0.006484766,0.007322723,0.0043200995],"category_scores_gemma":[0.07215737,0.00094970106,0.00094806333,0.007731751,0.022701561,0.0051163253,0.016176123,0.011752668,0.0006470158],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001743556,0.00059041905,0.012895815,0.00044015673,0.000015195874,0.01527496,0.91195786,0.00035985187,0.0013695663,0.012499511,0.0046735867,0.039748754],"study_design_scores_gemma":[0.000016709231,0.0001586276,0.005010426,0.00028656796,0.000012453703,0.00094922667,0.9682639,0.00017909841,0.00032456056,0.00075563125,0.023984296,0.000058472826],"about_ca_topic_score_codex":0.77096766,"about_ca_topic_score_gemma":0.9158056,"teacher_disagreement_score":0.8833891,"about_ca_system_score_codex":0.11661089,"about_ca_system_score_gemma":0.19291034,"threshold_uncertainty_score":0.8460752},"labels":[],"label_agreement":null},{"id":"W2139024900","doi":"10.5430/ijhe.v2n4p143","title":"“What do I do here?”: Higher Order Learning Effects of Enhancing Task Instructions","year":2013,"lang":"en","type":"article","venue":"International Journal of Higher Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Griffith University","keywords":"Psychological intervention; Task (project management); Comprehension; Explication; Psychology; Order (exchange); Reading comprehension; Computer science; Mathematics education; Reading (process); Engineering","score_opus":0.00911962686682635,"score_gpt":0.35042354684175814,"score_spread":0.3413039199749318,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2139024900","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.994118,0.00009959577,0.0020801844,0.00020419653,0.000056665976,0.00045835428,0.000047350084,0.00014775741,0.002787853],"genre_scores_gemma":[0.97491235,0.0003162272,0.020757608,0.00031243844,0.00005378423,0.0012796612,0.00010747337,0.000041150197,0.0022193268],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9982205,0.0010655381,0.00012030918,0.0002131983,0.0002599392,0.00012056336],"domain_scores_gemma":[0.9582659,0.0360671,0.0024255894,0.0013614844,0.00064319733,0.0012366708],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002356738,0.00057775906,0.000601854,0.00043398258,0.00049973675,0.0008153975,0.0007472603,0.0008276693,0.0047312398],"category_scores_gemma":[0.028462552,0.00025921658,0.00036630957,0.00025015956,0.0006157212,0.0009845378,0.0010351441,0.0016221436,0.00051990146],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.014986266,0.108899795,0.012725459,0.0034311917,0.0003116684,0.0003307997,0.029517815,0.0033469987,0.06156062,0.0017746083,0.003264443,0.7598503],"study_design_scores_gemma":[0.018462932,0.2620959,0.4806464,0.0033146574,0.0022970508,0.00088758726,0.022682263,0.015252251,0.13574965,0.009276671,0.04868233,0.00065232784],"about_ca_topic_score_codex":0.00071166933,"about_ca_topic_score_gemma":0.0011278017,"teacher_disagreement_score":0.0047312398,"about_ca_system_score_codex":0.00034351542,"about_ca_system_score_gemma":0.0010477548,"threshold_uncertainty_score":0.015827596},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_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","score_opus":0.25949078778983575,"score_gpt":0.4333496664294458,"score_spread":0.17385887863961003,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2140654065","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.79482794,0.078665785,0.02743819,0.057890836,0.0006268189,0.00052680227,0.000081727114,0.00011563606,0.03982628],"genre_scores_gemma":[0.9775637,0.0103001185,0.008453204,0.0014856278,0.00012783862,0.00028834026,0.000023475935,0.000013804582,0.0017438341],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.95286345,0.03224491,0.0018875719,0.0012444373,0.010581601,0.0011780849],"domain_scores_gemma":[0.80127734,0.16962077,0.0083126025,0.004568855,0.013051407,0.0031690162],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.060785268,0.0003098734,0.00039688303,0.0035121276,0.0040477547,0.009527551,0.0020296548,0.0016720569,0.0007184774],"category_scores_gemma":[0.16369438,0.00037124616,0.00013752645,0.0045399573,0.020739883,0.005822222,0.0039598867,0.002222047,0.000076180826],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000047161615,0.00015663507,0.02167033,0.0006638361,0.000021302541,0.00024074534,0.68897265,0.000115848125,0.000641271,0.017858619,0.0015334728,0.26807806],"study_design_scores_gemma":[0.000039134033,0.00027744775,0.085330725,0.0034452963,0.000044408658,0.0010360098,0.78864384,0.0006115046,0.0011394433,0.030631429,0.08872092,0.000079863275],"about_ca_topic_score_codex":0.067804776,"about_ca_topic_score_gemma":0.13772894,"teacher_disagreement_score":0.067804776,"about_ca_system_score_codex":0.016574552,"about_ca_system_score_gemma":0.02701417,"threshold_uncertainty_score":0.32146704},"labels":[],"label_agreement":null},{"id":"W2142362115","doi":"10.5539/elt.v4n1p214","title":"The Relationship between Peer Assessment and the Cognition Hypothesis","year":2011,"lang":"en","type":"article","venue":"English Language Teaching","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology; Task (project management); Peer assessment; Cognition; Consistency (knowledge bases); Peer feedback; Set (abstract data type); Cognitive psychology; Scale (ratio); Cognitive complexity; Rating scale; Mathematics education; Developmental psychology; Computer science; Artificial intelligence","score_opus":0.07356505215943827,"score_gpt":0.35661802034715906,"score_spread":0.2830529681877208,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2142362115","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9475605,0.0010997223,0.01585493,0.002702938,0.0001449663,0.0003576376,0.00012491657,0.00009247621,0.032061987],"genre_scores_gemma":[0.9966517,0.00017992345,0.0023853756,0.00013789987,0.00007363958,0.00009507032,0.000029187291,0.000009660646,0.00043744818],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9850113,0.0063295565,0.000785462,0.0017759908,0.0054413304,0.0006564061],"domain_scores_gemma":[0.7306654,0.22261843,0.024695115,0.006299531,0.011243779,0.004477782],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010330371,0.0005256888,0.000545443,0.0017753434,0.00064842484,0.0015777315,0.0011811091,0.0011430205,0.004052898],"category_scores_gemma":[0.11180467,0.00023295387,0.0005992197,0.00075655937,0.0039512482,0.0025789973,0.0018405662,0.0015267049,0.0003178419],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014511888,0.0028955669,0.8330605,0.00073485036,0.00068877876,0.0012339428,0.012255253,0.0033446632,0.0026529916,0.034429472,0.001519383,0.10573336],"study_design_scores_gemma":[0.00022796223,0.0020344604,0.9432572,0.00018913193,0.00020197894,0.0011599123,0.0034031302,0.006874777,0.001922685,0.037632797,0.0029814409,0.00011452837],"about_ca_topic_score_codex":0.002432361,"about_ca_topic_score_gemma":0.0008227497,"teacher_disagreement_score":0.010330371,"about_ca_system_score_codex":0.001416599,"about_ca_system_score_gemma":0.0018091042,"threshold_uncertainty_score":0.054632843},"labels":[],"label_agreement":null},{"id":"W2142506285","doi":"10.1017/s0267190509090060","title":"FORMATIVE ASSESSMENT IN LANGUAGE EDUCATION POLICIES: EMERGING LESSONS FROM WALES AND SCOTLAND","year":2009,"lang":"en","type":"article","venue":"Annual Review of Applied Linguistics","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Formative assessment; Devolution (biology); Welsh; Political science; Autonomy; Ideology; Politics; Public administration; Policy learning; State (computer science); Pedagogy; Sociology; Geography; Law","score_opus":0.015926529424384373,"score_gpt":0.41923635554121186,"score_spread":0.4033098261168275,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2142506285","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.43034473,0.045569807,0.0015318635,0.38429525,0.0012767982,0.00015451129,0.00017093049,0.000050498995,0.13660567],"genre_scores_gemma":[0.9566472,0.014121894,0.0007149519,0.019534927,0.00022214599,0.00007634973,0.000064868895,0.00002690843,0.0085907625],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9869982,0.005683569,0.0009822901,0.0005380492,0.0025819007,0.003215913],"domain_scores_gemma":[0.9645972,0.022211242,0.0019346017,0.0007502527,0.0070673674,0.0034394078],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.023261677,0.0003019863,0.00056368345,0.002255764,0.004135553,0.010359609,0.0016866697,0.0031489294,0.0023455345],"category_scores_gemma":[0.03341849,0.0003778102,0.00044014264,0.0037386194,0.007676325,0.0062288265,0.006986962,0.0044720657,0.00019308866],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00048173842,0.00044036916,0.030910166,0.0018269137,0.00004288576,0.0031854585,0.14134979,0.0010642988,0.0010101653,0.3930116,0.026906792,0.39976984],"study_design_scores_gemma":[0.00021707003,0.0009569339,0.14780514,0.005287128,0.00007757491,0.0010142287,0.19973604,0.00090960006,0.0012845185,0.039309885,0.603115,0.0002868623],"about_ca_topic_score_codex":0.3979325,"about_ca_topic_score_gemma":0.42814478,"teacher_disagreement_score":0.3979325,"about_ca_system_score_codex":0.025145236,"about_ca_system_score_gemma":0.043294925,"threshold_uncertainty_score":0.7912326},"labels":[],"label_agreement":null},{"id":"W2143532033","doi":"10.5539/elt.v4n1p156","title":"On the Interaction of Test Washback and Teacher Assessment Literacy: The Case of Iranian EFL Secondary School Teachers","year":2011,"lang":"en","type":"article","venue":"English Language Teaching","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":47,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Summative assessment; Psychology; Literacy; Context (archaeology); Mathematics education; Pedagogy; Test (biology); Formative assessment","score_opus":0.01969515509746019,"score_gpt":0.33426519506656943,"score_spread":0.31457003996910926,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2143532033","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9978582,0.00006878582,0.00009430112,0.0005297439,0.0000015426602,0.0000074427103,0.0000037623336,0.0000022162294,0.001433977],"genre_scores_gemma":[0.9995129,0.000058514568,0.00010736806,0.000050291066,0.0000017959566,0.0000065136956,0.000003134158,0.0000016335428,0.00025779405],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.99359196,0.0045014955,0.00014432664,0.0002442049,0.0004890881,0.0010288854],"domain_scores_gemma":[0.9686441,0.025344742,0.0029304947,0.0006621137,0.0011390172,0.0012794583],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0071696863,0.00025958457,0.00043453666,0.0009821234,0.0043883636,0.0018416581,0.0010216307,0.0016811521,0.0023469855],"category_scores_gemma":[0.025403945,0.00035481484,0.00033729637,0.0007845661,0.0035467395,0.0016275235,0.0018793974,0.0017481719,0.00020002623],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00047301888,0.0015682275,0.38592294,0.000109774744,0.00004867097,0.016327867,0.5559959,0.0003219301,0.0016395504,0.0021188918,0.0008432449,0.034629963],"study_design_scores_gemma":[0.00007150773,0.0005569562,0.35890892,0.00014617071,0.00008680422,0.004416016,0.62711686,0.0010402176,0.001432172,0.0014292302,0.0047372077,0.000057957455],"about_ca_topic_score_codex":0.036230918,"about_ca_topic_score_gemma":0.053407673,"teacher_disagreement_score":0.036230918,"about_ca_system_score_codex":0.0034857122,"about_ca_system_score_gemma":0.002824526,"threshold_uncertainty_score":0.07204008},"labels":[],"label_agreement":null},{"id":"W2144199041","doi":"10.1080/17425960902830385","title":"Responding to the Challenges Posed by Summative Teacher Candidate Evaluation: A collaborative self-study of practicum supervision by faculty","year":2009,"lang":"en","type":"article","venue":"Studying Teacher Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brock University","funders":"","keywords":"Practicum; Formative assessment; Summative assessment; Medical education; Psychology; Pedagogy; Faculty development; Professional development; Medicine","score_opus":0.06576449714630696,"score_gpt":0.4328585198866927,"score_spread":0.3670940227403858,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2144199041","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9909087,0.00010819822,0.0055298726,0.0011419953,0.000057664947,0.00028729383,0.000009130918,0.00006317337,0.0018939498],"genre_scores_gemma":[0.99153167,0.00011687765,0.006125198,0.00027700778,0.000057942398,0.0005075513,0.000018093588,0.00006123078,0.00130449],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.8380441,0.13702305,0.0041520107,0.0047079013,0.011006807,0.005066065],"domain_scores_gemma":[0.6819307,0.24145186,0.023776444,0.017057166,0.02085673,0.014927081],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.115800105,0.0010480883,0.0013179259,0.0025600854,0.017249582,0.010419159,0.004507719,0.0044417246,0.0011046675],"category_scores_gemma":[0.27355814,0.0012338138,0.0009426043,0.0013440953,0.011547188,0.005054895,0.010972077,0.0056446805,0.0005107321],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013201566,0.0011683381,0.017273357,0.00012915296,0.000029621415,0.00063262356,0.9416389,0.00020496418,0.0017109679,0.0006709895,0.0007162773,0.035692804],"study_design_scores_gemma":[0.00013607231,0.0028802457,0.021129383,0.00024016711,0.000054642285,0.0014722602,0.95482624,0.0018527049,0.0055236383,0.0012600682,0.010450921,0.00017373035],"about_ca_topic_score_codex":0.0020619181,"about_ca_topic_score_gemma":0.0050310385,"teacher_disagreement_score":0.115800105,"about_ca_system_score_codex":0.0054731565,"about_ca_system_score_gemma":0.008175443,"threshold_uncertainty_score":0.6124168},"labels":[],"label_agreement":null},{"id":"W2147077701","doi":"10.5539/ells.v1n2p89","title":"Ethics and Validity Stance in Educational Assessment","year":2011,"lang":"en","type":"article","venue":"English Language and Literature Studies","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Engineering ethics; Test (biology); Curriculum; Psychology; Professional ethics; Pedagogy; Engineering","score_opus":0.06718898482724732,"score_gpt":0.404638927251174,"score_spread":0.3374499424239267,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2147077701","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03917068,0.021604106,0.36109754,0.30430746,0.004513932,0.00088465185,0.00009409775,0.00017451319,0.268153],"genre_scores_gemma":[0.8270611,0.004717816,0.12278118,0.02763858,0.00441935,0.0020183236,0.000047350164,0.00020451107,0.011111786],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.61800206,0.31322032,0.012455563,0.0077419803,0.045775883,0.0028041159],"domain_scores_gemma":[0.5139082,0.4170547,0.016676852,0.016018216,0.032431167,0.003910864],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.21611974,0.00083397503,0.001598289,0.006332476,0.006552956,0.013795405,0.0026332878,0.005766386,0.0018041983],"category_scores_gemma":[0.30806246,0.0006374369,0.00086596486,0.0028514955,0.07724661,0.011310752,0.010499267,0.011807154,0.00047783973],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030184388,0.000039458184,0.002425053,0.00026911445,0.000038925955,0.00012619972,0.01171901,0.00044210968,0.00023999512,0.96105003,0.0022131419,0.02140674],"study_design_scores_gemma":[0.00003069792,0.000089112815,0.0018421512,0.0011006184,0.000025788733,0.00026744927,0.004065732,0.0013800489,0.00063117966,0.95867974,0.031841595,0.000045869332],"about_ca_topic_score_codex":0.0030488435,"about_ca_topic_score_gemma":0.00205028,"teacher_disagreement_score":0.21611974,"about_ca_system_score_codex":0.00900859,"about_ca_system_score_gemma":0.015691655,"threshold_uncertainty_score":0.9666639},"labels":[],"label_agreement":null},{"id":"W2147146043","doi":"10.5430/ijhe.v3n3p70","title":"Teachers’ Accounts of Their Perceptions and Practices of Providing Written Feedback to Nursing Students on Their Assignments","year":2014,"lang":"en","type":"article","venue":"International Journal of Higher Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Perception; Competence (human resources); Psychology; Affect (linguistics); Exploratory research; Medical education; Sample (material); Mathematics education; Pedagogy; Medicine; Social psychology; Sociology; Communication","score_opus":0.04166792534371942,"score_gpt":0.4427322760168186,"score_spread":0.40106435067309915,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2147146043","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99333316,0.00023235772,0.0021901731,0.00048206537,0.00002329529,0.00007589552,0.0000858891,0.0000368832,0.0035402572],"genre_scores_gemma":[0.9949779,0.0003530925,0.0013893467,0.000101084486,0.000009778519,0.00010657626,0.00006376315,0.000020106261,0.002978447],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9932433,0.004148531,0.00061608054,0.00040213767,0.0010755841,0.000514438],"domain_scores_gemma":[0.96716845,0.022271834,0.004580105,0.001547588,0.0031681997,0.0012637468],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0053119957,0.0004143475,0.00047474564,0.0012688182,0.0031471609,0.0021589776,0.00070300704,0.0007509832,0.0019637584],"category_scores_gemma":[0.025691899,0.0005102601,0.00027011655,0.00095797685,0.00212566,0.0017824551,0.0020904725,0.0016462887,0.000478648],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000118670636,0.00012858452,0.023449756,0.00014280541,0.000005982379,0.00080132484,0.95053303,0.00013672278,0.0025515156,0.00031561684,0.0007713644,0.021044636],"study_design_scores_gemma":[0.000017881297,0.0003242416,0.033664253,0.00027642178,0.00001551851,0.00096944143,0.9410898,0.0006614718,0.0030480605,0.0002631183,0.019596567,0.00007322017],"about_ca_topic_score_codex":0.0042833895,"about_ca_topic_score_gemma":0.010608658,"teacher_disagreement_score":0.0053119957,"about_ca_system_score_codex":0.0020266783,"about_ca_system_score_gemma":0.0021061632,"threshold_uncertainty_score":0.028092861},"labels":[],"label_agreement":null},{"id":"W2147604064","doi":"10.1097/acm.0b013e3181ed42f2","title":"Which Factors, Personal or External, Most Influence Studentsʼ Generation of Learning Goals?","year":2010,"lang":"en","type":"article","venue":"Academic Medicine","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":54,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia Hospital; University of British Columbia","funders":"","keywords":"Perception; Observer (physics); Psychology; Quality (philosophy); Applied psychology; Medical education; Medicine","score_opus":0.06773309048148761,"score_gpt":0.4094149782330245,"score_spread":0.34168188775153685,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2147604064","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9966473,0.00015997616,0.0011656091,0.0003309038,0.000009903591,0.000023433407,0.000040577972,0.000018721248,0.0016037249],"genre_scores_gemma":[0.99939406,0.000072307565,0.000326706,0.000024814066,0.0000048848606,0.000008552538,0.000025731553,0.0000042426077,0.00013863386],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9968575,0.0013285298,0.00030376477,0.00027373046,0.00088409067,0.00035228764],"domain_scores_gemma":[0.9697679,0.015045591,0.00857849,0.00066219067,0.0027468237,0.0031990192],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0037523946,0.0003019808,0.00033917875,0.0008509856,0.00029550798,0.0016160212,0.00025715987,0.0004307572,0.002702338],"category_scores_gemma":[0.0332717,0.00012773895,0.00033073017,0.0005441085,0.0008007693,0.00066489796,0.0006457581,0.0006094739,0.00046164525],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010961064,0.00023138322,0.96251553,0.000089243884,0.00006824579,0.00007263265,0.002709407,0.00019152256,0.00092756527,0.00013593772,0.00024418393,0.032704726],"study_design_scores_gemma":[0.000007064485,0.00029181078,0.9932039,0.000057753718,0.00004109981,0.00012166538,0.0032115448,0.00085634005,0.001321028,0.00026884407,0.00060265476,0.000016352617],"about_ca_topic_score_codex":0.0015252308,"about_ca_topic_score_gemma":0.0023903602,"teacher_disagreement_score":0.0037523946,"about_ca_system_score_codex":0.00054098916,"about_ca_system_score_gemma":0.0012708785,"threshold_uncertainty_score":0.01984483},"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,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.35000712176952,"score_gpt":0.4785186624063204,"score_spread":0.12851154063680043,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2147628522","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98084027,0.0003375392,0.012328153,0.00050739135,0.000022979091,0.0003131847,0.00047008763,0.0000797025,0.005100605],"genre_scores_gemma":[0.9959928,0.000059051028,0.002909049,0.000020479256,0.000010112802,0.00011099726,0.0004269933,0.00003576854,0.00043473844],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.96066153,0.016240198,0.003578163,0.0024089343,0.015819676,0.0012914796],"domain_scores_gemma":[0.7006871,0.20708704,0.044355348,0.013669944,0.031449337,0.0027512142],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03741658,0.0006228805,0.00070638035,0.008264165,0.0011086657,0.004221463,0.0017212237,0.00083199545,0.0025232069],"category_scores_gemma":[0.19992882,0.0007479638,0.0016397991,0.006322259,0.0020381974,0.003215144,0.0041111982,0.0018907207,0.00047845778],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000042698884,0.000055859837,0.9746601,0.000049315226,0.00009363974,0.00006636975,0.0038087165,0.00047165176,0.0002852333,0.0014487026,0.0003193657,0.018698413],"study_design_scores_gemma":[0.000004311712,0.000103171275,0.9897703,0.000049906645,0.000025141158,0.00014228527,0.00303944,0.0045552505,0.00040359728,0.0008476386,0.001023723,0.000035295245],"about_ca_topic_score_codex":0.010438164,"about_ca_topic_score_gemma":0.008527434,"teacher_disagreement_score":0.03741658,"about_ca_system_score_codex":0.003058731,"about_ca_system_score_gemma":0.0026926014,"threshold_uncertainty_score":0.19788015},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.08174915342893448,"score_gpt":0.3820792831741884,"score_spread":0.3003301297452539,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2148189517","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9969146,0.000024044846,0.001758699,0.000027984537,0.000012046174,0.00014186467,0.00001882563,0.000028451213,0.0010734774],"genre_scores_gemma":[0.9950936,0.0000370403,0.0034779257,0.000029530876,0.000013163279,0.0002469599,0.0000392203,0.000012792389,0.00104981],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9814222,0.011094475,0.0013583626,0.001494109,0.0041179187,0.0005129417],"domain_scores_gemma":[0.9035031,0.058620844,0.011878702,0.005536868,0.017024446,0.0034361298],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01938182,0.0003390672,0.000660887,0.001891392,0.0012667086,0.0014811208,0.0009699783,0.0005243614,0.0022197317],"category_scores_gemma":[0.092006445,0.00030505648,0.00030834277,0.0005282774,0.0009131139,0.0015093969,0.0021548315,0.0007388576,0.00069770956],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0034756798,0.006326817,0.5271579,0.0005042432,0.0002908446,0.00053290115,0.117126346,0.0013742961,0.026126156,0.0011983464,0.0027690658,0.31311736],"study_design_scores_gemma":[0.00036067932,0.014378335,0.8344499,0.00022191256,0.00020720772,0.0009646505,0.08579387,0.016849827,0.036470685,0.0023373358,0.0076447404,0.00032074234],"about_ca_topic_score_codex":0.0009312224,"about_ca_topic_score_gemma":0.0016502441,"teacher_disagreement_score":0.9806182,"about_ca_system_score_codex":0.00055497506,"about_ca_system_score_gemma":0.00067771814,"threshold_uncertainty_score":0.10250211},"labels":[],"label_agreement":null},{"id":"W2149953989","doi":"","title":"Formative assessment: A systematic and artistic process of instruction for supporting school and lifelong learning","year":2012,"lang":"en","type":"article","venue":"Canadian Journal of Education / Revue canadienne de l éducation","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Formative assessment; Lifelong learning; Process (computing); Adaptation (eye); Mathematics education; Pedagogy; Engineering ethics; Knowledge management; Psychology; Computer science; Engineering","score_opus":0.03395313789157107,"score_gpt":0.35764916895792603,"score_spread":0.323696031066355,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2149953989","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04605912,0.007754957,0.8090822,0.014969683,0.0015850902,0.005769431,0.0005670802,0.00453241,0.10968004],"genre_scores_gemma":[0.25436214,0.00633859,0.7231249,0.0012341088,0.0005821489,0.002934794,0.0003009538,0.00031520892,0.010807119],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.93803525,0.037998963,0.002909258,0.001419507,0.019049581,0.00058739015],"domain_scores_gemma":[0.8813711,0.08021983,0.0070579234,0.012493401,0.016318167,0.0025396098],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.07143188,0.0012101203,0.0008736702,0.008040677,0.0027927666,0.009582184,0.0032810331,0.0016541319,0.0029337897],"category_scores_gemma":[0.13832235,0.00048397013,0.0005020052,0.0035983128,0.0066681923,0.006842867,0.004733506,0.0025622621,0.0011110886],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000089674424,0.00039847492,0.0052610887,0.0011931167,0.000043895383,0.0001017242,0.017897861,0.00096771895,0.0034116374,0.04067784,0.0124072265,0.9175498],"study_design_scores_gemma":[0.00025013363,0.0021962118,0.03105172,0.010155631,0.00016577757,0.0020283435,0.021832487,0.009451029,0.019771747,0.23141937,0.6710207,0.0006569298],"about_ca_topic_score_codex":0.003484262,"about_ca_topic_score_gemma":0.006111406,"teacher_disagreement_score":0.07143188,"about_ca_system_score_codex":0.003571943,"about_ca_system_score_gemma":0.018867696,"threshold_uncertainty_score":0.3777724},"labels":[],"label_agreement":null},{"id":"W2155777959","doi":"10.5539/ijel.v2n1p35","title":"The Effect of Student Receptivity to Instructional Feedback on Writing Proficiency among Chinese Speaking English Language Learners","year":2012,"lang":"en","type":"article","venue":"International Journal of English Linguistics","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Paragraph; Receptivity; Psychology; Mathematics education; Corrective feedback; Principal (computer security); Computer science; Medicine","score_opus":0.013271327943449672,"score_gpt":0.3607904881070761,"score_spread":0.34751916016362644,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2155777959","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9995408,0.000018430928,0.00007094783,0.00002763838,0.0000025773243,0.00000885519,0.0000034157415,0.000003322397,0.00032402293],"genre_scores_gemma":[0.99955696,0.000027123197,0.00013339751,0.000016385524,0.0000027327078,0.0000126437835,0.000007842075,0.0000023935327,0.00024053587],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9942086,0.0030898787,0.0005002687,0.00032704647,0.0015175209,0.0003566684],"domain_scores_gemma":[0.92433345,0.051447116,0.011345357,0.0022114376,0.006735566,0.003927006],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0074623986,0.00033029693,0.00038302827,0.00065469905,0.0005965062,0.0017408262,0.00047836977,0.00061941316,0.001380291],"category_scores_gemma":[0.061917268,0.0002503409,0.00043735275,0.00025412854,0.00075234845,0.00073427614,0.0008937279,0.0010417893,0.0002513032],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006326367,0.0010751659,0.91562635,0.00011561515,0.000089139015,0.00044112437,0.04473668,0.00016832528,0.008932556,0.000097162,0.00010250762,0.027982766],"study_design_scores_gemma":[0.000022774671,0.0027520037,0.9626521,0.0000710625,0.00007594273,0.00041452012,0.02762058,0.0009268895,0.0047407527,0.00013602873,0.0005391577,0.00004832773],"about_ca_topic_score_codex":0.0017305879,"about_ca_topic_score_gemma":0.001508904,"teacher_disagreement_score":0.0074623986,"about_ca_system_score_codex":0.0004495067,"about_ca_system_score_gemma":0.0011368115,"threshold_uncertainty_score":0.039465427},"labels":[],"label_agreement":null},{"id":"W2156268470","doi":"10.5206/cjsotl-rcacea.2011.2.5","title":"Writing Helpful Feedback: The Influence of Feedback Type on Students’ Perceptions and Writing Performance","year":2011,"lang":"en","type":"article","venue":"The Canadian Journal for the Scholarship of Teaching and Learning","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":36,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Humber Polytechnic; Carleton University; Mount Royal University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Helpfulness; Humanities; Psychology; Perception; Social psychology; Art","score_opus":0.06405168957209802,"score_gpt":0.3494725568997996,"score_spread":0.2854208673277016,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2156268470","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9976768,0.00021911124,0.0010071389,0.00008314281,0.000027789763,0.000047675963,0.000027245738,0.000027650396,0.00088343193],"genre_scores_gemma":[0.9970409,0.0001857516,0.0016722404,0.0000515549,0.000025424693,0.00007795694,0.00004736686,0.000016956958,0.0008817809],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98779744,0.0055909287,0.0012914174,0.00082634477,0.0040495303,0.00044427376],"domain_scores_gemma":[0.8856984,0.07944068,0.017624833,0.0025250497,0.009982248,0.0047287494],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01043193,0.0004793966,0.00060504605,0.0008164914,0.00036793103,0.0017452767,0.0004342158,0.00052871165,0.0021106608],"category_scores_gemma":[0.0768192,0.00018778077,0.00061494793,0.00046694177,0.0006086575,0.00082195114,0.00087543274,0.0009301938,0.00046467548],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0040713428,0.0035935522,0.66311824,0.0016576903,0.0006010135,0.0004982529,0.032028943,0.0009373049,0.03693633,0.00020004353,0.0011542226,0.25520316],"study_design_scores_gemma":[0.00014635948,0.006408707,0.96463937,0.00030448422,0.00032329414,0.00036191722,0.011910664,0.0019161275,0.010586782,0.0003337381,0.0029508206,0.00011778049],"about_ca_topic_score_codex":0.0006458114,"about_ca_topic_score_gemma":0.0007980772,"teacher_disagreement_score":0.01043193,"about_ca_system_score_codex":0.00033670713,"about_ca_system_score_gemma":0.00065991643,"threshold_uncertainty_score":0.05517},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.06401151606627827,"score_gpt":0.4566933338742858,"score_spread":0.39268181780800754,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2159609851","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96071553,0.00033067845,0.01445856,0.0004667196,0.000037044312,0.007025859,0.0004268307,0.00023839943,0.016300356],"genre_scores_gemma":[0.9315376,0.00036200185,0.052951995,0.00024309706,0.00003468316,0.010535528,0.00025868588,0.000052633823,0.00402367],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.95475256,0.027016846,0.005813431,0.0028335128,0.007963849,0.001619732],"domain_scores_gemma":[0.9352966,0.022130534,0.006743305,0.0064598476,0.026848633,0.0025210904],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.044195637,0.00059095735,0.0005557169,0.004196423,0.0024874099,0.0023115845,0.0014129665,0.00053172756,0.0020146067],"category_scores_gemma":[0.073291585,0.00041830871,0.0002716429,0.0029839056,0.002312854,0.0013039681,0.0031252482,0.0007570963,0.001132535],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00088822603,0.002255439,0.2514513,0.0007885541,0.000029856768,0.00036994877,0.15963951,0.00046729107,0.0112481965,0.0010812179,0.0019613898,0.5698192],"study_design_scores_gemma":[0.00032431594,0.002467649,0.7964455,0.0010251944,0.00006302998,0.00054443744,0.123649575,0.0030743196,0.030028025,0.001700874,0.040468313,0.00020877109],"about_ca_topic_score_codex":0.01155767,"about_ca_topic_score_gemma":0.023019541,"teacher_disagreement_score":0.044195637,"about_ca_system_score_codex":0.004144968,"about_ca_system_score_gemma":0.0062302044,"threshold_uncertainty_score":0.23373169},"labels":[],"label_agreement":null},{"id":"W2160202591","doi":"10.1002/j.2168-9830.2010.tb01072.x","title":"Students' Conceptions of Tutor and Automated Feedback in Professional Writing","year":2010,"lang":"en","type":"article","venue":"Journal of Engineering Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":53,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Australian Research Council; University of Sydney; Carnegie Mellon University","keywords":"TUTOR; Perception; Mathematics education; Peer feedback; Engineering education; Psychology; Relation (database); Pedagogy; Computer science; Engineering; Mechanical engineering","score_opus":0.010193223868575763,"score_gpt":0.36939951109769625,"score_spread":0.3592062872291205,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2160202591","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99644536,0.000114804156,0.00090763235,0.00016555924,0.0000068091745,0.000018198885,0.000004971466,0.0000074772875,0.0023292871],"genre_scores_gemma":[0.99907565,0.000051506282,0.00025696837,0.000028567103,0.0000016910823,0.000013716976,0.000003397431,0.0000024779288,0.0005661206],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9893031,0.0059364433,0.00066013716,0.00068489474,0.0027189439,0.00069634005],"domain_scores_gemma":[0.9757008,0.013454958,0.0044743307,0.00095917046,0.0027268918,0.0026838512],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010798494,0.0002912495,0.0003292098,0.0019404977,0.0019437491,0.009972599,0.0008783868,0.0013201565,0.0015759456],"category_scores_gemma":[0.02898738,0.00047606757,0.0004292488,0.0007044956,0.0060270997,0.0029793696,0.0029532686,0.0017569922,0.00021714675],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022857633,0.0007251232,0.18207024,0.0001288902,0.00003390324,0.00047693495,0.7757616,0.0007574576,0.0030929162,0.009097795,0.00039503604,0.027231568],"study_design_scores_gemma":[0.000115568575,0.0020342164,0.20698354,0.00037204343,0.00009066291,0.0014637122,0.74796236,0.006267902,0.0040347846,0.013269413,0.017196948,0.00020887367],"about_ca_topic_score_codex":0.0017923096,"about_ca_topic_score_gemma":0.0013405847,"teacher_disagreement_score":0.010798494,"about_ca_system_score_codex":0.0022658845,"about_ca_system_score_gemma":0.0018563722,"threshold_uncertainty_score":0.05710858},"labels":[],"label_agreement":null},{"id":"W2160982769","doi":"10.1145/1734263.1734380","title":"Turning exams into a learning experience","year":2010,"lang":"en","type":"article","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Mathematics education; Psychology; Computer science","score_opus":0.021424129341993347,"score_gpt":0.3681600372934324,"score_spread":0.34673590795143905,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2160982769","genre_codex":"empirical","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9416553,0.000409659,0.016028607,0.0010340736,0.00032341148,0.00027446894,0.00011730201,0.00082970824,0.039327472],"genre_scores_gemma":[0.9644549,0.00034073487,0.013458853,0.0005823783,0.00016847343,0.00015710971,0.0002443329,0.0001241525,0.02046912],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9977176,0.0010570815,0.00008704528,0.00027419245,0.00048728133,0.00037676236],"domain_scores_gemma":[0.99320376,0.0032045583,0.0004903556,0.0007211257,0.00040999491,0.0019700918],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001622342,0.0007566646,0.00049100316,0.00057799066,0.0008604881,0.0038072474,0.0010622431,0.0013197523,0.011900929],"category_scores_gemma":[0.012344719,0.00030688927,0.0006100115,0.00038920832,0.00073609594,0.001629661,0.0038973964,0.0015080565,0.002605349],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015348173,0.0052832253,0.040593818,0.00090852263,0.000104032224,0.006073786,0.07903947,0.0014795623,0.14544298,0.0069862227,0.029792286,0.6827614],"study_design_scores_gemma":[0.000585123,0.021169297,0.3157544,0.0009918248,0.00027818469,0.012128662,0.07876962,0.0050559333,0.06208346,0.014933894,0.48763168,0.0006178316],"about_ca_topic_score_codex":0.00024912658,"about_ca_topic_score_gemma":0.00054575474,"teacher_disagreement_score":0.011900929,"about_ca_system_score_codex":0.0003770442,"about_ca_system_score_gemma":0.00032581488,"threshold_uncertainty_score":0.039812565},"labels":[],"label_agreement":null},{"id":"W2162144918","doi":"10.7202/1006438ar","title":"Formative Assessment: Revisiting the territory from the point of view of teachers","year":2011,"lang":"en","type":"article","venue":"McGill Journal of Education / Revue des sciences de l éducation de McGill","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Formative assessment; Negotiation; Point (geometry); Pedagogy; Sociology; Mathematics education; Psychology; Social science","score_opus":0.3482909014551487,"score_gpt":0.45681419665933376,"score_spread":0.10852329520418508,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2162144918","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.35020512,0.020970918,0.47609228,0.045235585,0.00080632244,0.00075446843,0.00010886889,0.00042785046,0.10539852],"genre_scores_gemma":[0.92981356,0.0036153179,0.061844062,0.0013368177,0.00020945196,0.0005699136,0.00004502248,0.00014259809,0.0024232394],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.86919576,0.10529776,0.0051123113,0.0037637232,0.014661943,0.0019685857],"domain_scores_gemma":[0.73375493,0.21495824,0.0066034696,0.018980661,0.023198439,0.0025041793],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.11403736,0.0008225807,0.0010344584,0.0065520774,0.0048543066,0.015820248,0.0035688418,0.002191398,0.0012839974],"category_scores_gemma":[0.16684562,0.00077768456,0.00043279398,0.0034549206,0.03652102,0.025686605,0.0100022415,0.0062223948,0.00025812944],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008838124,0.00011307864,0.007710271,0.00085779757,0.000027550004,0.00036474428,0.64522636,0.0005048879,0.0028358279,0.1332814,0.0008969461,0.20809275],"study_design_scores_gemma":[0.0000654713,0.0007782502,0.026048277,0.0069537726,0.00008740823,0.0024768643,0.5463618,0.0051513724,0.010343419,0.2249795,0.17649333,0.00026048537],"about_ca_topic_score_codex":0.006839964,"about_ca_topic_score_gemma":0.009453095,"teacher_disagreement_score":0.11403736,"about_ca_system_score_codex":0.008025885,"about_ca_system_score_gemma":0.013195109,"threshold_uncertainty_score":0.6030944},"labels":[],"label_agreement":null},{"id":"W2162556894","doi":"10.21432/t21c7r","title":"Utilizing peer interactions to promote learning through a web-based peer assessment system","year":2009,"lang":"en","type":"article","venue":"Canadian Journal of Learning and Technology","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Peer evaluation; Psychology; Ligne; Valuation (finance); Pedagogy; Higher education; Humanities; Political science; Philosophy","score_opus":0.022870909531472555,"score_gpt":0.34798379124800916,"score_spread":0.32511288171653663,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2162556894","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8449707,0.00032794857,0.12408804,0.00081861,0.00011763586,0.0019691875,0.00008641023,0.0031057098,0.024515668],"genre_scores_gemma":[0.8698185,0.00026049555,0.11978216,0.00018248378,0.00010105901,0.0011025108,0.000121063735,0.00016340152,0.008468295],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9932643,0.004245394,0.00030692824,0.00048414635,0.0014239437,0.00027529456],"domain_scores_gemma":[0.9830397,0.011044972,0.0013021643,0.0012121929,0.0020474892,0.0013534795],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005168278,0.0006146418,0.00036380976,0.0012546865,0.0012525563,0.0020603272,0.0010689878,0.00060835533,0.003982828],"category_scores_gemma":[0.022989236,0.00026453228,0.00031466648,0.00048394292,0.00048278572,0.0023288038,0.0035041047,0.0007093019,0.0012633571],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00087313453,0.005407139,0.049777877,0.0010039659,0.00011574266,0.0012241269,0.03208848,0.0021704077,0.048445713,0.0022623911,0.007999502,0.8486315],"study_design_scores_gemma":[0.0012398339,0.027877824,0.3438398,0.0018303602,0.0008204216,0.0064088106,0.051949043,0.09499285,0.13084684,0.016405579,0.3228469,0.0009417445],"about_ca_topic_score_codex":0.00058352813,"about_ca_topic_score_gemma":0.0013649982,"teacher_disagreement_score":0.005168278,"about_ca_system_score_codex":0.0003718857,"about_ca_system_score_gemma":0.0014002162,"threshold_uncertainty_score":0.027332783},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.007292918176272418,"score_gpt":0.38894998801684083,"score_spread":0.3816570698405684,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2167507251","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.113404326,0.12109973,0.6425041,0.06648628,0.004146755,0.0013562762,0.0014710303,0.008384572,0.04114687],"genre_scores_gemma":[0.42199805,0.021437868,0.54297113,0.0031278206,0.0030642308,0.0011663598,0.0011403576,0.0003732296,0.0047208974],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9566417,0.030412754,0.002153307,0.0019257831,0.008348688,0.00051776785],"domain_scores_gemma":[0.7734265,0.14129652,0.015150118,0.010387668,0.05477065,0.0049686055],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.05951421,0.0013980523,0.0012390806,0.0069895466,0.00080610934,0.007054998,0.003336206,0.0035153616,0.00488366],"category_scores_gemma":[0.19458582,0.0004612153,0.0006371727,0.004369089,0.003251604,0.007326131,0.002921549,0.002574365,0.0026307693],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002079735,0.00019818566,0.014451092,0.0005183487,0.000060130104,0.00003717383,0.0004447543,0.0042421557,0.0009994615,0.008236101,0.011824213,0.95878035],"study_design_scores_gemma":[0.00061797845,0.0029132734,0.15759291,0.006719451,0.00028518392,0.0014678268,0.003072107,0.30723798,0.008224366,0.29284033,0.21812671,0.0009019316],"about_ca_topic_score_codex":0.0026360168,"about_ca_topic_score_gemma":0.0021608975,"teacher_disagreement_score":0.05951421,"about_ca_system_score_codex":0.0022846307,"about_ca_system_score_gemma":0.003589103,"threshold_uncertainty_score":0.314745},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.06736112885207077,"score_gpt":0.45624517824613237,"score_spread":0.3888840493940616,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2167980328","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.88953024,0.002012019,0.07161687,0.0018825814,0.000068157504,0.00015469875,0.00006970538,0.00006811202,0.034597598],"genre_scores_gemma":[0.9944149,0.00017347549,0.0049466244,0.00010577286,0.0000121739795,0.000054322303,0.000021131846,0.000010455296,0.0002610098],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.96028346,0.028801193,0.001760899,0.0023029353,0.0062379297,0.0006136644],"domain_scores_gemma":[0.7310295,0.22817512,0.015101825,0.01022615,0.013524362,0.001943087],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.047060907,0.00038001966,0.0006694117,0.0028271396,0.00056585815,0.0052421005,0.0010860974,0.0010095389,0.00085595896],"category_scores_gemma":[0.1964387,0.00031511378,0.00044255165,0.001709631,0.0049663223,0.0047061336,0.0038868557,0.0020530508,0.00013260498],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00042206782,0.00039160976,0.5219948,0.0007004667,0.00036220797,0.00023177265,0.12164846,0.0024954432,0.0026258484,0.08830694,0.00039224405,0.26042813],"study_design_scores_gemma":[0.00004481295,0.0010984243,0.79357266,0.0010284975,0.00013927498,0.0009835673,0.047347896,0.022428984,0.0037250903,0.12076071,0.0086218985,0.00024822744],"about_ca_topic_score_codex":0.001688461,"about_ca_topic_score_gemma":0.0014236389,"teacher_disagreement_score":0.047060907,"about_ca_system_score_codex":0.001169547,"about_ca_system_score_gemma":0.0014111982,"threshold_uncertainty_score":0.24888486},"labels":[],"label_agreement":null},{"id":"W2170205952","doi":"10.5539/elt.v8n1p1","title":"Influence of Instructor Personality on Student Evaluation of Teaching: A Comparison between English Majors and Non-English Majors","year":2014,"lang":"en","type":"article","venue":"English Language Teaching","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology; Neuroticism; Personality; Extraversion and introversion; Class (philosophy); Mathematics education; Scale (ratio); Big Five personality traits; Social psychology; Pedagogy","score_opus":0.023434109967104204,"score_gpt":0.3660662689247755,"score_spread":0.3426321589576713,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2170205952","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99982613,0.000011936766,0.000013944464,0.000005329555,0.0000017421282,0.0000013370908,0.00000470871,6.812715e-7,0.00013404296],"genre_scores_gemma":[0.9998685,0.000011756214,0.000017437736,0.0000044801072,0.0000019823235,0.0000013351178,0.000012057557,5.63238e-7,0.00008186558],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9992347,0.0002583131,0.00008421037,0.00006818679,0.00025556746,0.00009910387],"domain_scores_gemma":[0.99182785,0.002704876,0.0021152704,0.0003278578,0.0011266578,0.0018975489],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011874003,0.00016756597,0.00027634623,0.0006867959,0.00026625922,0.0005430782,0.00013507092,0.0002041348,0.0010259252],"category_scores_gemma":[0.007932656,0.00012731856,0.00029868656,0.0002874123,0.00028013217,0.00024363834,0.00039543078,0.00030886062,0.00021709892],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030076964,0.00023888396,0.9905268,0.000008703306,0.00003095245,0.00007800421,0.0010160273,0.000027342705,0.0011484629,0.000009574495,0.000043055592,0.0065714396],"study_design_scores_gemma":[0.000006124147,0.00040731957,0.9983821,0.0000025961308,0.000008006414,0.00007867,0.0007463336,0.00012470578,0.00016629079,0.000007860621,0.00006666634,0.0000032756354],"about_ca_topic_score_codex":0.0011204531,"about_ca_topic_score_gemma":0.0020976448,"teacher_disagreement_score":0.0011874003,"about_ca_system_score_codex":0.00021584668,"about_ca_system_score_gemma":0.00020341028,"threshold_uncertainty_score":0.0062796474},"labels":[],"label_agreement":null},{"id":"W2170425544","doi":"10.5539/ies.v8n6p46","title":"What Are the Learning Approaches Applied by Undergraduate Students in English Process Writing Based on Gender?","year":2015,"lang":"en","type":"article","venue":"International Education Studies","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Mathematics education; Context (archaeology); Psychology; Process (computing); Writing process; Computer science","score_opus":0.18188207616860608,"score_gpt":0.4501978746869645,"score_spread":0.2683157985183584,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2170425544","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99754864,0.00038736648,0.00017011614,0.00013076187,0.000019017458,0.000009686461,0.000042584026,0.0000038400553,0.0016878657],"genre_scores_gemma":[0.99854195,0.0002873389,0.00012928747,0.00006403943,0.000010173117,0.000010285184,0.000047938804,0.000003901865,0.0009051576],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99894315,0.00024605336,0.0000912649,0.00012502838,0.0004052446,0.00018928984],"domain_scores_gemma":[0.9939237,0.0021536932,0.0021365145,0.00013866938,0.0006815503,0.00096582976],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013783172,0.00026008597,0.00030252282,0.0010012768,0.0003877958,0.0014101134,0.0003038858,0.00036934254,0.0027518743],"category_scores_gemma":[0.007958949,0.00014798882,0.0003007921,0.00048283985,0.0005129852,0.000897796,0.0005168316,0.00038055182,0.0009160069],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033749733,0.00032846816,0.9131765,0.000089507834,0.00005609768,0.00032256753,0.013726715,0.000057038065,0.0029745789,0.00022877696,0.0004200208,0.06828224],"study_design_scores_gemma":[0.000011790534,0.00055197655,0.9774405,0.000081968596,0.000021850612,0.00072119816,0.01864457,0.0001910934,0.0006597788,0.00029606355,0.0013622898,0.000016951286],"about_ca_topic_score_codex":0.0010424872,"about_ca_topic_score_gemma":0.0016760454,"teacher_disagreement_score":0.0027518743,"about_ca_system_score_codex":0.0003326014,"about_ca_system_score_gemma":0.00037679498,"threshold_uncertainty_score":0.009205997},"labels":[],"label_agreement":null},{"id":"W2171832653","doi":"","title":"Alternative sources of feedback and second language writing development in university content courses","year":2011,"lang":"en","type":"article","venue":"DOAJ (DOAJ: Directory of Open Access Journals)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":41,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Content (measure theory); Mathematics education; Higher education; Computer science; Pedagogy; Psychology; Political science; Mathematics","score_opus":0.30687951107584355,"score_gpt":0.5127492825080466,"score_spread":0.20586977143220309,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2171832653","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99540365,0.00009488075,0.0013809412,0.00017541897,0.000013267528,0.00003489882,0.000019517129,0.000031546293,0.0028458175],"genre_scores_gemma":[0.99760795,0.000051982304,0.0014760422,0.00002972403,0.0000054929737,0.00002139823,0.000012824638,0.000011296547,0.0007833973],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.9858943,0.009775677,0.0005447437,0.00061017304,0.0025685471,0.000606496],"domain_scores_gemma":[0.92572737,0.05256181,0.008642966,0.0027072465,0.007374325,0.002986422],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012590527,0.00049587496,0.0005294653,0.0021814043,0.0026793033,0.0046996525,0.0011096906,0.001140388,0.002933091],"category_scores_gemma":[0.06407065,0.0003532732,0.00032134034,0.0009931608,0.0016588555,0.0018573172,0.003248019,0.0011627167,0.0003405074],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00061687554,0.0012839078,0.20787668,0.00051751774,0.000058036752,0.0031434288,0.59530246,0.00054174266,0.012827885,0.0016895854,0.001068057,0.17507383],"study_design_scores_gemma":[0.00013454292,0.0034912908,0.2679798,0.0013037132,0.00012699574,0.0036737642,0.6676894,0.0042009032,0.019208442,0.0031695177,0.028830687,0.00019089678],"about_ca_topic_score_codex":0.0030689149,"about_ca_topic_score_gemma":0.004758579,"teacher_disagreement_score":0.012590527,"about_ca_system_score_codex":0.001946834,"about_ca_system_score_gemma":0.0021320223,"threshold_uncertainty_score":0.0665859},"labels":[],"label_agreement":null},{"id":"W2179337464","doi":"10.5296/jei.v1i2.8381","title":"A Smart Way of Coping with Common Core Challenges - Introduction to CAFA SmartWorkbook","year":2015,"lang":"en","type":"article","venue":"Journal of Educational Issues","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Formative assessment; Coping (psychology); Information and Communications Technology; Mathematics education; Pedagogy; Computer science; Psychology","score_opus":0.08941035088302628,"score_gpt":0.4076068602910477,"score_spread":0.3181965094080214,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2179337464","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06668609,0.009036968,0.49251425,0.10430832,0.014751111,0.0027454991,0.0026895439,0.03530711,0.27196112],"genre_scores_gemma":[0.1262946,0.006924451,0.6310957,0.014980589,0.0026853054,0.0028946684,0.0018994983,0.002999889,0.21022534],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983677,0.00069165416,0.00012374816,0.00017440073,0.0005203502,0.0001221209],"domain_scores_gemma":[0.99488056,0.0025306803,0.00024570443,0.0006064389,0.0009932725,0.0007432857],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028834203,0.0010086255,0.0005635993,0.0016784422,0.0017089987,0.0036717467,0.0014655392,0.002701744,0.021270877],"category_scores_gemma":[0.008551301,0.00035816064,0.00043938574,0.0009212672,0.0015935738,0.0045625023,0.0027043973,0.0032774813,0.008822614],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007177112,0.00035087252,0.0022067525,0.00033949374,0.000010054684,0.0006372614,0.0071218302,0.00067593757,0.005519476,0.018664015,0.40308824,0.5613142],"study_design_scores_gemma":[0.000017790042,0.00020311898,0.0027462977,0.00037511665,0.000005745114,0.0014318897,0.0026784705,0.0011354538,0.0019509027,0.0071247155,0.98225963,0.00007095477],"about_ca_topic_score_codex":0.001334802,"about_ca_topic_score_gemma":0.0027279127,"teacher_disagreement_score":0.021270877,"about_ca_system_score_codex":0.00081215537,"about_ca_system_score_gemma":0.0015921072,"threshold_uncertainty_score":0.07115817},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.13742489297286617,"score_gpt":0.5795117938372106,"score_spread":0.44208690086434443,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2183435816","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00024926834,0.9972396,0.0005561354,0.0008709863,0.00016866504,0.00007580891,0.00021362817,0.000011542816,0.0006142973],"genre_scores_gemma":[0.0030696886,0.99308175,0.002676064,0.00050985155,0.00011715362,0.0001618511,0.00025237413,0.000008908911,0.00012238573],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.9841541,0.003658684,0.006487186,0.0011018958,0.004334907,0.00026318192],"domain_scores_gemma":[0.9449297,0.036479093,0.007558456,0.00096644164,0.009522762,0.0005435169],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.025188955,0.0012994491,0.0053110137,0.017954974,0.00084608834,0.003551908,0.0033269657,0.002146365,0.0025024132],"category_scores_gemma":[0.06414508,0.0008883267,0.0025402955,0.015681155,0.0023816095,0.0041477755,0.0028436505,0.0024254657,0.00062873133],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001248835,0.000075461816,0.0021587333,0.15369926,0.0005238173,0.00005114418,0.00046485334,0.00024195107,0.00025422088,0.0044345963,0.013288813,0.8246823],"study_design_scores_gemma":[0.000109902474,0.00023915106,0.014817286,0.45674878,0.005636623,0.00071982417,0.0010867497,0.00033010874,0.0010776788,0.0052996716,0.5137883,0.00014591766],"about_ca_topic_score_codex":0.010991415,"about_ca_topic_score_gemma":0.01972708,"teacher_disagreement_score":0.025188955,"about_ca_system_score_codex":0.0047452627,"about_ca_system_score_gemma":0.02158045,"threshold_uncertainty_score":0.13321352},"labels":[],"label_agreement":null},{"id":"W2183500712","doi":"10.3968/7840","title":"On the Analysis of the Effective Implementation of Peer Feedback in Non-English Majors’ Writing","year":2015,"lang":"en","type":"article","venue":"Studies in literature and language","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Peer feedback; Computer science; Process (computing); Checklist; Second language writing; Key (lock); Mathematics education; Psychology; Second language; Cognitive psychology; Linguistics","score_opus":0.019006474254120956,"score_gpt":0.39053473684621026,"score_spread":0.3715282625920893,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2183500712","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97406816,0.0015152923,0.006201848,0.00046926775,0.000049913815,0.0006868857,0.000084893785,0.000039714843,0.016884057],"genre_scores_gemma":[0.99607855,0.00051816186,0.002030238,0.0000398294,0.0000143204215,0.0001341384,0.00004758116,0.000007296905,0.0011297805],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9625146,0.021542946,0.0033116648,0.0012305934,0.010259342,0.0011409661],"domain_scores_gemma":[0.74432415,0.19082057,0.017946826,0.0039059808,0.03879728,0.0042051882],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02503106,0.00031357488,0.0005407618,0.003144266,0.0010187557,0.0019965265,0.00088053534,0.00048245312,0.002180711],"category_scores_gemma":[0.14834717,0.00015254664,0.0006357545,0.0018196995,0.0009754262,0.0016040785,0.0010251206,0.0006006002,0.0003032809],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008317579,0.0012419209,0.30991003,0.0032009073,0.00025696328,0.0009734219,0.088319406,0.00071845955,0.004713636,0.003857371,0.0014525233,0.5845235],"study_design_scores_gemma":[0.00008588048,0.003044642,0.8755363,0.0019916415,0.0003477606,0.00097300817,0.087063655,0.0034896608,0.008365343,0.0022197503,0.016773367,0.00010901752],"about_ca_topic_score_codex":0.001589551,"about_ca_topic_score_gemma":0.002173246,"teacher_disagreement_score":0.02503106,"about_ca_system_score_codex":0.0019307386,"about_ca_system_score_gemma":0.004048937,"threshold_uncertainty_score":0.13237846},"labels":[],"label_agreement":null},{"id":"W2186483225","doi":"10.37514/wac-j.2005.16.1.06","title":"Dangerous Partnerships: How Competence Testing Can Sabotage WAC","year":2005,"lang":"en","type":"article","venue":"The WAC Journal","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Competence (human resources); Business; Engineering; Psychology; Social psychology","score_opus":0.14391756235668948,"score_gpt":0.3537266698029337,"score_spread":0.20980910744624423,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2186483225","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09865045,0.002572941,0.15244511,0.2748281,0.002676474,0.0009100652,0.00014901359,0.0020784382,0.46568936],"genre_scores_gemma":[0.8845183,0.0011185347,0.04382172,0.030879004,0.0003669381,0.0009891241,0.00012520507,0.0007343029,0.037446998],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.876719,0.08675022,0.0024302248,0.0068111597,0.015988743,0.01130063],"domain_scores_gemma":[0.85220265,0.08228175,0.009020154,0.016550291,0.017038818,0.022906344],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.07510418,0.0010787109,0.00086106354,0.0033375002,0.025319317,0.024211787,0.0053924182,0.011017374,0.024961757],"category_scores_gemma":[0.18948403,0.001480953,0.001160103,0.0023241774,0.03323773,0.029224325,0.034560177,0.01644999,0.0076453746],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017006972,0.000927622,0.02527572,0.00033032257,0.000072351075,0.0034749666,0.08337364,0.0034458993,0.0010130036,0.58271945,0.092993915,0.20620301],"study_design_scores_gemma":[0.00013006513,0.00038637122,0.004978027,0.001239572,0.000042637384,0.0014099297,0.07409991,0.0072179656,0.0019196377,0.55315346,0.35519454,0.00022790447],"about_ca_topic_score_codex":0.020311559,"about_ca_topic_score_gemma":0.021448312,"teacher_disagreement_score":0.07510418,"about_ca_system_score_codex":0.012883981,"about_ca_system_score_gemma":0.036984127,"threshold_uncertainty_score":0.3971936},"labels":[],"label_agreement":null},{"id":"W2187181284","doi":"","title":"Re/Viewing Student Success in an Era of Accountability","year":2011,"lang":"en","type":"article","venue":"DOAJ (DOAJ: Directory of Open Access Journals)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Accountability; Student achievement; Perspective (graphical); Success factors; Point (geometry); Academic achievement; Mathematics education; Student engagement; Psychology; Public relations; Political science; Pedagogy; Computer science; Business","score_opus":0.43951187835644734,"score_gpt":0.6218540625177319,"score_spread":0.18234218416128456,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2187181284","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.26959726,0.012120447,0.015459306,0.3805767,0.004070633,0.00006746001,0.00034824348,0.00035380715,0.31740606],"genre_scores_gemma":[0.98344904,0.0024995033,0.0011586096,0.002359638,0.00042789977,0.000024914996,0.000049163365,0.0000958142,0.009935371],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.987867,0.0046870136,0.00037049156,0.00052891305,0.0045687603,0.0019778977],"domain_scores_gemma":[0.9854578,0.0033338093,0.0019694404,0.0010205557,0.0047727707,0.003445585],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009585774,0.0008545288,0.00077994337,0.004676133,0.014213816,0.022532655,0.0016693518,0.002143704,0.0031108132],"category_scores_gemma":[0.013875381,0.00031690547,0.00052716123,0.004192255,0.042096112,0.016982244,0.015256758,0.008664936,0.00042406947],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006238019,0.00006555092,0.025818419,0.00018672278,0.000031549436,0.00047350224,0.48196974,0.000492225,0.00067300803,0.40751916,0.026731966,0.05597587],"study_design_scores_gemma":[0.000012862907,0.00009017349,0.043064725,0.000612229,0.000047075606,0.00020470798,0.38997766,0.0009639158,0.0007195777,0.10561739,0.45854738,0.00014229503],"about_ca_topic_score_codex":0.48957446,"about_ca_topic_score_gemma":0.60608774,"teacher_disagreement_score":0.48957446,"about_ca_system_score_codex":0.051633697,"about_ca_system_score_gemma":0.03074532,"threshold_uncertainty_score":0.97344965},"labels":[],"label_agreement":null},{"id":"W2194885127","doi":"10.5206/cjsotl-rcacea.2015.3.2","title":"A Systematic Assessment of ‘None of the Above’ on Multiple Choice Tests in a First Year Psychology Classroom","year":2015,"lang":"en","type":"article","venue":"The Canadian Journal for the Scholarship of Teaching and Learning","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Brock University; McMaster University","funders":"","keywords":"Psychology; Experimental psychology; Cognitive psychology; Quality (philosophy); Social psychology; Epistemology; Cognition","score_opus":0.0797850047565336,"score_gpt":0.40178674937091463,"score_spread":0.322001744614381,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2194885127","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8849657,0.001239877,0.08613917,0.001313044,0.0008801349,0.0034952583,0.0009762945,0.0017089951,0.01928158],"genre_scores_gemma":[0.7735049,0.0009987424,0.20915924,0.0014608429,0.00023802117,0.0063075987,0.0010184206,0.00053375954,0.0067784493],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.95124334,0.0192252,0.009612168,0.0046774675,0.0141636925,0.001078018],"domain_scores_gemma":[0.80781865,0.09861836,0.026152525,0.02310855,0.039601292,0.0047005164],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.036477037,0.0012919356,0.0014571963,0.0024966185,0.001219,0.0019481956,0.0014657457,0.0014725436,0.0049748663],"category_scores_gemma":[0.12275656,0.0005766703,0.0012544182,0.0016050135,0.001965244,0.0017951081,0.0023163126,0.0021875696,0.003138599],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0021160766,0.005756851,0.2489404,0.0027372146,0.00048744987,0.00060944544,0.010918031,0.00079617085,0.1133708,0.004432939,0.0186991,0.59113556],"study_design_scores_gemma":[0.00018452738,0.012351842,0.8390014,0.0013442455,0.0002492112,0.0015292892,0.004498783,0.0039002823,0.0728626,0.005774472,0.057859242,0.00044419622],"about_ca_topic_score_codex":0.000421222,"about_ca_topic_score_gemma":0.0019099823,"teacher_disagreement_score":0.036477037,"about_ca_system_score_codex":0.00084862683,"about_ca_system_score_gemma":0.0020435136,"threshold_uncertainty_score":0.19291133},"labels":[],"label_agreement":null},{"id":"W2197088744","doi":"","title":"Electronic Peer Assessment Tool","year":2008,"lang":"en","type":"article","venue":"Society for Information Technology & Teacher Education International Conference","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Computer science","score_opus":0.026709120625550482,"score_gpt":0.37287959423006173,"score_spread":0.34617047360451125,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2197088744","genre_codex":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06054333,0.0015351108,0.13212186,0.0017923359,0.003618028,0.0120516075,0.026672564,0.07147885,0.69018626],"genre_scores_gemma":[0.13350977,0.001161391,0.17688033,0.0015430867,0.0008944756,0.008670147,0.01644634,0.004770339,0.6561241],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9939632,0.0012511951,0.0007865531,0.0005107476,0.0032733595,0.00021497402],"domain_scores_gemma":[0.9850936,0.0057478407,0.0007347083,0.0018774105,0.0058166236,0.00072976766],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0034291593,0.00078035414,0.0007398253,0.004779943,0.0008713163,0.0023187029,0.0014669598,0.0008332593,0.19382714],"category_scores_gemma":[0.024636107,0.0003493635,0.00045054161,0.0020279507,0.00025517496,0.0021663855,0.003298907,0.0007314392,0.086658314],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003698848,0.0007089469,0.0047520967,0.0006090761,0.000030231773,0.00021900074,0.00043277457,0.00019844102,0.0037123743,0.0031640686,0.1921097,0.7936934],"study_design_scores_gemma":[0.00019695857,0.00050086866,0.020263502,0.00047632778,0.000083876876,0.0015003285,0.00052194274,0.002458608,0.012157745,0.004572274,0.9571335,0.00013420856],"about_ca_topic_score_codex":0.00051497057,"about_ca_topic_score_gemma":0.0009484609,"teacher_disagreement_score":0.19382714,"about_ca_system_score_codex":0.00031417367,"about_ca_system_score_gemma":0.0013619991,"threshold_uncertainty_score":0.6484164},"labels":[],"label_agreement":null},{"id":"W2206067169","doi":"10.47678/cjhe.v45i4.184831","title":"Framing Student Perspectives into the Higher Education Institutional Review Policy Process","year":2015,"lang":"en","type":"article","venue":"Canadian Journal of Higher Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"University of Alberta","keywords":"Framing (construction); CLARITY; Process (computing); Higher education; Public relations; Political science; Pedagogy; Sociology; Psychology; Computer science","score_opus":0.04157630342662869,"score_gpt":0.43192402969644056,"score_spread":0.39034772626981185,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2206067169","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.29882503,0.0048215003,0.12851466,0.48570555,0.003734719,0.0013684675,0.0001444303,0.00044543092,0.07644026],"genre_scores_gemma":[0.9537638,0.0012475676,0.02318178,0.015109446,0.0005593842,0.000661543,0.00002993384,0.00010727124,0.005339341],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.43052357,0.5007846,0.016899439,0.007394018,0.029459754,0.014938692],"domain_scores_gemma":[0.42795464,0.4838903,0.020863652,0.011711693,0.04143422,0.014145576],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.4263225,0.0009905621,0.0014074127,0.005305618,0.028581038,0.052400604,0.004359664,0.016728122,0.0028012414],"category_scores_gemma":[0.36646327,0.0018246798,0.0014084063,0.0043894346,0.03700835,0.025848648,0.024906294,0.025288604,0.00084944034],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011841424,0.00016078938,0.0077318987,0.0003220058,0.000046612757,0.0010563734,0.71910644,0.0011221333,0.0015880744,0.19571526,0.012155028,0.060876984],"study_design_scores_gemma":[0.00006261108,0.00023916933,0.003359903,0.0016118239,0.000045495697,0.00047107768,0.63072556,0.0031149294,0.0043639443,0.090686426,0.26496372,0.000355426],"about_ca_topic_score_codex":0.007846454,"about_ca_topic_score_gemma":0.009003893,"teacher_disagreement_score":0.4263225,"about_ca_system_score_codex":0.033299107,"about_ca_system_score_gemma":0.06565506,"threshold_uncertainty_score":0.7074465},"labels":[],"label_agreement":null},{"id":"W2206430552","doi":"10.82308/51495","title":"The effects of audio-taped feedback on ESL graduate student writing","year":2003,"lang":"en","type":"article","venue":"eScholarship@McGill (McGill)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Graduate students; Computer science; Higher education; Psychology; Medical education; Pedagogy; Mathematics education; Multimedia; Medicine; Political science","score_opus":0.029484367536438984,"score_gpt":0.3092915513043904,"score_spread":0.27980718376795144,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2206430552","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9926402,0.0003905179,0.0016521193,0.00034873598,0.00009824198,0.00020178642,0.00008836776,0.00019528082,0.0043846834],"genre_scores_gemma":[0.9908635,0.0004559845,0.006460717,0.00019033386,0.00012231003,0.0003130327,0.000078060206,0.000060615796,0.0014555035],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9772602,0.016273484,0.0012013346,0.0008770806,0.0038409103,0.00054691825],"domain_scores_gemma":[0.632558,0.3235835,0.016196867,0.0074920864,0.016275216,0.0038943212],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013778035,0.00092182524,0.0006852849,0.001295879,0.0011693632,0.0019715521,0.0010180746,0.0010345017,0.0045474865],"category_scores_gemma":[0.22737066,0.0005254188,0.0005297301,0.00078174705,0.0009795164,0.0011307467,0.0020016371,0.0012485101,0.0008371933],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.010714702,0.004417904,0.046663925,0.0033072324,0.00027088195,0.0014021022,0.13574125,0.0013777554,0.04719847,0.0002358179,0.003363496,0.74530643],"study_design_scores_gemma":[0.0028605182,0.057162967,0.7035667,0.004236505,0.0011593603,0.003810859,0.13652648,0.00641266,0.05205558,0.0017224252,0.029840564,0.0006453984],"about_ca_topic_score_codex":0.00090501056,"about_ca_topic_score_gemma":0.0014138744,"teacher_disagreement_score":0.013778035,"about_ca_system_score_codex":0.0006526498,"about_ca_system_score_gemma":0.0008314256,"threshold_uncertainty_score":0.07286608},"labels":[],"label_agreement":null},{"id":"W2206649886","doi":"10.47678/cjhe.v45i4.184403","title":"The Challenge of Differing Perspectives Surrounding Grades in the Assessment Education of Pre Service Teachers","year":2015,"lang":"en","type":"article","venue":"Canadian Journal of Higher Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"St. Francis Xavier University","funders":"","keywords":"Bachelor; Mathematics education; Teacher education; Ranking (information retrieval); Higher education; Psychology; Pedagogy; Rank (graph theory); Rubric; Service (business); Philosophy of education; sort; Sociology; Computer science; Political science; Mathematics","score_opus":0.053751278267874125,"score_gpt":0.3906394212021311,"score_spread":0.33688814293425695,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2206649886","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.80884784,0.0027797408,0.027999148,0.09075462,0.0010134359,0.00014026962,0.00011223978,0.00011367746,0.06823905],"genre_scores_gemma":[0.99206394,0.00041066523,0.0023119769,0.0020148235,0.00007097442,0.0000359066,0.000014281052,0.00003970854,0.0030376988],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.95207,0.031312607,0.0019050279,0.0021484434,0.00974919,0.0028148042],"domain_scores_gemma":[0.93352175,0.04156911,0.003912496,0.0016674761,0.010599948,0.008729084],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.033147868,0.00044189315,0.00070592744,0.002345396,0.014591654,0.019492459,0.0027094444,0.004000818,0.0027551528],"category_scores_gemma":[0.08758452,0.00065402465,0.00039708705,0.0017950217,0.018023044,0.0100524165,0.009449961,0.008686705,0.00038523367],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000037777696,0.00005279863,0.008596086,0.00010487861,0.000011178893,0.00061676983,0.93881166,0.0001721802,0.0006713425,0.022106437,0.0019483789,0.026870603],"study_design_scores_gemma":[0.000007809389,0.00005905502,0.0047902064,0.0002867713,0.0000112423995,0.00047138406,0.93647784,0.000371833,0.00044382302,0.015829563,0.04117747,0.00007297581],"about_ca_topic_score_codex":0.051725764,"about_ca_topic_score_gemma":0.07121638,"teacher_disagreement_score":0.051725764,"about_ca_system_score_codex":0.0122493375,"about_ca_system_score_gemma":0.012225407,"threshold_uncertainty_score":0.17530477},"labels":[],"label_agreement":null},{"id":"W2228140964","doi":"10.1080/02671522.2015.1086015","title":"Predictability in high-stakes examinations: students’ perspectives on a perennial assessment dilemma<sup>*</sup>","year":2015,"lang":"en","type":"article","venue":"Research Papers in Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Queen's University; Queen's University Belfast; University of Oxford","keywords":"Dilemma; Certificate; Context (archaeology); Active listening; Irish; Pedagogy; Predictability; Relevance (law); Psychology; Quality (philosophy); Medical education; Engineering ethics; Public relations; Political science; Computer science; Medicine; Epistemology; Engineering","score_opus":0.0924787417886633,"score_gpt":0.4819874739115618,"score_spread":0.3895087321228985,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2228140964","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9632974,0.00038109283,0.0025750166,0.023731843,0.00019804577,0.00004830813,0.000014676283,0.000039445214,0.009714007],"genre_scores_gemma":[0.9963303,0.00018103479,0.00067095016,0.0011909566,0.000040032486,0.000024204472,0.0000070684587,0.00001754794,0.0015378568],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.9541366,0.03265827,0.0018384272,0.00136599,0.0059195333,0.004081135],"domain_scores_gemma":[0.9332166,0.044036537,0.0070072683,0.0021138666,0.0057694633,0.007856357],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03925771,0.000524975,0.0007713876,0.0011695359,0.008810679,0.017951744,0.0019244666,0.004618935,0.0018229245],"category_scores_gemma":[0.06743272,0.0007072813,0.0008187988,0.00084571313,0.016902152,0.007240955,0.009883835,0.011342432,0.00052212056],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006790728,0.00012211285,0.018573653,0.0000646596,0.0000138057285,0.0015433037,0.95408833,0.00028631586,0.0014637097,0.0062955804,0.0028777234,0.014602902],"study_design_scores_gemma":[0.000009668611,0.00015954817,0.0047648614,0.000110558576,0.000009379866,0.0007960134,0.96746325,0.00061664503,0.0007643697,0.004704118,0.020537456,0.000064080195],"about_ca_topic_score_codex":0.0033180946,"about_ca_topic_score_gemma":0.0040407153,"teacher_disagreement_score":0.03925771,"about_ca_system_score_codex":0.005789662,"about_ca_system_score_gemma":0.005549662,"threshold_uncertainty_score":0.20761704},"labels":[],"label_agreement":null},{"id":"W2237938873","doi":"10.37119/ojs2015.v21i2.214","title":"Inquiring into the Assessment Education of Preservice Teachers: A Collaborative Self-Study of Teacher Educators","year":2015,"lang":"en","type":"article","venue":"in education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"St. Francis Xavier University","funders":"","keywords":"Bachelor; Teacher education; Teacher preparation; Mathematics education; Pedagogy; Psychology","score_opus":0.03333096806200037,"score_gpt":0.42589355295932946,"score_spread":0.3925625848973291,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2237938873","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99761665,0.0001419609,0.00068204716,0.00045226287,0.000013907162,0.000070023605,0.000006768437,0.000011133965,0.0010052794],"genre_scores_gemma":[0.9974227,0.00016266899,0.00075905997,0.00023418014,0.000014494091,0.00010348018,0.000013790188,0.000010219393,0.0012793522],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.98375905,0.011481318,0.00075405143,0.0010439323,0.0017519544,0.0012097291],"domain_scores_gemma":[0.9271552,0.049807873,0.006934448,0.0031787027,0.005646696,0.0072769835],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.025937058,0.00068715366,0.0011075368,0.0028379706,0.009676392,0.011378942,0.00207312,0.0029215545,0.0013343596],"category_scores_gemma":[0.06994634,0.0009724295,0.0006166253,0.0011849457,0.009566992,0.005370283,0.0082469685,0.005706386,0.00042866587],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027683542,0.00060457626,0.017752726,0.000038568887,0.0000065658305,0.00026465862,0.9739871,0.000025779205,0.00061658217,0.00042188235,0.00018476856,0.0060691736],"study_design_scores_gemma":[0.000020894728,0.00030700478,0.010470635,0.000066510096,0.000008091978,0.00033893719,0.9836844,0.00015363502,0.0005645972,0.0004195184,0.0039419318,0.000023757488],"about_ca_topic_score_codex":0.0023475573,"about_ca_topic_score_gemma":0.005253038,"teacher_disagreement_score":0.025937058,"about_ca_system_score_codex":0.0026812316,"about_ca_system_score_gemma":0.00505098,"threshold_uncertainty_score":0.13716996},"labels":[],"label_agreement":null},{"id":"W2241999475","doi":"","title":"Blending community and authentic assessment in a hybrid course","year":2007,"lang":"en","type":"article","venue":"E-Learn: World Conference on E-Learning in Corporate, Government, Healthcare, and Higher Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Course (navigation); Computer science; Engineering","score_opus":0.09098612383706327,"score_gpt":0.38366467255759934,"score_spread":0.29267854872053606,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2241999475","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.70324403,0.0000983561,0.2811994,0.00043670047,0.00010998796,0.0004184875,0.000043587934,0.001953677,0.012495796],"genre_scores_gemma":[0.8752017,0.000021078058,0.11909196,0.000062542225,0.000016155267,0.00011586224,0.00005386954,0.0000772289,0.0053596054],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9970114,0.0012590147,0.00013333114,0.0004987215,0.0009081878,0.00018929297],"domain_scores_gemma":[0.99045044,0.0049191252,0.00032892099,0.0013113135,0.0015472459,0.0014429999],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003759289,0.0003362409,0.00045376082,0.00066499785,0.0006752595,0.002492474,0.0013255443,0.0012250462,0.0033786285],"category_scores_gemma":[0.013430814,0.0003001155,0.00026995258,0.00038491024,0.00044456846,0.0025720997,0.003553841,0.0009844642,0.00088173465],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002076303,0.0079707345,0.024172872,0.00018999963,0.00007748333,0.00047035314,0.006650256,0.01977202,0.054377474,0.011268158,0.0037997428,0.86917454],"study_design_scores_gemma":[0.00076520065,0.0062532383,0.03187986,0.00014075005,0.00022911139,0.0014409329,0.0050050816,0.82518125,0.060323235,0.0385747,0.02987598,0.0003306414],"about_ca_topic_score_codex":0.0010763331,"about_ca_topic_score_gemma":0.002472088,"teacher_disagreement_score":0.003759289,"about_ca_system_score_codex":0.0004626003,"about_ca_system_score_gemma":0.0010826591,"threshold_uncertainty_score":0.019881308},"labels":[],"label_agreement":null},{"id":"W2249312354","doi":"10.11575/prism/5279","title":"Developing Preservice Teachers' Assessment Literacy: A Problem-Based Learning Approach","year":2014,"lang":"en","type":"article","venue":"Open MIND","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Authentic assessment; Curriculum; Mathematics education; Pedagogy; Assessment for learning; Government (linguistics); Literacy; Educational assessment; Standardized test; Formative assessment; Psychology; Medical education; Medicine","score_opus":0.06303854882660766,"score_gpt":0.40843042952233605,"score_spread":0.3453918806957284,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2249312354","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19029175,0.00074987055,0.70342904,0.008244664,0.000120161814,0.0026972543,0.00007020704,0.0006067497,0.0937903],"genre_scores_gemma":[0.43263504,0.00072696374,0.54859173,0.00052104547,0.00003718731,0.0013061645,0.00008505777,0.0000437839,0.016053008],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99638605,0.002102338,0.00016743486,0.00036708984,0.0008119513,0.00016505516],"domain_scores_gemma":[0.99477166,0.003530668,0.00029530967,0.00035974162,0.0007132615,0.000329361],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005128763,0.0006265679,0.00053451373,0.0019226713,0.0014073083,0.0063210186,0.0024953363,0.0012937894,0.0025808306],"category_scores_gemma":[0.009627271,0.00040007904,0.0004194785,0.0010019672,0.0029025658,0.0027670537,0.0032741153,0.0024146975,0.0005514935],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000749249,0.003937665,0.010448002,0.0012012749,0.000059372534,0.00068553333,0.059592523,0.007011223,0.006789765,0.12724487,0.0057039284,0.77725095],"study_design_scores_gemma":[0.0004466315,0.0021838672,0.021770306,0.0019097273,0.0001795744,0.0034830386,0.12741284,0.07472522,0.03258919,0.4891533,0.24596499,0.0001813913],"about_ca_topic_score_codex":0.0015490502,"about_ca_topic_score_gemma":0.0034703873,"teacher_disagreement_score":0.0063210186,"about_ca_system_score_codex":0.0024623908,"about_ca_system_score_gemma":0.0055094124,"threshold_uncertainty_score":0.027123809},"labels":[],"label_agreement":null},{"id":"W2255198894","doi":"10.20381/ruor-20086","title":"Implications of the multiple-use of large-scale assessments for the process of validation: A case study of the multiple-use of a Grade 9 mathematics assessment","year":2011,"lang":"en","type":"dissertation","venue":"uO Research (University of Ottawa)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Accountability; Scale (ratio); Process (computing); Argument (complex analysis); Quality (philosophy); Perspective (graphical); Test (biology); Data collection; Computer science; Management science; Data science; Psychology; Mathematics education; Engineering; Mathematics; Artificial intelligence; Medicine; Statistics; Political science; Geography","score_opus":0.1975998779485343,"score_gpt":0.4601881434004951,"score_spread":0.2625882654519608,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2255198894","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8585783,0.0009373532,0.07135868,0.024123851,0.00017017804,0.001388098,0.000066832465,0.00014231632,0.043234434],"genre_scores_gemma":[0.96790445,0.0003471048,0.026853327,0.0013109776,0.000045907953,0.0010112694,0.000024979463,0.000102838894,0.002399211],"study_design_codex":"qualitative","study_design_gemma":"case_report","domain_scores_codex":[0.5047944,0.43944532,0.010734537,0.007644144,0.028814508,0.008567005],"domain_scores_gemma":[0.45882738,0.46749422,0.019786032,0.025667908,0.022194855,0.006029563],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.21715681,0.0013925205,0.0015912546,0.0049250196,0.03383186,0.019673966,0.008038285,0.01078385,0.0017458851],"category_scores_gemma":[0.3146715,0.002659301,0.0021871293,0.005786421,0.043465994,0.027666518,0.026363088,0.0151875075,0.00063625094],"study_design_candidate":"case_report","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006499186,0.00033662404,0.016434845,0.00023196654,0.00003514058,0.0067568566,0.91639066,0.0008504001,0.00082093023,0.037993293,0.0010972419,0.01898714],"study_design_scores_gemma":[0.00008030575,0.0005131589,0.0105917035,0.0016604767,0.000058674206,0.006468888,0.89580715,0.0054418226,0.0029376624,0.0282037,0.048002962,0.00023347216],"about_ca_topic_score_codex":0.017790787,"about_ca_topic_score_gemma":0.02587624,"teacher_disagreement_score":0.21715681,"about_ca_system_score_codex":0.019723631,"about_ca_system_score_gemma":0.022196406,"threshold_uncertainty_score":0.965385},"labels":[],"label_agreement":null},{"id":"W2267422080","doi":"10.55016/ojs/ajer.v61i1.56028","title":"Assessment and Grading Practices in Outreach Schools","year":2015,"lang":"en","type":"article","venue":"Alberta Journal of Educational Research","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Lethbridge","funders":"","keywords":"Grading (engineering); Outreach; Mathematics education; Psychology; Pedagogy; Medical education; Political science; Medicine; Engineering","score_opus":0.3218829329466501,"score_gpt":0.5831476598950716,"score_spread":0.26126472694842146,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2267422080","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9822579,0.00059237384,0.0011498216,0.00038829359,0.00003539991,0.00021152884,0.00012916695,0.0001658677,0.015069647],"genre_scores_gemma":[0.988325,0.00042615348,0.0028185984,0.00010582286,0.0000095371915,0.00004405081,0.00016245023,0.000028902452,0.008079573],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99161434,0.0019280805,0.00047407887,0.0011803729,0.0038599889,0.0009431728],"domain_scores_gemma":[0.98395133,0.00311255,0.003080583,0.0013830086,0.0057946034,0.002678045],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005591778,0.00046320562,0.00059683283,0.004346206,0.0036809405,0.0035984598,0.0021180282,0.0008130009,0.0031388602],"category_scores_gemma":[0.02039081,0.00042817168,0.00027916726,0.004015254,0.001747414,0.0014528297,0.0025682857,0.00095394027,0.0006413394],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002376321,0.00059792056,0.43016103,0.00043619183,0.000021784344,0.0004706911,0.16158906,0.00054103567,0.004962295,0.0015342807,0.0035865519,0.39586154],"study_design_scores_gemma":[0.000022495626,0.00034119096,0.8982613,0.0003213004,0.000027317385,0.00019999218,0.06982425,0.00035869298,0.002488498,0.0009064427,0.027158303,0.00009018748],"about_ca_topic_score_codex":0.1811784,"about_ca_topic_score_gemma":0.43219653,"teacher_disagreement_score":0.1811784,"about_ca_system_score_codex":0.010209478,"about_ca_system_score_gemma":0.01192979,"threshold_uncertainty_score":0.3602476},"labels":[],"label_agreement":null},{"id":"W2269884609","doi":"10.5539/hes.v6n1p136","title":"An Examination of Using Self-, Peer-, and Teacher-Assessment in Higher Education: A Case Study in Teacher Education","year":2016,"lang":"en","type":"article","venue":"Higher Education Studies","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":47,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Summative assessment; Formative assessment; Peer assessment; Psychology; Teacher education; Self-assessment; Medical education; Peer evaluation; Presentation (obstetrics); Mathematics education; Pedagogy; Higher education; Medicine","score_opus":0.11012340218764399,"score_gpt":0.4709792748283706,"score_spread":0.3608558726407266,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2269884609","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9868052,0.0005071873,0.004376237,0.0007916443,0.00003510076,0.00015364942,0.00001247295,0.000024201614,0.0072944476],"genre_scores_gemma":[0.99310935,0.00042490268,0.0041346946,0.000110701665,0.00001336714,0.00007509947,0.000011222807,0.000015702737,0.002104964],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9551034,0.036531027,0.0010898688,0.00115561,0.0043384004,0.0017816988],"domain_scores_gemma":[0.96500844,0.025069589,0.0018797298,0.0023196626,0.0039107776,0.001811712],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.021947188,0.000441526,0.0005752287,0.0016426336,0.005185997,0.0041417745,0.0017944947,0.0022998499,0.0012084846],"category_scores_gemma":[0.039195187,0.00042269702,0.00052907335,0.0016591257,0.004058478,0.0025194078,0.0035076027,0.0021405935,0.00039938116],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014157977,0.0028453604,0.09562769,0.000666314,0.000043453976,0.014780736,0.7862994,0.0004858105,0.003785117,0.005143997,0.0009036183,0.089276895],"study_design_scores_gemma":[0.000042866945,0.0015689882,0.05698223,0.0006873476,0.00006615489,0.020940071,0.8790411,0.0025678906,0.0073381998,0.0013665942,0.029279368,0.00011933871],"about_ca_topic_score_codex":0.005972316,"about_ca_topic_score_gemma":0.015389225,"teacher_disagreement_score":0.021947188,"about_ca_system_score_codex":0.0032102389,"about_ca_system_score_gemma":0.003372374,"threshold_uncertainty_score":0.1160692},"labels":[],"label_agreement":null},{"id":"W2272782403","doi":"","title":"Process-Oriented Assessment in Mathematics Education","year":2009,"lang":"en","type":"article","venue":"E-Learn: World Conference on E-Learning in Corporate, Government, Healthcare, and Higher Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Process (computing); Mathematics education; Computer science; Mathematics; Programming language","score_opus":0.06589933623880866,"score_gpt":0.378212484093377,"score_spread":0.3123131478545683,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2272782403","genre_codex":"methods","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.25139204,0.0009915468,0.6794319,0.0011441845,0.0002049471,0.001482825,0.00008627858,0.0008653532,0.06440094],"genre_scores_gemma":[0.80847186,0.0003493339,0.18441832,0.00009710769,0.000018487588,0.00043672152,0.00008362333,0.00006293082,0.006061546],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99170697,0.0055008247,0.00034832224,0.00034301882,0.0018984833,0.00020247513],"domain_scores_gemma":[0.9868443,0.00925745,0.0005059168,0.00048674076,0.0025241042,0.0003813792],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00915682,0.00046857682,0.00028284325,0.0011879122,0.0005489133,0.0024380856,0.00074476533,0.00076951954,0.0024752177],"category_scores_gemma":[0.027661894,0.00021358512,0.00035537727,0.00081073376,0.00071314804,0.0027941987,0.0012764236,0.0008736327,0.0006004314],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00083809387,0.001580302,0.022130808,0.0005036326,0.000046407098,0.00014871359,0.00730681,0.012931747,0.006750764,0.09885709,0.0028971913,0.84600836],"study_design_scores_gemma":[0.0008170369,0.0038891986,0.07186447,0.00096601003,0.00026218852,0.0008697819,0.011682057,0.44645503,0.043658372,0.36254054,0.056777567,0.00021774729],"about_ca_topic_score_codex":0.0026414266,"about_ca_topic_score_gemma":0.0027009167,"teacher_disagreement_score":0.00915682,"about_ca_system_score_codex":0.001302395,"about_ca_system_score_gemma":0.002463669,"threshold_uncertainty_score":0.04842651},"labels":[],"label_agreement":null},{"id":"W2274734137","doi":"10.2304/pfie.2012.10.4.447","title":"Building Teacher Capacity within the Evolving Assessment Culture in Canadian Education","year":2012,"lang":"en","type":"article","venue":"Policy Futures in Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":35,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Brock University; Queen's University","funders":"","keywords":"Formative assessment; Accountability; Professional development; Faculty development; Educational assessment; Assessment for learning; Pedagogy; Scale (ratio); Focus group; Summative assessment; Best practice; Professional learning community; Psychology; Teacher education; Sociology; Mathematics education; Political science","score_opus":0.024756394277784217,"score_gpt":0.41317470547846463,"score_spread":0.38841831120068043,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2274734137","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6580832,0.011734856,0.0064461706,0.072772704,0.00065254694,0.00025295344,0.00028706095,0.0002893233,0.2494812],"genre_scores_gemma":[0.98392224,0.0017082951,0.0028384828,0.00097229716,0.000015929978,0.00004878647,0.00004836307,0.000036093952,0.010409478],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.97716695,0.006615446,0.0015432402,0.0020109129,0.0076330565,0.005030369],"domain_scores_gemma":[0.9460375,0.015227728,0.0024889668,0.0027194966,0.02568863,0.007837668],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.023604766,0.00034844727,0.0005092092,0.0038641861,0.029046774,0.016509019,0.0028920167,0.0015312035,0.0023036178],"category_scores_gemma":[0.03806663,0.0006365451,0.0003994095,0.0053270333,0.015286784,0.0055595445,0.009180524,0.0030771217,0.00025054815],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.00008343844,0.000101378275,0.04288852,0.00072020857,0.000030791332,0.0012989575,0.61104286,0.0012010947,0.001554289,0.09886857,0.019205714,0.22300422],"study_design_scores_gemma":[0.000022698552,0.00010542964,0.08643937,0.0014037458,0.000050101407,0.0005799184,0.44530737,0.0015161309,0.0017744469,0.015626285,0.44682193,0.00035252055],"about_ca_topic_score_codex":0.98615205,"about_ca_topic_score_gemma":0.9902552,"teacher_disagreement_score":0.7643076,"about_ca_system_score_codex":0.23569237,"about_ca_system_score_gemma":0.33334887,"threshold_uncertainty_score":0.8864885},"labels":[],"label_agreement":null},{"id":"W2283163237","doi":"10.14288/1.0102214","title":"Teacher evaluation in British Columbia as perceived by teachers, a survey study","year":2011,"lang":"en","type":"article","venue":"cIRcle (University of British Columbia)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Medical education; Psychology; Pedagogy; Mathematics education; Medicine","score_opus":0.03735594129290467,"score_gpt":0.26701512243704506,"score_spread":0.22965918114414038,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2283163237","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9971457,0.00019897913,0.000044333006,0.00024532902,0.000005815075,0.000027370685,0.00011535254,0.0000065689956,0.002210636],"genre_scores_gemma":[0.99504614,0.0004748117,0.00015091363,0.00025523658,0.0000051631923,0.000057749545,0.0001703298,0.000007021312,0.003832556],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99827814,0.00042822192,0.00012876143,0.00013585684,0.0006662295,0.0003628755],"domain_scores_gemma":[0.99057466,0.0018808541,0.0011345376,0.0002081592,0.0045098327,0.0016919343],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015523524,0.00016544173,0.00028036706,0.0010848173,0.003896092,0.0020542175,0.0004169424,0.00044379916,0.0024889032],"category_scores_gemma":[0.008168574,0.00041646333,0.00009300783,0.002125311,0.00071271526,0.0005419682,0.00066204567,0.0007782484,0.00039615238],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002249342,0.00035523504,0.7682751,0.00025418962,0.000020614065,0.001060976,0.16670449,0.00015744175,0.0032987178,0.00020254689,0.006903886,0.05254181],"study_design_scores_gemma":[0.000011656935,0.00016157489,0.8728824,0.00010005908,0.000006597151,0.00015058785,0.11436401,0.00021093224,0.00027869595,0.000020251222,0.011785569,0.000027617907],"about_ca_topic_score_codex":0.8827097,"about_ca_topic_score_gemma":0.9448273,"teacher_disagreement_score":0.8827097,"about_ca_system_score_codex":0.010851293,"about_ca_system_score_gemma":0.015002588,"threshold_uncertainty_score":0.2359621},"labels":[],"label_agreement":null},{"id":"W2288795982","doi":"10.18806/tesl.v32i0.1215","title":"Building Teachers’ Assessment Capacity for Supporting English Language Learners Through the Implementation of the STEP Language Assessment in Ontario K-12 Schools","year":2016,"lang":"en","type":"article","venue":"TESL Canada Journal","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Ell; Christian ministry; Psychology; Mathematics education; Language proficiency; Pedagogy; English language; Sociology; Teaching method; Political science","score_opus":0.029337185190978634,"score_gpt":0.3732268630508298,"score_spread":0.3438896778598512,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2288795982","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9780426,0.00021431709,0.0040847464,0.002349741,0.00004060131,0.0015307629,0.00023657738,0.00023021127,0.013270385],"genre_scores_gemma":[0.97612303,0.0002628223,0.016823722,0.0001822231,0.0000067617502,0.0010104668,0.00022925582,0.00003223175,0.005329483],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.98563945,0.0051300856,0.0009995461,0.0011354764,0.004624959,0.002470457],"domain_scores_gemma":[0.9653997,0.0046345433,0.0027368797,0.0024802748,0.018023433,0.0067252894],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02007388,0.00041711712,0.00048965897,0.0014697523,0.0059533603,0.00360743,0.0026608824,0.00063175714,0.002031628],"category_scores_gemma":[0.032171555,0.00092600717,0.0005715202,0.0013221375,0.003123552,0.0022778215,0.0063234274,0.0014619672,0.00056974933],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003743744,0.0017942624,0.32233047,0.00086806,0.000053435397,0.00077965116,0.33191046,0.002396363,0.009061722,0.0023150474,0.01159728,0.31651884],"study_design_scores_gemma":[0.0001526398,0.0009841772,0.73837143,0.0007262147,0.000077685654,0.00012827708,0.16960394,0.0039836513,0.0056488425,0.0009053554,0.0791211,0.0002966674],"about_ca_topic_score_codex":0.8629119,"about_ca_topic_score_gemma":0.9417021,"teacher_disagreement_score":0.8629119,"about_ca_system_score_codex":0.041377246,"about_ca_system_score_gemma":0.16285774,"threshold_uncertainty_score":0.30021435},"labels":[],"label_agreement":null},{"id":"W2289974468","doi":"10.18806/tesl.v32i0.1220","title":"PBLA: Moving Toward Sustainability","year":2016,"lang":"en","type":"article","venue":"TESL Canada Journal","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Valuation (finance); Portfolio; Sustainability; Political science; Humanities; Sociology; Business; Art; Accounting","score_opus":0.019074220604149927,"score_gpt":0.31347581332822944,"score_spread":0.2944015927240795,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2289974468","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02288072,0.014154934,0.12506317,0.4424194,0.002662374,0.00070425635,0.0003493837,0.0019613507,0.3898045],"genre_scores_gemma":[0.55623126,0.022445273,0.20565304,0.05096991,0.001191051,0.0014883324,0.00091375224,0.0013039397,0.15980344],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.96648204,0.013332834,0.00083877635,0.0020920762,0.014259675,0.0029946466],"domain_scores_gemma":[0.9725582,0.0054035927,0.0011338221,0.002138983,0.012330286,0.0064350925],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03305485,0.0007917627,0.0005650093,0.002613387,0.008792264,0.020198446,0.0037956093,0.0044387165,0.011019644],"category_scores_gemma":[0.039573573,0.00042184323,0.0006685468,0.0026489862,0.013804956,0.016139245,0.01924671,0.0072526946,0.004074379],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000036607933,0.0001721727,0.0033973958,0.0005225581,0.00002517162,0.00013435821,0.00930533,0.0014178738,0.00061842037,0.47794005,0.06670829,0.4397218],"study_design_scores_gemma":[0.00002231398,0.00008217122,0.002316536,0.0010403986,0.000013548653,0.0001257376,0.009171991,0.0015802738,0.00097262027,0.20900945,0.7756199,0.000045107172],"about_ca_topic_score_codex":0.15384753,"about_ca_topic_score_gemma":0.117540345,"teacher_disagreement_score":0.15384753,"about_ca_system_score_codex":0.0380274,"about_ca_system_score_gemma":0.15380967,"threshold_uncertainty_score":0.30590403},"labels":[],"label_agreement":null},{"id":"W2291984861","doi":"10.19173/irrodl.v17i2.2221","title":"Learners’ Interpersonal Beliefs and Generated Feedback in an Online Role-Playing Peer- Feedback Activity: An Exploratory Study","year":2016,"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":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Peer feedback; Interpersonal communication; Psychology; Computer-mediated communication; Perception; Constructive; Quality (philosophy); Exploratory research; Interpersonal relationship; Social psychology; Mathematics education; Computer science; The Internet; World Wide Web","score_opus":0.1796078959938181,"score_gpt":0.4821766519664574,"score_spread":0.3025687559726393,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2291984861","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99928576,0.000027947546,0.00024952434,0.000016220816,0.0000016729441,0.00003103742,0.0000066598354,0.0000027230155,0.00037844398],"genre_scores_gemma":[0.99890494,0.00007146615,0.00049785455,0.000018026272,0.0000039542238,0.00005477609,0.000011844488,0.0000028723698,0.00043431163],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99620676,0.0021864541,0.00019001325,0.00026151628,0.00078996236,0.00036522385],"domain_scores_gemma":[0.9894616,0.006608256,0.0013356984,0.0003614238,0.0013713456,0.00086166954],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0055688475,0.000446336,0.00054133346,0.0010029523,0.0012120543,0.0018912399,0.0006317502,0.0006572389,0.0014024429],"category_scores_gemma":[0.017139863,0.00029336585,0.00041593486,0.00039179088,0.00082816865,0.0011639079,0.0011288422,0.0009725722,0.00034066197],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00046651188,0.007966898,0.34844843,0.0004754227,0.000105376246,0.0019564219,0.55283475,0.00029738332,0.012064484,0.00033792088,0.00039712674,0.07464927],"study_design_scores_gemma":[0.00007530206,0.008211496,0.45991334,0.00025300303,0.00014235548,0.0019796188,0.5113945,0.0018202926,0.010605523,0.00037535068,0.005103844,0.0001253597],"about_ca_topic_score_codex":0.00085261546,"about_ca_topic_score_gemma":0.0011670185,"teacher_disagreement_score":0.0055688475,"about_ca_system_score_codex":0.0005017251,"about_ca_system_score_gemma":0.00059203355,"threshold_uncertainty_score":0.029451251},"labels":[],"label_agreement":null},{"id":"W2295570895","doi":"10.18192/olbiwp.v4i0.1105","title":"Digital Documentation: Using digital technologies to promote language assessment for the 21st century","year":2012,"lang":"en","type":"article","venue":"OLBI Journal","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Formative assessment; Documentation; Curriculum; Computer science; Process (computing); Language acquisition; Digital learning; Multimedia; Mathematics education; Pedagogy; Psychology","score_opus":0.02947728125630048,"score_gpt":0.38375803982468853,"score_spread":0.35428075856838803,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2295570895","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6448945,0.005041446,0.1332581,0.0073467838,0.0010006926,0.0014487647,0.00030532252,0.0024817728,0.2042226],"genre_scores_gemma":[0.8027717,0.002880283,0.16670634,0.00070323836,0.00017153333,0.0005053092,0.00017796477,0.00017358694,0.025910124],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9971559,0.0012438543,0.0001966898,0.00012621252,0.0011641172,0.00011320049],"domain_scores_gemma":[0.9951153,0.0029839505,0.00037697566,0.0004092914,0.0006951016,0.00041928445],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0032731877,0.0002967092,0.00020471915,0.0017774735,0.00078728586,0.0028013412,0.000430677,0.0006502542,0.0040097483],"category_scores_gemma":[0.014142244,0.000109484994,0.00019765599,0.001080592,0.00074507867,0.0019584796,0.0024094642,0.00069571234,0.0007693435],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014022681,0.00050814333,0.006967023,0.00073927786,0.000011212524,0.00042932984,0.012968972,0.00033019145,0.011224111,0.0077054836,0.005302176,0.9536739],"study_design_scores_gemma":[0.000402522,0.0038399636,0.07790004,0.0029842362,0.00012210991,0.0077538444,0.022975612,0.0063495804,0.075573735,0.025871068,0.77597374,0.00025359957],"about_ca_topic_score_codex":0.00062612345,"about_ca_topic_score_gemma":0.0011758258,"teacher_disagreement_score":0.0040097483,"about_ca_system_score_codex":0.00063315826,"about_ca_system_score_gemma":0.0017664767,"threshold_uncertainty_score":0.0173105},"labels":[],"label_agreement":null},{"id":"W2298211336","doi":"10.1057/9781137440068_10","title":"Using Screen Capture Software to Improve the Value of Feedback on Academic Assignments in Teacher Education","year":2015,"lang":"en","type":"book-chapter","venue":"Palgrave Macmillan UK eBooks","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brock University","funders":"","keywords":"Cursor (databases); Computer science; Software; Context (archaeology); Multimedia; Value (mathematics); Focus (optics); Component (thermodynamics); Audio feedback; Human–computer interaction; Engineering; Artificial intelligence; Operating system","score_opus":0.06286936481616026,"score_gpt":0.35525782345666784,"score_spread":0.29238845864050755,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2298211336","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18349893,0.02027361,0.29758403,0.007191115,0.002246587,0.0012689714,0.001614331,0.015038613,0.47128388],"genre_scores_gemma":[0.44231895,0.014516188,0.3187733,0.0019136568,0.00053649646,0.0010686625,0.0013360688,0.0019343633,0.2176023],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99741036,0.001226801,0.000098540084,0.00012652458,0.0010514521,0.000086281456],"domain_scores_gemma":[0.9874127,0.010815706,0.0002413316,0.00040598333,0.0009957616,0.0001285138],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003430763,0.0005748645,0.00027696314,0.0014885474,0.0005441717,0.0027977098,0.00081766705,0.0008813937,0.015618381],"category_scores_gemma":[0.012970252,0.00017950333,0.00023731217,0.0014485988,0.0007486031,0.0016570243,0.0014742517,0.00092224084,0.0048381425],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001270605,0.00009019714,0.0015511236,0.000710608,0.000013243557,0.00018998847,0.006467602,0.00047853144,0.009721524,0.004356149,0.039499547,0.9367945],"study_design_scores_gemma":[0.00016018367,0.001808171,0.068835944,0.005365596,0.00014680142,0.0031618867,0.012569754,0.009030971,0.0518999,0.023742631,0.82302624,0.00025185678],"about_ca_topic_score_codex":0.0023566363,"about_ca_topic_score_gemma":0.0047531375,"teacher_disagreement_score":0.015618381,"about_ca_system_score_codex":0.00071603584,"about_ca_system_score_gemma":0.0009118359,"threshold_uncertainty_score":0.052248716},"labels":[],"label_agreement":null},{"id":"W2308497147","doi":"10.11575/prism/5282","title":"Exploring New Frontiers in Self and Peer Assessment","year":2014,"lang":"en","type":"article","venue":"Open MIND","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Literacy; Pedagogy; Peer assessment; Mathematics education; Psychology; Sociology; Public relations; Political science","score_opus":0.1448085639772032,"score_gpt":0.3969174249054853,"score_spread":0.2521088609282821,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2308497147","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13765606,0.064274974,0.21411753,0.23041882,0.0021862327,0.00049158203,0.00011018657,0.00075449946,0.34999013],"genre_scores_gemma":[0.8809413,0.008930092,0.09379412,0.0030376965,0.000780273,0.00040250635,0.000049086448,0.00016044315,0.011904558],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9494696,0.038228836,0.0008652041,0.0022875809,0.006788737,0.0023599367],"domain_scores_gemma":[0.9206858,0.06004057,0.0010652858,0.0047217435,0.0084928665,0.004993699],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.07180489,0.0007390516,0.0010714415,0.0037863732,0.005216734,0.01972766,0.0031342441,0.0033703297,0.0068802675],"category_scores_gemma":[0.036067214,0.0005083081,0.0008251121,0.0025919543,0.049559996,0.024346959,0.013893589,0.0054072025,0.00075892097],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007958146,0.00020701044,0.00393895,0.0003927738,0.000026684964,0.00015594049,0.06600914,0.00052600587,0.0005065141,0.66445273,0.0041638734,0.25954083],"study_design_scores_gemma":[0.00008849727,0.00035297606,0.0043609487,0.0010438476,0.00002246409,0.0003342605,0.056193322,0.003101619,0.0007741128,0.7431552,0.1904829,0.000089854984],"about_ca_topic_score_codex":0.01904476,"about_ca_topic_score_gemma":0.025290674,"teacher_disagreement_score":0.07180489,"about_ca_system_score_codex":0.010084454,"about_ca_system_score_gemma":0.024045527,"threshold_uncertainty_score":0.37974507},"labels":[],"label_agreement":null},{"id":"W2312774039","doi":"10.18192/olbiwp.v4i0.1106","title":"Multidimensionality of assessment in the Common European Framework of Reference for languages (CEFR)","year":2012,"lang":"en","type":"article","venue":"OLBI Journal","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Perspective (graphical); Context (archaeology); Process (computing); Raising (metalworking); Domain (mathematical analysis); Computer science; Psychology; Linguistics; Artificial intelligence; Geography; Engineering","score_opus":0.07346238474137637,"score_gpt":0.4446475901687345,"score_spread":0.3711852054273581,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2312774039","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09411692,0.011278588,0.6844282,0.016088719,0.0010997705,0.00080282876,0.00023886017,0.0004269345,0.19151923],"genre_scores_gemma":[0.75268257,0.0018161075,0.2402866,0.00079995237,0.0001144822,0.0007085989,0.00021175998,0.000080404,0.0032995048],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.8819574,0.08160238,0.01334521,0.0053554415,0.014885273,0.0028542883],"domain_scores_gemma":[0.94494206,0.028587863,0.004459722,0.0077823373,0.012406235,0.0018216915],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.05626076,0.0010378174,0.001317323,0.008942441,0.0037795675,0.01777954,0.0019137629,0.0035950611,0.0016675204],"category_scores_gemma":[0.06348694,0.0005749993,0.0014353995,0.0071897097,0.024900734,0.015620609,0.013671726,0.003996023,0.00029822448],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019562021,0.0000228005,0.0022509007,0.00027035407,0.000031004565,0.00014501443,0.019773675,0.0009042777,0.0003988308,0.9324255,0.00093051855,0.042827487],"study_design_scores_gemma":[0.000019734936,0.00014314044,0.0075640376,0.0021783048,0.000063800304,0.0011485857,0.026374124,0.004370065,0.0005818562,0.81991184,0.13747063,0.00017401385],"about_ca_topic_score_codex":0.009528847,"about_ca_topic_score_gemma":0.0060503543,"teacher_disagreement_score":0.05626076,"about_ca_system_score_codex":0.008148476,"about_ca_system_score_gemma":0.0127239,"threshold_uncertainty_score":0.29753894},"labels":[],"label_agreement":null},{"id":"W2316879809","doi":"10.15405/futureacademy/ejsbs(2301-2218).2012.1.8","title":"The Enabling Constraints of Building an Assessment Pedagogy: Engaging Pre-service Teachers in a Professional Exploration of Current Conceptions of Classroom Assessment","year":2012,"lang":"en","type":"article","venue":"The European Journal of Social & Behavioural Sciences","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Summative assessment; Formative assessment; Context (archaeology); Psychology; Pedagogy; Class (philosophy); Professional development; Assessment for learning; Thematic analysis; Mathematics education; Sociology; Qualitative research; Computer science","score_opus":0.1823104768364378,"score_gpt":0.4975260007389156,"score_spread":0.3152155239024778,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2316879809","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.76023203,0.0041633425,0.118481934,0.049785268,0.0004967898,0.0006887187,0.000044077886,0.00030258356,0.0658052],"genre_scores_gemma":[0.9609221,0.0018905856,0.031213844,0.001735422,0.000052208856,0.00045236872,0.000016573746,0.00007064202,0.0036461146],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9818627,0.013599357,0.0005632926,0.0007653443,0.0019564836,0.0012527979],"domain_scores_gemma":[0.97396445,0.01959342,0.0011104468,0.0011930717,0.001554453,0.0025841226],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.017532254,0.00052358577,0.00074443355,0.0014462797,0.010639539,0.012548718,0.0020232266,0.0022364587,0.0018783879],"category_scores_gemma":[0.025365952,0.0008762038,0.00050613104,0.0011734918,0.02080086,0.012348912,0.013666686,0.007263531,0.00063127145],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025010959,0.00020105526,0.0035413208,0.00032337598,0.000007388891,0.0013160344,0.93033147,0.00023968892,0.0020443352,0.022710804,0.0019975535,0.037262004],"study_design_scores_gemma":[0.000023170944,0.00015282501,0.00337413,0.0008548227,0.000017289281,0.0016591768,0.8720939,0.0010857093,0.001424576,0.03149525,0.08776952,0.000049629216],"about_ca_topic_score_codex":0.0042751404,"about_ca_topic_score_gemma":0.008658733,"teacher_disagreement_score":0.017532254,"about_ca_system_score_codex":0.0050019193,"about_ca_system_score_gemma":0.01464732,"threshold_uncertainty_score":0.09272057},"labels":[],"label_agreement":null},{"id":"W2318621088","doi":"10.1515/cercles-2014-0009","title":"Investigating language assessment literacy: Collaboration between assessment specialists and Canadian university admissions officers","year":2014,"lang":"en","type":"article","venue":"Language Learning in Higher Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"McGill University","funders":"","keywords":"Test (biology); Psychology; Language assessment; Literacy; Medical education; Diversity (politics); Language proficiency; Pedagogy; Applied psychology; Sociology; Medicine","score_opus":0.017945070602510656,"score_gpt":0.3650585029343927,"score_spread":0.347113432331882,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2318621088","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98982877,0.00019949069,0.00052782876,0.0029295045,0.000067590685,0.00042873522,0.00008557777,0.000036315476,0.0058960626],"genre_scores_gemma":[0.99604416,0.00014391729,0.0010728927,0.00074292044,0.000030899493,0.00018657204,0.000050396437,0.000010140646,0.0017180882],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9563934,0.020066965,0.00220917,0.0020744368,0.00905849,0.010197481],"domain_scores_gemma":[0.85238856,0.03829233,0.008860885,0.0021996703,0.052639656,0.04561891],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.036881667,0.00052456564,0.00108363,0.0043706764,0.020441238,0.0069994363,0.002698525,0.0015576859,0.0042830356],"category_scores_gemma":[0.09600493,0.00091874314,0.00054444,0.0030953444,0.0049400753,0.0017238568,0.011357521,0.0034122812,0.0005886615],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031769776,0.0010913501,0.22581734,0.0002718766,0.000044300556,0.0013741052,0.70817226,0.00023928589,0.001790543,0.0005510471,0.0057634884,0.0545666],"study_design_scores_gemma":[0.000041722808,0.0004912408,0.14317052,0.00023798403,0.000023787477,0.00017534225,0.843514,0.00068967,0.00071088795,0.00028452824,0.010562261,0.00009803332],"about_ca_topic_score_codex":0.68461514,"about_ca_topic_score_gemma":0.8093952,"teacher_disagreement_score":0.95315474,"about_ca_system_score_codex":0.046845276,"about_ca_system_score_gemma":0.11506572,"threshold_uncertainty_score":0.6344844},"labels":[],"label_agreement":null},{"id":"W2326599554","doi":"10.3138/cmlr.2802","title":"Putting Students at the Centre of Classroom L2 Writing Assessment","year":2016,"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":42,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Summative assessment; Formative assessment; Assessment for learning; Writing assessment; Mathematics education; Pedagogy; Psychology","score_opus":0.017451156989710875,"score_gpt":0.3097419731982567,"score_spread":0.2922908162085458,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2326599554","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.32683277,0.01572934,0.24219333,0.08886739,0.0044977553,0.0025486161,0.0003025271,0.00382282,0.31520543],"genre_scores_gemma":[0.8375806,0.0047853743,0.12154162,0.0050450945,0.00034218334,0.0009412003,0.00013729776,0.00024802587,0.029378619],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9817762,0.010936294,0.00095916947,0.0011455651,0.004189606,0.0009932801],"domain_scores_gemma":[0.9789716,0.007404934,0.0014101376,0.0012887662,0.008133935,0.0027906485],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013434352,0.0006988028,0.0010500972,0.0023599996,0.0045569483,0.007220322,0.0020521493,0.002567256,0.0041720825],"category_scores_gemma":[0.036943115,0.00035965603,0.00056081044,0.0011476688,0.0042089797,0.005208071,0.008489288,0.00362044,0.0020359252],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015650407,0.0004867127,0.010750891,0.0014459443,0.0000295874,0.00082717807,0.16727406,0.00047765084,0.0060885497,0.030500043,0.016514331,0.76544863],"study_design_scores_gemma":[0.00016604832,0.0011662544,0.040206574,0.005272055,0.00016375876,0.0023841066,0.13869587,0.002302481,0.020064669,0.06218389,0.7270461,0.00034824864],"about_ca_topic_score_codex":0.015089754,"about_ca_topic_score_gemma":0.029746864,"teacher_disagreement_score":0.015089754,"about_ca_system_score_codex":0.0051309094,"about_ca_system_score_gemma":0.017901368,"threshold_uncertainty_score":0.0710485},"labels":[],"label_agreement":null},{"id":"W2333528754","doi":"10.2304/elea.2011.8.4.296","title":"‘We've Spent too Much Money to Go Back Now’: Credit-Crunched Literacy and a Future for Learning","year":2011,"lang":"en","type":"article","venue":"E-Learning and Digital Media","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Literacy; Scholarship; Discipline; Diversity (politics); Intervention (counseling); Information literacy; Sociology; Pedagogy; Public relations; Mathematics education; Engineering ethics; Psychology; Political science; Social science; Engineering","score_opus":0.02779370566600818,"score_gpt":0.3081507892681815,"score_spread":0.2803570836021733,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2333528754","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.37527984,0.003248339,0.005978942,0.4255739,0.003225731,0.00007691982,0.000044840075,0.00012453509,0.18644693],"genre_scores_gemma":[0.95465064,0.00080352376,0.00094691553,0.016807538,0.00020107461,0.00006432446,0.000014757986,0.000038487513,0.026472624],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.9945479,0.0038954758,0.00009402585,0.00023414227,0.0005288774,0.0006995145],"domain_scores_gemma":[0.9934529,0.0035306632,0.00068004546,0.00031545616,0.00049991894,0.0015211108],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005217613,0.00028296004,0.0003432959,0.00049952767,0.008184201,0.0069885766,0.0007213047,0.004308823,0.0068752193],"category_scores_gemma":[0.01804314,0.00016853251,0.00023645979,0.00052606774,0.016155003,0.010180112,0.0073076393,0.007710084,0.00072291255],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002121406,0.00056469324,0.006439375,0.00022303197,0.00001783315,0.0014546779,0.42434782,0.00016711869,0.0010865841,0.27096948,0.12760845,0.16690873],"study_design_scores_gemma":[0.000067147135,0.0002351656,0.0058248835,0.00059397065,0.000014073731,0.0013132368,0.4796869,0.00037292638,0.0009462967,0.11652037,0.39435297,0.00007204413],"about_ca_topic_score_codex":0.0024924893,"about_ca_topic_score_gemma":0.0044666007,"teacher_disagreement_score":0.008184201,"about_ca_system_score_codex":0.0030350636,"about_ca_system_score_gemma":0.0036352475,"threshold_uncertainty_score":0.027593672},"labels":[],"label_agreement":null},{"id":"W2336837379","doi":"10.55016/ojs/jet.v42i1.52475","title":"Equity in Multicultural Student Assessment","year":2018,"lang":"en","type":"article","venue":"Journal of educational thought.","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brock University","funders":"","keywords":"Equity (law); Multiculturalism; Multicultural education; Psychology; Pedagogy; Mathematics education; Political science","score_opus":0.07106421306515492,"score_gpt":0.513175145370691,"score_spread":0.44211093230553605,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2336837379","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8004184,0.002386723,0.050651304,0.02114291,0.00042952795,0.00050295464,0.00006782082,0.00014547307,0.12425478],"genre_scores_gemma":[0.9948953,0.000086611755,0.0035820834,0.00052188244,0.000044090935,0.000058792484,0.000005510702,0.000010406856,0.0007953496],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.8966458,0.0771729,0.003265837,0.0030278952,0.01682602,0.0030614843],"domain_scores_gemma":[0.88095605,0.07996388,0.00740024,0.009728425,0.017226538,0.004724922],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.08321262,0.00029876461,0.0005729563,0.0019235095,0.0037706995,0.006489059,0.0010939008,0.0009974455,0.0024960393],"category_scores_gemma":[0.17202933,0.0002494334,0.0004278994,0.0011173364,0.0064179446,0.005570635,0.012559525,0.0016928618,0.00018370977],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00044669377,0.0005038581,0.20726594,0.00034292994,0.00013255783,0.00020349554,0.10433658,0.0015157382,0.0012001699,0.0906973,0.0035216336,0.589833],"study_design_scores_gemma":[0.00016208606,0.0014311707,0.2543275,0.0017833287,0.00014327119,0.0007961981,0.11658258,0.009157191,0.007938209,0.55390215,0.053544093,0.00023228842],"about_ca_topic_score_codex":0.0036948519,"about_ca_topic_score_gemma":0.0053832857,"teacher_disagreement_score":0.08321262,"about_ca_system_score_codex":0.004306473,"about_ca_system_score_gemma":0.0065305354,"threshold_uncertainty_score":0.44007564},"labels":[],"label_agreement":null},{"id":"W2341533239","doi":"10.1007/978-3-319-23398-7_7","title":"Current Policies Surrounding Assessment in Alberta: Future Implications","year":2015,"lang":"en","type":"book-chapter","venue":"˜The œenabling power of assessment","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Lethbridge","funders":"","keywords":"Current (fluid); Environmental planning; Political science; Environmental resource management; Geography; Environmental science; Geology; Oceanography","score_opus":0.05835413965550165,"score_gpt":0.39793250806224234,"score_spread":0.3395783684067407,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2341533239","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.045283984,0.013944742,0.004219649,0.48819932,0.0025540602,0.00010838571,0.0006191029,0.00043938647,0.44463146],"genre_scores_gemma":[0.5690122,0.020674145,0.01126477,0.0744689,0.0010092115,0.00014641834,0.00058888935,0.0001707467,0.32266477],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9903419,0.0013921064,0.00031338903,0.0005065003,0.004168854,0.003277218],"domain_scores_gemma":[0.9788886,0.006606454,0.0005784816,0.0004289143,0.008034879,0.005462814],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011580206,0.0004144113,0.00044262438,0.0019745748,0.009001726,0.016690556,0.004635703,0.006048118,0.018929824],"category_scores_gemma":[0.021906642,0.00034299266,0.0004325158,0.0039709457,0.010136353,0.004952404,0.0062422855,0.0074764783,0.0010308479],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010818412,0.00015296953,0.012098705,0.0005020464,0.000017755923,0.0005229602,0.006757576,0.004223409,0.0006453925,0.5959655,0.16296619,0.2160393],"study_design_scores_gemma":[0.00004977447,0.00006701669,0.036244642,0.0026095344,0.000046066532,0.00021748307,0.031119196,0.0028853032,0.00084237894,0.14767133,0.77802896,0.00021827538],"about_ca_topic_score_codex":0.9618433,"about_ca_topic_score_gemma":0.97963595,"teacher_disagreement_score":0.9203334,"about_ca_system_score_codex":0.07966664,"about_ca_system_score_gemma":0.3320193,"threshold_uncertainty_score":0.5780246},"labels":[],"label_agreement":null},{"id":"W2345957802","doi":"10.7202/1035611ar","title":"Suivi des apprentissages au moyen d’évaluations formatives par questions à choix multiples diffusées sur le Web par le logiciel eTests","year":2014,"lang":"fr","type":"article","venue":"Revue internationale des technologies en pédagogie universitaire","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Humanities; Physics; Philosophy","score_opus":0.05153691290710508,"score_gpt":0.3018681899848292,"score_spread":0.2503312770777241,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2345957802","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7313938,0.0033204847,0.17396875,0.0025217903,0.0005583464,0.0012102879,0.0015869634,0.0035253495,0.081914164],"genre_scores_gemma":[0.8885909,0.00096926815,0.0839806,0.0002736812,0.000116624506,0.00090240454,0.0010816788,0.0005053859,0.023579376],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9655403,0.017348895,0.002370958,0.0027426977,0.0109925745,0.0010046699],"domain_scores_gemma":[0.81583005,0.12037897,0.009534316,0.009230165,0.041734178,0.0032922598],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.024884498,0.0013447572,0.0009442141,0.0040137535,0.0010162648,0.0050250106,0.001058379,0.0017564712,0.012856157],"category_scores_gemma":[0.12744415,0.00046164723,0.0011654273,0.0015353411,0.00090612494,0.0046314364,0.0026699505,0.0019388999,0.0047722748],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003378297,0.0010179944,0.09773502,0.002385886,0.000584779,0.0005506908,0.01791162,0.0050325193,0.032984123,0.014228561,0.009205496,0.814985],"study_design_scores_gemma":[0.00064697483,0.010031979,0.4987608,0.0035388586,0.0014494457,0.002820286,0.031749923,0.0823737,0.13804826,0.055596303,0.17402793,0.00095563167],"about_ca_topic_score_codex":0.0023816242,"about_ca_topic_score_gemma":0.0025351366,"teacher_disagreement_score":0.024884498,"about_ca_system_score_codex":0.0014382298,"about_ca_system_score_gemma":0.0020762407,"threshold_uncertainty_score":0.13160336},"labels":[],"label_agreement":null},{"id":"W2393663033","doi":"10.21083/nrsc.v0i9.3672","title":"The Power of Peer Evaluation: Rethinking Pedagogy in L2 Conversation Courses","year":2016,"lang":"en","type":"article","venue":"Nouvelle Revue Synergies Canada","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Conversation; Peer evaluation; Peer review; Peer feedback; Power (physics); Pedagogy; Psychology; Peer assessment; Perception; Higher education; Engineering ethics; Mathematics education; Political science; Engineering","score_opus":0.027354771169304487,"score_gpt":0.3364956000897792,"score_spread":0.3091408289204747,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2393663033","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6457263,0.009594602,0.13640879,0.03828033,0.0014254057,0.0020937738,0.000076445234,0.00078125467,0.16561314],"genre_scores_gemma":[0.9741943,0.0010319882,0.02044835,0.00077321765,0.00020531101,0.00046908486,0.000014120492,0.00011427454,0.0027493113],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.7110597,0.24877241,0.003946054,0.004894345,0.029318932,0.0020086141],"domain_scores_gemma":[0.5465472,0.387641,0.013293088,0.016990101,0.031048927,0.0044798222],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.17453198,0.000845361,0.0010605156,0.0044904733,0.0058470746,0.01376081,0.0029504322,0.002396146,0.0028184312],"category_scores_gemma":[0.38987583,0.0005164177,0.00061328977,0.0020660402,0.01204846,0.013342519,0.013283415,0.0037434297,0.00061921665],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034102335,0.0003839066,0.019491812,0.0011296093,0.00010179353,0.00024869517,0.26709846,0.0007591093,0.002286506,0.02660495,0.0037874468,0.6777667],"study_design_scores_gemma":[0.0004127982,0.005076086,0.10036256,0.01197969,0.0005940797,0.0015126562,0.43326992,0.019098649,0.018818088,0.19721295,0.21090554,0.00075708114],"about_ca_topic_score_codex":0.005583689,"about_ca_topic_score_gemma":0.009921779,"teacher_disagreement_score":0.17453198,"about_ca_system_score_codex":0.006528722,"about_ca_system_score_gemma":0.01168506,"threshold_uncertainty_score":0.92302436},"labels":[],"label_agreement":null},{"id":"W2397824374","doi":"10.59236/td2014vol7iss21213","title":"How Am I Doing? Formative Feedback for Graduate Students Learning to Teach","year":2014,"lang":"en","type":"article","venue":"Transformative Dialogues Teaching and Learning Journal","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Formative assessment; Graduate students; Psychology; Peer feedback; Pedagogy; Medical education; Mathematics education; Medicine","score_opus":0.0361386311556136,"score_gpt":0.3420188290598755,"score_spread":0.3058801979042619,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2397824374","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92173904,0.0010505833,0.029479453,0.014794823,0.00068130926,0.00088545977,0.0006995271,0.00078998896,0.029879887],"genre_scores_gemma":[0.97561127,0.0010047402,0.018482665,0.0010048554,0.00011189927,0.0006916413,0.0001892233,0.00007076243,0.0028328937],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.97748476,0.017217025,0.0008092893,0.00046784276,0.0034106844,0.000610441],"domain_scores_gemma":[0.8906349,0.07849723,0.008711291,0.0043714666,0.013298113,0.004486939],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.034,0.00058127416,0.00058156514,0.0019294848,0.001512682,0.0033848719,0.0011451615,0.0009305899,0.0021310498],"category_scores_gemma":[0.16187072,0.0001852374,0.00043423934,0.0011607844,0.001418522,0.0020739883,0.002144609,0.0022134148,0.000831011],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00054099946,0.0011797276,0.08400299,0.001180242,0.0000738493,0.00064781425,0.376535,0.0005917832,0.0058219307,0.0037986499,0.018894127,0.5067329],"study_design_scores_gemma":[0.00019607757,0.0067819813,0.2462146,0.0038353421,0.00022813989,0.0025685402,0.5554925,0.0040568435,0.014824762,0.018659478,0.1466219,0.0005197868],"about_ca_topic_score_codex":0.00076969736,"about_ca_topic_score_gemma":0.0017983768,"teacher_disagreement_score":0.034,"about_ca_system_score_codex":0.0020056933,"about_ca_system_score_gemma":0.0030245334,"threshold_uncertainty_score":0.1798113},"labels":[],"label_agreement":null},{"id":"W2405113580","doi":"10.1177/0098628316649312","title":"The Impact of Participating in a Peer Assessment Activity on Subsequent Academic Performance","year":2016,"lang":"en","type":"article","venue":"Teaching of Psychology","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kwantlen Polytechnic University","funders":"","keywords":"Attendance; Psychology; Peer assessment; Peer evaluation; Medical education; Peer feedback; Academic achievement; Higher education; Mathematics education; Medicine","score_opus":0.10341006593162669,"score_gpt":0.524978013856735,"score_spread":0.4215679479251083,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2405113580","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99790406,0.000112940885,0.0003384527,0.000058533366,0.000034351855,0.00007582116,0.000014645556,0.000021746735,0.0014394153],"genre_scores_gemma":[0.99716115,0.00013573421,0.0011371814,0.000030813284,0.00003879197,0.00008849442,0.000051374893,0.000006999313,0.0013495841],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99507755,0.0025598048,0.00030347786,0.0005057636,0.0010939928,0.0004594988],"domain_scores_gemma":[0.9813619,0.009064327,0.0019540149,0.001624028,0.0016751448,0.0043205144],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0040968815,0.00061643316,0.0007316717,0.00044136398,0.0005702994,0.00079944194,0.00058413466,0.0006122531,0.00275741],"category_scores_gemma":[0.02075194,0.00016706613,0.0004505627,0.00020355832,0.00034578517,0.00040229806,0.0010165815,0.0007591857,0.0005219277],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.013206504,0.08001479,0.16182175,0.0008116611,0.00059119985,0.0005881333,0.0048076054,0.0008551742,0.092708476,0.00027748515,0.0015036152,0.6428137],"study_design_scores_gemma":[0.000571909,0.081795156,0.892944,0.000116529816,0.00044727654,0.00032750706,0.001629597,0.0011271544,0.017345399,0.00032895932,0.0032904327,0.000076125485],"about_ca_topic_score_codex":0.0006181814,"about_ca_topic_score_gemma":0.0010995944,"teacher_disagreement_score":0.99590313,"about_ca_system_score_codex":0.00018017346,"about_ca_system_score_gemma":0.0006840853,"threshold_uncertainty_score":0.021666646},"labels":[],"label_agreement":null},{"id":"W2408321301","doi":"10.5539/ies.v9n6p76","title":"The Influence of Educational Programme on Teachers’ Error Correction Preferences in the Speaking Skill: Insights from English as a Foreign Language Context","year":2016,"lang":"en","type":"article","venue":"International Education Studies","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Context (archaeology); Mathematics education; Class (philosophy); Psychology; English as a foreign language; Curriculum; Error detection and correction; Foreign language; Corrective feedback; Teaching method; Language proficiency; Error analysis; Pedagogy; Computer science; Mathematics","score_opus":0.04945085154891508,"score_gpt":0.4092691588517989,"score_spread":0.3598183073028838,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2408321301","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99880135,0.000032275828,0.00005199979,0.000053168038,0.0000016615763,0.00000558971,0.000005655534,9.0758107e-7,0.0010474662],"genre_scores_gemma":[0.9996183,0.000042101045,0.00004889679,0.000013578925,0.0000015138354,0.000007663113,0.00000467426,0.0000018365338,0.00026131625],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.99554956,0.0029949155,0.00015521377,0.00027183432,0.00051164324,0.00051690254],"domain_scores_gemma":[0.98246884,0.013362956,0.0020251065,0.0002484161,0.00090393366,0.0009906943],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004214089,0.00019206884,0.00038610335,0.0006836405,0.0014051045,0.0023860354,0.00043948545,0.0004590562,0.002625366],"category_scores_gemma":[0.015388532,0.00020307911,0.00023706455,0.00057981256,0.0014627052,0.00092602073,0.0015395669,0.0007914112,0.00021422778],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009486821,0.0021745318,0.32459295,0.000373463,0.0000541099,0.001708003,0.61804885,0.00030281732,0.0053665238,0.0009703785,0.0004399924,0.04501957],"study_design_scores_gemma":[0.000043397824,0.0008249125,0.5369486,0.00013168952,0.000041558418,0.0002027565,0.4574543,0.00034601064,0.0011065692,0.00032386617,0.0025436068,0.00003271631],"about_ca_topic_score_codex":0.0067888964,"about_ca_topic_score_gemma":0.0135804955,"teacher_disagreement_score":0.0067888964,"about_ca_system_score_codex":0.0013145468,"about_ca_system_score_gemma":0.0013257401,"threshold_uncertainty_score":0.022286534},"labels":[],"label_agreement":null},{"id":"W2408838614","doi":"","title":"Examining the examination: Canadian versus US certification exam.","year":2000,"lang":"en","type":"letter","venue":"PubMed","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Medicine; Certification; Family medicine; Medical physics; Medical education; Management","score_opus":0.11618409775338881,"score_gpt":0.29285253471322986,"score_spread":0.17666843695984105,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2408838614","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0035962667,0.0012641185,0.00010803884,0.9615794,0.006681653,0.000029589319,0.00021928635,0.000047890946,0.026473748],"genre_scores_gemma":[0.06981813,0.0023746132,0.00075057975,0.8406838,0.013838882,0.00007502173,0.00022078035,0.000059020895,0.07217915],"study_design_codex":"not_applicable","study_design_gemma":"observational","domain_scores_codex":[0.9969212,0.0005324375,0.00047186407,0.0003547105,0.0012015734,0.0005181269],"domain_scores_gemma":[0.971648,0.013077538,0.0010111819,0.00043062758,0.009659192,0.0041735526],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0044804867,0.00030457816,0.0005693937,0.0013396256,0.004486016,0.0023259504,0.001798482,0.028023545,0.016458316],"category_scores_gemma":[0.05206406,0.0003123745,0.00040639058,0.0008039446,0.0018894506,0.0017971992,0.0011942219,0.010564096,0.0051503573],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009927584,0.000035895748,0.0043915384,0.000036968544,0.0000039100833,0.0017437126,0.00020702704,0.00004588641,0.00014745857,0.001952477,0.97388285,0.017452957],"study_design_scores_gemma":[0.00031094332,0.00023420097,0.04673661,0.0013869539,0.00006663292,0.010814941,0.0055944505,0.0013673615,0.00096953614,0.008896866,0.9234671,0.00015437751],"about_ca_topic_score_codex":0.23329991,"about_ca_topic_score_gemma":0.53475136,"teacher_disagreement_score":0.9955195,"about_ca_system_score_codex":0.011433991,"about_ca_system_score_gemma":0.01361892,"threshold_uncertainty_score":0.46388394},"labels":[],"label_agreement":null},{"id":"W2411843932","doi":"10.5539/elt.v9n7p129","title":"Be Creative and Collaborative: Strategies and Implications of Blogging in EFL Classes","year":2016,"lang":"en","type":"article","venue":"English Language Teaching","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Immediacy; Psychology; Context (archaeology); Curriculum; Collaborative writing; Pedagogy; Mathematics education","score_opus":0.014874673134921329,"score_gpt":0.3516294710616509,"score_spread":0.3367547979267296,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2411843932","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94125116,0.00041469545,0.0023915132,0.0039511556,0.00013497143,0.00020387191,0.00003523543,0.000095188305,0.05152209],"genre_scores_gemma":[0.99200857,0.00020206363,0.0021624013,0.0003445088,0.000020074878,0.00010787061,0.000019422348,0.000026985737,0.0051080487],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9915175,0.0061648814,0.00023853865,0.000523316,0.0007242693,0.0008314011],"domain_scores_gemma":[0.9714073,0.020791514,0.0019839595,0.0012647235,0.0013570262,0.003195385],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008024354,0.0006989284,0.00038843532,0.0017569497,0.009680487,0.01029929,0.0019529262,0.0025389811,0.0041441335],"category_scores_gemma":[0.028166035,0.00040627303,0.00031748638,0.0011072457,0.0059713935,0.005829143,0.005488673,0.002544633,0.00078542414],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013138773,0.0010870857,0.01926661,0.00022998781,0.000012491532,0.0017421658,0.8845639,0.00008200233,0.0021786182,0.00547873,0.0027724528,0.08245449],"study_design_scores_gemma":[0.000031219188,0.00015604355,0.0127272345,0.0002043155,0.000012076437,0.0007399814,0.95720965,0.0003425242,0.00074804464,0.0030219557,0.024775593,0.000031405405],"about_ca_topic_score_codex":0.00175735,"about_ca_topic_score_gemma":0.0039762943,"teacher_disagreement_score":0.01029929,"about_ca_system_score_codex":0.0017880644,"about_ca_system_score_gemma":0.0025800352,"threshold_uncertainty_score":0.042437315},"labels":[],"label_agreement":null},{"id":"W2441041702","doi":"10.1111/medu.12985","title":"Taking the sting out of assessment: is there a role for progress testing?","year":2016,"lang":"en","type":"review","venue":"Medical Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":51,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; University of Ottawa","funders":"","keywords":"Context (archaeology); Curriculum; Test (biology); Standardized test; Assessment for learning; Educational assessment; Formative assessment; Unintended consequences; Educational measurement; Risk assessment; Computer science; Psychology; Engineering ethics; Mathematics education; Engineering; Pedagogy; Political science","score_opus":0.09766983136844255,"score_gpt":0.5079418249069397,"score_spread":0.4102719935384972,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2441041702","genre_codex":"commentary","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022286352,0.060562473,0.15566699,0.7116199,0.007709091,0.00070830755,0.00018124391,0.0019007818,0.039364796],"genre_scores_gemma":[0.52882296,0.049593702,0.29943106,0.10390422,0.005839964,0.0021433907,0.0003738516,0.0011357957,0.00875511],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.8083539,0.14105383,0.008285033,0.0068217963,0.032153595,0.003331764],"domain_scores_gemma":[0.36075562,0.4745783,0.036257632,0.03650757,0.06812955,0.023771312],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.22974747,0.0014313149,0.002328632,0.0046401853,0.00268813,0.013438183,0.0075251823,0.0081259655,0.006310282],"category_scores_gemma":[0.5259007,0.00075345224,0.0016703136,0.0029369018,0.02140061,0.036286544,0.009033089,0.012621288,0.002642701],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034754325,0.00028515345,0.02601042,0.0029586751,0.00013425079,0.00044705605,0.00914927,0.0007038063,0.0004926733,0.074129075,0.027073693,0.8582683],"study_design_scores_gemma":[0.00039032212,0.0032869107,0.041525107,0.056723118,0.0004945042,0.005364839,0.032352876,0.0075509744,0.0053121103,0.41156736,0.43453753,0.00089442375],"about_ca_topic_score_codex":0.005300208,"about_ca_topic_score_gemma":0.006281208,"teacher_disagreement_score":0.22974747,"about_ca_system_score_codex":0.0061763544,"about_ca_system_score_gemma":0.027053215,"threshold_uncertainty_score":0.9498585},"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,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology; Perception; Peer feedback; Constructive; Video feedback; Control (management); Mathematics education; Pedagogy; Computer science","score_opus":0.01930918518031864,"score_gpt":0.3550008529784101,"score_spread":0.33569166779809145,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2461301006","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9992873,0.000033889257,0.00018626051,0.000024565985,0.0000069100365,0.00004533448,0.000015101864,0.000010597669,0.00039018184],"genre_scores_gemma":[0.99810946,0.0000658645,0.0009843453,0.000029384768,0.000011097699,0.00009781415,0.000028328077,0.000003775431,0.0006700167],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99679166,0.0015277476,0.00030805287,0.0002953742,0.00084054854,0.00023665138],"domain_scores_gemma":[0.97702765,0.01516428,0.0036557242,0.0009321452,0.0018788844,0.001341355],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005466695,0.00039567795,0.00060557737,0.00057224266,0.0004792664,0.0011903968,0.00042962498,0.00051917444,0.002386369],"category_scores_gemma":[0.020580854,0.00017429571,0.0003426926,0.0002954209,0.0004012136,0.00054028805,0.0006189092,0.0005292973,0.00031818124],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.008812625,0.023857743,0.3474854,0.0019390568,0.0002327001,0.0005745931,0.06611079,0.00079008884,0.08151216,0.0001968642,0.0008975406,0.46759045],"study_design_scores_gemma":[0.00048294835,0.04533347,0.88122815,0.0003254042,0.00034251198,0.00024923982,0.034689017,0.001857422,0.031595737,0.0002791689,0.003496944,0.00011989421],"about_ca_topic_score_codex":0.00079604203,"about_ca_topic_score_gemma":0.0011208614,"teacher_disagreement_score":0.005466695,"about_ca_system_score_codex":0.00041478855,"about_ca_system_score_gemma":0.0006041238,"threshold_uncertainty_score":0.028910995},"labels":[],"label_agreement":null},{"id":"W2464754146","doi":"","title":"The Untried Path: Exemplary Elementary School Teachers’ Understanding of and Experiences with Classroom Assessment","year":2016,"lang":"en","type":"dissertation","venue":"Brock University Digital Repository (Brock University)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Mathematics education; Path (computing); Pedagogy; Psychology; Sociology; Computer science","score_opus":0.017084391693825737,"score_gpt":0.25224128652641625,"score_spread":0.2351568948325905,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2464754146","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98301345,0.0005633781,0.0044243657,0.0019738777,0.00005822761,0.00008794581,0.000054723154,0.000046483707,0.009777467],"genre_scores_gemma":[0.9938262,0.00040471007,0.0012677712,0.000376413,0.000008815459,0.0000602525,0.000029573732,0.000037377682,0.0039888467],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9904745,0.0056697847,0.00031938282,0.00078005495,0.0013970359,0.0013591731],"domain_scores_gemma":[0.9881152,0.008386555,0.000610867,0.0005414039,0.0011373606,0.0012084992],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007236658,0.0005699166,0.0008632639,0.0014222359,0.012368806,0.0067279045,0.0017847286,0.0018900881,0.0015399202],"category_scores_gemma":[0.018182524,0.00078020757,0.00039853647,0.0013597148,0.015718147,0.004249572,0.006796112,0.004491588,0.00030132482],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011350259,0.00002145426,0.0015490652,0.000027901528,0.0000016784254,0.00050531916,0.9942021,0.000022048423,0.0003997592,0.00074733264,0.0002273911,0.0022846393],"study_design_scores_gemma":[0.0000018349567,0.00002133256,0.0012072466,0.000066780856,0.0000034891068,0.00031016694,0.9884758,0.000050603965,0.00024172808,0.00035039923,0.009257302,0.000013263006],"about_ca_topic_score_codex":0.058820296,"about_ca_topic_score_gemma":0.119241625,"teacher_disagreement_score":0.058820296,"about_ca_system_score_codex":0.0068727196,"about_ca_system_score_gemma":0.006326008,"threshold_uncertainty_score":0.11695588},"labels":[],"label_agreement":null},{"id":"W2470295771","doi":"","title":"THE CONTRIBUTIONS OF DIGITAL CONCEPT MAPS TO ASSESSMENT FOR LEARNING PRACTICES","year":2013,"lang":"en","type":"article","venue":"Cognition and Exploratory Learning in Digital Age","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Formative assessment; Variety (cybernetics); Computer science; Workload; Strengths and weaknesses; Digital learning; Multimedia; Assessment for learning; Human–computer interaction; Data science; Mathematics education; Artificial intelligence; Psychology","score_opus":0.040250405043100866,"score_gpt":0.36111613432163386,"score_spread":0.320865729278533,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2470295771","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5473969,0.007078513,0.3135491,0.008072013,0.00049324875,0.0010268528,0.00026027928,0.0011170255,0.12100615],"genre_scores_gemma":[0.8337775,0.0015221634,0.16168809,0.00020642267,0.00013809233,0.00031740754,0.00005319093,0.00007577459,0.0022213596],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98488337,0.009580006,0.0005764818,0.00047044616,0.0042557544,0.00023389579],"domain_scores_gemma":[0.88302106,0.09626676,0.0029938107,0.0055925455,0.009632083,0.0024937433],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015178218,0.00065438845,0.0003524633,0.00507968,0.0007430688,0.005341282,0.0008168879,0.0007326196,0.0020327826],"category_scores_gemma":[0.095913194,0.0002823588,0.00031957417,0.0017866096,0.0024676262,0.005692122,0.0030731587,0.0010663352,0.0003011964],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015805963,0.00035728526,0.02283145,0.0007384649,0.00004576087,0.00013047029,0.012317353,0.0019216316,0.0017248023,0.03227983,0.001744518,0.92575026],"study_design_scores_gemma":[0.00024790288,0.0030485059,0.16003439,0.00367991,0.0004025934,0.0028812154,0.031241314,0.06226541,0.020301664,0.5307414,0.18454,0.0006157197],"about_ca_topic_score_codex":0.0016570607,"about_ca_topic_score_gemma":0.0017493956,"teacher_disagreement_score":0.015178218,"about_ca_system_score_codex":0.0012657245,"about_ca_system_score_gemma":0.0021936179,"threshold_uncertainty_score":0.080271065},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.08897567591661655,"score_gpt":0.4676807480738409,"score_spread":0.3787050721572244,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2472075195","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0028277203,0.98201513,0.0034710888,0.004914734,0.0006040175,0.00017562327,0.0000510355,0.000027265356,0.005913349],"genre_scores_gemma":[0.0560399,0.9300365,0.009087312,0.0025604283,0.00036762308,0.000533677,0.00014529795,0.000032657776,0.0011966203],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.95629257,0.024818879,0.006562093,0.0016909097,0.010007771,0.00062772183],"domain_scores_gemma":[0.76310533,0.20488133,0.009693179,0.0034023062,0.018251702,0.0006661583],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.051355753,0.0010970624,0.0034348818,0.018317094,0.0016152989,0.007423318,0.0030919574,0.003056044,0.004298945],"category_scores_gemma":[0.16831045,0.0011652074,0.0020719278,0.015548998,0.0057046604,0.010027175,0.00410487,0.0031047992,0.00095394155],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009728548,0.00011335027,0.0012366952,0.109047,0.0004675871,0.00045547093,0.009397997,0.0004234482,0.00034159358,0.028563352,0.009895733,0.8399606],"study_design_scores_gemma":[0.000086055676,0.000295413,0.007582978,0.56704295,0.001329129,0.001355223,0.015672382,0.0007069353,0.0010938478,0.041269124,0.36345008,0.00011591437],"about_ca_topic_score_codex":0.002772161,"about_ca_topic_score_gemma":0.0047632065,"teacher_disagreement_score":0.9486442,"about_ca_system_score_codex":0.005699094,"about_ca_system_score_gemma":0.01597768,"threshold_uncertainty_score":0.2715984},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Engineering ethics; Computer science; Engineering management; Engineering","score_opus":0.041019253824978785,"score_gpt":0.3993390365835251,"score_spread":0.3583197827585463,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2479837187","genre_codex":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0028900418,0.061750904,0.14566869,0.5755782,0.0102428,0.00034376894,0.00011371119,0.0012489153,0.20216298],"genre_scores_gemma":[0.25275326,0.09619332,0.41679305,0.072905205,0.015713604,0.002274571,0.0003101121,0.0015142959,0.14154255],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9618586,0.022589935,0.001614517,0.0014988023,0.011487482,0.00095066737],"domain_scores_gemma":[0.88586575,0.09141654,0.0017430576,0.005697603,0.011287071,0.0039899596],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0541296,0.0009734,0.0015148506,0.001873669,0.0028288336,0.02083368,0.0044211457,0.0080569405,0.009620931],"category_scores_gemma":[0.09115326,0.00061742804,0.00071519666,0.0015828384,0.017593687,0.025142152,0.011063178,0.01656519,0.0039117215],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019476936,0.000089471716,0.0003433909,0.00070652005,0.000015628753,0.00004254864,0.0021730629,0.00064096623,0.00022472025,0.4577105,0.09436889,0.44366482],"study_design_scores_gemma":[0.00002420359,0.000092725764,0.00057473715,0.0024107196,0.000010426585,0.00012875404,0.0022454085,0.0014252568,0.00031653518,0.5762968,0.41643214,0.000042286512],"about_ca_topic_score_codex":0.0048449105,"about_ca_topic_score_gemma":0.0059245867,"teacher_disagreement_score":0.0541296,"about_ca_system_score_codex":0.006355197,"about_ca_system_score_gemma":0.02890906,"threshold_uncertainty_score":0.28626812},"labels":[],"label_agreement":null},{"id":"W2481621308","doi":"10.4018/978-1-4666-0068-3.ch006","title":"Assessing Science Inquiry","year":2012,"lang":"en","type":"book-chapter","venue":"Advances in educational technologies and instructional design book series","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University; University of Victoria","funders":"","keywords":"Summative assessment; Psychology; Mathematics education; Process (computing); Inquiry-based learning; Cognition; Pedagogy; Computer science; Formative assessment","score_opus":0.057102462581540815,"score_gpt":0.37366891643471717,"score_spread":0.31656645385317633,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2481621308","genre_codex":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0143704275,0.0077084177,0.08155778,0.0018522595,0.0010226764,0.00059856224,0.00073512085,0.0016987614,0.89045596],"genre_scores_gemma":[0.063710414,0.017258555,0.20517859,0.0016428783,0.00027038393,0.00056750106,0.0017623109,0.00055109727,0.7090582],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9991543,0.0001475829,0.00003978448,0.00010078985,0.00052617944,0.000031292635],"domain_scores_gemma":[0.9986958,0.0005875336,0.000044827186,0.00007448691,0.0005229803,0.00007429381],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0008965202,0.00058164215,0.00031970887,0.0012846219,0.0004949647,0.003258984,0.0006887978,0.00075678143,0.023357654],"category_scores_gemma":[0.0030306648,0.00019329369,0.00024075854,0.00095386925,0.00045442226,0.002164773,0.0012004885,0.0012700683,0.010896878],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015638127,0.00012514852,0.001309435,0.00048217684,0.0000070976753,0.00007753223,0.002525767,0.000758427,0.005373139,0.037000734,0.094846025,0.8574789],"study_design_scores_gemma":[0.000005456007,0.00011545064,0.00457518,0.0008153982,0.000008372761,0.0008103519,0.0016409814,0.0014660807,0.005026084,0.029280007,0.95622915,0.000027484764],"about_ca_topic_score_codex":0.0012158365,"about_ca_topic_score_gemma":0.0036614204,"teacher_disagreement_score":0.023357654,"about_ca_system_score_codex":0.00083579164,"about_ca_system_score_gemma":0.0013510598,"threshold_uncertainty_score":0.07813913},"labels":[],"label_agreement":null},{"id":"W2485771798","doi":"10.4018/978-1-59140-732-4.ch010","title":"Self-Assessment During Online Discussion","year":2011,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Perspective (graphical); Action (physics); Self-assessment; Process (computing); Action research; Citizen journalism; Psychology; Online assessment; Computer science; Mathematics education; Pedagogy; Formative assessment; World Wide Web; Artificial intelligence","score_opus":0.026535787720943914,"score_gpt":0.32138575955527415,"score_spread":0.29484997183433026,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2485771798","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.43084317,0.0013309394,0.12447136,0.001411271,0.0011991668,0.0060620895,0.0023072127,0.0032709583,0.4291038],"genre_scores_gemma":[0.6252028,0.0010618997,0.09914603,0.0005915939,0.00017853595,0.005262536,0.0018815218,0.00075840694,0.26591676],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9954418,0.0017849805,0.00022920246,0.0005465192,0.0017909997,0.00020647145],"domain_scores_gemma":[0.9911686,0.0044927034,0.000522999,0.00060568604,0.0028361052,0.0003738815],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003544603,0.0005064964,0.000401602,0.0010997846,0.0011187174,0.0018859198,0.0007983932,0.00051163865,0.021923374],"category_scores_gemma":[0.013091586,0.00018148834,0.000279842,0.00050805334,0.0004419151,0.0014783568,0.0017899667,0.0010074544,0.010010087],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00028697675,0.0012759055,0.009464618,0.00084872986,0.000018625406,0.00024299907,0.0809165,0.00051860313,0.025582079,0.008256789,0.030207738,0.8423805],"study_design_scores_gemma":[0.00008689243,0.0012807287,0.04584166,0.0015306332,0.000034073288,0.00095708563,0.04991155,0.004523264,0.058048863,0.015327258,0.8223078,0.00015019294],"about_ca_topic_score_codex":0.00027090783,"about_ca_topic_score_gemma":0.0005001234,"teacher_disagreement_score":0.021923374,"about_ca_system_score_codex":0.0005196381,"about_ca_system_score_gemma":0.00081826135,"threshold_uncertainty_score":0.07334095},"labels":[],"label_agreement":null},{"id":"W2487148800","doi":"10.4018/978-1-59140-732-4.ch020","title":"Effects of Anonymity and Accountability During Online Peer Assessment","year":2011,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Anonymity; Accountability; Peer feedback; Psychology; Peer assessment; Peer group; Online discussion; Quality (philosophy); Peer review; Social psychology; Mathematics education; Computer science; World Wide Web; Political science; Computer security","score_opus":0.025561739298318783,"score_gpt":0.33107803161382754,"score_spread":0.30551629231550875,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2487148800","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9953608,0.00005788218,0.0013624767,0.00015957552,0.000043538155,0.00024155508,0.000017740522,0.00003676332,0.002719683],"genre_scores_gemma":[0.9970131,0.000031960823,0.0019798283,0.000081067556,0.000032670672,0.000290865,0.000017674969,0.000009902957,0.0005429308],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.90146756,0.07447404,0.005948468,0.004423254,0.01091488,0.002771962],"domain_scores_gemma":[0.43724602,0.47164813,0.05306857,0.01918277,0.009815802,0.009038687],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.03687149,0.000827693,0.000846273,0.00081599044,0.0018720209,0.002566542,0.001399413,0.001340902,0.0036190727],"category_scores_gemma":[0.22262742,0.00075767876,0.00080842525,0.00045410485,0.0030947,0.00437617,0.0037640186,0.001827668,0.00031039293],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.102240756,0.04413505,0.36719385,0.0023053533,0.0010657558,0.0012931528,0.06889303,0.0067913793,0.10574095,0.0053014024,0.0016197007,0.29341966],"study_design_scores_gemma":[0.007950886,0.11732907,0.7439449,0.00073917327,0.001186098,0.0009664235,0.021696016,0.015998982,0.06667768,0.011892149,0.010729169,0.0008894521],"about_ca_topic_score_codex":0.0008624648,"about_ca_topic_score_gemma":0.0011428059,"teacher_disagreement_score":0.9631285,"about_ca_system_score_codex":0.0016881315,"about_ca_system_score_gemma":0.001975333,"threshold_uncertainty_score":0.19499743},"labels":[],"label_agreement":null},{"id":"W2489507737","doi":"10.4018/978-1-59140-747-8.ch009","title":"Testing the Validity of the Post and Vote Model of Web-Based Peer Assessment","year":2006,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Peer assessment; Pearson product-moment correlation coefficient; Psychology; Product (mathematics); Correlation coefficient; Peer evaluation; Computer science; Mathematics education; Statistics; Mathematics; Higher education; Political science","score_opus":0.06111622158566674,"score_gpt":0.3232555010889074,"score_spread":0.2621392795032406,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2489507737","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9138433,0.00018907263,0.047346417,0.0006255773,0.00036112926,0.0028588907,0.00075023645,0.00025805435,0.03376736],"genre_scores_gemma":[0.97449625,0.000071150906,0.018996118,0.00015902607,0.00006727066,0.002368325,0.0004899247,0.00007354739,0.003278351],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9401009,0.03139809,0.0033350417,0.004450341,0.019378696,0.0013369282],"domain_scores_gemma":[0.71136147,0.20551749,0.013837809,0.028063206,0.038911894,0.0023081177],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.045391195,0.0006135195,0.0008178864,0.0017880695,0.0008806906,0.0020881959,0.0015197716,0.0014142704,0.002701261],"category_scores_gemma":[0.17238946,0.00042840568,0.0012067127,0.0013520103,0.0027973852,0.00392647,0.0031768915,0.0015667097,0.0012383219],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004261311,0.0028126398,0.760771,0.00037722426,0.00067821314,0.00008668428,0.009057498,0.0032034537,0.0048116622,0.0058917077,0.0032665082,0.20478211],"study_design_scores_gemma":[0.0010984311,0.010838788,0.8783004,0.0004247691,0.00040974966,0.00050061493,0.0079948725,0.06637727,0.012743013,0.009719947,0.01133521,0.00025677917],"about_ca_topic_score_codex":0.0032628202,"about_ca_topic_score_gemma":0.00441828,"teacher_disagreement_score":0.9546088,"about_ca_system_score_codex":0.0013629774,"about_ca_system_score_gemma":0.002234441,"threshold_uncertainty_score":0.24005443},"labels":[],"label_agreement":null},{"id":"W2490078899","doi":"","title":"SYMPOSIUM: The Validity of Testing: Perceptions of Stakeholders","year":2016,"lang":"en","type":"article","venue":"ITC 2016 Conference","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Perception; Psychology; Computer science","score_opus":0.24014471523629496,"score_gpt":0.3671960779230274,"score_spread":0.12705136268673242,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2490078899","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.047273368,0.008075241,0.0064153215,0.84519565,0.027440961,0.00042701827,0.0003108583,0.00045391705,0.064407766],"genre_scores_gemma":[0.6906788,0.009202149,0.0066901455,0.19435886,0.008932988,0.0007973705,0.0005360506,0.0007772507,0.08802649],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98293394,0.008517014,0.0005338627,0.000969908,0.004974648,0.0020706689],"domain_scores_gemma":[0.9577552,0.01369398,0.0016627708,0.0008492707,0.014486316,0.0115524065],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.024163878,0.000670896,0.0006387438,0.00087911024,0.0068294182,0.010972998,0.0018298911,0.0065302844,0.026931148],"category_scores_gemma":[0.05266505,0.00065192865,0.0006659314,0.0009826032,0.0050886893,0.009455554,0.007535564,0.011558564,0.004320327],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011296433,0.00020392479,0.010509415,0.00059539406,0.000020038515,0.0006390756,0.119962186,0.00024660595,0.0019997777,0.016946625,0.7788451,0.06991887],"study_design_scores_gemma":[0.000016889115,0.00022543572,0.008976918,0.0010443963,0.0000138498235,0.0004788177,0.16776992,0.00054534303,0.0006864922,0.008341879,0.81178784,0.000112171125],"about_ca_topic_score_codex":0.0052990746,"about_ca_topic_score_gemma":0.0028802825,"teacher_disagreement_score":0.026931148,"about_ca_system_score_codex":0.0042429003,"about_ca_system_score_gemma":0.010116631,"threshold_uncertainty_score":0.1277923},"labels":[],"label_agreement":null},{"id":"W2491036265","doi":"10.4018/978-1-4666-4458-8.ch017","title":"Evaluation of Course Curriculum and Teaching","year":2013,"lang":"en","type":"book-chapter","venue":"Advances in higher education and professional development book series","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Curriculum; Checklist; Teaching method; Mathematics education; Medical education; Computer science; Psychology; Pedagogy; Medicine","score_opus":0.03734643498440647,"score_gpt":0.3990359738613538,"score_spread":0.3616895388769473,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2491036265","genre_codex":"empirical","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.46463323,0.006992333,0.08538937,0.0034620878,0.0023528875,0.006931543,0.0044739577,0.0030595332,0.4227051],"genre_scores_gemma":[0.5649972,0.0077849086,0.180329,0.0013183388,0.0005479546,0.0035937554,0.007900508,0.0010576117,0.23247072],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9909821,0.0022286722,0.00043423436,0.00041163998,0.005700176,0.00024309977],"domain_scores_gemma":[0.9748585,0.00445034,0.0015284234,0.00079979666,0.01749078,0.00087219424],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008128495,0.00045028576,0.0004984627,0.002636126,0.00042214713,0.002167197,0.00072444696,0.00039618844,0.010066942],"category_scores_gemma":[0.029462278,0.00012779476,0.00032691166,0.0014479174,0.00022039675,0.0010355327,0.0007416005,0.00057830143,0.0036147765],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001402794,0.0005677666,0.013017922,0.00049371505,0.000026614705,0.000039550912,0.0011452427,0.0006821768,0.0061697965,0.0014717547,0.027401816,0.9488433],"study_design_scores_gemma":[0.0001728602,0.0035455637,0.4309505,0.0030141387,0.00020682943,0.00070437987,0.005672423,0.011475988,0.0590413,0.0042450507,0.48071685,0.00025410604],"about_ca_topic_score_codex":0.002128031,"about_ca_topic_score_gemma":0.0038456335,"teacher_disagreement_score":0.010066942,"about_ca_system_score_codex":0.0018860006,"about_ca_system_score_gemma":0.0020744256,"threshold_uncertainty_score":0.04298812},"labels":[],"label_agreement":null},{"id":"W2492545673","doi":"10.4018/978-1-4666-9680-8.ch011","title":"Effective Feedback in Online Learning","year":2015,"lang":"en","type":"book-chapter","venue":"Advances in educational technologies and instructional design book series","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Computer science; Peer feedback; Quality (philosophy); Online learning; Multimedia; Component (thermodynamics); Psychology; Mathematics education","score_opus":0.026308220738459686,"score_gpt":0.33023002523297734,"score_spread":0.30392180449451767,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2492545673","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0069999257,0.13977309,0.104536735,0.011111816,0.008437477,0.00047849264,0.00018699197,0.0013121181,0.72716326],"genre_scores_gemma":[0.12978505,0.20097695,0.15960518,0.007776676,0.0063895117,0.00081376935,0.0005288435,0.00067212497,0.4934519],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99669087,0.0009971256,0.00015857913,0.00017286002,0.0018216985,0.00015887385],"domain_scores_gemma":[0.9966594,0.002113693,0.00015806907,0.00020382012,0.0006533636,0.00021172645],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025934807,0.0006166174,0.0005172293,0.0015267412,0.0011533991,0.0036997015,0.0010205441,0.0016622569,0.027509948],"category_scores_gemma":[0.007712408,0.00022608857,0.00034435402,0.0012272553,0.0015950447,0.006267265,0.0025948233,0.0017156352,0.006812105],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000032101092,0.00014570158,0.00018452233,0.0012349528,0.00000703134,0.00011793727,0.00208356,0.0005286031,0.001449227,0.14320907,0.08362523,0.76738214],"study_design_scores_gemma":[0.000010540868,0.00012066307,0.0006768511,0.002953653,0.000008970933,0.0006382279,0.0010477827,0.0007054433,0.0015833877,0.059497114,0.93272877,0.000028648734],"about_ca_topic_score_codex":0.00070383225,"about_ca_topic_score_gemma":0.001102441,"teacher_disagreement_score":0.027509948,"about_ca_system_score_codex":0.0013827236,"about_ca_system_score_gemma":0.0016468798,"threshold_uncertainty_score":0.09202999},"labels":[],"label_agreement":null},{"id":"W2493216399","doi":"10.1007/978-3-319-17727-4_23-1","title":"Structural Assessment of Knowledge as, of, and for Learning","year":2016,"lang":"en","type":"book-chapter","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":6,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Formative assessment; Summative assessment; Grading (engineering); Computer science; Knowledge survey; Knowledge transfer; Knowledge management; Engineering; Psychology; Mathematics education","score_opus":0.05211381892530292,"score_gpt":0.40406893827398954,"score_spread":0.3519551193486866,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2493216399","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009530015,0.014474115,0.18314886,0.0067081484,0.0014315569,0.00018967045,0.00037104997,0.00082699966,0.7833196],"genre_scores_gemma":[0.25230932,0.017889109,0.18677154,0.0012122514,0.0007432525,0.00031753213,0.0008103436,0.00040796946,0.5395387],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.998558,0.00031046377,0.00007757413,0.00011296295,0.00089816825,0.000042854685],"domain_scores_gemma":[0.99738306,0.0012694693,0.00012565248,0.0001756041,0.00094473327,0.00010136634],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017420306,0.0006553958,0.00039495365,0.0012338767,0.0004253847,0.0028045932,0.0009549277,0.00069734064,0.01192495],"category_scores_gemma":[0.0075487164,0.0002132392,0.0002857829,0.00084281137,0.0019130819,0.0028488745,0.001463388,0.0014880259,0.0035158664],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021556632,0.00004294934,0.0011282352,0.0003443553,0.000009111285,0.000032278505,0.0017198902,0.0008108101,0.0012362099,0.22776543,0.05616264,0.71072656],"study_design_scores_gemma":[0.0000053067583,0.00008565573,0.006026421,0.0011630636,0.000020113535,0.0003972237,0.0022693188,0.0060325223,0.0036603962,0.5403843,0.43991753,0.000038116115],"about_ca_topic_score_codex":0.0033509217,"about_ca_topic_score_gemma":0.009020932,"teacher_disagreement_score":0.01192495,"about_ca_system_score_codex":0.0017021957,"about_ca_system_score_gemma":0.0029921487,"threshold_uncertainty_score":0.039892912},"labels":[],"label_agreement":null},{"id":"W2493760347","doi":"","title":"Students' Perceptions of Assessment and Feedback in Higher Education","year":2016,"lang":"en","type":"article","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Education and Early Childhood Development","funders":"","keywords":"Perception; Psychology; Higher education; Mathematics education; Medical education; Pedagogy; Political science; Medicine","score_opus":0.03813233689198699,"score_gpt":0.414825810401811,"score_spread":0.376693473509824,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2493760347","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9972078,0.000076047836,0.00016103948,0.00035412775,0.000021335169,0.000013250771,0.000009783718,0.000010104399,0.0021465328],"genre_scores_gemma":[0.9991763,0.00003055131,0.00008109412,0.00006621633,0.0000068178024,0.0000069974835,0.000009405194,0.0000032800738,0.0006192074],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.9850305,0.00612966,0.0010780289,0.00057238556,0.0053580306,0.0018314531],"domain_scores_gemma":[0.91711414,0.034069687,0.01367428,0.0013169445,0.011719589,0.02210543],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011274841,0.00036556457,0.0005399315,0.0013698798,0.0018144101,0.0055462522,0.0006819587,0.0014786941,0.0046190205],"category_scores_gemma":[0.07533299,0.0003152523,0.0009032079,0.0006137959,0.0015350934,0.0016414009,0.002517302,0.0028004928,0.0007528515],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0019412509,0.005481934,0.83483213,0.00019191753,0.00014059343,0.0005498747,0.08666962,0.00067248166,0.004464295,0.0012794057,0.0026579974,0.06111849],"study_design_scores_gemma":[0.00014451535,0.0040697907,0.860825,0.00021610114,0.000092770206,0.000392619,0.12180844,0.002284796,0.003159118,0.0011534186,0.0056831893,0.00017020323],"about_ca_topic_score_codex":0.0061966917,"about_ca_topic_score_gemma":0.007142001,"teacher_disagreement_score":0.011274841,"about_ca_system_score_codex":0.002104452,"about_ca_system_score_gemma":0.0029811675,"threshold_uncertainty_score":0.05962777},"labels":[],"label_agreement":null},{"id":"W2494203092","doi":"10.4018/978-1-59904-337-1.ch010","title":"Assessment and Evaluation","year":2007,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Accountability; Peer assessment; Product (mathematics); Psychology; Online assessment; Authentic assessment; Quantitative assessment; Power (physics); Pedagogy; Public relations; Engineering ethics; Engineering; Political science; Formative assessment","score_opus":0.0740225412028311,"score_gpt":0.4119845652970274,"score_spread":0.33796202409419634,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2494203092","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0031669324,0.01871091,0.11413837,0.019598927,0.0051479125,0.0047795814,0.0023974276,0.0028487744,0.8292112],"genre_scores_gemma":[0.14605157,0.036610298,0.29158187,0.014024501,0.0040630377,0.011284032,0.0068567563,0.0037537431,0.48577425],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9217906,0.037091717,0.006216113,0.0038978742,0.029391428,0.0016122609],"domain_scores_gemma":[0.9111386,0.026489547,0.0036488224,0.01037623,0.044331685,0.004015129],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.045658216,0.0013789777,0.001993715,0.0066496874,0.0031246762,0.019368751,0.003224948,0.0031890676,0.07033906],"category_scores_gemma":[0.12021221,0.00055495603,0.0009681378,0.0050684023,0.0050396174,0.01141575,0.008394441,0.0030388518,0.040177345],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014516777,0.00013824107,0.001448078,0.0013153394,0.00004059039,0.000088414476,0.0015230022,0.0006215769,0.00035242396,0.14657372,0.18784866,0.6599049],"study_design_scores_gemma":[0.000032478318,0.00011053643,0.0016111532,0.0023763163,0.000025450207,0.0002765872,0.0015774546,0.00053763884,0.00041653437,0.062529355,0.9304561,0.000050329887],"about_ca_topic_score_codex":0.0036626712,"about_ca_topic_score_gemma":0.0029107803,"teacher_disagreement_score":0.07033906,"about_ca_system_score_codex":0.0076933643,"about_ca_system_score_gemma":0.014800397,"threshold_uncertainty_score":0.24146658},"labels":[],"label_agreement":null},{"id":"W2494774283","doi":"10.4018/978-1-4666-2110-7.ch016","title":"Community of Inquiry Framework, Digital Technologies, and Student Assessment in Higher Education","year":2012,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Mount Royal University","funders":"","keywords":"Peer assessment; Memorization; Mathematics education; Reflection (computer programming); Peer feedback; Higher education; Computer science; Pedagogy; Psychology; Political science","score_opus":0.07475372496962068,"score_gpt":0.38591376788283255,"score_spread":0.31116004291321187,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2494774283","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.040475193,0.12779474,0.13969181,0.034802526,0.0015751412,0.0007161966,0.00009586474,0.00041395603,0.65443456],"genre_scores_gemma":[0.73365283,0.052697558,0.10837975,0.0031647116,0.00057581573,0.0013592738,0.00013655655,0.00017125008,0.09986217],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9958727,0.002887695,0.00011470339,0.00023639713,0.0007034433,0.00018512392],"domain_scores_gemma":[0.996121,0.0030148725,0.00012711524,0.00013291031,0.00023942548,0.00036480845],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00513838,0.00055043504,0.0004780657,0.002660909,0.0034483252,0.0083673475,0.001419201,0.002293721,0.0046534557],"category_scores_gemma":[0.0035284646,0.00021546979,0.0003041919,0.004299678,0.015762389,0.009321996,0.004821446,0.0032517663,0.00057039043],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000127304265,0.00008735942,0.0006418429,0.0005415206,0.000004237436,0.00019390964,0.041959707,0.00055328046,0.0001872245,0.7890687,0.01038679,0.15636273],"study_design_scores_gemma":[0.000013651048,0.00007183721,0.0014866312,0.0015949956,0.0000055769997,0.0006255517,0.039215233,0.0015450988,0.00015894539,0.5664234,0.38882828,0.0000308006],"about_ca_topic_score_codex":0.006640405,"about_ca_topic_score_gemma":0.011630116,"teacher_disagreement_score":0.0083673475,"about_ca_system_score_codex":0.008057638,"about_ca_system_score_gemma":0.006446249,"threshold_uncertainty_score":0.05846256},"labels":[],"label_agreement":null},{"id":"W2496700758","doi":"10.1007/978-3-319-39211-0_14","title":"Assessment for Learning: A Framework for Educators’ Professional Growth and Evaluation Cycles","year":2016,"lang":"en","type":"book-chapter","venue":"˜The œenabling power of assessment","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Professional development; Professional learning community; Psychology; Engineering ethics; Knowledge management; Mathematics education; Computer science; Pedagogy; Engineering","score_opus":0.045348998370124655,"score_gpt":0.41359797986238844,"score_spread":0.3682489814922638,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2496700758","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00680028,0.001875791,0.7605923,0.014805212,0.00048311564,0.0007288038,0.00016643053,0.0012104852,0.21333751],"genre_scores_gemma":[0.27688095,0.0010402737,0.6667655,0.00080224907,0.00012998344,0.0014071278,0.00019332541,0.0005786644,0.052202],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9858584,0.009296643,0.0008238654,0.00077868113,0.002728533,0.00051390624],"domain_scores_gemma":[0.9757893,0.015170264,0.00085198396,0.001965412,0.00499343,0.0012296295],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.017513791,0.00095072004,0.00051985506,0.0032641494,0.0037916412,0.016261946,0.0032232655,0.002580758,0.008243798],"category_scores_gemma":[0.037721757,0.00074360153,0.0005550375,0.0021949615,0.011543825,0.013482907,0.00653557,0.004401312,0.0021353695],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000107433,0.000029742745,0.00037643468,0.00007488229,0.0000032766402,0.000041925276,0.006430551,0.0014611029,0.00015349324,0.8786899,0.0077855093,0.104942426],"study_design_scores_gemma":[0.000008061386,0.000028786983,0.00034650223,0.00029968529,0.0000055753335,0.00010420859,0.0030984876,0.009516484,0.0008873185,0.8349499,0.15072459,0.000030406272],"about_ca_topic_score_codex":0.009829188,"about_ca_topic_score_gemma":0.010382581,"teacher_disagreement_score":0.017513791,"about_ca_system_score_codex":0.010912322,"about_ca_system_score_gemma":0.01899891,"threshold_uncertainty_score":0.092622936},"labels":[],"label_agreement":null},{"id":"W2506618750","doi":"10.4018/978-1-59140-732-4.ch001","title":"Research Styles and the Internet","year":2011,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"The Internet; Research data; Internet research; Online research methods; Computer science; Political science; Internet privacy; World Wide Web; Data science","score_opus":0.08498205871038783,"score_gpt":0.3763165802994835,"score_spread":0.2913345215890957,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2506618750","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0044409046,0.028023334,0.01301808,0.019514652,0.0019982082,0.000095923504,0.000105490195,0.00028177624,0.9325216],"genre_scores_gemma":[0.11021721,0.06022094,0.029425574,0.009202884,0.0030974515,0.0006257238,0.00030304116,0.00091025,0.78599685],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.995981,0.0021754056,0.00015147982,0.00031409477,0.0012512536,0.00012675722],"domain_scores_gemma":[0.9929597,0.004237405,0.00032194075,0.00087181415,0.00085984345,0.00074930186],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0044300053,0.00074312335,0.00039684013,0.0032168971,0.0028846941,0.013383981,0.0013603411,0.0012573897,0.02796916],"category_scores_gemma":[0.007885953,0.00039127356,0.00035409894,0.0037359807,0.005442046,0.013898686,0.004446553,0.0037954075,0.0096872],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018713672,0.00004443507,0.00032762508,0.00031523325,0.000006639696,0.00010769889,0.021340404,0.000113184906,0.00036661365,0.6962994,0.074278645,0.20678149],"study_design_scores_gemma":[0.000007458151,0.000017297592,0.00025314724,0.0005099076,0.0000035837736,0.00022678127,0.004475838,0.000114595205,0.00009949209,0.12784077,0.8664427,0.000008356143],"about_ca_topic_score_codex":0.0007845867,"about_ca_topic_score_gemma":0.0012249933,"teacher_disagreement_score":0.99557,"about_ca_system_score_codex":0.0031499371,"about_ca_system_score_gemma":0.0018390487,"threshold_uncertainty_score":0.09356612},"labels":[],"label_agreement":null},{"id":"W2509141998","doi":"10.1080/14926150309556551","title":"Developing classroom‐focused research in technology education","year":2003,"lang":"en","type":"article","venue":"Canadian Journal of Science Mathematics and Technology Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":25,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Mathematics education; Psychology; Pedagogy; Sociology; Engineering ethics; Engineering","score_opus":0.06727428818462765,"score_gpt":0.4098745844057686,"score_spread":0.34260029622114097,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2509141998","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.29462686,0.007840029,0.50108284,0.03194215,0.00089750125,0.005497951,0.0003928043,0.0029617248,0.15475817],"genre_scores_gemma":[0.414987,0.0033318426,0.56706625,0.00159028,0.00008904458,0.0017613358,0.00030273251,0.0001944995,0.01067701],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9619876,0.028778732,0.0018801115,0.0014872119,0.0049353763,0.00093087665],"domain_scores_gemma":[0.8124989,0.12529543,0.005874215,0.011279008,0.03389428,0.011158129],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.07086909,0.00069453474,0.00077789987,0.0039895866,0.0020103662,0.008809864,0.0033610943,0.0026685873,0.004568587],"category_scores_gemma":[0.14380194,0.0008132081,0.0004758425,0.0014830586,0.0024073976,0.0075915614,0.0064193164,0.002421636,0.0014134236],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010767456,0.0017143425,0.015119588,0.0015447604,0.000063399195,0.00033243207,0.045339238,0.0011464996,0.014023749,0.031535596,0.011503829,0.87756896],"study_design_scores_gemma":[0.0007805088,0.0027963493,0.054634124,0.011712762,0.00046406902,0.0014055009,0.18728323,0.01616593,0.08676162,0.20098187,0.43675512,0.00025897258],"about_ca_topic_score_codex":0.007201618,"about_ca_topic_score_gemma":0.015605125,"teacher_disagreement_score":0.07086909,"about_ca_system_score_codex":0.0050170515,"about_ca_system_score_gemma":0.032160867,"threshold_uncertainty_score":0.37479603},"labels":[],"label_agreement":null},{"id":"W2510347771","doi":"10.1021/acs.jchemed.6b00028","title":"Score Increase and Partial-Credit Validity When Administering Multiple-Choice Tests Using an Answer-Until-Correct Format","year":2016,"lang":"en","type":"article","venue":"Journal of Chemical Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Trent University","funders":"Brock University","keywords":"Allotment; Test (biology); Post hoc; Multiple choice; Econometrics; Polytomous Rasch model; Statistics; Actuarial science; Computer science; Psychology; Mathematics; Economics; Medicine; Psychometrics; Internal medicine; Item response theory","score_opus":0.09711035673035426,"score_gpt":0.3936019198884978,"score_spread":0.2964915631581435,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2510347771","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9704132,0.00017411934,0.015883438,0.00028550328,0.00013704816,0.00046168725,0.00028797722,0.00022583918,0.012131193],"genre_scores_gemma":[0.9763417,0.000120407196,0.019581396,0.00016902231,0.00006789331,0.00039768798,0.00027152454,0.00007160965,0.0029787587],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9665477,0.01615391,0.0020590487,0.0016232228,0.012905657,0.0007105524],"domain_scores_gemma":[0.8166217,0.13874587,0.019940713,0.012381517,0.0102005545,0.0021096186],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.022426529,0.0005811401,0.00058645953,0.0011919837,0.00037877634,0.0011181878,0.00061883667,0.0008183503,0.005130247],"category_scores_gemma":[0.15482399,0.0002521788,0.00092391047,0.0010974497,0.0011210835,0.0011954871,0.0013195851,0.0011984936,0.0011746164],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.006993327,0.0026991263,0.6133235,0.0006591983,0.00051637087,0.00016769032,0.0027502836,0.0030254766,0.033448692,0.0017731427,0.0029442625,0.3316989],"study_design_scores_gemma":[0.00009585417,0.01194568,0.93004006,0.00012634399,0.00011756279,0.00044040766,0.00060280063,0.006072585,0.045108154,0.002075053,0.0032872322,0.00008820334],"about_ca_topic_score_codex":0.00079547294,"about_ca_topic_score_gemma":0.0022662997,"teacher_disagreement_score":0.022426529,"about_ca_system_score_codex":0.00040502744,"about_ca_system_score_gemma":0.00080339663,"threshold_uncertainty_score":0.11860424},"labels":[],"label_agreement":null},{"id":"W251327719","doi":"10.55016/ojs/ajer.v58i4.55670","title":"What assessment knowledge and skills do initial teacher education programs address? A Western Canadian perspective","year":2013,"lang":"en","type":"article","venue":"Alberta Journal of Educational Research","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":37,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Alberta","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Perspective (graphical); Psychology; Pedagogy; Knowledge level; Mathematics education; Perspective-taking; Teacher education; Educational assessment; Social psychology","score_opus":0.07173820836995133,"score_gpt":0.500320049850776,"score_spread":0.42858184148082473,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W251327719","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.87227374,0.01256171,0.00055325846,0.03287554,0.00022118002,0.00012380375,0.0012099111,0.00006410554,0.08011677],"genre_scores_gemma":[0.9884393,0.005410635,0.00046865834,0.0010227427,0.000027625645,0.000018868092,0.00022205758,0.000013657673,0.0043764845],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.9961546,0.00030016122,0.000097809985,0.00020957827,0.0016265172,0.0016112804],"domain_scores_gemma":[0.9909021,0.0007864809,0.0006550595,0.00011328085,0.004782695,0.002760347],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0030998972,0.00036168384,0.00059132837,0.0036230122,0.005697873,0.0045599756,0.0017255652,0.0007118671,0.0029458362],"category_scores_gemma":[0.01049072,0.00027409327,0.0003011996,0.00549819,0.0026523983,0.0019293003,0.0011528422,0.0013562397,0.00030550035],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025840636,0.00058981305,0.5567499,0.000889282,0.00007747343,0.00073549064,0.069825575,0.0006980153,0.001380848,0.00703326,0.031783033,0.32997897],"study_design_scores_gemma":[0.000016494489,0.00010296842,0.9008225,0.00085827935,0.0000620407,0.00018029776,0.065845266,0.0004560587,0.00048998813,0.0007918109,0.030299915,0.000074309515],"about_ca_topic_score_codex":0.9960304,"about_ca_topic_score_gemma":0.9980751,"teacher_disagreement_score":0.93243873,"about_ca_system_score_codex":0.06756126,"about_ca_system_score_gemma":0.110569544,"threshold_uncertainty_score":0.49019355},"labels":[],"label_agreement":null},{"id":"W2517561083","doi":"10.22329/celt.v9i0.4442","title":"Is Fine Tuning Possible with Grade-Focused Students?","year":2016,"lang":"en","type":"article","venue":"Collected Essays on Learning and Teaching","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Brock University","funders":"","keywords":"Formative assessment; Psychology; Summative assessment; Allegiance; Mathematics education; Pedagogy","score_opus":0.02298403361912248,"score_gpt":0.329031261894698,"score_spread":0.3060472282755755,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2517561083","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9040814,0.0008365488,0.017508306,0.03423428,0.00071658223,0.00048641718,0.00014016591,0.00088941393,0.04110689],"genre_scores_gemma":[0.9735014,0.0005522668,0.009859779,0.0046883393,0.00017963134,0.0004111387,0.00012685737,0.000088928035,0.010591682],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9919863,0.003370116,0.0003457541,0.001146001,0.0018914574,0.0012603693],"domain_scores_gemma":[0.97539014,0.0036487863,0.0039951685,0.0037880763,0.0038894617,0.009288447],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008676958,0.00047858435,0.0005770744,0.0011361365,0.0035421802,0.008913776,0.0024588446,0.002638628,0.0055907257],"category_scores_gemma":[0.05895662,0.00040721058,0.00045417022,0.0011055076,0.0018551641,0.0054639312,0.004800235,0.002799473,0.0030658874],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019765733,0.0022339968,0.14467432,0.00014199503,0.00004209656,0.00038683193,0.04932693,0.00015468666,0.0029308302,0.0049802233,0.015419267,0.7795111],"study_design_scores_gemma":[0.00032536342,0.0073146657,0.4015824,0.0012186135,0.00019206424,0.0023529385,0.22554575,0.001759227,0.0132124275,0.041265618,0.30476856,0.00046235532],"about_ca_topic_score_codex":0.0027403932,"about_ca_topic_score_gemma":0.005519153,"teacher_disagreement_score":0.008913776,"about_ca_system_score_codex":0.0019075904,"about_ca_system_score_gemma":0.003465865,"threshold_uncertainty_score":0.045888722},"labels":[],"label_agreement":null},{"id":"W2520023658","doi":"","title":"Language Assessment Literacy as Professional Competence: The Case of Canadian Admissions Decision Makers","year":2016,"lang":"en","type":"article","venue":"DOAJ (DOAJ: Directory of Open Access Journals)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Literacy; Competence (human resources); Language assessment; Professional development; Psychology; Medical education; Pedagogy; Medicine; Social psychology","score_opus":0.18758794809744395,"score_gpt":0.6183511057041936,"score_spread":0.43076315760674966,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2520023658","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9377523,0.00024859203,0.0011549969,0.013221815,0.000055256452,0.00018380022,0.000048066737,0.000027350432,0.047307782],"genre_scores_gemma":[0.9940123,0.00013537501,0.0008587007,0.0006214812,0.000013977069,0.00003821411,0.000020820153,0.000010709418,0.004288501],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.9750968,0.011496215,0.0006707288,0.0010346203,0.0052587343,0.0064429333],"domain_scores_gemma":[0.9657608,0.01386756,0.0019503664,0.0009614063,0.0071425927,0.010317206],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.018021094,0.0005556208,0.0005355681,0.0028248096,0.036996685,0.0141948555,0.003075193,0.0034615675,0.006171255],"category_scores_gemma":[0.036919408,0.0006042266,0.0005293662,0.0035170056,0.016964901,0.0029947816,0.011757836,0.0053876047,0.00057303655],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010229404,0.0003460614,0.038686637,0.000093705545,0.000012746048,0.008314453,0.89854187,0.0006380258,0.0007265909,0.014638735,0.0040473887,0.033851594],"study_design_scores_gemma":[0.000031431347,0.00007034083,0.025990501,0.00017054062,0.00001444124,0.00065857486,0.93196523,0.0015101549,0.0005689075,0.0031481492,0.03580289,0.00006872075],"about_ca_topic_score_codex":0.905272,"about_ca_topic_score_gemma":0.92796236,"teacher_disagreement_score":0.104214035,"about_ca_system_score_codex":0.104214035,"about_ca_system_score_gemma":0.12905245,"threshold_uncertainty_score":0.75612926},"labels":[],"label_agreement":null},{"id":"W2523280788","doi":"10.1080/10627197.2016.1236677","title":"Approaches to Classroom Assessment Inventory: A New Instrument to Support Teacher Assessment Literacy","year":2016,"lang":"en","type":"article","venue":"Educational Assessment","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":112,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Accountability; Literacy; Construct (python library); Educational assessment; Psychology; Construct validity; Mathematics education; Standards for Educational and Psychological Testing; Standardized test; Standards-based assessment; Process (computing); Authentic assessment; Pedagogy; Psychometrics; Higher education; Computer science; Political science; Education theory; Curriculum","score_opus":0.1328510477980371,"score_gpt":0.4138136676963231,"score_spread":0.28096261989828597,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2523280788","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.51862025,0.0032803665,0.30645108,0.008135222,0.0012549064,0.0142283365,0.010333793,0.009342569,0.12835348],"genre_scores_gemma":[0.34230158,0.0016432806,0.625768,0.0009850942,0.00025262713,0.013551587,0.003683569,0.00056000095,0.011254266],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99148566,0.003093509,0.0015499623,0.000520675,0.00306019,0.00029003498],"domain_scores_gemma":[0.97121584,0.01304952,0.004314045,0.0020226561,0.007819675,0.0015782956],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008253588,0.00043044097,0.0005822259,0.0038586024,0.0009327062,0.0019965426,0.0010598757,0.00040752764,0.0030607965],"category_scores_gemma":[0.034305673,0.00044070103,0.0006528134,0.002093418,0.0008376984,0.0031293628,0.0036657213,0.0025388037,0.001466707],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016975823,0.0012260206,0.16603029,0.00044914393,0.00008644386,0.00019090564,0.011236252,0.00089482113,0.004672242,0.0062153847,0.027115552,0.7817132],"study_design_scores_gemma":[0.00026054282,0.0017751808,0.68682206,0.0009772708,0.00022402017,0.0018730275,0.010905188,0.011249821,0.006550833,0.016683644,0.26232648,0.00035193362],"about_ca_topic_score_codex":0.0034212815,"about_ca_topic_score_gemma":0.009186864,"teacher_disagreement_score":0.008253588,"about_ca_system_score_codex":0.001490116,"about_ca_system_score_gemma":0.0059663807,"threshold_uncertainty_score":0.043649673},"labels":[],"label_agreement":null},{"id":"W2523536876","doi":"10.5539/ijel.v6n5p54","title":"The Effect of Using Automated Essay Evaluation on ESL Undergraduate Students’ Writing Skill","year":2016,"lang":"en","type":"article","venue":"International Journal of English Linguistics","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":43,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Formative assessment; Grammar; Computer science; Mathematics education; Test (biology); Software; Second language writing; Relation (database); Academic writing; Artificial intelligence; Natural language processing; Psychology; Second language; Linguistics; Programming language","score_opus":0.02576910350022154,"score_gpt":0.41499898338215163,"score_spread":0.3892298798819301,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2523536876","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9978265,0.000056142188,0.0009065881,0.00007524213,0.000022808417,0.0000683007,0.000040777795,0.000094647876,0.0009090079],"genre_scores_gemma":[0.9927812,0.00006496031,0.005828116,0.000044829216,0.000024879268,0.00014843649,0.00012056769,0.000012799253,0.0009742963],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98830694,0.0063853804,0.0012766455,0.0012326514,0.0024515628,0.0003467773],"domain_scores_gemma":[0.86569786,0.091124915,0.017022012,0.005962432,0.0150258625,0.005166912],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010416063,0.0006822122,0.000678687,0.00094145583,0.0004094361,0.0016576848,0.0006875189,0.0006424136,0.0012877783],"category_scores_gemma":[0.07827056,0.00026890347,0.00036873532,0.00073687115,0.0003758961,0.0010518063,0.0011837555,0.00077867496,0.00046183253],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.005539922,0.009105214,0.28265113,0.00046392588,0.00022880541,0.00018026492,0.0039694137,0.0022989896,0.021540102,0.00014686005,0.0020125192,0.67186296],"study_design_scores_gemma":[0.00047110155,0.035172943,0.9249775,0.00016198102,0.0002351848,0.00022457118,0.0024731779,0.0109370835,0.022024052,0.00032558115,0.0028497325,0.00014719467],"about_ca_topic_score_codex":0.000584076,"about_ca_topic_score_gemma":0.0011590216,"teacher_disagreement_score":0.010416063,"about_ca_system_score_codex":0.00044643175,"about_ca_system_score_gemma":0.00090647716,"threshold_uncertainty_score":0.055086076},"labels":[],"label_agreement":null},{"id":"W2527389382","doi":"10.26522/brocked.v25i1.483","title":"Knowledge Mobilization and Educational Research: Politics, Languages, and Responsibilities","year":2016,"lang":"en","type":"article","venue":"Brock Education Journal","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Brock University","funders":"","keywords":"CLARITY; Mobilization; Politics; China; Political science; Political mobilization; Sociology; Law","score_opus":0.08644552274295823,"score_gpt":0.4706870418880458,"score_spread":0.38424151914508753,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2527389382","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012429489,0.112607345,0.030460848,0.2740532,0.00574726,0.00018474962,0.000036891615,0.0001651938,0.564315],"genre_scores_gemma":[0.545333,0.12923929,0.040653996,0.0636327,0.010689515,0.001375433,0.000117806965,0.0006090241,0.20834917],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9697483,0.022607027,0.000892982,0.0010562431,0.004546573,0.0011488165],"domain_scores_gemma":[0.9416759,0.052865658,0.0014966679,0.0014100136,0.0015568569,0.0009947971],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.023137618,0.00079733756,0.0010803841,0.0040219356,0.008245724,0.025794677,0.0017925064,0.0052697407,0.004401611],"category_scores_gemma":[0.023764413,0.0007776579,0.0005406631,0.00660808,0.064457595,0.026781596,0.010354178,0.009718962,0.0011054982],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007671927,0.000013756641,0.00016828366,0.00017861997,0.0000037012398,0.000055340057,0.06609346,0.000064730375,0.0000620357,0.89591134,0.012216353,0.025224702],"study_design_scores_gemma":[0.0000098517685,0.00003299163,0.0005581149,0.0016932866,0.00000609559,0.0002364765,0.054851815,0.00019907126,0.00017347581,0.38760903,0.55460066,0.000029126286],"about_ca_topic_score_codex":0.0023908482,"about_ca_topic_score_gemma":0.0033656706,"teacher_disagreement_score":0.025794677,"about_ca_system_score_codex":0.006818786,"about_ca_system_score_gemma":0.008961775,"threshold_uncertainty_score":0.12236488},"labels":[],"label_agreement":null},{"id":"W2530098379","doi":"","title":"What are the Learning Values of Grades? Exploring Grading Policies in Canada and China","year":2016,"lang":"en","type":"article","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Grading (engineering); Internationalization; China; Christian ministry; Political science; Globalization; Academic achievement; Immigration; Mathematics education; Pedagogy; Psychology; Business","score_opus":0.06302609960879271,"score_gpt":0.3195045298828628,"score_spread":0.25647843027407013,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2530098379","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9859109,0.00037462512,0.00020024156,0.0012446623,0.000009007223,0.000030100364,0.00045559712,0.0000104382225,0.011764328],"genre_scores_gemma":[0.9982318,0.00019192741,0.00020249549,0.00006582303,0.0000016189445,0.000010417368,0.00016643011,0.0000042688503,0.0011252727],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.99593925,0.00072009966,0.00022313348,0.00032251474,0.0015085195,0.0012865291],"domain_scores_gemma":[0.98347825,0.0027354488,0.0016591067,0.00059806206,0.008978828,0.0025504287],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0041134204,0.00023275205,0.00050657365,0.0036999616,0.0060095177,0.004946995,0.0012431003,0.00039171844,0.0011005768],"category_scores_gemma":[0.013173897,0.00019613122,0.00031857972,0.009991301,0.0031818936,0.0012938245,0.0020939598,0.0009916278,0.00006917908],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023785999,0.00012587072,0.7675277,0.0002007815,0.0000989466,0.00048039097,0.10078762,0.0017900101,0.0008090815,0.026037863,0.0046586255,0.09724523],"study_design_scores_gemma":[0.000012647064,0.00003895113,0.8970667,0.0001602889,0.000041952542,0.000029426963,0.08468018,0.0016743051,0.000553552,0.0013784422,0.014290652,0.000072879266],"about_ca_topic_score_codex":0.9934024,"about_ca_topic_score_gemma":0.99703383,"teacher_disagreement_score":0.111578315,"about_ca_system_score_codex":0.111578315,"about_ca_system_score_gemma":0.13935249,"threshold_uncertainty_score":0.80956113},"labels":[],"label_agreement":null},{"id":"W2530320759","doi":"10.5539/elt.v9n11p38","title":"Students and the Teacher’s Perceptions on Incorporating the Blog Task and Peer Feedback into EFL Writing Classes Through Blogs","year":2016,"lang":"en","type":"article","venue":"English Language Teaching","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Task (project management); Psychology; Perception; Construct (python library); Collaborative writing; Second language writing; Peer feedback; Mathematics education; English as a foreign language; Focus group; Pedagogy; Computer science; Second language; Linguistics","score_opus":0.01755278614143207,"score_gpt":0.3458826899913446,"score_spread":0.3283299038499125,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2530320759","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.998575,0.000025720126,0.000103930055,0.00010460692,0.000006626637,0.000020018404,0.000008150188,0.0000065162776,0.0011492698],"genre_scores_gemma":[0.99862385,0.00005772418,0.00017624997,0.0000446143,0.0000048933584,0.000033174176,0.000015212088,0.00000448869,0.0010398882],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.99663407,0.0015409024,0.00029632845,0.00027370537,0.00073030364,0.00052467023],"domain_scores_gemma":[0.9835526,0.0058597447,0.0036704645,0.00046580954,0.002856454,0.003594967],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003984642,0.00031408563,0.00040645295,0.00097371073,0.0014041642,0.003367006,0.00050461316,0.00079693424,0.0029637248],"category_scores_gemma":[0.016281424,0.0003133606,0.0004251652,0.00046131248,0.0010863013,0.001338249,0.0015645295,0.0012982906,0.0007921163],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00042530132,0.0047545666,0.49575892,0.00041302302,0.000043144668,0.00148779,0.41013053,0.00024372335,0.013484935,0.0003792846,0.001822331,0.07105646],"study_design_scores_gemma":[0.000058445657,0.0017072002,0.5444889,0.0001884509,0.000049251536,0.00043000886,0.4413425,0.0008444181,0.003424126,0.00023252722,0.0071455697,0.00008860263],"about_ca_topic_score_codex":0.0029769822,"about_ca_topic_score_gemma":0.0038386271,"teacher_disagreement_score":0.003984642,"about_ca_system_score_codex":0.0007710834,"about_ca_system_score_gemma":0.0010901864,"threshold_uncertainty_score":0.021073043},"labels":[],"label_agreement":null},{"id":"W2546528314","doi":"10.5430/jnep.v7n3p94","title":"Nurse teachers’ conceptions and practices of written feedback in Karachi","year":2016,"lang":"en","type":"article","venue":"Journal of Nursing Education and Practice","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Workload; Nurse educator; Medical education; Sample (material); Psychology; Nurse education; Distraction; Nursing; Medicine; Pedagogy; Computer science","score_opus":0.09877677895829202,"score_gpt":0.4965999707333705,"score_spread":0.39782319177507847,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2546528314","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99629337,0.0007329204,0.00017637257,0.00074453966,0.000021368076,0.000018268109,0.00001715147,0.0000054533684,0.0019905514],"genre_scores_gemma":[0.99843496,0.0007301205,0.00017501815,0.00015236846,0.0000045668553,0.000014147357,0.000010750749,0.0000025276604,0.00047546654],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99756753,0.0009889932,0.00024715305,0.00016923649,0.0007005138,0.00032664923],"domain_scores_gemma":[0.994027,0.0024499134,0.001384019,0.00016166654,0.0011903485,0.0007869878],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0025615958,0.00019780174,0.0002428975,0.0007063898,0.0019266026,0.00222337,0.00052821345,0.00055219594,0.001055827],"category_scores_gemma":[0.010732211,0.00032431958,0.00014887397,0.00053201447,0.0019251343,0.00095468666,0.0014358754,0.0007181081,0.00017886415],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010660768,0.00017069685,0.20138209,0.00045238726,0.000010273319,0.0022093933,0.75543714,0.00012570886,0.002161359,0.00044757288,0.0008805197,0.036616404],"study_design_scores_gemma":[0.000012576253,0.00040239803,0.13717613,0.0004562168,0.000015421623,0.0018855083,0.85017854,0.0001756375,0.00061281474,0.0002503622,0.00878151,0.00005285713],"about_ca_topic_score_codex":0.016385363,"about_ca_topic_score_gemma":0.02017015,"teacher_disagreement_score":0.016385363,"about_ca_system_score_codex":0.002510587,"about_ca_system_score_gemma":0.0054762117,"threshold_uncertainty_score":0.032580018},"labels":[],"label_agreement":null},{"id":"W2547886194","doi":"","title":"Exploring Assessment Literacy","year":2016,"lang":"en","type":"article","venue":"Higher education of social science","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Scope (computer science); Literacy; Dual (grammatical number); Service (business); Professional development; Pedagogy; Mathematics education; Psychology; Engineering ethics; Sociology; Computer science; Linguistics; Business; Engineering","score_opus":0.10488469311012355,"score_gpt":0.44300809837082267,"score_spread":0.3381234052606991,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2547886194","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.62492007,0.05684524,0.041479245,0.017529955,0.00031216364,0.00054952566,0.0003408017,0.000078581084,0.25794438],"genre_scores_gemma":[0.97723514,0.01285732,0.006434941,0.00083860283,0.000036203757,0.00021622014,0.000061531005,0.000010712011,0.0023093107],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9947212,0.0035864178,0.0002823467,0.0003343371,0.0008113362,0.00026443903],"domain_scores_gemma":[0.98123956,0.015251374,0.001185966,0.0002544061,0.0017687551,0.00030000188],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0064897942,0.0002510733,0.00044804838,0.0046738787,0.0009830376,0.0047767363,0.00051584386,0.0008588024,0.0030256521],"category_scores_gemma":[0.018484274,0.00019289288,0.00050659105,0.0033650864,0.0037332026,0.0069800215,0.0035219071,0.0012352072,0.0002208166],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009302107,0.0002469235,0.06929901,0.0061646923,0.00012201878,0.0010493483,0.2783016,0.00029158307,0.0024768116,0.21174613,0.0029197587,0.4272892],"study_design_scores_gemma":[0.00003841574,0.0005553203,0.13827357,0.015728835,0.0003064786,0.0037360047,0.51085794,0.0014096906,0.0037966375,0.13460746,0.1905901,0.000099491204],"about_ca_topic_score_codex":0.002828012,"about_ca_topic_score_gemma":0.005520187,"teacher_disagreement_score":0.0064897942,"about_ca_system_score_codex":0.0028475106,"about_ca_system_score_gemma":0.0058868616,"threshold_uncertainty_score":0.034321725},"labels":[],"label_agreement":null},{"id":"W2552734705","doi":"10.3968/8877","title":"An Overview of Studies Conducted on Washback, Impact and Validity","year":2016,"lang":"en","type":"article","venue":"Studies in literature and language","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Test of English as a Foreign Language; Language assessment; Test (biology); Psychology; English language; Mathematics education; China; Pedagogy; Political science","score_opus":0.1500407982298959,"score_gpt":0.49733186619505443,"score_spread":0.3472910679651585,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2552734705","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1643477,0.7479888,0.025936052,0.003354541,0.001284235,0.003895903,0.0018491626,0.00015950411,0.05118402],"genre_scores_gemma":[0.47436225,0.4645639,0.045440007,0.0026487121,0.00077704224,0.0058949613,0.0016777903,0.00021046674,0.0044248444],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9164376,0.040266193,0.016135909,0.0037806744,0.022065584,0.001314112],"domain_scores_gemma":[0.5534519,0.37790096,0.017900141,0.011382509,0.038182694,0.0011819064],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.065170065,0.0012022085,0.0021875375,0.018160107,0.0024214678,0.006653496,0.0022288032,0.0017069215,0.0040129074],"category_scores_gemma":[0.21310365,0.0009932636,0.0026132255,0.015990341,0.003326577,0.005875652,0.003644989,0.0022436397,0.0007960401],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00062582444,0.00054873223,0.056786995,0.060327735,0.0011686778,0.00035324332,0.029534485,0.00026275383,0.0012780527,0.00931677,0.0027626734,0.83703417],"study_design_scores_gemma":[0.00011108039,0.0025309934,0.29644603,0.25700372,0.0057129115,0.0026595774,0.09400326,0.0006681179,0.009844886,0.012114127,0.31856623,0.00033907878],"about_ca_topic_score_codex":0.0061894516,"about_ca_topic_score_gemma":0.0067341016,"teacher_disagreement_score":0.065170065,"about_ca_system_score_codex":0.00611538,"about_ca_system_score_gemma":0.008704769,"threshold_uncertainty_score":0.34465635},"labels":[],"label_agreement":null},{"id":"W2554401887","doi":"10.5539/elt.v9n12p79","title":"Graduate Students’ Needs and Preferences for Written Feedback on Academic Writing","year":2016,"lang":"en","type":"article","venue":"English Language Teaching","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology; Graduate students; Preference; Constructive; Mathematics education; Academic writing; English for academic purposes; Medical education; Higher education; Pedagogy; Computer science; Process (computing); Medicine","score_opus":0.0443805151304807,"score_gpt":0.36799825618220555,"score_spread":0.32361774105172486,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2554401887","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9983253,0.00012688062,0.00013418465,0.00047993512,0.000012405561,0.000015077084,0.000019299963,0.000008519016,0.0008784553],"genre_scores_gemma":[0.99843067,0.00016740795,0.0004699731,0.00018598943,0.00001110737,0.00002633065,0.000029365812,0.000003741364,0.0006754105],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99442935,0.0022451147,0.00062478206,0.0002638426,0.0017022074,0.00073475216],"domain_scores_gemma":[0.9749665,0.009536446,0.0051246705,0.0005311452,0.0051006866,0.0047404724],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0056761513,0.00021907307,0.0004972969,0.00079847616,0.00076623587,0.0020532012,0.00049846934,0.0008732308,0.002255086],"category_scores_gemma":[0.033009198,0.00021281856,0.00048739067,0.00052182225,0.00049661525,0.00087337894,0.0010603347,0.0012154892,0.00049954455],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006081428,0.0015743892,0.60998535,0.0006958754,0.000088783825,0.0024588937,0.16767035,0.00032215758,0.009078289,0.00036564787,0.0035621547,0.20359004],"study_design_scores_gemma":[0.00007959391,0.004594173,0.5332372,0.00042538252,0.00006325895,0.0041587367,0.4442848,0.0010274597,0.0027978516,0.0005417155,0.008631952,0.00015789323],"about_ca_topic_score_codex":0.0007381186,"about_ca_topic_score_gemma":0.001414981,"teacher_disagreement_score":0.0056761513,"about_ca_system_score_codex":0.0005298811,"about_ca_system_score_gemma":0.0012354014,"threshold_uncertainty_score":0.030018687},"labels":[],"label_agreement":null},{"id":"W2555293682","doi":"10.5539/hes.v6n4p181","title":"Students’ and Teacher’s Experiences of the Validity and Reliability of Assessment in a Bioscience Course","year":2016,"lang":"en","type":"article","venue":"Higher Education Studies","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology; Reliability (semiconductor); Recall; Validity; Perception; Mathematics education; Alternative assessment; Quality (philosophy); Medical education; Test validity; Psychometrics; Developmental psychology; Medicine; Cognitive psychology","score_opus":0.09076394953386803,"score_gpt":0.4697572589009536,"score_spread":0.3789933093670856,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2555293682","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9951833,0.00015228834,0.0011113241,0.0006590703,0.000026866419,0.00002280504,0.0000060501607,0.000015512891,0.0028227821],"genre_scores_gemma":[0.9988556,0.00006547181,0.00037612775,0.000058491754,0.00000881694,0.00001539066,0.0000060021753,0.000007262286,0.0006068663],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.93178886,0.050749406,0.0033790853,0.002080236,0.008891364,0.0031110242],"domain_scores_gemma":[0.8382107,0.11708299,0.013572078,0.004616175,0.019576946,0.0069412007],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.04037908,0.00040405005,0.0008457216,0.0015318847,0.0032172718,0.005633726,0.0010603373,0.001597234,0.0011975123],"category_scores_gemma":[0.1295651,0.0006071621,0.00068530487,0.00078800117,0.0041373796,0.0019635528,0.0042737704,0.003448928,0.0003329777],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030143556,0.00046843168,0.07718848,0.00021909144,0.000053076845,0.0014201086,0.8708826,0.00042669542,0.0044821533,0.00067240733,0.000840084,0.043045573],"study_design_scores_gemma":[0.00006426488,0.0023450614,0.12733917,0.0004712956,0.000107203115,0.0031567537,0.83266455,0.002565286,0.009676304,0.0010331814,0.02025026,0.00032664096],"about_ca_topic_score_codex":0.0029450646,"about_ca_topic_score_gemma":0.003320586,"teacher_disagreement_score":0.04037908,"about_ca_system_score_codex":0.002877141,"about_ca_system_score_gemma":0.002157925,"threshold_uncertainty_score":0.21354753},"labels":[],"label_agreement":null},{"id":"W2556416203","doi":"10.5430/jnep.v7n4p55","title":"Effect of peer evaluation training on senior nursing students’ performance enrolled in nursing administration course","year":2016,"lang":"en","type":"article","venue":"Journal of Nursing Education and Practice","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Checklist; Nursing; Nurse education; Test (biology); Medicine; Psychology; Scale (ratio); Medical education","score_opus":0.09115151949713247,"score_gpt":0.5404954326644517,"score_spread":0.4493439131673192,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2556416203","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9986525,0.00012684222,0.00009050243,0.000057379177,0.000035633046,0.000050076702,0.000006266771,0.000011745803,0.0009691051],"genre_scores_gemma":[0.99898523,0.00009454413,0.00021344,0.000014750804,0.00002102152,0.000032787353,0.000014270257,0.0000017406962,0.0006221744],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9979644,0.00091921387,0.0001501639,0.00015560273,0.0005528462,0.00025780566],"domain_scores_gemma":[0.99130285,0.0026626382,0.0010543343,0.00044262613,0.0017537894,0.0027837614],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001981948,0.00035060933,0.00042281894,0.00032954896,0.00046069524,0.0004757983,0.00034900926,0.0002755136,0.0020131846],"category_scores_gemma":[0.013995425,0.000095229574,0.00041198533,0.00012951,0.00020330907,0.00029470553,0.0006845585,0.00047009857,0.0002857802],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0075786076,0.057782758,0.24654306,0.00093313865,0.000353331,0.0005217842,0.0084405225,0.0012206119,0.02370965,0.0001691809,0.0036454885,0.649102],"study_design_scores_gemma":[0.00032959066,0.06484354,0.912415,0.00028408782,0.00029810556,0.00031438874,0.0048516043,0.0017096591,0.011128131,0.00015244339,0.003603387,0.00007001574],"about_ca_topic_score_codex":0.00076741446,"about_ca_topic_score_gemma":0.0010675238,"teacher_disagreement_score":0.0020131846,"about_ca_system_score_codex":0.00022886819,"about_ca_system_score_gemma":0.0006837415,"threshold_uncertainty_score":0.010481656},"labels":[],"label_agreement":null},{"id":"W2559480382","doi":"10.5539/ijel.v6n7p99","title":"The Impact of Student-Based Instruction on Improving IBT TOEFL Scores of Iranian Students","year":2016,"lang":"en","type":"article","venue":"International Journal of English Linguistics","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Test of English as a Foreign Language; Class (philosophy); Psychology; Mathematics education; Test (biology); Significant difference; Qualitative research; Control (management); Qualitative property; Medical education; English language; Computer science; Medicine; Sociology","score_opus":0.023862006187260646,"score_gpt":0.38996538785848867,"score_spread":0.366103381671228,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2559480382","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9992086,0.000040582167,0.000037400914,0.00003978862,0.000005090515,0.00001611987,0.000009930596,0.000007768922,0.0006348124],"genre_scores_gemma":[0.99909246,0.000066903514,0.0003273374,0.000016329748,0.000004288574,0.000016492704,0.000020752008,0.0000015210165,0.00045385314],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9997023,0.000076169024,0.000026702217,0.000029188868,0.00009835951,0.00006728999],"domain_scores_gemma":[0.99898785,0.00026172443,0.0002065222,0.000044973654,0.00020648971,0.00029244844],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005529338,0.00022841847,0.00023412958,0.0002824571,0.00019006795,0.00025968286,0.0002861076,0.00023626756,0.0018215056],"category_scores_gemma":[0.002643562,0.00006454621,0.0002659312,0.00015313849,0.00016060215,0.0001822988,0.00033380726,0.0003682767,0.00017447428],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004795344,0.038314704,0.2124064,0.0011843812,0.00018227953,0.0004865263,0.011194561,0.0015808269,0.037524782,0.00040818963,0.002866578,0.68905544],"study_design_scores_gemma":[0.0003470478,0.024980173,0.9406111,0.00018377425,0.00025433578,0.00021974265,0.0071617104,0.001329153,0.021586526,0.00021592363,0.003066116,0.000044410346],"about_ca_topic_score_codex":0.001690623,"about_ca_topic_score_gemma":0.0030899136,"teacher_disagreement_score":0.0018215056,"about_ca_system_score_codex":0.00021627355,"about_ca_system_score_gemma":0.0006904359,"threshold_uncertainty_score":0.0060935616},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.09606259991720532,"score_gpt":0.5312202756607064,"score_spread":0.43515767574350106,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2568968076","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9926892,0.00008420713,0.0051549682,0.00015864304,0.000006474003,0.00017027544,0.000008532467,0.00003949925,0.0016880468],"genre_scores_gemma":[0.98734134,0.00012299616,0.011316079,0.00004581262,0.000004124359,0.00013711718,0.000017858152,0.000014795146,0.0009998094],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.98900837,0.0068847206,0.00084595603,0.00087980775,0.0018032875,0.0005779425],"domain_scores_gemma":[0.9652471,0.02213945,0.0037658531,0.0018171773,0.005399879,0.0016306214],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014388298,0.00046103267,0.0004786877,0.00114554,0.0015463841,0.002997622,0.0008436659,0.000592549,0.00053724874],"category_scores_gemma":[0.064056784,0.00051161257,0.00025164944,0.0005428637,0.0015408731,0.0018937306,0.002702406,0.0011438908,0.00018020782],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023109293,0.0010684977,0.14714673,0.00047432072,0.000022920458,0.00050062407,0.6324392,0.0008564424,0.02730686,0.0010367974,0.0006278595,0.18828864],"study_design_scores_gemma":[0.00023054068,0.004367725,0.4733175,0.000723426,0.00013209124,0.0015109866,0.4179944,0.012431728,0.04920613,0.0037196947,0.03600125,0.0003645755],"about_ca_topic_score_codex":0.00527504,"about_ca_topic_score_gemma":0.009447907,"teacher_disagreement_score":0.014388298,"about_ca_system_score_codex":0.0015999464,"about_ca_system_score_gemma":0.004630459,"threshold_uncertainty_score":0.076093495},"labels":[],"label_agreement":null},{"id":"W2584951375","doi":"10.5539/ies.v10n2p84","title":"The Psychological Effect of Errors in Standardized Language Test Items on EFL Students’ Responses to the Following Item","year":2017,"lang":"en","type":"article","venue":"International Education Studies","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology; Test (biology); Affect (linguistics); Social psychology; Stratified sampling; Test of English as a Foreign Language; Mathematics education; Personality; Language assessment; Statistics","score_opus":0.0729122271749704,"score_gpt":0.5470174107587235,"score_spread":0.4741051835837531,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2584951375","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.999469,0.000022587854,0.00014111151,0.00003148014,0.000006329826,0.0000062926715,0.000010570602,0.0000067557658,0.00030590803],"genre_scores_gemma":[0.9994893,0.000023382014,0.00018245472,0.000034403343,0.000008519697,0.00000684795,0.000023312923,0.0000035821113,0.00022801294],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9924165,0.0035116752,0.0005582584,0.00045685642,0.002614715,0.00044196675],"domain_scores_gemma":[0.9086837,0.056886256,0.022769112,0.004410419,0.0038724192,0.0033780932],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004158388,0.00045344868,0.0005329634,0.0009122212,0.00039371502,0.0010572094,0.00027559843,0.0005773324,0.0029024733],"category_scores_gemma":[0.046214383,0.00030230402,0.000750048,0.0004539261,0.0011022331,0.00038601208,0.00089012075,0.0012107308,0.00048167267],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002347334,0.0023566564,0.9401282,0.000099979276,0.00021128204,0.00034247953,0.0051182653,0.00042770966,0.012850694,0.00010651746,0.000277955,0.035732895],"study_design_scores_gemma":[0.000034606648,0.002894272,0.990071,0.000012374675,0.00007300415,0.00028977366,0.0024961727,0.0004599607,0.0032216257,0.000107564476,0.00030201112,0.000037611226],"about_ca_topic_score_codex":0.00059594045,"about_ca_topic_score_gemma":0.00087665557,"teacher_disagreement_score":0.004158388,"about_ca_system_score_codex":0.00044541585,"about_ca_system_score_gemma":0.00037020675,"threshold_uncertainty_score":0.021991968},"labels":[],"label_agreement":null},{"id":"W2586705862","doi":"10.5430/jct.v6n1p14","title":"A Comparison between Students' Self-Assessment and Teachers' Assessment","year":2017,"lang":"en","type":"article","venue":"Journal of Curriculum and Teaching","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":40,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Self-assessment; Psychology; Mathematics education; Medical education; Pedagogy; Medicine","score_opus":0.033138408901531385,"score_gpt":0.4507190949126307,"score_spread":0.4175806860110993,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2586705862","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99785465,0.00010422558,0.00041038875,0.000026830085,0.000015794494,0.00001561644,0.000026514648,0.000012812172,0.0015330595],"genre_scores_gemma":[0.99911135,0.000044443404,0.00023279997,0.000009256385,0.000004630429,0.000011818859,0.000044892946,0.0000037361604,0.0005370803],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9960842,0.0012167101,0.00039035737,0.00028841838,0.0017809344,0.00023947284],"domain_scores_gemma":[0.98735446,0.004638378,0.0020678523,0.0006790722,0.004115028,0.0011451789],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003425332,0.00016886371,0.00029359135,0.0013632145,0.00025679162,0.00085369946,0.000271421,0.00029305022,0.0017939534],"category_scores_gemma":[0.019594004,0.00010927576,0.0002704575,0.0004435591,0.00030733726,0.00071284873,0.0006416885,0.00033448418,0.00039616012],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003949168,0.0007769909,0.919244,0.00009928747,0.000085546264,0.00008218638,0.0053265593,0.00013994741,0.002297359,0.00020772216,0.00046267337,0.07088279],"study_design_scores_gemma":[0.000022517002,0.0010275589,0.9908722,0.000045261106,0.00002942232,0.00021028396,0.0041510863,0.0006706254,0.0014661062,0.00011974857,0.0013655951,0.00001953753],"about_ca_topic_score_codex":0.0009159785,"about_ca_topic_score_gemma":0.0013134886,"teacher_disagreement_score":0.003425332,"about_ca_system_score_codex":0.00030999162,"about_ca_system_score_gemma":0.0004501952,"threshold_uncertainty_score":0.018115103},"labels":[],"label_agreement":null},{"id":"W2586976612","doi":"10.1093/pch/17.suppl_a.26a","title":"Running: How is it Taught and Evaluated in British Columbian Schools?","year":2012,"lang":"en","type":"article","venue":"Paediatrics & Child Health","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Mathematics education; Medical education; Medicine; Psychology","score_opus":0.034796460936936335,"score_gpt":0.3528587779920568,"score_spread":0.31806231705512045,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2586976612","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9494162,0.002574616,0.00039817687,0.019963164,0.0004422424,0.00012966686,0.00089346414,0.000118692966,0.02606385],"genre_scores_gemma":[0.9876836,0.0009364518,0.00084772025,0.0007775684,0.000027639453,0.000057761416,0.00020852026,0.00003824345,0.009422469],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.991193,0.0030055256,0.00053774426,0.00065681094,0.0027928404,0.0018140875],"domain_scores_gemma":[0.9497203,0.0059347693,0.0037388986,0.001219113,0.02505809,0.0143287],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0073754303,0.0002846251,0.0006036645,0.0023638231,0.007868379,0.0063331635,0.0018619203,0.0016583635,0.00639588],"category_scores_gemma":[0.032796077,0.00057054055,0.00032852034,0.0030045288,0.002436006,0.002107274,0.0028498364,0.0030544114,0.0011753517],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003515467,0.0008333058,0.64212203,0.00048557925,0.000039381484,0.0003580082,0.059813973,0.0006589534,0.0008700197,0.0017049997,0.046143405,0.24661869],"study_design_scores_gemma":[0.000021145008,0.00022265536,0.910969,0.001081957,0.00003440494,0.00007603232,0.058473874,0.0005651843,0.00076952594,0.0005385902,0.027144106,0.00010355858],"about_ca_topic_score_codex":0.8418253,"about_ca_topic_score_gemma":0.93016106,"teacher_disagreement_score":0.966018,"about_ca_system_score_codex":0.033981968,"about_ca_system_score_gemma":0.093540795,"threshold_uncertainty_score":0.3182124},"labels":[],"label_agreement":null},{"id":"W2587410353","doi":"10.3968/9141","title":"Study on Training Strategies for Effective Peer Review","year":2016,"lang":"en","type":"article","venue":"Cross-cultural communication","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Popularity; Peer review; Training (meteorology); Peer feedback; Computer science; Medical education; Best practice; Psychology; Mathematics education; Medicine; Political science","score_opus":0.14356662356351346,"score_gpt":0.4964878632974721,"score_spread":0.3529212397339586,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2587410353","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.87745917,0.0032518946,0.040062282,0.0035008048,0.00025626182,0.0036487384,0.00005656728,0.00027200734,0.071492255],"genre_scores_gemma":[0.93049514,0.0017022882,0.05802027,0.00044866325,0.000078417426,0.0012949147,0.000045843542,0.00004392774,0.007870629],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.97654736,0.01774924,0.00088701653,0.00080725964,0.003383545,0.000625574],"domain_scores_gemma":[0.82702005,0.14339393,0.007054201,0.004561244,0.014686999,0.003283582],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.015810354,0.00044066153,0.00040336078,0.0014639532,0.0012119868,0.002164701,0.0017809193,0.0009877952,0.0045746285],"category_scores_gemma":[0.12254091,0.00026835207,0.0003591274,0.0010319385,0.0007641398,0.0030431023,0.0010549477,0.0012519374,0.0010097495],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00035730857,0.0049306205,0.023593953,0.0028861747,0.00009397623,0.00059289654,0.070691586,0.00076690485,0.007144482,0.012092176,0.0048174346,0.87203246],"study_design_scores_gemma":[0.001364298,0.02379435,0.25324255,0.0136783905,0.0010864697,0.010898692,0.25479335,0.029402597,0.045622636,0.032998547,0.33261263,0.0005055865],"about_ca_topic_score_codex":0.00073383545,"about_ca_topic_score_gemma":0.0011986472,"teacher_disagreement_score":0.9841896,"about_ca_system_score_codex":0.0015319685,"about_ca_system_score_gemma":0.003825481,"threshold_uncertainty_score":0.08361417},"labels":[],"label_agreement":null},{"id":"W2588954709","doi":"10.4236/ojn.2017.72016","title":"Pass/Fail and Discretionary Grading: A Snapshot of Their Influences on Learning","year":2017,"lang":"en","type":"article","venue":"Open Journal of Nursing","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Athabasca University","funders":"","keywords":"Grading (engineering); Snapshot (computer storage); Subjectivity; Computer science; Psychology; Mathematics education; Epistemology; Engineering; Philosophy","score_opus":0.1097130137790854,"score_gpt":0.4472999753315051,"score_spread":0.33758696155241974,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2588954709","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7255369,0.044093516,0.02344533,0.05285986,0.0022841766,0.00023062588,0.00072570523,0.0008061589,0.15001777],"genre_scores_gemma":[0.9775349,0.008172606,0.005365186,0.0017098716,0.0003446009,0.00007012344,0.0001447516,0.00021676389,0.0064412663],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9799498,0.009099166,0.000982875,0.0011307519,0.0075237956,0.0013135849],"domain_scores_gemma":[0.9429579,0.02633936,0.007857622,0.00260249,0.013676974,0.0065656956],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015143545,0.00036295372,0.00045646884,0.0036497826,0.0022120841,0.0058491314,0.0008283893,0.000630931,0.0026123445],"category_scores_gemma":[0.042346817,0.00032244818,0.0005031293,0.0027486766,0.0037378466,0.0031091429,0.004976347,0.002646094,0.00032857142],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021525842,0.0001589699,0.17866625,0.00065112294,0.00011521854,0.0002530462,0.030886434,0.0004287783,0.0008491313,0.024132483,0.013557787,0.75008553],"study_design_scores_gemma":[0.000015805905,0.0004274696,0.8086079,0.0018636417,0.00012799383,0.0008186685,0.038677253,0.0008619105,0.0015212994,0.015825834,0.13099998,0.00025221118],"about_ca_topic_score_codex":0.014839162,"about_ca_topic_score_gemma":0.03526176,"teacher_disagreement_score":0.015143545,"about_ca_system_score_codex":0.00517415,"about_ca_system_score_gemma":0.006321399,"threshold_uncertainty_score":0.08008766},"labels":[],"label_agreement":null},{"id":"W2590462553","doi":"10.1111/jcal.12178","title":"Short answers to deep questions: supporting teachers in large‐class settings","year":2017,"lang":"en","type":"article","venue":"Journal of Computer Assisted Learning","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Formative assessment; Grading (engineering); Mathematics education; Class (philosophy); Context (archaeology); Praxis; Psychology; Computer science; Pedagogy; Artificial intelligence; Engineering","score_opus":0.024637365506783682,"score_gpt":0.37571994380463364,"score_spread":0.35108257829784995,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2590462553","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9280955,0.00015917963,0.057963274,0.0037185447,0.00010602659,0.00090980117,0.00037627673,0.0014577315,0.007213663],"genre_scores_gemma":[0.91956735,0.00018329926,0.07434941,0.0005878574,0.00006528722,0.0009928404,0.00038682524,0.00017076085,0.0036963292],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9818757,0.013563541,0.00067651726,0.0012514854,0.0017653789,0.0008673686],"domain_scores_gemma":[0.8810211,0.09139427,0.008631499,0.004290213,0.007848629,0.0068143746],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01716085,0.00091110973,0.0006894555,0.0013165227,0.0018387894,0.0038312348,0.0021169188,0.0017858148,0.0061703804],"category_scores_gemma":[0.092020705,0.00039166244,0.00033165625,0.00074346154,0.0017190318,0.0037033043,0.0059382846,0.0017870144,0.0021802909],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012440798,0.004271928,0.063705884,0.0018499568,0.00006829019,0.001813326,0.32614413,0.0039934227,0.05044101,0.0027267106,0.019370036,0.5243712],"study_design_scores_gemma":[0.00057559693,0.009987899,0.12628265,0.0030053863,0.00014056514,0.0022504646,0.4625041,0.035637632,0.059013605,0.036450036,0.26347834,0.0006736823],"about_ca_topic_score_codex":0.0007428112,"about_ca_topic_score_gemma":0.0021041909,"teacher_disagreement_score":0.01716085,"about_ca_system_score_codex":0.0013257073,"about_ca_system_score_gemma":0.0023698064,"threshold_uncertainty_score":0.0907563},"labels":[],"label_agreement":null},{"id":"W2593362570","doi":"10.18260/p.27121","title":"Using a Delphi Approach to Develop Rubric Criteria","year":2016,"lang":"en","type":"article","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"American Association for the Advancement of Science","keywords":"Rubric; Delphi method; Delphi; Computer science; Teamwork; Outcome (game theory); Work (physics); Medical education; Management science; Knowledge management; Psychology; Process management; Mathematics education; Engineering; Medicine; Artificial intelligence; Political science","score_opus":0.15513021429365023,"score_gpt":0.41844162254475975,"score_spread":0.26331140825110955,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2593362570","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.09759036,0.0006430703,0.68753326,0.0030511732,0.00067207386,0.16120906,0.0022640168,0.0010312874,0.046005674],"genre_scores_gemma":[0.061038624,0.00055079296,0.8339438,0.0006045615,0.000055319153,0.09645905,0.0012176107,0.00024061881,0.0058895983],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.85420233,0.09813358,0.020402318,0.003886724,0.019581083,0.0037939136],"domain_scores_gemma":[0.8545377,0.070835784,0.005936072,0.0054231742,0.0607131,0.0025541417],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.14602509,0.0030673365,0.0022303532,0.026771687,0.005229727,0.004988959,0.004476197,0.0020843938,0.011238137],"category_scores_gemma":[0.18879496,0.0017414006,0.0025783288,0.011250293,0.004361011,0.0040655783,0.013263524,0.003361479,0.0031680292],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007472135,0.0010072789,0.0061717294,0.012237982,0.00032387237,0.002126659,0.2275371,0.014473098,0.025548711,0.087226406,0.03343766,0.5891623],"study_design_scores_gemma":[0.00083764456,0.0030024752,0.018392833,0.010646628,0.0004451455,0.0019344549,0.31889877,0.06990646,0.025844296,0.20549498,0.34299356,0.0016027851],"about_ca_topic_score_codex":0.0077364645,"about_ca_topic_score_gemma":0.0144304745,"teacher_disagreement_score":0.14602509,"about_ca_system_score_codex":0.009570055,"about_ca_system_score_gemma":0.02481429,"threshold_uncertainty_score":0.7722637},"labels":[],"label_agreement":null},{"id":"W2593520074","doi":"10.1057/978-1-137-46484-2_3","title":"How Do We Assess?","year":2017,"lang":"en","type":"book-chapter","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Psychology","score_opus":0.09308519081929405,"score_gpt":0.36970893093176066,"score_spread":0.2766237401124666,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2593520074","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007621112,0.053648878,0.08150803,0.58345646,0.015721299,0.0005911184,0.001181831,0.0011696448,0.25510162],"genre_scores_gemma":[0.29427278,0.10187075,0.20053315,0.25235584,0.010221514,0.003094136,0.0026808227,0.0018010315,0.13316995],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9712395,0.01682554,0.001548428,0.002889381,0.0065041836,0.0009929047],"domain_scores_gemma":[0.96778005,0.011488694,0.0020868063,0.0030855075,0.012508712,0.0030502335],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.028068282,0.0009565809,0.00092783436,0.0030385805,0.0028417099,0.013265695,0.0021784783,0.003523532,0.012480181],"category_scores_gemma":[0.08567567,0.00056424324,0.000465489,0.0027048935,0.0142988255,0.021607373,0.0037514963,0.0075554173,0.014292907],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000033473003,0.0000827208,0.0124116065,0.0009695901,0.0000613599,0.00014719684,0.013314351,0.00022087761,0.00033972628,0.226376,0.32063308,0.42541006],"study_design_scores_gemma":[0.000012579078,0.000051571566,0.0053570354,0.0034879597,0.000034821165,0.0007079478,0.012399169,0.00031817573,0.000373205,0.20262761,0.77455837,0.000071581926],"about_ca_topic_score_codex":0.0121432785,"about_ca_topic_score_gemma":0.012312401,"teacher_disagreement_score":0.028068282,"about_ca_system_score_codex":0.0052023595,"about_ca_system_score_gemma":0.013390626,"threshold_uncertainty_score":0.14844108},"labels":[],"label_agreement":null},{"id":"W2593712670","doi":"10.24908/pceea.v0i0.6465","title":"Testing Inter-Rater Reliability in Rubrics for Large Scale Undergraduate Independent Projects","year":2017,"lang":"en","type":"article","venue":"Proceedings of the Canadian Engineering Education Association (CEEA)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Rubric; Deliverable; Reliability (semiconductor); Peer assessment; Consistency (knowledge bases); Supervisor; Inter-rater reliability; Psychology; Computer science; Work (physics); Mathematics education; Engineering; Rating scale; Political science; Systems engineering; Artificial intelligence","score_opus":0.022010159642869193,"score_gpt":0.29583113541512635,"score_spread":0.27382097577225717,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2593712670","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.709207,0.0020981268,0.24863045,0.00069815165,0.001551998,0.010867445,0.0012189541,0.0015029955,0.024224877],"genre_scores_gemma":[0.8512404,0.00051029475,0.13030377,0.00031058866,0.00021454,0.011586907,0.001715663,0.0006488106,0.0034690183],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.7559672,0.14292748,0.026260963,0.011477025,0.060316492,0.003050983],"domain_scores_gemma":[0.4876661,0.26599497,0.026007107,0.048386313,0.1692651,0.0026804118],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.22783458,0.001376256,0.0011210894,0.004101294,0.0020317526,0.0025957527,0.0023246706,0.0010339051,0.00257645],"category_scores_gemma":[0.38040516,0.00073912163,0.0021348677,0.0030645763,0.0022576463,0.0026654822,0.0043493127,0.0019252716,0.0017985351],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0038689529,0.0026500493,0.36558208,0.0044018487,0.0026365353,0.0004628506,0.077071555,0.007070543,0.035341498,0.009030243,0.020730235,0.47115365],"study_design_scores_gemma":[0.001019556,0.007324922,0.75111175,0.0023589267,0.0010437869,0.0011820347,0.024425944,0.055979658,0.06095643,0.01128629,0.08247519,0.00083555357],"about_ca_topic_score_codex":0.0019759752,"about_ca_topic_score_gemma":0.004246484,"teacher_disagreement_score":0.7721654,"about_ca_system_score_codex":0.001842036,"about_ca_system_score_gemma":0.002305442,"threshold_uncertainty_score":0.95221746},"labels":[],"label_agreement":null},{"id":"W2595424209","doi":"","title":"Impact on Learning - Designing Assessment","year":2014,"lang":"en","type":"article","venue":"Murdoch Research Repository (Murdoch University)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Curriculum; Quality (philosophy); Task (project management); Presentation (obstetrics); Quality assurance; Mathematics education; Computer science; Psychology; Pedagogy; Medical education; Engineering; Operations management; Medicine","score_opus":0.06543662287441881,"score_gpt":0.41411004948605745,"score_spread":0.34867342661163864,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2595424209","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19425085,0.0025972666,0.40046453,0.027419457,0.0036873224,0.006934421,0.0011513517,0.010221039,0.35327378],"genre_scores_gemma":[0.50992984,0.001353329,0.4384444,0.0050151916,0.00060807244,0.0018535473,0.00078892027,0.0014804435,0.0405263],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.805121,0.13926002,0.008546964,0.0058319373,0.03834888,0.0028912586],"domain_scores_gemma":[0.6983556,0.18544333,0.008685156,0.049674414,0.052257493,0.0055839648],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.104586385,0.0019253056,0.001042369,0.0024199514,0.0019168012,0.012387161,0.0037450346,0.00312206,0.021040333],"category_scores_gemma":[0.29094052,0.0010114493,0.0016879637,0.0019088737,0.0021589838,0.007844977,0.009027319,0.0033155147,0.007016355],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00068869424,0.0017736809,0.020669347,0.0023409564,0.00009285773,0.00038945716,0.012766545,0.0081421,0.00764878,0.017465375,0.015412427,0.9126098],"study_design_scores_gemma":[0.0007342861,0.009068845,0.049441356,0.0073800026,0.00070562825,0.0024020697,0.02160485,0.031346794,0.044684388,0.062332705,0.76974887,0.00055021036],"about_ca_topic_score_codex":0.0028224706,"about_ca_topic_score_gemma":0.003099691,"teacher_disagreement_score":0.104586385,"about_ca_system_score_codex":0.0048726443,"about_ca_system_score_gemma":0.0071546547,"threshold_uncertainty_score":0.55311227},"labels":[],"label_agreement":null},{"id":"W2597652891","doi":"","title":"Assessment as a Learning Project: Online Surveys with Immediate Formative Feedback","year":2017,"lang":"en","type":"article","venue":"Purdue e-Pubs (Purdue University System)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Formative assessment; Computer science; Online assessment; Online learning; Psychology; Mathematics education; Multimedia","score_opus":0.025218442993307874,"score_gpt":0.3127259221443371,"score_spread":0.2875074791510292,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2597652891","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4724884,0.00020141214,0.37094173,0.0022689423,0.0004171089,0.11686332,0.0025992312,0.004246175,0.029973676],"genre_scores_gemma":[0.44652727,0.0002021329,0.42293188,0.0008206773,0.00021401217,0.12281322,0.0018024999,0.00019185271,0.004496336],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.89457905,0.08559955,0.0054728445,0.0025953674,0.009622941,0.0021302588],"domain_scores_gemma":[0.8549313,0.08014478,0.013276028,0.021211427,0.025824303,0.0046121394],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.07685752,0.0014169794,0.0008437005,0.0020652215,0.001394322,0.0033898589,0.0019312698,0.0010158612,0.0051712375],"category_scores_gemma":[0.117225215,0.00069901766,0.000719891,0.0021866404,0.0011698417,0.0027643733,0.0029957984,0.0013716514,0.0027798424],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013387027,0.0134664625,0.0631659,0.0009634078,0.000095987525,0.00010015411,0.0075027817,0.0032127888,0.0076628025,0.0028006067,0.012633638,0.8870567],"study_design_scores_gemma":[0.0076581803,0.09684689,0.43846494,0.0031268443,0.0004558113,0.0009377,0.03031055,0.07628512,0.08457057,0.026932076,0.2338486,0.0005627051],"about_ca_topic_score_codex":0.0006044435,"about_ca_topic_score_gemma":0.0007893265,"teacher_disagreement_score":0.07685752,"about_ca_system_score_codex":0.0015905079,"about_ca_system_score_gemma":0.005057651,"threshold_uncertainty_score":0},"labels":[],"label_agreement":null},{"id":"W2598237572","doi":"10.24908/pceea.v0i0.6537","title":"Group and individual evaluation in engineering project courses","year":2017,"lang":"en","type":"article","venue":"Proceedings of the Canadian Engineering Education Association (CEEA)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Conestoga College","funders":"","keywords":"Praise; Group work; Group (periodic table); Diversity (politics); Task (project management); Psychology; Mathematics education; Work (physics); Computer science; Point (geometry); Social psychology; Engineering; Sociology; Mathematics","score_opus":0.029063601637837187,"score_gpt":0.3164027994406403,"score_spread":0.28733919780280315,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2598237572","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.70857763,0.0032280285,0.17723694,0.0011374808,0.00073890766,0.0027495725,0.00026862437,0.0010512236,0.1050116],"genre_scores_gemma":[0.8879481,0.0009659072,0.09198164,0.00013023776,0.00012370746,0.0009684926,0.00017052202,0.00018820477,0.017523177],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9477115,0.03678175,0.0017261904,0.0018574365,0.01106269,0.0008603976],"domain_scores_gemma":[0.9459621,0.032197338,0.0036007843,0.0031798668,0.012765038,0.002294955],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03355793,0.00054232817,0.00080049963,0.003687203,0.0012739622,0.002758909,0.0011463222,0.00075555535,0.004481589],"category_scores_gemma":[0.06492093,0.00019087722,0.00036546664,0.0025307538,0.0015279076,0.001968433,0.0034618555,0.0008438528,0.0012924518],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000902366,0.0006546122,0.024753382,0.00055904716,0.00007169116,0.00013869822,0.012828149,0.001989833,0.003595025,0.004641889,0.004690991,0.9451744],"study_design_scores_gemma":[0.0005780402,0.015763722,0.47170785,0.0036064363,0.00041395935,0.002431972,0.077324994,0.060224287,0.060548395,0.0686408,0.23781766,0.0009419546],"about_ca_topic_score_codex":0.0017660409,"about_ca_topic_score_gemma":0.0034305723,"teacher_disagreement_score":0.03355793,"about_ca_system_score_codex":0.0012790066,"about_ca_system_score_gemma":0.0015500218,"threshold_uncertainty_score":0.17747343},"labels":[],"label_agreement":null},{"id":"W2599956837","doi":"10.1177/0265532216684576","title":"Book Review: Focus on Assessment","year":2016,"lang":"en","type":"article","venue":"Language Testing","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Focus (optics); Psychology; Linguistics; Philosophy; Optics","score_opus":0.032919987551438844,"score_gpt":0.3820371374063785,"score_spread":0.3491171498549397,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2599956837","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00021572,0.86540973,0.0005078069,0.033716016,0.08324899,0.000108859436,0.000244589,0.000077404984,0.016470943],"genre_scores_gemma":[0.0025707837,0.7831941,0.00084395515,0.035481606,0.096836634,0.00029123394,0.00043766867,0.00014676683,0.08019734],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9963728,0.0009885344,0.0003695254,0.00034101724,0.001734142,0.00019400126],"domain_scores_gemma":[0.97439945,0.011693326,0.0018304056,0.00043226936,0.009765799,0.0018787518],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0038767129,0.0013775115,0.0032618681,0.009181574,0.0006649477,0.0050927415,0.0016451323,0.0038212894,0.03993967],"category_scores_gemma":[0.026358377,0.0005778097,0.00095743715,0.009497337,0.0012991398,0.0033399882,0.0019784754,0.0045454754,0.022344206],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002834032,0.000023874594,0.00007753744,0.0040723905,0.000023076294,0.000046329184,0.000024362247,0.00005936294,0.00010631386,0.00060117914,0.8857649,0.10917237],"study_design_scores_gemma":[0.000033321416,0.00004624589,0.0006890746,0.006838445,0.000048471655,0.00036695026,0.000052432406,0.00003632399,0.000057437366,0.0006401936,0.9911747,0.000016378799],"about_ca_topic_score_codex":0.0034027696,"about_ca_topic_score_gemma":0.013135827,"teacher_disagreement_score":0.03993967,"about_ca_system_score_codex":0.0033571783,"about_ca_system_score_gemma":0.0055536265,"threshold_uncertainty_score":0.1336115},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Accountability; Psychology; Medical education; Political science; Medicine","score_opus":0.12258459740226811,"score_gpt":0.5148076355503635,"score_spread":0.39222303814809534,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2600733185","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11047169,0.0077255713,0.09586354,0.51935446,0.0043922113,0.00032203618,0.00011926294,0.0013457026,0.26040554],"genre_scores_gemma":[0.7978379,0.006200644,0.051717814,0.041979495,0.0011525952,0.00051115284,0.00015188458,0.00040900335,0.100039475],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.98399323,0.008023634,0.0006391404,0.0013605729,0.0034255872,0.0025579212],"domain_scores_gemma":[0.95298755,0.016498078,0.0041022003,0.003371358,0.009192582,0.013848302],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02269946,0.00037476222,0.00051519915,0.00089560624,0.006982223,0.013473852,0.0016558691,0.0062753805,0.0093769375],"category_scores_gemma":[0.04361229,0.00055352703,0.00024319878,0.00065627805,0.007994081,0.018247254,0.016736776,0.010582175,0.005695342],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001354123,0.0005840354,0.015658066,0.00068845076,0.000023333941,0.0011800148,0.10901565,0.0010800326,0.0032269717,0.44078654,0.13930124,0.28832027],"study_design_scores_gemma":[0.00003705346,0.00016258963,0.0064823152,0.0009940208,0.000012044042,0.00087768224,0.060138598,0.0017207453,0.0020065568,0.18313481,0.74435776,0.00007589757],"about_ca_topic_score_codex":0.0034595646,"about_ca_topic_score_gemma":0.007254483,"teacher_disagreement_score":0.02269946,"about_ca_system_score_codex":0.0041013625,"about_ca_system_score_gemma":0.020156164,"threshold_uncertainty_score":0.12004763},"labels":[],"label_agreement":null},{"id":"W2602102095","doi":"","title":"Ontario's Grade 6 Learners' Mathematics Achievement Profiles Underlying the EQAO Junior Division Assessment","year":2016,"lang":"en","type":"dissertation","venue":"TSpace (University of Toronto)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Mathematics education; Division (mathematics); Mathematics; Psychology; Arithmetic","score_opus":0.04426223872004224,"score_gpt":0.348418480087242,"score_spread":0.30415624136719976,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2602102095","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9962453,0.000015466969,0.000063710875,0.000037955044,0.0000013204561,0.000013001177,0.000285638,0.000004530438,0.0033330007],"genre_scores_gemma":[0.9977203,0.000037456135,0.000120706405,0.0000069445514,6.113452e-7,0.000011462259,0.00028212514,0.0000027026215,0.0018177312],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9992478,0.000056268604,0.000052690804,0.000084566476,0.00043823727,0.00012051617],"domain_scores_gemma":[0.99770397,0.00026632546,0.00047747223,0.00008486529,0.0010796371,0.00038770676],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007724311,0.00014709798,0.00022092483,0.0011546132,0.0010056678,0.0011678543,0.00032528787,0.0001913229,0.0018903463],"category_scores_gemma":[0.004670734,0.00011925239,0.00016626074,0.001124141,0.0005088014,0.00034178686,0.00091641897,0.0002389111,0.0004245921],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007773667,0.000033343505,0.9690609,0.000023271677,0.000008684131,0.000115115356,0.011057374,0.00013890861,0.0014615637,0.0001904889,0.0004261936,0.01740646],"study_design_scores_gemma":[7.6275006e-7,0.000028427725,0.99546117,0.000007260046,0.0000026305029,0.000023976816,0.003489603,0.000104938874,0.0001972854,0.000024376774,0.0006548383,0.000004806897],"about_ca_topic_score_codex":0.55022556,"about_ca_topic_score_gemma":0.73649675,"teacher_disagreement_score":0.44977444,"about_ca_system_score_codex":0.0031841116,"about_ca_system_score_gemma":0.003793344,"threshold_uncertainty_score":0.9048465},"labels":[],"label_agreement":null},{"id":"W2602322515","doi":"10.5539/jedp.v7n1p229","title":"Exploring Correlates of Business Undergraduates’ Closed Versus Open Grading Assessment Learning Perceptions","year":2017,"lang":"en","type":"article","venue":"Journal of Educational and Developmental Psychology","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology; Grading (engineering); Reputation; Variance (accounting); Stepwise regression; Perception; Explained variation; Applied psychology; Confirmatory factor analysis; Social psychology; Mathematics education; Statistics; Mathematics; Structural equation modeling; Engineering; Social science; Accounting; Sociology","score_opus":0.2591831070170039,"score_gpt":0.4751121751058542,"score_spread":0.21592906808885026,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2602322515","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9992981,0.000022111533,0.00008783487,0.000033034685,0.0000039583915,0.0000060892257,0.000014936406,0.0000032003004,0.0005307183],"genre_scores_gemma":[0.99970657,0.00001298732,0.000075431,0.000008591096,0.0000026913672,0.000004380381,0.00002460612,9.399284e-7,0.00016380046],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.997945,0.00050373503,0.00023280534,0.00019440746,0.00086400966,0.00025995646],"domain_scores_gemma":[0.9776864,0.00700513,0.005736626,0.0006905904,0.004048328,0.004832908],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004542007,0.0001564292,0.0002943478,0.0012527221,0.0004931622,0.0017806981,0.00029508115,0.00032699798,0.0013515281],"category_scores_gemma":[0.022992872,0.00014562215,0.00018601015,0.0007817202,0.00069474994,0.00073838036,0.0012212035,0.0007857659,0.00023861519],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010317454,0.00049403985,0.9668396,0.000022993287,0.000019546076,0.00003750018,0.0056921476,0.00007131475,0.001009176,0.00014853987,0.00023860365,0.025323277],"study_design_scores_gemma":[0.00000316764,0.0002074655,0.99480045,0.0000092398295,0.000003821822,0.000023524788,0.004178788,0.00021522652,0.00021255521,0.000080216545,0.000259275,0.000006453838],"about_ca_topic_score_codex":0.003734652,"about_ca_topic_score_gemma":0.007286717,"teacher_disagreement_score":0.004542007,"about_ca_system_score_codex":0.0005797908,"about_ca_system_score_gemma":0.00075178046,"threshold_uncertainty_score":0.024020731},"labels":[],"label_agreement":null},{"id":"W2603140028","doi":"","title":"The knowledge connections analyzer","year":2012,"lang":"en","type":"article","venue":"View","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Formative assessment; SQL; Usability; Asynchronous communication; World Wide Web; Knowledge management; Human–computer interaction; Mathematics education; Database; Psychology","score_opus":0.06088683430738525,"score_gpt":0.40721072893110305,"score_spread":0.3463238946237178,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2603140028","genre_codex":"methods","genre_gemma":"software","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"software","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.047100805,0.0005956868,0.6202194,0.0010188692,0.00024447264,0.0020505923,0.027340591,0.23597124,0.06545842],"genre_scores_gemma":[0.250579,0.0005189056,0.67994153,0.00050004775,0.0001000524,0.0016649116,0.035657067,0.008176606,0.022861911],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.996393,0.0006644592,0.0004664184,0.00081066793,0.0014887382,0.0001765885],"domain_scores_gemma":[0.9928848,0.003632003,0.00050667813,0.0011497936,0.0015300997,0.00029665872],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029612335,0.00083871593,0.00051656686,0.005773816,0.000955462,0.0039496776,0.0016568998,0.00087552355,0.01604114],"category_scores_gemma":[0.015930519,0.0007464319,0.00060225854,0.0027712607,0.0006183426,0.0075193155,0.0034354613,0.0014237318,0.008006099],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004059023,0.00035390028,0.020200677,0.00081821263,0.00010361941,0.00079830777,0.0028604495,0.0023520442,0.01084559,0.050223574,0.09598102,0.81505674],"study_design_scores_gemma":[0.00020174874,0.00020779118,0.01920248,0.00034303436,0.0001522014,0.0023102975,0.0018647315,0.098236084,0.05008918,0.07735192,0.7498526,0.0001878632],"about_ca_topic_score_codex":0.0031133578,"about_ca_topic_score_gemma":0.0028789283,"teacher_disagreement_score":0.01604114,"about_ca_system_score_codex":0.00083332637,"about_ca_system_score_gemma":0.0024332022,"threshold_uncertainty_score":0.053662896},"labels":[],"label_agreement":null},{"id":"W2604298682","doi":"","title":"Enseignement et évaluation structurés","year":2010,"lang":"fr","type":"article","venue":"Canadian Family Physician","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Humanities; Computer science; Library science; Philosophy","score_opus":0.03546237938090538,"score_gpt":0.3113231019364217,"score_spread":0.2758607225555163,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2604298682","genre_codex":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.10759212,0.0042709005,0.37911978,0.014393766,0.0008092676,0.003574162,0.0030436257,0.0042525157,0.48294377],"genre_scores_gemma":[0.47094882,0.0021387418,0.28966045,0.0010553017,0.00037610074,0.0022316282,0.0042924867,0.0009932863,0.22830325],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9792093,0.008702583,0.0017427073,0.0017039105,0.007634857,0.0010066292],"domain_scores_gemma":[0.9598279,0.010631811,0.0026224244,0.005009894,0.019798951,0.0021089807],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.019257573,0.0005020177,0.0004414082,0.0033802893,0.0030176612,0.007379669,0.0016243599,0.0012348079,0.023356719],"category_scores_gemma":[0.04861302,0.00040428084,0.00044280564,0.0027660145,0.0023851513,0.0054701413,0.0037704092,0.0013846391,0.0061485847],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00044750524,0.00042432733,0.010700207,0.0006703635,0.000040979336,0.00028538663,0.015293114,0.0034666476,0.0036625725,0.22713366,0.04341465,0.6944605],"study_design_scores_gemma":[0.00012882736,0.00053246476,0.027039846,0.0011970556,0.00006762903,0.0004920286,0.009440437,0.014868701,0.018624185,0.117081344,0.810373,0.0001544356],"about_ca_topic_score_codex":0.02056712,"about_ca_topic_score_gemma":0.018018335,"teacher_disagreement_score":0.023356719,"about_ca_system_score_codex":0.008740351,"about_ca_system_score_gemma":0.017051287,"threshold_uncertainty_score":0.101845026},"labels":[],"label_agreement":null},{"id":"W2607048716","doi":"","title":"Investigating the Effectiveness of Peer Reviewing in a Moroccan University EFL Writing Class","year":2016,"lang":"en","type":"article","venue":"Higher education of social science","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Paragraph; Psychology; Peer feedback; Context (archaeology); Test (biology); Class (philosophy); Second language writing; Relevance (law); Mathematics education; Session (web analytics); Quality (philosophy); Arabic; Task (project management); English as a foreign language; Medical education; Pedagogy; Computer science; Second language; Linguistics","score_opus":0.03971718920983726,"score_gpt":0.37040377560353266,"score_spread":0.3306865863936954,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2607048716","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99938035,0.000052493346,0.0000518007,0.00004059297,0.0000053739705,0.000058055375,0.00000531965,0.0000040158466,0.00040202567],"genre_scores_gemma":[0.9982413,0.000111353875,0.00076840044,0.000062534855,0.000019724717,0.00010143402,0.000015617547,0.000004463275,0.0006751719],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.99088925,0.0054115853,0.00050675805,0.0008746037,0.001353896,0.0009638145],"domain_scores_gemma":[0.96789014,0.015422107,0.005296533,0.001657763,0.005965147,0.003768254],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010337509,0.00054680754,0.0008224663,0.00091566565,0.003213222,0.0022250072,0.0013444461,0.0007773008,0.0014106528],"category_scores_gemma":[0.028278282,0.0003125538,0.00030943475,0.00051598693,0.0012349401,0.00066274795,0.0012574219,0.00065049564,0.00044292177],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002121822,0.016902272,0.31975615,0.0019576466,0.00016452925,0.0033535843,0.40073377,0.00055551186,0.046147354,0.00034579667,0.0017370975,0.2062244],"study_design_scores_gemma":[0.0002382337,0.01965122,0.7822898,0.00041211286,0.00021623618,0.00084811077,0.17067194,0.0010897553,0.014751534,0.0001765205,0.009481584,0.00017298646],"about_ca_topic_score_codex":0.004171706,"about_ca_topic_score_gemma":0.009668677,"teacher_disagreement_score":0.010337509,"about_ca_system_score_codex":0.0018632412,"about_ca_system_score_gemma":0.0032606653,"threshold_uncertainty_score":0.05467069},"labels":[],"label_agreement":null},{"id":"W2611549767","doi":"10.18806/tesl.v34i1.1260","title":"Post-Admission Language Assessment of University Students (J. Read (ed.), 2016)","year":2017,"lang":"en","type":"article","venue":"TESL Canada Journal","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Language assessment; Psychology; Linguistics; Mathematics education; Pedagogy; Philosophy","score_opus":0.01633748164551186,"score_gpt":0.3578796298138933,"score_spread":0.34154214816838147,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2611549767","genre_codex":"empirical","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9808178,0.003890017,0.00054649345,0.003519815,0.00078613596,0.00012488531,0.00041708903,0.00013218346,0.009765625],"genre_scores_gemma":[0.9764837,0.00341034,0.0016458331,0.00049910176,0.00013110318,0.00008045252,0.0004615321,0.000038915096,0.017249055],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99849296,0.00046605364,0.00017646233,0.000069396076,0.0006176528,0.0001774372],"domain_scores_gemma":[0.9890127,0.0013250369,0.00085038797,0.00018010182,0.0049477094,0.00368414],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029417481,0.00033273906,0.000598689,0.0012647182,0.0008977062,0.0015566177,0.0008086871,0.0006484619,0.00461319],"category_scores_gemma":[0.022321317,0.00016462439,0.00035509688,0.00062109885,0.00039076587,0.0006897739,0.0019644634,0.001429416,0.0026298922],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015765117,0.0031819132,0.2100756,0.00030231706,0.000053675103,0.00072720234,0.0081645185,0.00031313204,0.0014478753,0.0001447232,0.042842455,0.7311701],"study_design_scores_gemma":[0.00012259308,0.0054143094,0.94937366,0.0007434161,0.00011279143,0.0011501325,0.01894109,0.00082182226,0.004705361,0.00052163657,0.01794788,0.00014532001],"about_ca_topic_score_codex":0.027223177,"about_ca_topic_score_gemma":0.07074386,"teacher_disagreement_score":0.027223177,"about_ca_system_score_codex":0.0012860132,"about_ca_system_score_gemma":0.0039986484,"threshold_uncertainty_score":0.05412942},"labels":[],"label_agreement":null},{"id":"W2611871119","doi":"","title":"Instructor Comments on Student Writing: Learner Response to Electronic Written Feedback","year":2016,"lang":"en","type":"article","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Mount Royal University","funders":"","keywords":"Writing process; Legibility; Thematic analysis; Psychology; Peer feedback; Process (computing); Qualitative research; Multimedia; Computer science; Mathematics education","score_opus":0.025483229253907346,"score_gpt":0.36045114603416256,"score_spread":0.3349679167802552,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2611871119","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9924366,0.000113546645,0.002897977,0.0006617034,0.000069921116,0.00007509357,0.00010824246,0.00012412177,0.0035128482],"genre_scores_gemma":[0.9930353,0.00016860872,0.0025445602,0.00031645296,0.00006652937,0.000121335026,0.00012015164,0.00006054888,0.0035664646],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.98981994,0.006377831,0.00061699474,0.0005488861,0.0022583175,0.00037804482],"domain_scores_gemma":[0.8927367,0.07864363,0.011201552,0.0032704358,0.0119445175,0.0022032496],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00850487,0.00049406587,0.0005376844,0.0010416048,0.0012466414,0.0018212517,0.00075616693,0.0011161828,0.0038465904],"category_scores_gemma":[0.08694078,0.00023191405,0.00037738474,0.0005308995,0.0009312269,0.0012293461,0.0023339265,0.0014754724,0.001005882],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015178479,0.0006317317,0.14910991,0.00080517866,0.00012283768,0.0024951946,0.60638356,0.0008248801,0.030017694,0.00063132215,0.0063351663,0.2011246],"study_design_scores_gemma":[0.00028585477,0.0067952652,0.26119715,0.0012365251,0.00028612395,0.0044222167,0.5676891,0.01264958,0.05823809,0.0025144916,0.08413995,0.00054574443],"about_ca_topic_score_codex":0.0004818816,"about_ca_topic_score_gemma":0.0007800292,"teacher_disagreement_score":0.00850487,"about_ca_system_score_codex":0.0005928786,"about_ca_system_score_gemma":0.0005407327,"threshold_uncertainty_score":0.04497856},"labels":[],"label_agreement":null},{"id":"W2615639425","doi":"","title":"PAPER: Measuring Teachers’ Assessment Literacy and Conceptions of Assessment in a High Performative Canadian Context: A Construct Validity Study","year":2016,"lang":"en","type":"article","venue":"ITC 2016 Conference","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Performative utterance; Psychology; Literacy; Context (archaeology); Construct (python library); Construct validity; Mathematics education; Pedagogy; Psychometrics; Computer science; Developmental psychology","score_opus":0.06347086988825551,"score_gpt":0.3642921981591032,"score_spread":0.3008213282708477,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2615639425","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.987973,0.00021119589,0.00086995313,0.000552625,0.00004133345,0.000422158,0.0010208272,0.0000135946375,0.00889538],"genre_scores_gemma":[0.99342585,0.00033414637,0.0023735235,0.00024792276,0.000019121178,0.0004206114,0.00084025424,0.000015799445,0.002322847],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9903909,0.0011472224,0.0006851619,0.0009826417,0.0059632384,0.0008308022],"domain_scores_gemma":[0.9310805,0.013382258,0.007772631,0.0032195463,0.04096781,0.0035771953],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011739544,0.000460096,0.0005688453,0.0032212562,0.009140628,0.0039823437,0.0016607074,0.0006011861,0.0023829455],"category_scores_gemma":[0.059126217,0.00046491603,0.00064715307,0.0058397558,0.0033079218,0.0016706819,0.0033354214,0.0015312553,0.00031943558],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000121456775,0.00024282312,0.87417257,0.00022403366,0.000056833265,0.00012444251,0.085386366,0.00023452636,0.000652279,0.0015329429,0.0032174913,0.03403427],"study_design_scores_gemma":[0.000018489258,0.00009493572,0.94158775,0.00016853496,0.000043861193,0.00008241986,0.04828421,0.0004848715,0.0005320926,0.00022154706,0.008422924,0.00005842097],"about_ca_topic_score_codex":0.94443506,"about_ca_topic_score_gemma":0.95358855,"teacher_disagreement_score":0.05556494,"about_ca_system_score_codex":0.026048573,"about_ca_system_score_gemma":0.06963117,"threshold_uncertainty_score":0.1889965},"labels":[],"label_agreement":null},{"id":"W2618977613","doi":"10.5539/ies.v10n6p159","title":"The Effect of Peer Assessment on the Evaluation Process of Students","year":2017,"lang":"en","type":"article","venue":"International Education Studies","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":43,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"King Saud University","keywords":"Peer assessment; Credibility; Process (computing); Scope (computer science); Standards-based assessment; Psychology; Peer evaluation; Peer feedback; Peer review; Educational assessment; Alternative assessment; Formative assessment; Mathematics education; Higher education; Computer science; Political science","score_opus":0.12447706384515944,"score_gpt":0.6008781695317235,"score_spread":0.476401105686564,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2618977613","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97524047,0.00085422385,0.010206693,0.00056246744,0.00010790664,0.0003433119,0.000018938088,0.00017245472,0.012493502],"genre_scores_gemma":[0.99565566,0.0001307189,0.0030238624,0.00003604918,0.000031088308,0.00007832553,0.000010572706,0.000019845013,0.0010138304],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9126084,0.062627025,0.0033404191,0.0028091685,0.017182657,0.0014323256],"domain_scores_gemma":[0.59764665,0.31869885,0.026158536,0.01337345,0.03722113,0.006901375],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.027023956,0.0005663303,0.0007248002,0.0015776362,0.0015779862,0.0036304216,0.001108246,0.00097200804,0.0019054734],"category_scores_gemma":[0.2831477,0.00025824562,0.00079139724,0.0006474417,0.0013394227,0.002226228,0.002357901,0.0013697468,0.00044123715],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0038549644,0.0035500627,0.2413548,0.0012519518,0.0005191077,0.0009986472,0.066146694,0.005010891,0.021287417,0.0035608555,0.0019035771,0.6505611],"study_design_scores_gemma":[0.00067275594,0.019832615,0.7844689,0.0015571733,0.0010898174,0.0024206343,0.058333583,0.03749476,0.054589387,0.0116245365,0.027161125,0.0007546994],"about_ca_topic_score_codex":0.0015662429,"about_ca_topic_score_gemma":0.0013430723,"teacher_disagreement_score":0.027023956,"about_ca_system_score_codex":0.0012337028,"about_ca_system_score_gemma":0.0030179578,"threshold_uncertainty_score":0.14291805},"labels":[],"label_agreement":null},{"id":"W2619779668","doi":"10.1016/j.nedt.2017.05.016","title":"A qualitative study on feedback provided by students in nurse education","year":2017,"lang":"en","type":"article","venue":"Nurse Education Today","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Focus group; Peer feedback; Qualitative research; Medical education; Psychology; Narrative; Nurse education; Student nurse; Pedagogy; Medicine; Sociology","score_opus":0.04196839473542503,"score_gpt":0.49293822241707674,"score_spread":0.4509698276816517,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2619779668","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9884404,0.0005633593,0.0028504853,0.00206671,0.00020638165,0.0007104922,0.00027953304,0.000044110897,0.0048383833],"genre_scores_gemma":[0.98981583,0.00070506905,0.0022956275,0.0017662882,0.000067001485,0.0012245296,0.00012902982,0.00006501382,0.0039316504],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9293579,0.057963885,0.002405719,0.0015839769,0.0042710947,0.0044173906],"domain_scores_gemma":[0.72428024,0.225729,0.01153737,0.003346194,0.025244847,0.009862325],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.04788857,0.0010913002,0.0014285853,0.0039061904,0.020647835,0.007099792,0.002564269,0.0032549996,0.003782217],"category_scores_gemma":[0.119860284,0.001217004,0.0007965113,0.003641595,0.010645699,0.004354368,0.008500803,0.005846606,0.0006770658],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009694456,0.00021942261,0.005680951,0.0002457503,0.000005750213,0.00048461452,0.9867166,0.000020383764,0.0009131616,0.00022197943,0.00038691793,0.0050075627],"study_design_scores_gemma":[0.000013295233,0.00028907065,0.004180775,0.0003277118,0.000007792493,0.00020065602,0.9902957,0.000042157215,0.0006882987,0.0000820846,0.0038516626,0.000020851927],"about_ca_topic_score_codex":0.008273714,"about_ca_topic_score_gemma":0.020864962,"teacher_disagreement_score":0.04788857,"about_ca_system_score_codex":0.01077876,"about_ca_system_score_gemma":0.014735321,"threshold_uncertainty_score":0.25326192},"labels":[],"label_agreement":null},{"id":"W2620495706","doi":"10.5539/elt.v10n6p37","title":"Building a Positive Environment in Classrooms through Feedback and Praise","year":2017,"lang":"en","type":"article","venue":"English Language Teaching","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Praise; Psychology; Incentive; Perception; Mathematics education; Order (exchange); Pedagogy; Social psychology","score_opus":0.015840281702753478,"score_gpt":0.3369877777825241,"score_spread":0.3211474960797706,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2620495706","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8058863,0.0010737558,0.10842161,0.009958277,0.00035664614,0.0008176783,0.000065871245,0.0019489081,0.07147093],"genre_scores_gemma":[0.9528571,0.0004861755,0.039090544,0.0005463738,0.00007830477,0.00031819468,0.00002323432,0.00008963255,0.0065103713],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9789844,0.013426521,0.0006854264,0.0012001775,0.004687489,0.0010159594],"domain_scores_gemma":[0.96680766,0.01843067,0.0048124525,0.0023996108,0.003738575,0.0038110174],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011888123,0.0005106445,0.00074069796,0.0010409519,0.0022462553,0.004572321,0.0012183418,0.0014248644,0.0040893317],"category_scores_gemma":[0.028672809,0.00043420418,0.00047320232,0.0003103311,0.0031523637,0.0038408649,0.0044766897,0.0021712387,0.001241805],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004970854,0.0054674675,0.057174407,0.0024363657,0.0001148634,0.001413772,0.18219723,0.0017419736,0.076725766,0.01941041,0.0073789596,0.64544165],"study_design_scores_gemma":[0.00054776156,0.012817762,0.257821,0.0038227395,0.00027455014,0.004950164,0.2957421,0.0071722115,0.06391871,0.05304853,0.2986751,0.0012093624],"about_ca_topic_score_codex":0.00055023364,"about_ca_topic_score_gemma":0.00092717604,"teacher_disagreement_score":0.011888123,"about_ca_system_score_codex":0.00080221007,"about_ca_system_score_gemma":0.0027677354,"threshold_uncertainty_score":0.0628711},"labels":[],"label_agreement":null},{"id":"W2622935668","doi":"10.3138/jvme.0616-113r","title":"Adaptive Comparative Judgment: A Tool to Support Students' Assessment Literacy","year":2017,"lang":"en","type":"article","venue":"Journal of Veterinary Medical Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Ranking (information retrieval); Cohort; Task (project management); Psychology; Process (computing); Work (physics); Mathematics education; Medical education; Computer science; Applied psychology; Information retrieval; Statistics; Medicine; Mathematics; Engineering","score_opus":0.156100825334503,"score_gpt":0.5426009298816273,"score_spread":0.38650010454712436,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2622935668","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.70219004,0.00033480633,0.22642726,0.0020568715,0.00042767124,0.0058615915,0.0031719785,0.017726637,0.041803107],"genre_scores_gemma":[0.5947624,0.0003371919,0.3831021,0.00035082593,0.00013688399,0.005354252,0.0014062799,0.0008025517,0.013747579],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9890589,0.00585778,0.0012066462,0.0007656857,0.0026923956,0.0004186668],"domain_scores_gemma":[0.90753543,0.06572105,0.0052113803,0.006008937,0.01258925,0.002933987],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015444471,0.0007790999,0.0008074701,0.0045232885,0.0007083447,0.0020863267,0.0012986535,0.0007856906,0.011791082],"category_scores_gemma":[0.09309232,0.0003690944,0.00043811306,0.0024923177,0.00055206224,0.002213461,0.0032923566,0.001159508,0.004216715],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008255212,0.00226542,0.033624124,0.00081249245,0.000030797015,0.00031199693,0.026501449,0.0008418577,0.019357855,0.0015966673,0.034155447,0.8796764],"study_design_scores_gemma":[0.001209248,0.009862125,0.38493976,0.0020108058,0.00019957284,0.002813705,0.02727169,0.05857703,0.09135844,0.025298689,0.39530942,0.0011495604],"about_ca_topic_score_codex":0.00057943305,"about_ca_topic_score_gemma":0.0012357156,"teacher_disagreement_score":0.015444471,"about_ca_system_score_codex":0.0006293724,"about_ca_system_score_gemma":0.0017346118,"threshold_uncertainty_score":0.081679165},"labels":[],"label_agreement":null},{"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Psychology; Meta-analysis; Test (biology); Best practice; Presentation (obstetrics); Mathematics education; Applied psychology; Medicine","score_opus":0.7954275058930537,"score_gpt":0.643213236651155,"score_spread":0.15221426924189863,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2624412722","genre_codex":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01732506,0.9678293,0.009367925,0.0012427706,0.00088018994,0.0014610725,0.0008934905,0.00011870808,0.0008814466],"genre_scores_gemma":[0.57692194,0.3788173,0.032145467,0.0023984793,0.0006064837,0.006424193,0.0018291888,0.00032640863,0.0005305325],"study_design_codex":"meta_analysis","study_design_gemma":"meta_analysis","domain_scores_codex":[0.8246144,0.11192839,0.03956908,0.008198451,0.01480504,0.00088462885],"domain_scores_gemma":[0.6065734,0.33422408,0.02556903,0.018719202,0.0140432855,0.00087094726],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.15699442,0.0032082484,0.014339226,0.01233193,0.0008506694,0.0064822263,0.0043078735,0.0021827363,0.0017106722],"category_scores_gemma":[0.39118138,0.0019649223,0.039755814,0.011263541,0.0023085296,0.0052364343,0.003169201,0.0028948835,0.0002140418],"study_design_candidate":"meta_analysis","study_design_consensus":"meta_analysis","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013802334,0.000044165317,0.008096296,0.21694045,0.72892606,0.0001290453,0.0009382486,0.0006800748,0.00032019106,0.0008016152,0.0008352158,0.04090842],"study_design_scores_gemma":[0.0007520349,0.000667019,0.009264308,0.06802141,0.9107859,0.00017211796,0.00042971893,0.0005933147,0.0007853201,0.0020015668,0.0064308057,0.000096601],"about_ca_topic_score_codex":0.0061571575,"about_ca_topic_score_gemma":0.010352506,"teacher_disagreement_score":0.8430056,"about_ca_system_score_codex":0.0049704667,"about_ca_system_score_gemma":0.005785631,"threshold_uncertainty_score":0.8302758},"labels":[],"label_agreement":null},{"id":"W2707915995","doi":"10.7213/1981-416x.17.052.ds06","title":"Autoavaliação e avaliação pelos pares: uma análise de pesquisas internacionais recentes","year":2017,"lang":"pt","type":"article","venue":"Revista Diálogo Educacional","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Psychology; Humanities; Pedagogy; Philosophy","score_opus":0.07031719651890204,"score_gpt":0.3937317090621989,"score_spread":0.32341451254329684,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2707915995","genre_codex":"empirical","genre_gemma":"review","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7772469,0.10211724,0.013951278,0.022098312,0.001989523,0.0005321272,0.0021912113,0.0003211734,0.07955231],"genre_scores_gemma":[0.916943,0.053593203,0.009989589,0.0020408586,0.0005963439,0.00046674148,0.0011274583,0.00015810116,0.015084672],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.98807853,0.0045761433,0.0011502951,0.0014648092,0.003915108,0.0008150154],"domain_scores_gemma":[0.93344915,0.036634065,0.008113334,0.0028188096,0.015855651,0.0031289326],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01764096,0.00058530085,0.0009137513,0.005984612,0.0021011122,0.005823302,0.0013688763,0.0015600214,0.008257825],"category_scores_gemma":[0.053310737,0.00048212972,0.0010095994,0.0076023433,0.00255136,0.004850887,0.004959357,0.0021831673,0.0011354143],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005862237,0.00042337633,0.1451097,0.009368208,0.00025104667,0.0005297307,0.09201016,0.0007557879,0.002518278,0.009920216,0.012497432,0.72602993],"study_design_scores_gemma":[0.00003226792,0.0011464474,0.50845826,0.010021711,0.0003051977,0.0014192016,0.124754205,0.00070001534,0.002489239,0.0058236285,0.344683,0.00016688531],"about_ca_topic_score_codex":0.012718025,"about_ca_topic_score_gemma":0.028152974,"teacher_disagreement_score":0.98235905,"about_ca_system_score_codex":0.0046302564,"about_ca_system_score_gemma":0.012023319,"threshold_uncertainty_score":0.093295455},"labels":[],"label_agreement":null},{"id":"W2735739974","doi":"10.4018/978-1-5225-2953-8.ch004","title":"Technology and Teaching","year":2017,"lang":"en","type":"book-chapter","venue":"Advances in educational technologies and instructional design book series","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"MacEwan University","funders":"","keywords":"Implementation; Mathematics education; Student engagement; Student centered; Psychology; Work (physics); Pedagogy; Computer science; Engineering","score_opus":0.02251533609322583,"score_gpt":0.3289112032534644,"score_spread":0.3063958671602386,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2735739974","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0029959367,0.07618266,0.0024285791,0.0076180985,0.0015968714,0.00003315001,0.000038534195,0.000071673014,0.90903443],"genre_scores_gemma":[0.14101717,0.107478164,0.0046635685,0.0051225633,0.0015093248,0.00015294549,0.00013708729,0.00013807554,0.739781],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9993789,0.00023250194,0.000026523183,0.00009574293,0.0002026986,0.00006354207],"domain_scores_gemma":[0.9995739,0.00021191147,0.000036667763,0.000050265746,0.00004556689,0.0000817682],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00051647803,0.00047431776,0.00028856736,0.00083046796,0.001730008,0.007880355,0.0005008507,0.0014103175,0.027114451],"category_scores_gemma":[0.0013427864,0.0001451068,0.00018904533,0.0012097735,0.004651552,0.004570941,0.0025108939,0.002064564,0.0056351097],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012421177,0.00006423127,0.00059097534,0.00031423333,0.000006862668,0.000117364776,0.008600757,0.00021685376,0.00037082913,0.6315026,0.091194846,0.26700807],"study_design_scores_gemma":[0.000003682616,0.000019144565,0.0007367853,0.00053749006,0.0000025254672,0.00030546414,0.002578528,0.0000784339,0.000108897904,0.09012244,0.9054996,0.0000069892967],"about_ca_topic_score_codex":0.002306615,"about_ca_topic_score_gemma":0.0033836383,"teacher_disagreement_score":0.027114451,"about_ca_system_score_codex":0.0021742813,"about_ca_system_score_gemma":0.0021817456,"threshold_uncertainty_score":0.090706885},"labels":[],"label_agreement":null},{"id":"W2736595548","doi":"","title":"POSTER: A Validity Argument Approach to Collaborative Development of the Colleges Mathematics Assessment Program","year":2016,"lang":"en","type":"article","venue":"ITC 2016 Conference","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"York University; University of Toronto","funders":"","keywords":"Argument (complex analysis); Test (biology); Mathematics education; Computer science; Psychology","score_opus":0.08059059746095346,"score_gpt":0.3733509050348911,"score_spread":0.2927603075739377,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2736595548","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.01154037,0.0012037137,0.18149103,0.21376558,0.0026790036,0.00300185,0.00043748427,0.0004887584,0.58539224],"genre_scores_gemma":[0.5770336,0.0013494467,0.2186732,0.018836545,0.0015748566,0.004435054,0.0004980541,0.00054771407,0.17705165],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9545036,0.030741936,0.0013319404,0.0023609793,0.009532104,0.0015294413],"domain_scores_gemma":[0.91050273,0.058058538,0.0033451098,0.006080434,0.019155474,0.002857829],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.059498023,0.0006169098,0.0004832618,0.0029983986,0.0098161185,0.012015584,0.0036847568,0.006987207,0.049228773],"category_scores_gemma":[0.093991175,0.0006226134,0.0011163906,0.0016287202,0.013335868,0.0076285666,0.009948881,0.006297727,0.0048281797],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007726312,0.00015629028,0.0020987538,0.00049791834,0.0000194711,0.00046104818,0.023993907,0.0013539392,0.0004153223,0.8290516,0.069941185,0.07193331],"study_design_scores_gemma":[0.00014502011,0.0001693059,0.003465975,0.0022015502,0.000065537904,0.00034646873,0.013730791,0.0062458036,0.0018451267,0.33820826,0.63350016,0.00007593182],"about_ca_topic_score_codex":0.017234894,"about_ca_topic_score_gemma":0.02107902,"teacher_disagreement_score":0.059498023,"about_ca_system_score_codex":0.02031814,"about_ca_system_score_gemma":0.023629924,"threshold_uncertainty_score":0.31465942},"labels":[],"label_agreement":null},{"id":"W2748587261","doi":"10.23977/aetp.2017.12002","title":"An Empirical Study on Learning-oriented Assessment","year":2017,"lang":"en","type":"article","venue":"Advances in Educational Technology and Psychology","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Empirical research; Autonomy; Process (computing); Knowledge management; Management science; Psychology; Computer science; Mathematics education; Epistemology; Engineering; Political science","score_opus":0.038723680210979806,"score_gpt":0.5333790424297817,"score_spread":0.4946553622188019,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2748587261","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9899878,0.0001717119,0.001323716,0.00032016617,0.000028005972,0.0004719844,0.000104906525,0.000009563582,0.0075822654],"genre_scores_gemma":[0.99292845,0.00033798165,0.0028307105,0.0003145904,0.000025716861,0.00056161877,0.0001840105,0.000012894183,0.0028041224],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98877525,0.0068702274,0.0008005868,0.00078579556,0.0020667694,0.0007013715],"domain_scores_gemma":[0.9127984,0.06465756,0.0043451977,0.0038839453,0.010360794,0.0039541074],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013231616,0.0003674918,0.00068506686,0.001771828,0.0033699868,0.0024475663,0.0011626835,0.0013646809,0.005671938],"category_scores_gemma":[0.07196535,0.00040814016,0.00026037975,0.0021824797,0.002229969,0.0025927299,0.0022127011,0.0024863817,0.0013698648],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009172729,0.049007583,0.44363767,0.0017007275,0.00006919243,0.004025666,0.28971013,0.0009851146,0.004856941,0.0195774,0.0060726786,0.17943957],"study_design_scores_gemma":[0.0004133741,0.012510989,0.39142007,0.0017084483,0.000076784105,0.0035454484,0.47048336,0.0042897104,0.007643616,0.006102542,0.101620734,0.00018490168],"about_ca_topic_score_codex":0.0016403041,"about_ca_topic_score_gemma":0.0027406707,"teacher_disagreement_score":0.013231616,"about_ca_system_score_codex":0.0014192145,"about_ca_system_score_gemma":0.00312947,"threshold_uncertainty_score":0.06997633},"labels":[],"label_agreement":null},{"id":"W2749119382","doi":"10.1080/87567555.2017.1349075","title":"Improving the Quality of Constructive Peer Feedback","year":2017,"lang":"en","type":"article","venue":"College Teaching","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Constructive; Quality (philosophy); Computer science; Peer feedback; Simple (philosophy); Order (exchange); Mathematics education; Management science; Engineering ethics; Psychology; Epistemology; Engineering; Process (computing); Business","score_opus":0.0595169331783962,"score_gpt":0.4026046221552969,"score_spread":0.34308768897690073,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2749119382","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.16280454,0.0055432254,0.7550159,0.012167321,0.0046090595,0.006043992,0.00039933552,0.016955331,0.036461264],"genre_scores_gemma":[0.39810598,0.002538704,0.58306205,0.0017395074,0.002327936,0.0024568622,0.00032737534,0.0018673325,0.0075741773],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.7155651,0.15450452,0.022396917,0.00817747,0.096164525,0.0031915165],"domain_scores_gemma":[0.27642056,0.4175925,0.038217645,0.054434724,0.20792443,0.0054101064],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.15691592,0.0020125129,0.0020673976,0.006182557,0.0028335603,0.006713434,0.0035306602,0.0023774407,0.0054581226],"category_scores_gemma":[0.5551163,0.0009432799,0.0010154451,0.0024645096,0.0019438871,0.0065928255,0.005256724,0.0025889887,0.003111995],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000638024,0.00055251067,0.010796948,0.0023132858,0.00018723289,0.00021470635,0.014391772,0.0011846039,0.018734548,0.0025960251,0.015948031,0.9324424],"study_design_scores_gemma":[0.0019914627,0.013746223,0.14937635,0.013234071,0.0018357275,0.0058129816,0.03540185,0.05799259,0.25507924,0.049803335,0.41336033,0.0023658893],"about_ca_topic_score_codex":0.0013548648,"about_ca_topic_score_gemma":0.0017463778,"teacher_disagreement_score":0.8430841,"about_ca_system_score_codex":0.0018192562,"about_ca_system_score_gemma":0.004144232,"threshold_uncertainty_score":0.8298606},"labels":[],"label_agreement":null},{"id":"W2752208322","doi":"10.5539/elt.v10n10p1","title":"Exploring Students’ Perspectives toward Clarity and Familiarity of Writing Scoring Rubrics: The Case of Saudi EFL Students","year":2017,"lang":"en","type":"article","venue":"English Language Teaching","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Rubric; CLARITY; Psychology; Mathematics education; Quality (philosophy); Set (abstract data type); Strengths and weaknesses; Medical education; Computer science; Social psychology; Medicine; Chemistry","score_opus":0.09083715100315995,"score_gpt":0.39897892087104897,"score_spread":0.308141769867889,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2752208322","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9977494,0.00011762392,0.00065636105,0.00046341427,0.00000920155,0.000015442605,0.000006557695,0.000008203267,0.00097372965],"genre_scores_gemma":[0.9986965,0.00010374266,0.00061675557,0.00014959002,0.0000070274596,0.000011431348,0.00000909094,0.000006086326,0.00039983337],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9818902,0.010184488,0.0012622689,0.0008237989,0.004552119,0.001287135],"domain_scores_gemma":[0.95083684,0.02035509,0.011636215,0.0016804943,0.011320264,0.004171027],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013506642,0.000467897,0.00049580313,0.001696836,0.003065188,0.0055849254,0.0008706424,0.0013501927,0.0012954787],"category_scores_gemma":[0.04303417,0.00037552952,0.0004832568,0.00087051006,0.0029193289,0.0020677615,0.0025775344,0.0018520826,0.0004509877],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022515844,0.00042619024,0.19429675,0.00026216425,0.000044228804,0.003905204,0.73902947,0.00019239876,0.009057282,0.00081815926,0.0010551368,0.050687786],"study_design_scores_gemma":[0.000023635845,0.0005743303,0.10762859,0.0002388527,0.000040954485,0.003620907,0.8688674,0.0014249762,0.0047792573,0.0006898799,0.011973376,0.00013775109],"about_ca_topic_score_codex":0.003308568,"about_ca_topic_score_gemma":0.0045770565,"teacher_disagreement_score":0.013506642,"about_ca_system_score_codex":0.0018697707,"about_ca_system_score_gemma":0.0021140138,"threshold_uncertainty_score":0.07143074},"labels":[],"label_agreement":null},{"id":"W2752466276","doi":"10.5430/wje.v7n4p117","title":"Constructing Quality Feedback to the Students in Distance Learning: Review of the Current Evidence with Reference to the Online Master Degree in Transplantation","year":2017,"lang":"en","type":"article","venue":"World Journal of Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Distance education; Diversity (politics); Quality (philosophy); Curriculum; Construct (python library); Mathematics education; Course (navigation); Psychology; Computer science; Transplantation; Instructional design; Cultural diversity; Medical education; Pedagogy; Engineering; Medicine; Sociology","score_opus":0.18350038372953567,"score_gpt":0.4812443724095541,"score_spread":0.2977439886800184,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2752466276","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013844178,0.97683,0.0011111487,0.004642057,0.00054949534,0.0002936223,0.00021376535,0.000029236697,0.002486377],"genre_scores_gemma":[0.18088067,0.81123525,0.0037896354,0.0023613276,0.00040710668,0.00055408676,0.00031894876,0.000044789762,0.00040808876],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.9371076,0.02937763,0.012027123,0.0026722974,0.017560799,0.0012544757],"domain_scores_gemma":[0.519982,0.39037848,0.03313303,0.0044509503,0.048540197,0.0035152745],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.067037925,0.0006705534,0.0027908245,0.006448481,0.0009921778,0.0065539926,0.0033176548,0.0027043098,0.0051047322],"category_scores_gemma":[0.26210612,0.00078214006,0.0020317412,0.0069376496,0.002238687,0.004069913,0.0034617372,0.0020020562,0.00084784644],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00077706366,0.00047569952,0.012362634,0.17418991,0.0008515108,0.00010175045,0.0028887324,0.0001772435,0.00021315602,0.00072942016,0.004846488,0.8023864],"study_design_scores_gemma":[0.0005288782,0.0030901425,0.096862145,0.75633246,0.0048260535,0.0012930778,0.01388862,0.00057227566,0.0017473123,0.0013707672,0.1193118,0.00017654467],"about_ca_topic_score_codex":0.005757822,"about_ca_topic_score_gemma":0.010093297,"teacher_disagreement_score":0.067037925,"about_ca_system_score_codex":0.0047613303,"about_ca_system_score_gemma":0.013436502,"threshold_uncertainty_score":0.3545347},"labels":[],"label_agreement":null},{"id":"W2752920591","doi":"10.5430/wje.v7n4p85","title":"A Combination of Teacher-Led Assessment and Self-Assessment Drives the Learning Process in Online Master Degree in Transplantation","year":2017,"lang":"en","type":"article","venue":"World Journal of Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Summative assessment; Peer assessment; Psychology; Diversity (politics); Formative assessment; Online assessment; Self-assessment; Educational assessment; Medical education; Test (biology); Mathematics education; Process (computing); Alternative assessment; Educational measurement; Pedagogy; Curriculum; Computer science; Medicine","score_opus":0.04002629537659467,"score_gpt":0.4148616437604832,"score_spread":0.3748353483838885,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2752920591","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9921898,0.00014031603,0.004104632,0.00020933543,0.000017476581,0.00014816524,0.000017164593,0.000039210045,0.003133903],"genre_scores_gemma":[0.9946721,0.00007181496,0.0045843553,0.000038274728,0.000010188811,0.00007352739,0.000017846653,0.00000638265,0.0005254886],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98261017,0.009976661,0.0010297974,0.0009917041,0.004760579,0.0006311652],"domain_scores_gemma":[0.95581377,0.027028982,0.0063784323,0.0020369126,0.0058930125,0.0028489167],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014515041,0.00028050982,0.00048930297,0.0011858931,0.00063047925,0.0020850245,0.00073915016,0.0004366165,0.0017706224],"category_scores_gemma":[0.053245965,0.00021170967,0.00036697157,0.0005223463,0.0006955552,0.0015377267,0.002431254,0.000582947,0.00039239568],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00059436064,0.0026506875,0.48762855,0.0009097855,0.00013657413,0.00017374518,0.012633641,0.0011365641,0.0046062465,0.0006589374,0.0009020928,0.48796874],"study_design_scores_gemma":[0.00010482217,0.0059002945,0.94008166,0.0009821393,0.00022833188,0.0007589728,0.016070994,0.011953835,0.013462508,0.002659551,0.007671291,0.00012552728],"about_ca_topic_score_codex":0.00088459876,"about_ca_topic_score_gemma":0.0027914536,"teacher_disagreement_score":0.014515041,"about_ca_system_score_codex":0.00085548405,"about_ca_system_score_gemma":0.0033359763,"threshold_uncertainty_score":0.07676381},"labels":[],"label_agreement":null},{"id":"W2755415388","doi":"10.20381/ruor-20914","title":"Assessment Strategies in Higher Education: A Case Study of Conestoga College’s Fitness and Health Promotion Program","year":2017,"lang":"en","type":"dissertation","venue":"uO Research (University of Ottawa)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Promotion (chess); Medical education; Psychology; Gerontology; Mathematics education; Medicine; Political science","score_opus":0.20814197588610014,"score_gpt":0.5135839410944316,"score_spread":0.30544196520833145,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2755415388","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9833998,0.00021414075,0.0022743775,0.003899817,0.00004885417,0.00028009212,0.000023753873,0.000029226014,0.009829913],"genre_scores_gemma":[0.9878484,0.0003561747,0.003987988,0.001001996,0.000022600158,0.00012583389,0.000021960965,0.000030235891,0.006604703],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.981921,0.011661578,0.00046175727,0.0007139196,0.0021841396,0.0030575674],"domain_scores_gemma":[0.9730093,0.014819302,0.001185513,0.00064229785,0.0034855315,0.0068579717],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013556844,0.00078938965,0.0006770068,0.0020251204,0.020344263,0.007105328,0.0031362562,0.0036752438,0.0035942802],"category_scores_gemma":[0.019706348,0.00070828496,0.00055319635,0.0021727849,0.006648185,0.003144375,0.005463854,0.005474745,0.0005343933],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000048918024,0.0017604955,0.011818106,0.00014890675,0.000008527383,0.007776446,0.9482782,0.000215856,0.00089805946,0.0021986905,0.0017936439,0.02505409],"study_design_scores_gemma":[0.00001393358,0.00032123303,0.0050924774,0.00015214256,0.0000079031715,0.0013922283,0.9723893,0.0005599041,0.0007088785,0.00041474734,0.018921819,0.000025368461],"about_ca_topic_score_codex":0.03626327,"about_ca_topic_score_gemma":0.11872482,"teacher_disagreement_score":0.03626327,"about_ca_system_score_codex":0.013451528,"about_ca_system_score_gemma":0.016618991,"threshold_uncertainty_score":0.097598135},"labels":[],"label_agreement":null},{"id":"W2755836585","doi":"10.31468/cjsdwr.604","title":"Designing Effective Training Programs for Discipline-Specific Peer Writing Tutors","year":2017,"lang":"en","type":"article","venue":"Discourse and Writing/Rédactologie","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Ottawa","funders":"","keywords":"Writing center; TUTOR; Scholarship; Discipline; Professional writing; Staffing; Pedagogy; Statement (logic); Academic writing; Medical education; Writing process; Set (abstract data type); Mathematics education; Psychology; Computer science; Sociology; Medicine; Political science","score_opus":0.22245111841040197,"score_gpt":0.4834576000515734,"score_spread":0.26100648164117146,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2755836585","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.79585934,0.00079813524,0.14004615,0.0034985894,0.0004373873,0.025031561,0.00014718945,0.0013551293,0.03282651],"genre_scores_gemma":[0.7130843,0.0004504338,0.26697168,0.00045535152,0.00007939325,0.011838634,0.00014815548,0.00006315846,0.0069088787],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98956233,0.006891307,0.00036017242,0.00066540646,0.0012245598,0.0012962474],"domain_scores_gemma":[0.98321116,0.0055190814,0.0014530245,0.00085104385,0.00326892,0.005696839],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013551622,0.00045247478,0.0004975387,0.0015950471,0.0030626538,0.002018108,0.00326095,0.0013481099,0.0049115727],"category_scores_gemma":[0.030319475,0.00043129423,0.0003324169,0.00058225426,0.0009612157,0.0020141792,0.004449064,0.001431704,0.0012041768],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007001655,0.013696209,0.027792118,0.0017032716,0.000050491493,0.00046303982,0.040622048,0.011659447,0.0101161655,0.009471221,0.012393533,0.8713324],"study_design_scores_gemma":[0.009186154,0.044386417,0.17701599,0.0056436406,0.00053545035,0.0019002863,0.21052197,0.07725923,0.082683414,0.052105337,0.33820942,0.00055269874],"about_ca_topic_score_codex":0.0013862824,"about_ca_topic_score_gemma":0.004125878,"teacher_disagreement_score":0.013551622,"about_ca_system_score_codex":0.0029554316,"about_ca_system_score_gemma":0.011959633,"threshold_uncertainty_score":0.071668684},"labels":[],"label_agreement":null},{"id":"W2756771427","doi":"10.20343/teachlearninqu.5.2.8","title":"ComPAIR: A New Online Tool Using Adaptive Comparative Judgement to Support Learning with Peer Feedback","year":2017,"lang":"en","type":"article","venue":"Teaching & Learning Inquiry The ISSOTL Journal","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Peer feedback; Computer science; Grading (engineering); Judgement; Context (archaeology); Ranking (information retrieval); Set (abstract data type); Peer assessment; Mathematics education; Multimedia; Psychology; Artificial intelligence; Engineering","score_opus":0.20071591484426815,"score_gpt":0.44677908830839524,"score_spread":0.2460631734641271,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2756771427","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04700882,0.00046705152,0.8599152,0.00068322977,0.0005444256,0.0055833883,0.0030666639,0.06560898,0.017122185],"genre_scores_gemma":[0.09281096,0.00019106184,0.89372724,0.00023616356,0.00016687866,0.0043687075,0.0013988499,0.0019661754,0.0051338733],"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.9765846,0.011977093,0.0018426848,0.0018070509,0.0073943534,0.00039421904],"domain_scores_gemma":[0.85803455,0.11252529,0.005086304,0.01011083,0.011291036,0.0029520853],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.022386635,0.001696219,0.0013811423,0.008228572,0.0009248987,0.0032386545,0.0034206489,0.0015299865,0.019009208],"category_scores_gemma":[0.11116222,0.00085831364,0.0009639261,0.0037285183,0.0010669973,0.00443954,0.00609597,0.0014805228,0.0047709076],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011579236,0.0008830619,0.0038631372,0.0013430765,0.00017459806,0.00030178198,0.0028385504,0.002375855,0.008863385,0.0042472733,0.023190347,0.950761],"study_design_scores_gemma":[0.0034342392,0.0071475348,0.067331575,0.0031848266,0.000741168,0.0041146167,0.0043951995,0.25625542,0.055534035,0.071559295,0.52467126,0.0016308371],"about_ca_topic_score_codex":0.001015853,"about_ca_topic_score_gemma":0.0018749713,"teacher_disagreement_score":0.022386635,"about_ca_system_score_codex":0.0009242165,"about_ca_system_score_gemma":0.0020889759,"threshold_uncertainty_score":0.1183933},"labels":[],"label_agreement":null},{"id":"W2758542300","doi":"","title":"Supporting Preservice Mathematics Teachers","year":2017,"lang":"en","type":"article","venue":"2017 Conference of the Canadian Society for the Study of Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Mathematics education; Curriculum; Representation (politics); Reform mathematics; Connected Mathematics; Pedagogy; Computer science; Psychology; Political science","score_opus":0.09918820151996563,"score_gpt":0.4122161335718016,"score_spread":0.313027932051836,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2758542300","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9222061,0.0013870797,0.009177993,0.012213761,0.0004069456,0.00040595795,0.00014995314,0.00066820055,0.053384006],"genre_scores_gemma":[0.95388144,0.000873155,0.013093485,0.0024381406,0.00012719393,0.00030850625,0.00015655374,0.00004559686,0.029075934],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9958262,0.001625009,0.00014282762,0.00049121794,0.0009866023,0.0009281747],"domain_scores_gemma":[0.9800481,0.00372461,0.002052701,0.0013778594,0.0031616066,0.00963514],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004359148,0.00049858197,0.00041885077,0.000779463,0.0027867071,0.0049948306,0.0020151427,0.0026904717,0.013098957],"category_scores_gemma":[0.017452082,0.00035134633,0.0003068536,0.00035125704,0.0015634111,0.0029229815,0.0066038715,0.002695375,0.0046330965],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00041886975,0.012193087,0.1116858,0.0010570923,0.000040338957,0.002201116,0.19547361,0.0006399128,0.021677999,0.008919881,0.05230616,0.5933862],"study_design_scores_gemma":[0.00028358927,0.0034909719,0.0882342,0.0018255371,0.00009546376,0.004192255,0.33996487,0.0016131632,0.015603366,0.018496035,0.5260715,0.00012904301],"about_ca_topic_score_codex":0.0011259409,"about_ca_topic_score_gemma":0.0053248256,"teacher_disagreement_score":0.99887407,"about_ca_system_score_codex":0.0014623696,"about_ca_system_score_gemma":0.0060436823,"threshold_uncertainty_score":0.04382038},"labels":[],"label_agreement":null},{"id":"W2759176870","doi":"10.19173/irrodl.v18i6.2804","title":"An Evaluation Framework and Instrument for Evaluating e-Assessment Tools","year":2017,"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":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Class (philosophy); Evaluation methods; Empirical research; Human–computer interaction; Multimedia; Management science; Knowledge management; Artificial intelligence; Engineering","score_opus":0.3896306194989309,"score_gpt":0.6372387545112699,"score_spread":0.24760813501233897,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2759176870","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.043022614,0.0020368344,0.7824161,0.0050422573,0.0005573193,0.06706591,0.0021976372,0.0014691084,0.096192226],"genre_scores_gemma":[0.08999264,0.00076257996,0.8676165,0.0004889876,0.000049178543,0.03669153,0.001211729,0.000085755404,0.0031010057],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.81073385,0.12026415,0.023627518,0.0030951723,0.04004936,0.0022300144],"domain_scores_gemma":[0.8043435,0.065244,0.011533473,0.0072608874,0.108759515,0.0028585568],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.15816315,0.0015999364,0.0013237213,0.011659037,0.0037495007,0.0067373523,0.0027139501,0.0026440902,0.0036937443],"category_scores_gemma":[0.13822702,0.000644675,0.0021521028,0.007949091,0.0031276424,0.0072664986,0.004891179,0.0029555596,0.0017637744],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005421374,0.0024106246,0.030040884,0.004103756,0.00017464005,0.00015788162,0.008622338,0.006894657,0.007582832,0.15524834,0.027928894,0.75629294],"study_design_scores_gemma":[0.0010729713,0.012211865,0.16160995,0.02251768,0.00074282434,0.0012266976,0.050709397,0.065348625,0.029302182,0.14942189,0.5048837,0.0009523403],"about_ca_topic_score_codex":0.006338591,"about_ca_topic_score_gemma":0.006988918,"teacher_disagreement_score":0.15816315,"about_ca_system_score_codex":0.009339133,"about_ca_system_score_gemma":0.0337817,"threshold_uncertainty_score":0.83645666},"labels":[],"label_agreement":null},{"id":"W2759938145","doi":"10.4018/978-1-5225-3873-8.ch008","title":"Questioning the Role of Tomorrow's Teacher","year":2017,"lang":"en","type":"book-chapter","venue":"Advances in educational technologies and instructional design book series","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Prince Albert Grand Council; MacEwan University","funders":"","keywords":"Implementation; Student engagement; Mathematics education; Student centered; Pedagogy; Psychology; Work (physics); Student achievement; Academic achievement; Computer science; Engineering","score_opus":0.018020372229429902,"score_gpt":0.3109477808437555,"score_spread":0.2929274086143256,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2759938145","genre_codex":"other","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.33478716,0.007859261,0.015520172,0.09878065,0.004562827,0.0001774707,0.00020347873,0.00041299002,0.537696],"genre_scores_gemma":[0.68463,0.0027125413,0.0070115826,0.013097633,0.00020529448,0.00008850698,0.00010935472,0.00014201603,0.29200312],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.9992849,0.0003975731,0.000015119885,0.00009383034,0.000110393856,0.00009818371],"domain_scores_gemma":[0.99765104,0.0014877904,0.00013283269,0.00011169302,0.00027660112,0.00033999782],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016742646,0.00021678039,0.00022327072,0.0003209319,0.0030940278,0.0027820652,0.00070145144,0.0015417784,0.009049703],"category_scores_gemma":[0.0041212905,0.00013087958,0.00017755406,0.00026852483,0.0026764746,0.004752763,0.0016307831,0.0028717031,0.0015627205],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009326898,0.0004392405,0.017026901,0.00036973055,0.000013091657,0.0011185465,0.3893054,0.00026280942,0.005087494,0.10476869,0.20916094,0.27235386],"study_design_scores_gemma":[0.00001041323,0.00017115017,0.009004267,0.00042773446,0.0000069134794,0.00081282906,0.39296725,0.0004281403,0.0017609713,0.016514843,0.5778686,0.000026901429],"about_ca_topic_score_codex":0.006647448,"about_ca_topic_score_gemma":0.02294931,"teacher_disagreement_score":0.009049703,"about_ca_system_score_codex":0.0019697694,"about_ca_system_score_gemma":0.001934959,"threshold_uncertainty_score":0.030274332},"labels":[],"label_agreement":null},{"id":"W2763216313","doi":"","title":"Examining Teacher Educators","year":2017,"lang":"en","type":"article","venue":"2017 Conference of the Canadian Society for the Study of Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Literacy; Pedagogy; Teacher education; Mathematics education; Political science; Sociology; Psychology; Medical education; Medicine","score_opus":0.13190998328439435,"score_gpt":0.38739968457659785,"score_spread":0.2554897012922035,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2763216313","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.89914304,0.0022787594,0.0013618057,0.0109643275,0.00018990667,0.000087933164,0.00014344863,0.00002812757,0.08580269],"genre_scores_gemma":[0.988247,0.0013163587,0.000875238,0.0013145284,0.000032566113,0.000064209984,0.00006326601,0.000008583559,0.008078287],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.995018,0.0024816503,0.00028719506,0.0005670571,0.00094126066,0.00070483715],"domain_scores_gemma":[0.9741236,0.012192829,0.0038127257,0.0011735572,0.006199575,0.0024977794],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008224694,0.0001709466,0.00024566092,0.0020475658,0.004308244,0.0058149435,0.00096254353,0.00086621125,0.00435879],"category_scores_gemma":[0.034720447,0.0002503939,0.00014182294,0.0017377407,0.0034687205,0.004613039,0.004244851,0.0020118859,0.0004628669],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029897914,0.00023954341,0.2822837,0.0003063278,0.0000142080435,0.00055794977,0.6160016,0.000058666596,0.00039118322,0.019026563,0.008465765,0.07262461],"study_design_scores_gemma":[0.000012547194,0.00006736264,0.09265425,0.0006133488,0.000023352972,0.00032536953,0.8127463,0.00008011428,0.0005704722,0.0039913845,0.08890048,0.000014982392],"about_ca_topic_score_codex":0.035994604,"about_ca_topic_score_gemma":0.07316928,"teacher_disagreement_score":0.035994604,"about_ca_system_score_codex":0.0068367324,"about_ca_system_score_gemma":0.012717684,"threshold_uncertainty_score":0.07157016},"labels":[],"label_agreement":null},{"id":"W2765391846","doi":"10.5539/ells.v7n4p66","title":"Error Correction in the Intensive Reading Class of English Majors","year":2017,"lang":"en","type":"article","venue":"English Language and Literature Studies","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Perception; Corrective feedback; Negotiation; Class (philosophy); Reading (process); Mathematics education; Psychology; Empirical research; Pedagogy; Computer science; Mathematics; Linguistics; Sociology","score_opus":0.01941013569653671,"score_gpt":0.348323727994973,"score_spread":0.3289135922984363,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2765391846","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9996006,0.00004531316,0.000025160873,0.000022249076,0.0000024929986,0.00000304133,0.000004905433,0.0000030239223,0.00029321667],"genre_scores_gemma":[0.9989967,0.000054354652,0.000051655832,0.000017474767,0.000003456081,0.0000028957938,0.00001416608,0.0000016609872,0.0008576633],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99932134,0.0001668329,0.000058372214,0.00009607811,0.00023355322,0.00012383045],"domain_scores_gemma":[0.99561924,0.0013545319,0.0013433476,0.00014648713,0.00072885794,0.00080752774],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006528134,0.00030895483,0.00038128663,0.00084742764,0.0006275672,0.0008998056,0.00038968708,0.00042537964,0.0018679197],"category_scores_gemma":[0.0060322015,0.00017160492,0.0001906184,0.00027866417,0.00041390478,0.0003046621,0.00053483277,0.00054038205,0.00045103798],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006521526,0.003456478,0.78465736,0.00017186953,0.00005422255,0.0042972635,0.076464996,0.00012804041,0.021132061,0.000114050075,0.00072244764,0.10814904],"study_design_scores_gemma":[0.00001704684,0.0017080018,0.9580444,0.00003773349,0.000023764649,0.0017677845,0.032665312,0.00030100535,0.0034109012,0.00010182127,0.0018953807,0.000026944546],"about_ca_topic_score_codex":0.003349344,"about_ca_topic_score_gemma":0.005394741,"teacher_disagreement_score":0.003349344,"about_ca_system_score_codex":0.0005121253,"about_ca_system_score_gemma":0.00046521306,"threshold_uncertainty_score":0.0066596866},"labels":[],"label_agreement":null},{"id":"W2767175506","doi":"10.5539/jel.v7n1p184","title":"Identifying New Jersey Teachers’ Assessment Literacy as Precondition for Implementing Student Growth Objectives","year":2017,"lang":"en","type":"article","venue":"Journal of Education and Learning","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Summative assessment; Competence (human resources); Psychology; Literacy; Mathematics education; Test (biology); Medical education; Data collection; Formative assessment; Pedagogy; Mathematics; Statistics; Medicine; Social psychology","score_opus":0.05151849873937381,"score_gpt":0.487412330567119,"score_spread":0.4358938318277452,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2767175506","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9919951,0.00003989237,0.00043678924,0.0001594884,0.000004552844,0.000058368674,0.00007442165,0.000021267855,0.007210092],"genre_scores_gemma":[0.99746585,0.000052589116,0.0010247177,0.000031189447,0.0000028404231,0.00006052064,0.00013427796,0.000004340382,0.0012236419],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9980484,0.0005138,0.00016578636,0.00019127369,0.00075488637,0.0003258199],"domain_scores_gemma":[0.98152083,0.007763497,0.0032884788,0.0007318544,0.0055065644,0.0011887625],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0033549103,0.00009640006,0.00018960077,0.000739511,0.0006273994,0.0011210302,0.00028852254,0.00025092348,0.0025817747],"category_scores_gemma":[0.018285263,0.00023582847,0.00013452298,0.00036519498,0.0003912926,0.0008205719,0.00084039354,0.0006750948,0.0003244467],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001317584,0.0003639826,0.9284023,0.00010563485,0.000007845231,0.00021035723,0.017159633,0.00013637923,0.004316604,0.00028029995,0.0013966617,0.047488514],"study_design_scores_gemma":[0.0000032059127,0.0001341059,0.99281424,0.00003095061,0.000004438198,0.000042508622,0.0042797066,0.000176832,0.0009236895,0.000032866603,0.0015519276,0.0000055091487],"about_ca_topic_score_codex":0.03466498,"about_ca_topic_score_gemma":0.09268073,"teacher_disagreement_score":0.03466498,"about_ca_system_score_codex":0.0013207871,"about_ca_system_score_gemma":0.0034578342,"threshold_uncertainty_score":0.06892645},"labels":[],"label_agreement":null},{"id":"W2767233186","doi":"10.1007/978-3-319-66327-2_11","title":"Improving Teachers’ Assessment Literacy in Singapore Mathematics Classrooms: Authentic Assessment Task Design","year":2017,"lang":"en","type":"book-chapter","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Mathematics education; Competence (human resources); Authentic assessment; Literacy; Pedagogy; Task (project management); Psychology; Engineering; Curriculum","score_opus":0.05482641439953531,"score_gpt":0.37786931299253684,"score_spread":0.3230428985930015,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2767233186","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.35067803,0.000773295,0.61188287,0.0010236613,0.00024201286,0.0021681525,0.0002949376,0.0016014972,0.031335615],"genre_scores_gemma":[0.48600048,0.00038097482,0.49901786,0.0001786794,0.00003553825,0.0022623984,0.0003267273,0.00013154466,0.011665882],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9953117,0.003017374,0.0003309555,0.00043635117,0.0007422517,0.00016142579],"domain_scores_gemma":[0.9919482,0.0044970233,0.0004978452,0.0009768165,0.001486778,0.0005934523],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007462988,0.0005398294,0.0004201779,0.00047499436,0.00056428893,0.0018523628,0.0015222823,0.00073252426,0.0034592228],"category_scores_gemma":[0.014849893,0.00035246887,0.00043986915,0.00035089257,0.0007415215,0.001432733,0.002360342,0.0010884596,0.0008928363],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006877306,0.0014816822,0.00766401,0.00067883404,0.000052832693,0.000111099995,0.009771571,0.010259501,0.014963303,0.010718792,0.007708578,0.9359022],"study_design_scores_gemma":[0.0017219663,0.021124585,0.09670245,0.0017564399,0.00045310173,0.0015329206,0.020072311,0.3957844,0.09811839,0.11593547,0.24629179,0.00050612655],"about_ca_topic_score_codex":0.0009600871,"about_ca_topic_score_gemma":0.0019711638,"teacher_disagreement_score":0.007462988,"about_ca_system_score_codex":0.00079367426,"about_ca_system_score_gemma":0.001765846,"threshold_uncertainty_score":0.039468527},"labels":[],"label_agreement":null},{"id":"W2767325736","doi":"10.1111/medu.13476","title":"Emotions and assessment: considerations for rater‐based judgements of entrustment","year":2017,"lang":"en","type":"review","venue":"Medical Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Formative assessment; Summative assessment; Scrutiny; Psychology; Context (archaeology); Cognition; Narrative; Educational assessment; Applied psychology; Medical education; Pedagogy; Medicine","score_opus":0.16881108364826525,"score_gpt":0.535704857181989,"score_spread":0.36689377353372377,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2767325736","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14449355,0.34912038,0.3450649,0.09136831,0.008797723,0.0039887526,0.0012572341,0.000468533,0.05544061],"genre_scores_gemma":[0.7802035,0.06055268,0.13202387,0.013712271,0.0035215556,0.0068534296,0.0005553168,0.0002822872,0.0022950387],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.6228196,0.27993074,0.041992776,0.00832571,0.045281075,0.0016499864],"domain_scores_gemma":[0.2842167,0.6100166,0.039681073,0.017869405,0.046005927,0.002210309],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.34653357,0.0010311204,0.0032032062,0.006112463,0.0016242376,0.009373416,0.004586164,0.0027580815,0.0020203432],"category_scores_gemma":[0.6244739,0.0006544954,0.0027042455,0.004858155,0.011348311,0.009636747,0.008331944,0.0051131276,0.00071614154],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001298716,0.00017674339,0.077701025,0.035886332,0.0020865519,0.0009738391,0.16767828,0.002327093,0.0024789218,0.057171606,0.013213664,0.6390073],"study_design_scores_gemma":[0.00043384597,0.0022864956,0.2247937,0.12530617,0.0029305445,0.007615687,0.15958641,0.013065601,0.0068878266,0.23091853,0.22466569,0.0015094706],"about_ca_topic_score_codex":0.0032294453,"about_ca_topic_score_gemma":0.003465763,"teacher_disagreement_score":0.34653357,"about_ca_system_score_codex":0.0035142207,"about_ca_system_score_gemma":0.005001404,"threshold_uncertainty_score":0.8058405},"labels":[],"label_agreement":null},{"id":"W2767495722","doi":"10.5539/hes.v7n4p71","title":"A Review of Protocols in Higher Education; How My Experience Made Me Question the Process","year":2017,"lang":"en","type":"review","venue":"Higher Education Studies","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Grading (engineering); Syllabus; Appeal; Legitimacy; Higher education; Pedagogy; Process (computing); Mathematics education; Psychology; Academic standards; Public relations; Political science; Engineering ethics; Computer science; Engineering","score_opus":0.3590216986629853,"score_gpt":0.5980012229070725,"score_spread":0.2389795242440872,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2767495722","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001283748,0.79245794,0.04033491,0.13412401,0.019959813,0.0029463884,0.00034449794,0.00019111505,0.008357608],"genre_scores_gemma":[0.025456738,0.7942188,0.09215396,0.06623325,0.00431885,0.011370642,0.00050396036,0.0004964733,0.0052473554],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.64164174,0.24607638,0.05734702,0.008148061,0.04528593,0.0015008288],"domain_scores_gemma":[0.36875084,0.48428318,0.026832506,0.027457362,0.08995544,0.0027206396],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.30374965,0.0013187533,0.002796768,0.012538059,0.0036255834,0.009209657,0.005890806,0.0065997057,0.0031186873],"category_scores_gemma":[0.57275826,0.0025917855,0.0019840468,0.014758669,0.013474835,0.0146797225,0.0067108935,0.014456599,0.0027566038],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001190868,0.00007271567,0.0004941243,0.09168423,0.0004347769,0.00049082167,0.02209136,0.0004275996,0.0010912414,0.072833635,0.13937724,0.6708831],"study_design_scores_gemma":[0.000024796118,0.00007592613,0.00036629935,0.14349389,0.00018942032,0.00042903647,0.0033416182,0.00012451867,0.0006050439,0.012888015,0.83838457,0.00007693749],"about_ca_topic_score_codex":0.004762542,"about_ca_topic_score_gemma":0.0077600917,"teacher_disagreement_score":0.30374965,"about_ca_system_score_codex":0.010758507,"about_ca_system_score_gemma":0.045374695,"threshold_uncertainty_score":0.8586006},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Mathematics education; Thematic analysis; Terminology; Psychology; Portfolio; Coding (social sciences); Value (mathematics); Computer science; Qualitative research; Mathematics; Sociology","score_opus":0.038442820932403206,"score_gpt":0.43924623009331515,"score_spread":0.40080340916091195,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2770188235","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94074064,0.0008110243,0.0020906113,0.009675036,0.00019588268,0.000056779132,0.000087727974,0.00006492375,0.046277367],"genre_scores_gemma":[0.99583286,0.00032081496,0.0005174134,0.0005037736,0.00003955139,0.000021600898,0.00003051422,0.000013962103,0.0027194193],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.97411996,0.016956773,0.0011722661,0.0006736732,0.0051730773,0.0019041758],"domain_scores_gemma":[0.96073294,0.018072445,0.005305615,0.0012863285,0.007953293,0.0066492953],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012180344,0.00033655536,0.00054444594,0.001547111,0.0030046527,0.008629589,0.0007203244,0.0013873158,0.0035554322],"category_scores_gemma":[0.035842273,0.00020512518,0.00046714323,0.0013288511,0.0020115594,0.0023621111,0.005131399,0.0035138135,0.000924209],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002564452,0.0007717198,0.18624313,0.00033754364,0.00005383186,0.0019361,0.54447836,0.00051986915,0.0043356265,0.015725212,0.013798227,0.23154394],"study_design_scores_gemma":[0.000033621054,0.0011121756,0.10838859,0.00075879786,0.000038197257,0.002773765,0.6224597,0.001488976,0.0036368705,0.007508415,0.2516456,0.00015531384],"about_ca_topic_score_codex":0.0015514739,"about_ca_topic_score_gemma":0.0017288596,"teacher_disagreement_score":0.012180344,"about_ca_system_score_codex":0.002673273,"about_ca_system_score_gemma":0.002827907,"threshold_uncertainty_score":0.06441659},"labels":[],"label_agreement":null},{"id":"W2770688448","doi":"10.3138/cmlr.599","title":"<scp>icy lee</scp> <i>Classroom Writing Assessment and Feedback in L2 School Contexts</i>","year":2017,"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":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Mathematics education; Psychology; Pedagogy; Physics; Computer science","score_opus":0.020499500489784463,"score_gpt":0.31604494254137944,"score_spread":0.295545442051595,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2770688448","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005592045,0.0354847,0.009967967,0.42962462,0.04332822,0.0010298713,0.00918258,0.0039352006,0.4618547],"genre_scores_gemma":[0.13426034,0.041703835,0.02616604,0.15743393,0.014003288,0.0022514982,0.005953545,0.0029380617,0.6152895],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99664694,0.00079844316,0.00024051953,0.00023489032,0.0018600671,0.00021918713],"domain_scores_gemma":[0.9607389,0.010367328,0.00087179727,0.00089848344,0.024624612,0.0024988404],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005012241,0.00044919705,0.000596861,0.0031037722,0.0028290597,0.0025873221,0.0015339559,0.0024611251,0.08262394],"category_scores_gemma":[0.041268896,0.0002950713,0.0005458104,0.002176139,0.0013033225,0.0019409705,0.0023877488,0.0026778178,0.017937837],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004083256,0.00001838566,0.00045646162,0.00021444247,0.000006242116,0.00008173325,0.00028656164,0.00003162526,0.0002629051,0.0007762097,0.90864253,0.08918192],"study_design_scores_gemma":[0.000046819012,0.000069478556,0.01487045,0.0015514897,0.000031127278,0.00037371737,0.0024754046,0.0003031433,0.0012762785,0.0026928573,0.97625023,0.000059103837],"about_ca_topic_score_codex":0.15457976,"about_ca_topic_score_gemma":0.318677,"teacher_disagreement_score":0.15457976,"about_ca_system_score_codex":0.0030357505,"about_ca_system_score_gemma":0.010110973,"threshold_uncertainty_score":0.30736},"labels":[],"label_agreement":null},{"id":"W2774511859","doi":"10.1007/s41686-017-0012-2","title":"Exploring the Association Between Formative and Summative Assessments in a Pre-University Science Program","year":2017,"lang":"en","type":"article","venue":"Journal of Formative Design in Learning","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Summative assessment; Formative assessment; Association (psychology); Psychology; Mathematics education","score_opus":0.13295555539503517,"score_gpt":0.4044958197641522,"score_spread":0.27154026436911705,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2774511859","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9992034,0.000015279355,0.00017066342,0.00007096278,0.0000064656147,0.000021476975,0.000015516356,0.000006638913,0.00048973237],"genre_scores_gemma":[0.9992224,0.000015614492,0.0002894195,0.000019404419,0.0000040120804,0.00003879746,0.000026972504,0.0000035271912,0.00037983354],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9894248,0.00498582,0.0007041984,0.0007761885,0.0028985047,0.0012104807],"domain_scores_gemma":[0.83574474,0.11222848,0.014325988,0.0032201903,0.02439993,0.010080691],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.020439865,0.000330086,0.00050529785,0.0022536973,0.0023733138,0.003925088,0.0014884993,0.001038584,0.0014953534],"category_scores_gemma":[0.14653358,0.0003950271,0.0004434528,0.0014343666,0.0011914916,0.0015469842,0.0032242509,0.00258924,0.00028476192],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007023764,0.0036806278,0.93595153,0.000047859183,0.00007704383,0.0001511838,0.027866397,0.0003033628,0.0007518049,0.00028963372,0.00030781957,0.029870301],"study_design_scores_gemma":[0.00001814378,0.0018592364,0.96855336,0.000042351185,0.00003678682,0.00007114078,0.02550799,0.0018592675,0.0011298518,0.00029055696,0.0005952195,0.000036147136],"about_ca_topic_score_codex":0.017203849,"about_ca_topic_score_gemma":0.029857323,"teacher_disagreement_score":0.020439865,"about_ca_system_score_codex":0.0032388975,"about_ca_system_score_gemma":0.0062275366,"threshold_uncertainty_score":0.10809761},"labels":[],"label_agreement":null},{"id":"W2775898509","doi":"","title":"Grading Policies and Practices in Canada: A Landscape Study","year":2017,"lang":"en","type":"article","venue":"Canadian Journal of Educational Administration and Policy","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":18,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Queen's University","funders":"","keywords":"Grading (engineering); Accountability; Formative assessment; Policy analysis; Geography; Political science; Pedagogy; Psychology; Public administration; Engineering","score_opus":0.06697337941789532,"score_gpt":0.4357721105361669,"score_spread":0.36879873111827155,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2775898509","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.933982,0.027148383,0.0010861447,0.006914446,0.00006415595,0.00054331817,0.008612614,0.00008521871,0.021563787],"genre_scores_gemma":[0.987039,0.008265302,0.0015690126,0.0004727552,0.000007016031,0.00008704608,0.0011454066,0.000024774132,0.0013896698],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98705333,0.0023777164,0.0012940876,0.0011728787,0.0058920365,0.002210032],"domain_scores_gemma":[0.9243178,0.015848804,0.009399898,0.0016484666,0.044454228,0.0043307934],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011895978,0.00031122318,0.0008747923,0.011522723,0.008579188,0.00668576,0.0025772096,0.0007320508,0.001479182],"category_scores_gemma":[0.04275025,0.00048476935,0.0006434951,0.03504886,0.0035568702,0.0013733192,0.0025685423,0.0009654936,0.00010198505],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.00043294876,0.00013989992,0.5765526,0.0050207325,0.0004365952,0.0012683503,0.12304993,0.001821189,0.0016276289,0.011898379,0.01432261,0.2634291],"study_design_scores_gemma":[0.00003339861,0.00011740291,0.863373,0.0030238037,0.00031994568,0.00030245836,0.073632054,0.0010227108,0.00070093543,0.0007384675,0.05653212,0.00020367945],"about_ca_topic_score_codex":0.99678516,"about_ca_topic_score_gemma":0.9984446,"teacher_disagreement_score":0.8089124,"about_ca_system_score_codex":0.1910876,"about_ca_system_score_gemma":0.33447427,"threshold_uncertainty_score":0.9382237},"labels":[],"label_agreement":null},{"id":"W277639878","doi":"","title":"Teachers' Perceptions of Gender Equity in Writing Assessment.","year":2001,"lang":"en","type":"article","venue":"English quarterly","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Gender equity; Perception; Psychology; Equity (law); Pedagogy; Writing assessment; Secondary education; Higher education; Sociology; Mathematics education; Gender studies; Political science","score_opus":0.044112345819574,"score_gpt":0.4051884317873846,"score_spread":0.3610760859678106,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W277639878","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98450863,0.0004606999,0.0005736514,0.0019198128,0.00007505075,0.000022833481,0.000017412774,0.0000124661465,0.012409608],"genre_scores_gemma":[0.9990012,0.00005030469,0.00008080356,0.000081035774,0.000007739728,0.0000063589296,0.000003299095,0.0000034245998,0.00076581823],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.98231345,0.009949423,0.0007430814,0.0006472614,0.0049525225,0.0013941595],"domain_scores_gemma":[0.9468775,0.032891005,0.006705714,0.000959231,0.00676997,0.005796702],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014145656,0.00013556163,0.0002481092,0.00087265146,0.001814456,0.002762995,0.00031148025,0.0004814356,0.0040176897],"category_scores_gemma":[0.08678691,0.00019236666,0.00019089815,0.00036085825,0.0015885457,0.001551228,0.002506628,0.0013430127,0.00035573763],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010397035,0.00071345345,0.4898356,0.00017258579,0.000048175494,0.00065355137,0.3546357,0.00018065976,0.0057233637,0.004295054,0.0043046577,0.13839749],"study_design_scores_gemma":[0.00008592421,0.0009970625,0.6216776,0.00047125734,0.000058214962,0.0008246475,0.34302065,0.00075200706,0.004148065,0.0034240934,0.024457809,0.00008257767],"about_ca_topic_score_codex":0.0071992083,"about_ca_topic_score_gemma":0.011617422,"teacher_disagreement_score":0.014145656,"about_ca_system_score_codex":0.0015996522,"about_ca_system_score_gemma":0.0022962235,"threshold_uncertainty_score":0.07481027},"labels":[],"label_agreement":null},{"id":"W2777401606","doi":"10.5430/wje.v7n6p63","title":"Formative Value of an Active Learning Strategy: Technology Based Think-Pair-Share in an EFL Writing Classroom","year":2017,"lang":"en","type":"article","venue":"World Journal of Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Anadolu Üniversitesi","keywords":"Formative assessment; Rubric; Psychology; Mathematics education; Coding (social sciences); Grading (engineering); Qualitative research; Pedagogy; Medical education","score_opus":0.034334295241587674,"score_gpt":0.4022492978968033,"score_spread":0.36791500265521565,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2777401606","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.585516,0.00046735493,0.3503798,0.0019055319,0.00027634515,0.002347681,0.000096432006,0.0016552336,0.05735568],"genre_scores_gemma":[0.7688386,0.00031925595,0.2199266,0.00028003711,0.000119002594,0.0012539565,0.00010736276,0.00010684266,0.009048433],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9919194,0.0049667265,0.00029031103,0.000718026,0.0018362019,0.0002692641],"domain_scores_gemma":[0.9859117,0.0103097055,0.00094308093,0.0013434968,0.0007789186,0.0007131806],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005750459,0.00112986,0.00037501522,0.0012920229,0.0010055236,0.0042742817,0.0016197561,0.0013296993,0.0043167183],"category_scores_gemma":[0.018828949,0.0003391792,0.00046902144,0.0004993832,0.0016140544,0.0036937497,0.0034147291,0.0010442825,0.0009833515],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00074699067,0.0051721,0.014350143,0.0013271497,0.00007789888,0.0006591107,0.040266797,0.0014433529,0.043710206,0.011530839,0.0035077892,0.8772076],"study_design_scores_gemma":[0.0024947328,0.036012612,0.1367038,0.0038673296,0.0009927787,0.016589668,0.0950042,0.055945925,0.30559435,0.09542694,0.2502604,0.0011071502],"about_ca_topic_score_codex":0.0002249232,"about_ca_topic_score_gemma":0.000537356,"teacher_disagreement_score":0.005750459,"about_ca_system_score_codex":0.00075181416,"about_ca_system_score_gemma":0.0011237946,"threshold_uncertainty_score":0.03041172},"labels":[],"label_agreement":null},{"id":"W2777582008","doi":"10.1166/asl.2017.9796","title":"Competency Frameworks and Implications for Teacher Assessment","year":2017,"lang":"en","type":"article","venue":"Advanced Science Letters","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brock University","funders":"","keywords":"Psychology; Mathematics education; Medical education; Engineering ethics; Engineering; Medicine","score_opus":0.028069535469416044,"score_gpt":0.41606664144381283,"score_spread":0.3879971059743968,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2777582008","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08181592,0.010392092,0.36876643,0.2600853,0.0015449038,0.0008728224,0.00041638562,0.0007563723,0.27534974],"genre_scores_gemma":[0.8070446,0.0016887726,0.18095228,0.0027152789,0.0003097387,0.00082824,0.00019404019,0.00008177336,0.0061852643],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.97528255,0.016869104,0.0015284555,0.0012268175,0.0036568574,0.0014362476],"domain_scores_gemma":[0.9184812,0.05265324,0.002906457,0.0027822445,0.01666859,0.0065083243],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03279294,0.00075026933,0.00075288134,0.0074380934,0.006626633,0.014477268,0.0037887604,0.0045320527,0.006761186],"category_scores_gemma":[0.095464736,0.00065530837,0.0009829379,0.00352932,0.017244233,0.011988239,0.005740359,0.0054964717,0.00092079426],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001642004,0.00014055718,0.004903276,0.00016896614,0.00001170751,0.00008954063,0.00632448,0.0017429056,0.000085728454,0.93662906,0.004848143,0.045039233],"study_design_scores_gemma":[0.000020684922,0.000039002178,0.0053183017,0.0010722216,0.000022918886,0.0001602454,0.023228291,0.009731534,0.00032408268,0.93670666,0.023310067,0.00006607073],"about_ca_topic_score_codex":0.043765288,"about_ca_topic_score_gemma":0.05860869,"teacher_disagreement_score":0.043765288,"about_ca_system_score_codex":0.014326771,"about_ca_system_score_gemma":0.029584253,"threshold_uncertainty_score":0.1734277},"labels":[],"label_agreement":null},{"id":"W2781785512","doi":"10.26522/brocked.v26i2.610","title":"Book Review: Ipsative Assessment: Motivation Through Marking Progress","year":2017,"lang":"en","type":"article","venue":"Brock Education Journal","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Brock University","funders":"","keywords":"Psychology","score_opus":0.044413621072548565,"score_gpt":0.43272294765231784,"score_spread":0.38830932657976924,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2781785512","genre_codex":"review","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00024227724,0.88456655,0.0020422686,0.047142122,0.045817588,0.00015298986,0.00019044345,0.00014900269,0.01969672],"genre_scores_gemma":[0.004300167,0.8031147,0.0030038145,0.057135537,0.049240645,0.00050662505,0.00041903512,0.0002528685,0.082026586],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9953454,0.0012525157,0.0003676221,0.0003450736,0.0025458478,0.00014358116],"domain_scores_gemma":[0.9741725,0.0154479025,0.0014885821,0.00036239083,0.007684683,0.0008439455],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003592947,0.0011552827,0.0028228478,0.0047339755,0.00072733266,0.003190532,0.0018363441,0.004301571,0.018497026],"category_scores_gemma":[0.023472538,0.000781155,0.0010330451,0.004765856,0.0017335651,0.0032943196,0.0017910012,0.007276205,0.010983072],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028955274,0.000036132948,0.00006727906,0.002450702,0.00003418637,0.000034722412,0.000035351004,0.00007443066,0.00009302973,0.0010431675,0.8468185,0.14928357],"study_design_scores_gemma":[0.00007887613,0.0000930753,0.0011707656,0.0077185393,0.00012218171,0.0008265742,0.00007918786,0.00012179789,0.00017897533,0.0022054964,0.9873624,0.000042089177],"about_ca_topic_score_codex":0.0046671047,"about_ca_topic_score_gemma":0.0133613255,"teacher_disagreement_score":0.018497026,"about_ca_system_score_codex":0.0030149107,"about_ca_system_score_gemma":0.005779731,"threshold_uncertainty_score":0.06187868},"labels":[],"label_agreement":null},{"id":"W2781803835","doi":"10.5539/elt.v11n2p15","title":"The Impact of Assessment for Learning on Students’ Achievement in English for Specific Purposes A Case Study of Pre-Medical Students at Khartoum University: Sudan","year":2018,"lang":"en","type":"article","venue":"English Language Teaching","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":50,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Summative assessment; Psychology; Medical education; Mathematics education; Perception; Formative assessment; Medicine","score_opus":0.020853037814295875,"score_gpt":0.39673396274399214,"score_spread":0.37588092492969627,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2781803835","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99910754,0.000068738074,0.000025725894,0.00010865228,0.0000040827904,0.000014674411,0.0000021881674,7.887573e-7,0.0006677029],"genre_scores_gemma":[0.99924976,0.00017762149,0.00015867014,0.00004074575,0.000004258663,0.000014946285,0.0000042554598,6.727556e-7,0.0003490176],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99547136,0.002779834,0.00020120811,0.0001559217,0.0007103346,0.0006812679],"domain_scores_gemma":[0.99552673,0.0016122932,0.0006190648,0.00018368952,0.0006860586,0.0013722219],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0038556054,0.00036080202,0.00042759517,0.00092978793,0.003540333,0.0021251563,0.00056396605,0.00071221625,0.0011501696],"category_scores_gemma":[0.0051392796,0.0001783082,0.00035675408,0.0007789209,0.001068575,0.00061990955,0.002049133,0.00080815324,0.00019706906],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008877922,0.012081143,0.5415243,0.0009641853,0.0001588065,0.014967442,0.23580992,0.0010485228,0.02044438,0.0018348298,0.0013494549,0.1689293],"study_design_scores_gemma":[0.000060522558,0.0071522375,0.6947873,0.0002972943,0.00012721565,0.0020665715,0.27573898,0.0008876769,0.0071792067,0.00033987986,0.011287694,0.0000753321],"about_ca_topic_score_codex":0.0049121324,"about_ca_topic_score_gemma":0.013152973,"teacher_disagreement_score":0.0049121324,"about_ca_system_score_codex":0.0018915038,"about_ca_system_score_gemma":0.00300525,"threshold_uncertainty_score":0.02039063},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Set (abstract data type); Psychology; Mathematics education; Empirical research; Pedagogy; Computer science","score_opus":0.15926321810963798,"score_gpt":0.45656737289959937,"score_spread":0.2973041547899614,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2781958120","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9974706,0.00014032608,0.00036011147,0.00014889277,0.000006743544,0.000059929986,0.000015299767,0.0000043851924,0.0017936934],"genre_scores_gemma":[0.9983346,0.000088666435,0.0006802656,0.000049778788,0.0000021327005,0.00007556881,0.000017920533,0.0000050734575,0.000745985],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9819115,0.011425909,0.0009356186,0.0011386063,0.0030731147,0.00151527],"domain_scores_gemma":[0.86969596,0.0901467,0.010747711,0.0047405954,0.017300583,0.0073684724],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.021368386,0.00022000895,0.0004909112,0.0021790909,0.0051548155,0.004270278,0.0017297216,0.0013610953,0.0015520059],"category_scores_gemma":[0.113847055,0.0005518003,0.00047031709,0.001872732,0.0026857634,0.0025747628,0.0045780106,0.002650517,0.00028851235],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00058338593,0.0030219704,0.5414973,0.00018136838,0.000045872286,0.0003625768,0.37892693,0.00024338935,0.0022655476,0.0014592002,0.00036512164,0.0710474],"study_design_scores_gemma":[0.000045012774,0.0010507938,0.6825288,0.00019667148,0.000039481238,0.00034211774,0.30776468,0.0005959724,0.0010766882,0.00068295834,0.0056215976,0.00005526859],"about_ca_topic_score_codex":0.0118282875,"about_ca_topic_score_gemma":0.032174814,"teacher_disagreement_score":0.021368386,"about_ca_system_score_codex":0.004399624,"about_ca_system_score_gemma":0.0074646943,"threshold_uncertainty_score":0.11300814},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.18245862922193032,"score_gpt":0.5132713437504184,"score_spread":0.33081271452848804,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2782375796","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.32379025,0.53355265,0.11014269,0.017364152,0.0015529931,0.006101578,0.00087981997,0.00015620768,0.0064596264],"genre_scores_gemma":[0.8689556,0.05447753,0.06654858,0.0037876095,0.00019515507,0.0051614554,0.0003582157,0.00011946918,0.00039633585],"study_design_codex":"qualitative","study_design_gemma":"systematic_review","domain_scores_codex":[0.74442184,0.20750585,0.027224764,0.00859302,0.010349663,0.0019049065],"domain_scores_gemma":[0.26141024,0.6871106,0.018560624,0.019281922,0.012772307,0.00086427375],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.277291,0.0016118253,0.004838464,0.012877875,0.0028553717,0.009569612,0.0040061055,0.0021620586,0.0016451152],"category_scores_gemma":[0.45874414,0.0016026213,0.0036364826,0.008381753,0.0069407676,0.017215496,0.008853901,0.0051892106,0.00010388512],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00072752335,0.00033388272,0.028040595,0.12765524,0.013514762,0.00041418595,0.4336383,0.0014811318,0.001736386,0.02693461,0.0032764212,0.36224693],"study_design_scores_gemma":[0.0005584494,0.0009179476,0.034198668,0.4212689,0.03022719,0.0009804715,0.38144717,0.003945926,0.004883492,0.066341914,0.05475406,0.00047586448],"about_ca_topic_score_codex":0.010198089,"about_ca_topic_score_gemma":0.019743057,"teacher_disagreement_score":0.722709,"about_ca_system_score_codex":0.0092114415,"about_ca_system_score_gemma":0.025475541,"threshold_uncertainty_score":0.89122885},"labels":[],"label_agreement":null},{"id":"W2782628217","doi":"","title":"The Check Engine Light is on. Diagnosing and Repairing Mathematics Education in Ontario: Portfolio of Learning","year":2018,"lang":"en","type":"article","venue":"Brock University Digital Repository (Brock University)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Portfolio; Mathematics education; Computer science; Mathematics; Business; Finance","score_opus":0.010893129204634578,"score_gpt":0.22944287215297024,"score_spread":0.21854974294833565,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2782628217","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.39991453,0.0038195539,0.012205162,0.059400596,0.0015041592,0.0012325451,0.005207405,0.0039541055,0.51276183],"genre_scores_gemma":[0.54725444,0.0039086924,0.016537735,0.0017523373,0.000091999005,0.0001837632,0.0017976802,0.0004090134,0.42806435],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9990846,0.00010016125,0.000048899587,0.0000839518,0.0005049898,0.00017736854],"domain_scores_gemma":[0.9971584,0.00024045416,0.00015599746,0.00016485559,0.0013434294,0.00093679887],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0011476879,0.00033021538,0.0002497554,0.0016361596,0.0062597347,0.0031263952,0.001085935,0.0008115828,0.04162327],"category_scores_gemma":[0.0060942746,0.00028837816,0.00027925565,0.0014866883,0.0011904705,0.0016266063,0.0022118997,0.00072576094,0.0057720803],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011861862,0.00019439569,0.0687402,0.0002692657,0.0000115483,0.0011095342,0.023896191,0.0006411875,0.002776305,0.0038100036,0.21303466,0.685398],"study_design_scores_gemma":[0.000035368914,0.00022516664,0.17646465,0.0005106856,0.000034705794,0.0006824946,0.062938616,0.0016473631,0.0043575494,0.0034281383,0.74955595,0.00011929532],"about_ca_topic_score_codex":0.80725294,"about_ca_topic_score_gemma":0.926644,"teacher_disagreement_score":0.98392063,"about_ca_system_score_codex":0.016079359,"about_ca_system_score_gemma":0.031084819,"threshold_uncertainty_score":0.38776433},"labels":[],"label_agreement":null},{"id":"W2788510848","doi":"10.7202/1043983ar","title":"Logique du stagiaire dans son rapport à l’évaluation","year":2018,"lang":"fr","type":"article","venue":"Phronesis","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Trois-Rivières","funders":"","keywords":"Humanities; Philosophy; Political science; Valuation (finance); Business","score_opus":0.05840836912101833,"score_gpt":0.33848228309543765,"score_spread":0.28007391397441933,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2788510848","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5053313,0.0061934586,0.17832781,0.025486473,0.0019851015,0.0035479227,0.0012651866,0.0011389157,0.27672392],"genre_scores_gemma":[0.9228624,0.001824336,0.036500406,0.0013726467,0.0001912348,0.002050175,0.00031340244,0.00030465738,0.034580763],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.909659,0.05289986,0.005064545,0.0025680482,0.028091434,0.0017171206],"domain_scores_gemma":[0.85932785,0.08609335,0.009206676,0.0069613587,0.03612765,0.002283102],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.045591462,0.0008584674,0.00091058906,0.006500942,0.004335477,0.0087129045,0.0013460835,0.0016627302,0.008609644],"category_scores_gemma":[0.14114104,0.0004321243,0.00059318607,0.00411294,0.008556813,0.006040289,0.0047205216,0.0041315365,0.0016586367],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006908962,0.00028792108,0.022301974,0.0029996783,0.000113359056,0.0010090974,0.50716275,0.0009519994,0.012921571,0.1192938,0.019016465,0.31325045],"study_design_scores_gemma":[0.000097987955,0.00088019436,0.06643941,0.004712732,0.00018878345,0.0022855906,0.32586065,0.005520121,0.024273748,0.1002368,0.4690001,0.0005038423],"about_ca_topic_score_codex":0.0076767933,"about_ca_topic_score_gemma":0.010393399,"teacher_disagreement_score":0.045591462,"about_ca_system_score_codex":0.007402313,"about_ca_system_score_gemma":0.011215932,"threshold_uncertainty_score":0.24111354},"labels":[],"label_agreement":null},{"id":"W2792027373","doi":"10.5539/ijel.v8n3p345","title":"Investigating Saudi University EFL Teachers’ Assessment Literacy: Theory and Practice","year":2018,"lang":"en","type":"article","venue":"International Journal of English Linguistics","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Taif University","keywords":"Summative assessment; Memorization; Psychology; Context (archaeology); Mathematics education; Literacy; Formative assessment; Pedagogy; Medical education; Medicine","score_opus":0.025659876284601656,"score_gpt":0.3860961951589349,"score_spread":0.36043631887433325,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2792027373","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97716534,0.002908946,0.0063097863,0.0020911826,0.00003580761,0.0003895673,0.000038302776,0.000021977505,0.011039098],"genre_scores_gemma":[0.99197996,0.0016261106,0.0054932814,0.00023631379,0.000011551989,0.00019932303,0.000019455305,0.000004708642,0.00042923875],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.98728395,0.008066099,0.00096692704,0.0008290632,0.0023283183,0.0005256098],"domain_scores_gemma":[0.88417757,0.09142008,0.006292777,0.0025490792,0.013721082,0.0018393786],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.029711228,0.00041680806,0.00043997358,0.0034797187,0.0016150076,0.0037211378,0.0013014587,0.0011984999,0.0020754118],"category_scores_gemma":[0.06007359,0.0004718627,0.00033974543,0.002212104,0.0027831118,0.0030885877,0.0023727878,0.0008365996,0.0004221049],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002835904,0.002722947,0.24223205,0.0039868043,0.00014826299,0.0006996108,0.34230033,0.0010383645,0.0029942694,0.011222484,0.0013404611,0.39103082],"study_design_scores_gemma":[0.00020770152,0.0023720611,0.24766554,0.010519309,0.00037158697,0.0010743312,0.68462735,0.009220173,0.007810558,0.00996761,0.026017457,0.00014630557],"about_ca_topic_score_codex":0.0069678365,"about_ca_topic_score_gemma":0.009650372,"teacher_disagreement_score":0.029711228,"about_ca_system_score_codex":0.0046267565,"about_ca_system_score_gemma":0.008666136,"threshold_uncertainty_score":0.15712988},"labels":[],"label_agreement":null},{"id":"W2796537024","doi":"10.2307/4126487","title":"Towards Coherence between Classroom Assessment and Accountability: 103rd Yearbook of the National Society for the Study of Education, Part II","year":2005,"lang":"en","type":"article","venue":"Canadian Journal of Education / Revue canadienne de l éducation","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":59,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Yearbook; Accountability; Coherence (philosophical gambling strategy); Political science; Pedagogy; Mathematics education; Psychology; Sociology; Library science; Computer science; Law","score_opus":0.08536018163195189,"score_gpt":0.38251947441171646,"score_spread":0.2971592927797646,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2796537024","genre_codex":"review","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0016451268,0.6834995,0.032639824,0.18626167,0.0209116,0.0003890477,0.0013178346,0.00037239783,0.07296296],"genre_scores_gemma":[0.04350258,0.75390464,0.070053905,0.021308573,0.012396206,0.0012020693,0.003300007,0.0010239816,0.09330802],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9850953,0.0043724678,0.0021551163,0.00079190865,0.007133233,0.00045189395],"domain_scores_gemma":[0.9492118,0.019280946,0.0011565462,0.0021763267,0.026064081,0.0021103239],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.030095821,0.0020306131,0.0018044859,0.010461057,0.0033335974,0.009910568,0.0025569275,0.0044328095,0.004924398],"category_scores_gemma":[0.04917605,0.0016352853,0.00079696754,0.009860576,0.01377843,0.009381403,0.0044644196,0.008681002,0.0024200731],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000047692763,0.000120132165,0.0018523894,0.0010304895,0.000026835598,0.00005560937,0.0044088895,0.0009729987,0.00032051347,0.06283575,0.5394001,0.38892853],"study_design_scores_gemma":[0.000008586409,0.000022722197,0.0041908883,0.0027787976,0.000015535157,0.000092323695,0.0011572423,0.0002195279,0.00016423903,0.03506826,0.9562227,0.000059286413],"about_ca_topic_score_codex":0.2573055,"about_ca_topic_score_gemma":0.3415858,"teacher_disagreement_score":0.2573055,"about_ca_system_score_codex":0.01925485,"about_ca_system_score_gemma":0.06810985,"threshold_uncertainty_score":0.51161563},"labels":[],"label_agreement":null},{"id":"W2797014392","doi":"10.1177/0829573518765010","title":"Developing Proficiency in Standardized Cognitive Assessment Scoring: How Much Is Enough?","year":2018,"lang":"en","type":"article","venue":"Canadian Journal of School Psychology","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Psychology; Standardized test; Wechsler Intelligence Scale for Children; Wechsler Adult Intelligence Scale; Clinical psychology; Cognition; Wechsler Preschool and Primary Scale of Intelligence; Intelligence quotient; Medical education; Applied psychology; Mathematics education; Psychiatry; Medicine","score_opus":0.10395269919433764,"score_gpt":0.4554083521238081,"score_spread":0.35145565292947045,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2797014392","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9511231,0.0018505398,0.03877427,0.0032909736,0.00019207237,0.00049332617,0.0002092248,0.0002489594,0.0038175941],"genre_scores_gemma":[0.9725547,0.0010145033,0.025258198,0.00036532932,0.000069705275,0.0001827293,0.00027826751,0.000045116063,0.00023138084],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.93854225,0.033408884,0.009419599,0.0025131712,0.014928906,0.0011871656],"domain_scores_gemma":[0.69416696,0.19108972,0.04271829,0.023406968,0.04551142,0.0031066535],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0984753,0.00057021895,0.00073070667,0.0018899569,0.00054825866,0.0022153945,0.0015498187,0.0009215482,0.00038146533],"category_scores_gemma":[0.32309023,0.0003442347,0.0005344791,0.00165358,0.0016522502,0.004015172,0.001404439,0.001164631,0.00038152008],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001530308,0.00021418558,0.73373413,0.00026107347,0.00015138532,0.000050299834,0.0030038597,0.000789484,0.0008264555,0.00041164024,0.0010623927,0.25934207],"study_design_scores_gemma":[0.00003759809,0.0028180035,0.9666314,0.0010382596,0.00018141871,0.000826841,0.0053971494,0.008758591,0.0047071693,0.0027099983,0.006777225,0.00011641176],"about_ca_topic_score_codex":0.003220183,"about_ca_topic_score_gemma":0.005444341,"teacher_disagreement_score":0.0984753,"about_ca_system_score_codex":0.0010456484,"about_ca_system_score_gemma":0.0038753452,"threshold_uncertainty_score":0.5207934},"labels":[],"label_agreement":null},{"id":"W2801829489","doi":"10.1007/s10758-018-9363-2","title":"Online Project-Based Learning and Formative Assessment","year":2018,"lang":"en","type":"article","venue":"Technology Knowledge and Learning","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":59,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Formative assessment; Context (archaeology); Psychology; Mathematics education; Computer science; Knowledge management; Medical education; Pedagogy; Medicine","score_opus":0.02415889938500342,"score_gpt":0.3958033213554171,"score_spread":0.3716444219704137,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2801829489","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6325817,0.0010233661,0.25573584,0.0008709847,0.00043850526,0.003651279,0.0011289656,0.0020371065,0.102532215],"genre_scores_gemma":[0.8616805,0.00064597867,0.11359832,0.00015758029,0.00015473178,0.0028335454,0.00076182175,0.00013418225,0.020033384],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9797004,0.012785153,0.00093734014,0.0010681747,0.0050117113,0.000497256],"domain_scores_gemma":[0.912913,0.06102732,0.0042685675,0.0070933425,0.01073433,0.003963443],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.016110417,0.000813969,0.00093388575,0.0030795303,0.00092600496,0.0035385722,0.0013497504,0.00091546937,0.011731546],"category_scores_gemma":[0.07808691,0.00031228457,0.00061669934,0.0026027854,0.000506368,0.0038265095,0.0041264663,0.001151992,0.0032243181],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007511416,0.0055033593,0.035219904,0.00045217408,0.00008338233,0.000083358944,0.0031225283,0.0021296465,0.0024660467,0.0029396939,0.004392373,0.94285643],"study_design_scores_gemma":[0.001634129,0.024709186,0.56963766,0.0022183224,0.00073141203,0.002751017,0.01992868,0.10922938,0.055256154,0.099136524,0.11422788,0.00053968345],"about_ca_topic_score_codex":0.0007310908,"about_ca_topic_score_gemma":0.0011233113,"teacher_disagreement_score":0.016110417,"about_ca_system_score_codex":0.0007762715,"about_ca_system_score_gemma":0.0019485905,"threshold_uncertainty_score":0.085201085},"labels":[],"label_agreement":null},{"id":"W2802895273","doi":"10.3968/10161","title":"Alternative Assessment in the Moroccan EFL Classrooms Teachers’ Conceptions and Practices","year":2018,"lang":"en","type":"article","venue":"Higher education of social science","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":17,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Context (archaeology); Class (philosophy); Curriculum; Face (sociological concept); Alternative assessment; Mathematics education; Psychology; Focus group; Pedagogy; Medical education; Sociology; Computer science; Medicine; Social science","score_opus":0.0664318506703283,"score_gpt":0.4809214078683849,"score_spread":0.4144895571980566,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2802895273","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98753047,0.001615692,0.0011270418,0.0014738033,0.000015429507,0.000024414201,0.00001478386,0.000016231414,0.008182212],"genre_scores_gemma":[0.99776983,0.0003430777,0.0008216,0.0000811828,0.000003128,0.000010567264,0.000004243476,0.0000027419792,0.0009636228],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99296796,0.004059879,0.00042497794,0.0005712991,0.0013675467,0.00060843996],"domain_scores_gemma":[0.99245065,0.0037043313,0.0011730243,0.00040415666,0.0016458671,0.0006219037],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0061484626,0.00034400355,0.0004323604,0.0017244009,0.003410339,0.004370232,0.0007588504,0.0007718156,0.0012041637],"category_scores_gemma":[0.0071530226,0.00024918502,0.0001850598,0.0009551097,0.0047750706,0.0015396005,0.0024803812,0.00077889534,0.00015859191],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011459568,0.00013120516,0.081692226,0.00039861232,0.000013468762,0.0018027753,0.8022287,0.0003558844,0.005567444,0.007724929,0.0006622547,0.099307865],"study_design_scores_gemma":[0.000026226162,0.00030987454,0.18483573,0.0010623101,0.000027384393,0.001902318,0.7208253,0.0012180468,0.0024305298,0.003962314,0.08325237,0.00014770328],"about_ca_topic_score_codex":0.028480673,"about_ca_topic_score_gemma":0.0497223,"teacher_disagreement_score":0.028480673,"about_ca_system_score_codex":0.005543849,"about_ca_system_score_gemma":0.004187186,"threshold_uncertainty_score":0.056629777},"labels":[],"label_agreement":null},{"id":"W2804173549","doi":"10.3138/jvme.0117-015r","title":"Teaching Tip: A Method for Evaluating Learning Evidence when Using Cumulative Final Examinations","year":2018,"lang":"en","type":"article","venue":"Journal of Veterinary Medical Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Microsoft excel; Computer science; Medical education; Psychology; Mathematics education; Medicine","score_opus":0.4702388782930537,"score_gpt":0.6169445040889544,"score_spread":0.14670562579590068,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2804173549","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.056707498,0.0020758132,0.88928205,0.0012168409,0.0008582522,0.014776486,0.0025940896,0.0042324094,0.028256558],"genre_scores_gemma":[0.06107761,0.0006414511,0.92544484,0.00010751421,0.00007582409,0.009507394,0.000336126,0.00024603325,0.0025631278],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9040482,0.048582636,0.016191995,0.0032447304,0.027122773,0.00080953573],"domain_scores_gemma":[0.7197317,0.1712275,0.022399444,0.015410289,0.0686858,0.002545274],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.09057514,0.0015008536,0.0015741212,0.018417833,0.0022590593,0.0057754307,0.0029007117,0.0017239806,0.010141712],"category_scores_gemma":[0.29208657,0.00087163725,0.0021500518,0.008874395,0.002133856,0.0056443433,0.0048114555,0.0022851925,0.0027637398],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011211735,0.00030834714,0.031586766,0.0041255723,0.00042311256,0.0003181327,0.005999173,0.0008373307,0.008056603,0.011049821,0.011251405,0.9249225],"study_design_scores_gemma":[0.0018581044,0.017095024,0.26269156,0.0152153345,0.0046352465,0.01116824,0.03149864,0.070089094,0.14777699,0.10989185,0.325651,0.0024289885],"about_ca_topic_score_codex":0.0010795081,"about_ca_topic_score_gemma":0.0038958683,"teacher_disagreement_score":0.09057514,"about_ca_system_score_codex":0.0019763364,"about_ca_system_score_gemma":0.0056922645,"threshold_uncertainty_score":0.47901285},"labels":[],"label_agreement":null},{"id":"W2807722510","doi":"10.3138/jvme.0117-014r1","title":"Think Subscores Are a Helpful Form of Feedback? Think Again","year":2018,"lang":"en","type":"article","venue":"Journal of Veterinary Medical Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology; Medical education; Engineering ethics; Medicine; Engineering","score_opus":0.06954159974503704,"score_gpt":0.41994441087406226,"score_spread":0.3504028111290252,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2807722510","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.33475265,0.012928197,0.14576988,0.29399282,0.015301081,0.0011522968,0.0024683732,0.011738332,0.18189645],"genre_scores_gemma":[0.7946401,0.0073896013,0.15367989,0.02127803,0.0017188279,0.0011936692,0.0006007245,0.0014603231,0.018038841],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.97552425,0.015344265,0.0020553162,0.0006064394,0.0058899648,0.00057982974],"domain_scores_gemma":[0.83274066,0.103072196,0.017088993,0.012688716,0.029362591,0.005046849],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02589454,0.0008066534,0.00115605,0.0018791034,0.0009131395,0.0029269434,0.0008498301,0.0015563463,0.01397349],"category_scores_gemma":[0.2276297,0.0004753511,0.0006845314,0.0016121017,0.0022291224,0.007116579,0.0012558193,0.0031583733,0.0064897235],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005603943,0.0006007044,0.037969705,0.0016118914,0.00014212707,0.00031487283,0.01228754,0.00028697768,0.0037114162,0.0064019486,0.14359637,0.79251605],"study_design_scores_gemma":[0.00042812625,0.0038688849,0.19979559,0.012213257,0.00043074894,0.0051318957,0.05621767,0.0052235676,0.015426693,0.11644453,0.58383507,0.0009839145],"about_ca_topic_score_codex":0.001635272,"about_ca_topic_score_gemma":0.00411817,"teacher_disagreement_score":0.9741055,"about_ca_system_score_codex":0.00084273226,"about_ca_system_score_gemma":0.0017780352,"threshold_uncertainty_score":0.13694507},"labels":[],"label_agreement":null},{"id":"W2808382347","doi":"10.18162/fp.2018.458","title":"L’autoévaluation et l’évaluationpar les pairs en enseignementsupérieur : promesses et défis","year":2018,"lang":"fr","type":"article","venue":"Formation et profession","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Political science","score_opus":0.07013561867856578,"score_gpt":0.4178736721217637,"score_spread":0.3477380534431979,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2808382347","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.786015,0.0016591524,0.05871178,0.009601092,0.00041217,0.00047758734,0.00016460508,0.00024066736,0.142718],"genre_scores_gemma":[0.97661394,0.0004030536,0.011297866,0.00016754284,0.000046779187,0.00018031622,0.000043547723,0.00003496466,0.011212003],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.94963175,0.031624652,0.0016192514,0.0021752815,0.01322235,0.001726746],"domain_scores_gemma":[0.93234205,0.034923315,0.007539125,0.005766924,0.014567552,0.0048610284],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.030820405,0.00081848365,0.00076643407,0.002753157,0.002675598,0.011310747,0.0013855242,0.0011841191,0.010459577],"category_scores_gemma":[0.0826965,0.00035030465,0.0007083518,0.0019542985,0.005317809,0.0076367003,0.008273209,0.0019944212,0.0011336991],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00081338687,0.0007036619,0.106804565,0.00073452346,0.00016515458,0.0002337495,0.08473479,0.0019473359,0.002632535,0.12164725,0.005427088,0.67415595],"study_design_scores_gemma":[0.00021705352,0.0038757166,0.27145562,0.0025783428,0.0003651889,0.0010268544,0.28871378,0.023363233,0.01613748,0.18987373,0.20196123,0.0004318317],"about_ca_topic_score_codex":0.003923362,"about_ca_topic_score_gemma":0.0051720426,"teacher_disagreement_score":0.9691796,"about_ca_system_score_codex":0.0057273596,"about_ca_system_score_gemma":0.0078043854,"threshold_uncertainty_score":0.16299582},"labels":[],"label_agreement":null},{"id":"W2809613764","doi":"10.15760/nwjte.2011.9.1.1","title":"Using Exploratory Interviews to Re-frame Planned Research on Classroom Issues","year":2011,"lang":"en","type":"article","venue":"Northwest Journal of Teacher Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Interview; Exploratory research; Framing (construction); Grading (engineering); Psychology; Pedagogy; Medical education; Mathematics education; Sociology; Medicine; Social science","score_opus":0.38259458490481973,"score_gpt":0.5143041322206915,"score_spread":0.13170954731587176,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2809613764","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.29717797,0.0023981407,0.63322884,0.009180082,0.0013229533,0.016738513,0.0010856175,0.00090667116,0.03796112],"genre_scores_gemma":[0.56572497,0.0020924078,0.38206115,0.0026322778,0.00032642792,0.030064527,0.0008579162,0.00039181515,0.015848506],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.85729134,0.12675351,0.0034447717,0.004992799,0.0047534406,0.0027642378],"domain_scores_gemma":[0.75235146,0.20472896,0.0092377765,0.015402416,0.015891865,0.0023874962],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.10812359,0.0030341272,0.0013601357,0.0065571573,0.008432415,0.00920025,0.0039340802,0.0034804046,0.0052728583],"category_scores_gemma":[0.13152854,0.001733358,0.0011516941,0.0048773796,0.011729032,0.015471316,0.009072614,0.0053109983,0.0016886902],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020209995,0.00017332629,0.001533709,0.0007968844,0.000028635754,0.0010779856,0.91882426,0.00052853074,0.0035761802,0.021749977,0.0020442815,0.049464162],"study_design_scores_gemma":[0.00011120736,0.00033380522,0.0010335259,0.0017457515,0.00003763889,0.0007044761,0.8805051,0.001826704,0.0042287214,0.035686824,0.073668554,0.00011769621],"about_ca_topic_score_codex":0.0029175638,"about_ca_topic_score_gemma":0.0065339757,"teacher_disagreement_score":0.10812359,"about_ca_system_score_codex":0.0070449812,"about_ca_system_score_gemma":0.008637083,"threshold_uncertainty_score":0.57181907},"labels":[],"label_agreement":null},{"id":"W2853632348","doi":"10.1007/s10459-018-9841-2","title":"Comparatively salient: examining the influence of preceding performances on assessors’ focus and interpretations in written assessment comments","year":2018,"lang":"en","type":"article","venue":"Advances in Health Sciences Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":10,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Northern British Columbia","funders":"National Institute for Health and Care Research","keywords":"Optimal distinctiveness theory; Salience (neuroscience); Competence (human resources); Psychology; Cognitive psychology; Contrast (vision); Salient; Social psychology; Cognition; Benchmarking; Computer science; Artificial intelligence","score_opus":0.05070227454645189,"score_gpt":0.47750808015242924,"score_spread":0.42680580560597736,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2853632348","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9940382,0.00017423829,0.0013488696,0.00020331665,0.000058081616,0.000062785635,0.00007486466,0.00005079626,0.0039887633],"genre_scores_gemma":[0.99814284,0.00006710607,0.0010968021,0.00006400577,0.000042008083,0.00007312456,0.00006096678,0.00003936525,0.00041389657],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9676001,0.018785717,0.0031931452,0.0021598209,0.0072588273,0.0010024951],"domain_scores_gemma":[0.35469666,0.5562734,0.05420599,0.008144974,0.021968491,0.0047105444],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.022026177,0.0005284172,0.0005264811,0.0018388875,0.0013514026,0.0033604363,0.00081373757,0.0011415575,0.002286318],"category_scores_gemma":[0.39538065,0.0004974941,0.00050153484,0.0010662214,0.0012687474,0.0022730494,0.00244469,0.0019409383,0.00044770277],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.009964313,0.000878819,0.5817723,0.0012455392,0.0006867456,0.0008757501,0.22907984,0.000917388,0.051499937,0.00070016325,0.0018811843,0.12049804],"study_design_scores_gemma":[0.00010137678,0.0014623194,0.9564255,0.00037132818,0.00030146574,0.00035313854,0.030513836,0.0016113794,0.0061461753,0.0007391433,0.0018404092,0.00013399705],"about_ca_topic_score_codex":0.0022231466,"about_ca_topic_score_gemma":0.0042470424,"teacher_disagreement_score":0.9779738,"about_ca_system_score_codex":0.0009526727,"about_ca_system_score_gemma":0.0012316604,"threshold_uncertainty_score":0.11648697},"labels":[],"label_agreement":null},{"id":"W2884360845","doi":"10.1002/tl.20302","title":"Creating a Culture of Continuous Assessment to Improve Student Learning Through Curriculum Review","year":2018,"lang":"en","type":"article","venue":"New Directions for Teaching and Learning","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Curriculum; Curriculum development; Mathematics education; Pedagogy; Active learning (machine learning); Action (physics); Psychology; Computer science; Artificial intelligence","score_opus":0.016468156458477337,"score_gpt":0.39776346616416125,"score_spread":0.3812953097056839,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2884360845","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0947871,0.003008969,0.64893156,0.12107435,0.002637625,0.005267752,0.00013098466,0.0037211038,0.1204406],"genre_scores_gemma":[0.42539603,0.0014632687,0.5480734,0.0077040885,0.0004751231,0.0041662585,0.00012136945,0.00056490646,0.012035529],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.6829512,0.23256053,0.013034181,0.010488543,0.055987086,0.004978453],"domain_scores_gemma":[0.6769015,0.13509285,0.033017978,0.04614654,0.082616575,0.026224546],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.2192975,0.0010377325,0.0012218405,0.007466091,0.009087072,0.024698228,0.005557333,0.0032333604,0.0019984914],"category_scores_gemma":[0.1690693,0.0016436912,0.0012077505,0.0025201663,0.013422236,0.014716633,0.032195058,0.011283547,0.0014209219],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010426628,0.0014921703,0.016436728,0.0018776576,0.00032450937,0.00059697113,0.18182884,0.0038057705,0.0108917905,0.14474003,0.046086505,0.5918148],"study_design_scores_gemma":[0.00025975888,0.0012194006,0.01659296,0.006352251,0.00023329134,0.0017553952,0.08847944,0.012922488,0.0143673625,0.13383956,0.7231587,0.0008193917],"about_ca_topic_score_codex":0.0027424921,"about_ca_topic_score_gemma":0.007586028,"teacher_disagreement_score":0.2192975,"about_ca_system_score_codex":0.010378162,"about_ca_system_score_gemma":0.054896876,"threshold_uncertainty_score":0.9627452},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.014690897748753037,"score_gpt":0.39760354015591914,"score_spread":0.3829126424071661,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2885480655","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13630515,0.031884562,0.37841353,0.11143962,0.001927591,0.0007962334,0.00031167528,0.001021577,0.3379001],"genre_scores_gemma":[0.92622524,0.0044483296,0.05946134,0.0026888088,0.00030387277,0.0004908401,0.000059965372,0.00014412189,0.0061774487],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9347717,0.045657516,0.0027214768,0.0041462835,0.011579438,0.0011236182],"domain_scores_gemma":[0.90779513,0.067145355,0.007652782,0.0069094733,0.008267878,0.0022293474],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.034279887,0.00091775577,0.00073057367,0.0045101224,0.0035877987,0.014332072,0.0025010114,0.0029634233,0.004550879],"category_scores_gemma":[0.097875744,0.00053797767,0.00072699,0.002459213,0.04284441,0.015356211,0.011947586,0.004247147,0.0007554495],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002208004,0.00011679745,0.0063762497,0.0019670757,0.00008133025,0.0003237024,0.077940375,0.002589702,0.0014398668,0.6339277,0.0033042391,0.27171215],"study_design_scores_gemma":[0.00010448289,0.00029270886,0.005693409,0.0031737846,0.00008953539,0.00058653177,0.015218062,0.002766663,0.002172203,0.8568039,0.11297367,0.00012504452],"about_ca_topic_score_codex":0.0044332934,"about_ca_topic_score_gemma":0.0034291772,"teacher_disagreement_score":0.034279887,"about_ca_system_score_codex":0.0067164744,"about_ca_system_score_gemma":0.010175376,"threshold_uncertainty_score":0.18129152},"labels":[],"label_agreement":null},{"id":"W2885719062","doi":"","title":"Collaboration Between Content Experts and Assessment Specialists: Using a Validity Argument Framework to Develop a College Mathematics Assessment","year":2018,"lang":"en","type":"article","venue":"Canadian Journal of Education / Revue canadienne de l éducation","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"York University; Institute for Christian Studies; University of Toronto","funders":"","keywords":"Argument (complex analysis); Content validity; Psychology; Educational assessment; Content (measure theory); Mathematics education; Psychometrics; Medicine; Mathematics","score_opus":0.1838400374076336,"score_gpt":0.41436563256571973,"score_spread":0.23052559515808613,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2885719062","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14718702,0.0011979706,0.62955326,0.101799905,0.0010074781,0.0023668185,0.000045310127,0.00035965312,0.11648264],"genre_scores_gemma":[0.6164377,0.0003033052,0.3743626,0.0031419478,0.0001443514,0.0010868454,0.00004079244,0.000100287725,0.004382308],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.6921466,0.25877115,0.007280485,0.007248647,0.029354986,0.0051980987],"domain_scores_gemma":[0.57337224,0.3537756,0.012520061,0.011973505,0.038873963,0.009484662],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.24145605,0.0011025853,0.0011712349,0.0071676527,0.014124592,0.018757116,0.004196483,0.0080251815,0.0029027355],"category_scores_gemma":[0.30336595,0.001134718,0.0011070389,0.002136872,0.022243766,0.022758052,0.023757152,0.008372188,0.0007340386],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017561919,0.000655427,0.013667695,0.00076484005,0.00010830217,0.0019571157,0.47387376,0.0030106425,0.0040171063,0.34198827,0.007847857,0.15193336],"study_design_scores_gemma":[0.0003957034,0.0005321662,0.006957636,0.004053131,0.00015092044,0.0010210446,0.22711764,0.029638296,0.0066448688,0.58196634,0.14114095,0.00038122208],"about_ca_topic_score_codex":0.008870512,"about_ca_topic_score_gemma":0.013643315,"teacher_disagreement_score":0.24145605,"about_ca_system_score_codex":0.023552954,"about_ca_system_score_gemma":0.05056742,"threshold_uncertainty_score":0.93541974},"labels":[],"label_agreement":null},{"id":"W2889059640","doi":"10.5206/cie-eci.v47i1.9324","title":"Grading Policies in Canada and China: A Comparative Study","year":2018,"lang":"en","type":"article","venue":"Comparative and International Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Queen's University","funders":"","keywords":"Grading (engineering); China; Internationalization; Christian ministry; Immigration; Political science; Globalization; Comparative education; Academic achievement; Promotion (chess); Mathematics education; Pedagogy; Higher education; Psychology; Business","score_opus":0.1087710950017053,"score_gpt":0.46185380432581685,"score_spread":0.35308270932411157,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2889059640","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.991676,0.000629755,0.00006173577,0.00044546026,0.00001041815,0.000033141954,0.00054641766,0.00000796569,0.006589176],"genre_scores_gemma":[0.9966893,0.0006589639,0.00017984686,0.00015081956,0.000003940407,0.000018774836,0.00051274104,0.0000057694415,0.0017797974],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.9971535,0.0003076432,0.00013369396,0.00024228019,0.0010137776,0.0011490351],"domain_scores_gemma":[0.9907718,0.0012754748,0.0010617943,0.00027346404,0.0046867733,0.0019306208],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002226407,0.0003923388,0.00068318326,0.0060962965,0.009236704,0.0031624476,0.0014051045,0.000643585,0.002430633],"category_scores_gemma":[0.0063191713,0.00027418789,0.0004483406,0.021380683,0.0022284118,0.0010715195,0.0018792866,0.00096408365,0.00016206542],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031017695,0.00040360424,0.81566983,0.00032880425,0.00013133338,0.0019514227,0.09448143,0.0007505381,0.0008301736,0.008610294,0.005637078,0.070895255],"study_design_scores_gemma":[0.000015071507,0.00008079936,0.9058702,0.0001305558,0.00004920956,0.0001411206,0.07924763,0.0006248998,0.00026852102,0.00019296147,0.013312216,0.000066767534],"about_ca_topic_score_codex":0.9949635,"about_ca_topic_score_gemma":0.9977496,"teacher_disagreement_score":0.8984418,"about_ca_system_score_codex":0.10155821,"about_ca_system_score_gemma":0.10767196,"threshold_uncertainty_score":0.7368598},"labels":[],"label_agreement":null},{"id":"W2889522036","doi":"10.5539/ies.v11n9p12","title":"Interrater Scoring of Public Speaking Performances in English Language Teacher Education Program","year":2018,"lang":"en","type":"article","venue":"International Education Studies","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Grading (engineering); Psychology; Inter-rater reliability; Mathematics education; Curriculum; Rating scale; Qualitative research; Qualitative property; Empowerment; Pedagogy; Teacher education; Computer science","score_opus":0.08813912167534482,"score_gpt":0.47629297147951877,"score_spread":0.38815384980417394,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2889522036","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9812029,0.00023965247,0.011878313,0.00006031666,0.000080222475,0.00046117013,0.00024017894,0.00012092191,0.005716195],"genre_scores_gemma":[0.98714674,0.00017211855,0.010496612,0.000014781879,0.000018492916,0.00034145583,0.00023635381,0.000037260823,0.0015362136],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9765413,0.010710569,0.0034636068,0.0018826545,0.006753326,0.0006484881],"domain_scores_gemma":[0.96169394,0.011959208,0.002900279,0.00418554,0.018394511,0.0008664828],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02093384,0.00047158304,0.0006228063,0.0023060488,0.0010564891,0.0007834503,0.00074454106,0.0003836149,0.0012989015],"category_scores_gemma":[0.034994643,0.0002599053,0.00058178575,0.0009795635,0.0010832766,0.0005155978,0.0022676156,0.0004836014,0.0007063716],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014793061,0.0005495353,0.62530196,0.0011024609,0.00039485705,0.0007339625,0.07690802,0.0010461638,0.03695838,0.0010436163,0.002331216,0.25215054],"study_design_scores_gemma":[0.00005079648,0.0014377589,0.906138,0.00028601335,0.00024222881,0.0014200384,0.04308059,0.0063746674,0.03238069,0.0013705539,0.0070731496,0.00014550501],"about_ca_topic_score_codex":0.0010558894,"about_ca_topic_score_gemma":0.002529584,"teacher_disagreement_score":0.02093384,"about_ca_system_score_codex":0.00047877303,"about_ca_system_score_gemma":0.0009420495,"threshold_uncertainty_score":0.110710025},"labels":[],"label_agreement":null},{"id":"W2890137837","doi":"10.4018/978-1-5225-3940-7.ch005","title":"Using Computerized Formative Testing to Support Personalized Learning in Higher Education","year":2018,"lang":"en","type":"book-chapter","venue":"Advances in educational technologies and instructional design book series","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":19,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Formative assessment; Test (biology); Computer science; Psychology; Mathematics education","score_opus":0.0862099370797399,"score_gpt":0.36275300424261275,"score_spread":0.27654306716287286,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2890137837","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026997156,0.024190174,0.5585105,0.006174899,0.0023926203,0.0012936911,0.0010463914,0.014611885,0.36478275],"genre_scores_gemma":[0.07439242,0.02214456,0.7477088,0.0023138097,0.001018676,0.0009904496,0.0017259199,0.0011061388,0.14859922],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99865144,0.00032855934,0.00007444199,0.00010760175,0.00079317595,0.000044757784],"domain_scores_gemma":[0.99529463,0.0034035011,0.00020688873,0.00044964513,0.0005164763,0.00012885989],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020157786,0.00069151446,0.00035655688,0.0012278904,0.0002384694,0.0020659696,0.001551149,0.0008180189,0.014725167],"category_scores_gemma":[0.006952076,0.00025247663,0.0003086357,0.0016453305,0.0005313035,0.0025478434,0.0008829352,0.001163664,0.005441115],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019487288,0.00013697552,0.00069791084,0.00031316656,0.0000073994747,0.00009993342,0.00044594874,0.0011457877,0.0032905352,0.011699529,0.04532585,0.9368175],"study_design_scores_gemma":[0.000073992924,0.0006363681,0.011195407,0.0020342565,0.00004933473,0.002932759,0.0006667701,0.014069552,0.019179877,0.06671981,0.88233644,0.00010540069],"about_ca_topic_score_codex":0.00083805044,"about_ca_topic_score_gemma":0.0017413624,"teacher_disagreement_score":0.014725167,"about_ca_system_score_codex":0.0007231829,"about_ca_system_score_gemma":0.0010330707,"threshold_uncertainty_score":0.049260616},"labels":[],"label_agreement":null},{"id":"W2893953242","doi":"10.1177/1541931218621082","title":"Usability Analysis of Freeform Marking on Engineering Problem Solving","year":2018,"lang":"en","type":"article","venue":"Proceedings of the Human Factors and Ergonomics Society Annual Meeting","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Usability; Formative assessment; Consistency (knowledge bases); Computer science; Test (biology); Perspective (graphical); Group (periodic table); Sample (material); Mathematics education; Human–computer interaction; Psychology; Artificial intelligence","score_opus":0.018590048526772915,"score_gpt":0.27364103322569827,"score_spread":0.25505098469892534,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2893953242","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9920219,0.00012008295,0.005092132,0.000026470401,0.00002771512,0.00051997305,0.00014826328,0.000113569586,0.0019298001],"genre_scores_gemma":[0.98533964,0.00011775033,0.011908194,0.000036624064,0.000044602286,0.00086867047,0.0003468785,0.000058785256,0.0012788438],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.97674835,0.013993454,0.0020204955,0.00086115557,0.0058345827,0.0005418704],"domain_scores_gemma":[0.78983074,0.17170632,0.009700163,0.0060446365,0.021504145,0.0012140038],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.016562464,0.00085679046,0.00081397564,0.0034354876,0.00050232495,0.00095970987,0.00055787794,0.00046364675,0.001899634],"category_scores_gemma":[0.08945355,0.00025538867,0.00108305,0.0018356703,0.00054365356,0.0009940577,0.0010499366,0.00036271455,0.0003219475],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.009057068,0.002496719,0.27917883,0.0031879877,0.00057161227,0.00037469954,0.036540553,0.002899337,0.046305858,0.0005465324,0.0025023387,0.61633843],"study_design_scores_gemma":[0.00025428933,0.0152312005,0.93561226,0.00048404423,0.00031359037,0.00045554605,0.0102324905,0.010219845,0.022474179,0.00044802646,0.0040606926,0.00021374157],"about_ca_topic_score_codex":0.0009866483,"about_ca_topic_score_gemma":0.0015497878,"teacher_disagreement_score":0.016562464,"about_ca_system_score_codex":0.0006128627,"about_ca_system_score_gemma":0.0005510177,"threshold_uncertainty_score":0.08759171},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.019267145783885532,"score_gpt":0.3851389734389596,"score_spread":0.36587182765507403,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2897106912","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0029795463,0.006835451,0.021372166,0.45672074,0.24927308,0.00030860017,0.00058512087,0.0068075326,0.25511783],"genre_scores_gemma":[0.07098896,0.0114471475,0.019891644,0.30555817,0.058216427,0.0008113228,0.00086094433,0.003684855,0.52854043],"study_design_codex":"not_applicable","study_design_gemma":"qualitative","domain_scores_codex":[0.98415726,0.0065825633,0.0008658708,0.00080899487,0.0064706476,0.0011146682],"domain_scores_gemma":[0.963422,0.012100179,0.0021604747,0.0015931944,0.014325745,0.0063984557],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011059684,0.0012261414,0.00080416136,0.001296925,0.003079024,0.0056687575,0.0011855012,0.003545238,0.055472627],"category_scores_gemma":[0.08249448,0.00046709314,0.0008192706,0.0006645034,0.0034303355,0.006549837,0.0047652144,0.009461005,0.052992865],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000043589374,0.000030794687,0.00020812648,0.00011902288,0.0000058126425,0.000032005624,0.0012866625,0.000022650196,0.00028695937,0.002308949,0.9363122,0.059343226],"study_design_scores_gemma":[0.000011829971,0.000056880064,0.00054303533,0.0002250676,0.000006544767,0.000096110474,0.0015186104,0.000066013374,0.00041821547,0.0022603804,0.994764,0.000033359902],"about_ca_topic_score_codex":0.0020226385,"about_ca_topic_score_gemma":0.004630316,"teacher_disagreement_score":0.055472627,"about_ca_system_score_codex":0.001674452,"about_ca_system_score_gemma":0.003777085,"threshold_uncertainty_score":0.18557441},"labels":[],"label_agreement":null},{"id":"W2898183750","doi":"10.1007/978-3-319-92390-1_44","title":"Enhancing Mathematics Teaching and Learning Through Sound Assessment Practices","year":2018,"lang":"en","type":"book-chapter","venue":"Advances in mathematics education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Variety (cybernetics); Mathematics education; Plan (archaeology); Process (computing); Assessment for learning; Computer science; Psychology; Formative assessment; Artificial intelligence","score_opus":0.04105032535141184,"score_gpt":0.4358463200985673,"score_spread":0.39479599474715543,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2898183750","genre_codex":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.050669517,0.009649169,0.2907306,0.004969258,0.00092239515,0.00022599942,0.00008311459,0.00180868,0.64094126],"genre_scores_gemma":[0.35803893,0.013172912,0.32145962,0.00086415344,0.0003414294,0.00022856442,0.00013900195,0.0002850132,0.3054704],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99896204,0.00019139548,0.000027970673,0.000057664653,0.0007258262,0.000035067525],"domain_scores_gemma":[0.99874157,0.0007586529,0.00006292367,0.00009078826,0.0002676658,0.00007838792],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010251787,0.00048608534,0.00023089384,0.00071248744,0.00030244383,0.0022766527,0.000763548,0.00061854563,0.007449755],"category_scores_gemma":[0.0036312893,0.00011793865,0.00022034589,0.00039850452,0.00061655097,0.0018200012,0.0017429049,0.001067012,0.0018553653],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018816912,0.00017377269,0.0004691603,0.00022590581,0.0000056275135,0.000038916776,0.0011834168,0.00097293715,0.006594274,0.030922933,0.007020232,0.952374],"study_design_scores_gemma":[0.000047912818,0.00062762713,0.01092218,0.0020311668,0.00008004108,0.0010836443,0.0035935866,0.015901975,0.035095356,0.22852013,0.7020286,0.00006784841],"about_ca_topic_score_codex":0.00057428185,"about_ca_topic_score_gemma":0.001578658,"teacher_disagreement_score":0.007449755,"about_ca_system_score_codex":0.00057459116,"about_ca_system_score_gemma":0.0009797375,"threshold_uncertainty_score":0.024921894},"labels":[],"label_agreement":null},{"id":"W2898388844","doi":"10.1007/978-3-319-92390-1_43","title":"Re-Framing Testing to Better Fit Within Problem-solving Classrooms: Ways to Create and Review Tests","year":2018,"lang":"en","type":"book-chapter","venue":"Advances in mathematics education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Lethbridge; York University","funders":"","keywords":"Mathematics education; Framing (construction); Underpinning; Pencil (optics); Test (biology); Psychology; Pedagogy; Engineering","score_opus":0.05781820994205484,"score_gpt":0.3800965022162223,"score_spread":0.3222782922741675,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2898388844","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027152238,0.026185684,0.7017567,0.0585605,0.012264166,0.0012124092,0.0010092212,0.0090841465,0.16277489],"genre_scores_gemma":[0.10872677,0.007961706,0.8034367,0.004320576,0.0017235393,0.0006232202,0.0010296823,0.0027774023,0.06940037],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.98786616,0.006348534,0.001042457,0.00075998233,0.0037818986,0.00020095677],"domain_scores_gemma":[0.89750177,0.06251622,0.0055828984,0.009031134,0.023270788,0.0020972008],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.018947402,0.00093394396,0.0009040431,0.0041888226,0.00087247026,0.009037059,0.002506461,0.0018452975,0.01034795],"category_scores_gemma":[0.095375136,0.0004963739,0.00072123215,0.0025203775,0.0025364463,0.011807483,0.002976579,0.0035470477,0.004656964],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004371459,0.00013476462,0.001545039,0.0006228684,0.000032588105,0.0001283638,0.0040397323,0.001047152,0.0016808532,0.059541173,0.08987248,0.8413113],"study_design_scores_gemma":[0.000048533602,0.00028270145,0.0031654136,0.002370741,0.00014018922,0.0007294107,0.004508565,0.0075543663,0.006889341,0.27999428,0.69412345,0.00019295882],"about_ca_topic_score_codex":0.0016633635,"about_ca_topic_score_gemma":0.004860588,"teacher_disagreement_score":0.018947402,"about_ca_system_score_codex":0.002262189,"about_ca_system_score_gemma":0.0039566476,"threshold_uncertainty_score":0.10020465},"labels":[],"label_agreement":null},{"id":"W2902865842","doi":"10.3390/educsci8040211","title":"Assessing English: A Comparison between Canada and England’s Assessment Procedures","year":2018,"lang":"en","type":"article","venue":"Education Sciences","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Summative assessment; Formative assessment; Portfolio; Subject (documents); Mathematics education; Psychology; Pedagogy; Medical education; Computer science; Library science; Medicine; Business","score_opus":0.0673436257260798,"score_gpt":0.4531102707697182,"score_spread":0.38576664504363845,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2902865842","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.81314814,0.016468298,0.007330958,0.013086461,0.0006440568,0.0009372862,0.0035471385,0.0003506883,0.14448696],"genre_scores_gemma":[0.97275823,0.006049931,0.0066703167,0.0013293148,0.000048109843,0.0003246964,0.001417276,0.00014384591,0.011258125],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9710553,0.005175045,0.0021120447,0.0011189324,0.01811025,0.002428437],"domain_scores_gemma":[0.9026284,0.011509827,0.0036831917,0.0016189964,0.07496416,0.0055953288],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.017613256,0.00035023486,0.00059102266,0.004817206,0.004901141,0.004353293,0.0021611515,0.0007366788,0.002845014],"category_scores_gemma":[0.05367625,0.00044995834,0.0005966853,0.007516075,0.0022868055,0.0012825057,0.0035726842,0.0010072279,0.00045443134],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016092882,0.00034812492,0.33071154,0.002426846,0.00024166513,0.0007259661,0.09634817,0.002094033,0.0037218465,0.018874109,0.0331151,0.50978345],"study_design_scores_gemma":[0.000071800205,0.00026635604,0.89595664,0.0013390502,0.00008877717,0.0002446977,0.03216914,0.0006635341,0.0010661046,0.00042347,0.06756668,0.00014384116],"about_ca_topic_score_codex":0.983907,"about_ca_topic_score_gemma":0.9941907,"teacher_disagreement_score":0.073597424,"about_ca_system_score_codex":0.073597424,"about_ca_system_score_gemma":0.13040023,"threshold_uncertainty_score":0.5339892},"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,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_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","score_opus":0.046335732846251504,"score_gpt":0.44900247867417203,"score_spread":0.4026667458279205,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2906729407","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.032128304,0.014100767,0.80367595,0.017195657,0.0032040018,0.0037098583,0.001181918,0.045853395,0.07895018],"genre_scores_gemma":[0.075826496,0.0059929495,0.8933443,0.0013413734,0.0009272196,0.0014211612,0.0011860824,0.0026216784,0.017338775],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9385698,0.025039459,0.0048224214,0.0020802324,0.028826933,0.0006612387],"domain_scores_gemma":[0.8485611,0.064147115,0.01613017,0.019368464,0.047514137,0.004278972],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.04194926,0.0017028489,0.0018332107,0.011060712,0.0020135457,0.007017651,0.0031428344,0.0018068212,0.007484126],"category_scores_gemma":[0.141868,0.0007836456,0.00075403834,0.0065465206,0.0029972442,0.007692509,0.00443981,0.004416753,0.008593018],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005149847,0.00023554402,0.0016929436,0.0010786054,0.000023406821,0.00009212432,0.003350614,0.000412075,0.0075108404,0.0043028113,0.050591175,0.93065846],"study_design_scores_gemma":[0.00013350017,0.0015155799,0.027364556,0.0046990607,0.00009303227,0.0021831135,0.00552539,0.008571168,0.023900846,0.024492817,0.9009984,0.0005224897],"about_ca_topic_score_codex":0.0017317935,"about_ca_topic_score_gemma":0.0023437222,"teacher_disagreement_score":0.04194926,"about_ca_system_score_codex":0.0016371493,"about_ca_system_score_gemma":0.005469329,"threshold_uncertainty_score":0.22185153},"labels":[],"label_agreement":null},{"id":"W2907726877","doi":"10.5539/jel.v8n1p74","title":"Teachers’ Perceptions on Factors Influence Adoption of Formative Assessment","year":2018,"lang":"en","type":"article","venue":"Journal of Education and Learning","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Formative assessment; Stratified sampling; Psychology; Perception; Medical education; School teachers; Sample (material); Mathematics education; Pedagogy; Medicine","score_opus":0.029315647635401475,"score_gpt":0.4112247397543618,"score_spread":0.38190909211896035,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2907726877","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99605197,0.00025395976,0.00085327495,0.00029806234,0.000009912014,0.000038741175,0.00002355672,0.000012746714,0.0024578243],"genre_scores_gemma":[0.9989586,0.00014662006,0.00046150375,0.000030036019,0.000003502327,0.0000111500485,0.000015051869,0.0000024076721,0.00037116656],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.99398947,0.0022614496,0.0006660009,0.00026981832,0.0023215453,0.00049170735],"domain_scores_gemma":[0.96051955,0.020108128,0.007989982,0.0012302987,0.0078092576,0.0023428523],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0065012295,0.00020518602,0.0001977808,0.00059832254,0.0005202626,0.001756096,0.00027179235,0.00037136278,0.0016701666],"category_scores_gemma":[0.03153501,0.00021324937,0.000322285,0.0003577711,0.00047854672,0.00068836723,0.0005089976,0.00063072745,0.0002612506],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013110662,0.00037961136,0.89137256,0.00029330258,0.00005128004,0.00035588685,0.045882214,0.00021719851,0.0052921902,0.00027072043,0.00043899202,0.055315003],"study_design_scores_gemma":[0.000017726352,0.00066525,0.93226707,0.00026417413,0.00006333229,0.00040697653,0.057433877,0.00051582936,0.0022488309,0.00022190409,0.0058516436,0.000043371805],"about_ca_topic_score_codex":0.0063310633,"about_ca_topic_score_gemma":0.009702412,"teacher_disagreement_score":0.0065012295,"about_ca_system_score_codex":0.00087824994,"about_ca_system_score_gemma":0.0018558697,"threshold_uncertainty_score":0.034382164},"labels":[],"label_agreement":null},{"id":"W2907966827","doi":"10.5430/wje.v8n6p130","title":"Student Self-Assessment in Higher Education: The International Experience and the Greek Example","year":2018,"lang":"en","type":"article","venue":"World Journal of Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":28,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Self-assessment; Psychology; Higher education; Dialogical self; Self-efficacy; Affect (linguistics); Critical thinking; Formative assessment; Mathematics education; Self-regulated learning; Medical education; Pedagogy; Social psychology","score_opus":0.04237049182951008,"score_gpt":0.40659561016836215,"score_spread":0.36422511833885207,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2907966827","genre_codex":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.39745072,0.4979108,0.004248692,0.011218996,0.0014864485,0.00008395431,0.00016791318,0.000050232484,0.087382264],"genre_scores_gemma":[0.8708343,0.12224849,0.0015607673,0.0014058572,0.00032177859,0.000039034385,0.000098742814,0.00003159751,0.0034594194],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9941425,0.0035409832,0.0007539835,0.00037547873,0.0009643394,0.00022272753],"domain_scores_gemma":[0.99323857,0.004953638,0.00063126214,0.00029731906,0.00060677447,0.00027244867],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006220499,0.0004432068,0.0005782072,0.0033469223,0.000889523,0.003139151,0.00040540445,0.0011410547,0.0013398903],"category_scores_gemma":[0.008117012,0.00017173275,0.00042192405,0.006856033,0.0024841158,0.003527578,0.0028706794,0.0013437035,0.00030648493],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001812023,0.0002936047,0.059392665,0.007956628,0.0001502237,0.0037746953,0.17425513,0.0007448917,0.0013540095,0.03703731,0.008845449,0.7060142],"study_design_scores_gemma":[0.00002189719,0.0006481479,0.1249397,0.016198859,0.00015984669,0.01297637,0.15484497,0.00035657114,0.0021095448,0.0076182596,0.6800181,0.00010762592],"about_ca_topic_score_codex":0.00070282817,"about_ca_topic_score_gemma":0.00069495256,"teacher_disagreement_score":0.006220499,"about_ca_system_score_codex":0.0012536842,"about_ca_system_score_gemma":0.0012103319,"threshold_uncertainty_score":0.03289759},"labels":[],"label_agreement":null},{"id":"W2910055723","doi":"","title":"Assessment for learning in the teaching of traditional Newfoundland craft","year":2018,"lang":"en","type":"article","venue":"2018 Conference of the Canadian Society for the Study of Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Formative assessment; Context (archaeology); Craft; Government (linguistics); Assessment for learning; Pedagogy; Psychology; Work (physics); Mathematics education; Engineering; Geography","score_opus":0.0833379041947642,"score_gpt":0.37507077196851163,"score_spread":0.2917328677737474,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2910055723","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.83969176,0.0010247484,0.011109312,0.002572299,0.00008994909,0.00025147336,0.00033819667,0.0002510861,0.14467119],"genre_scores_gemma":[0.95347446,0.0008341542,0.020383187,0.00019953065,0.00000987681,0.00008184216,0.00015286484,0.000040558378,0.024823504],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.99840575,0.00054717483,0.00006807833,0.00015380773,0.0005519556,0.00027319093],"domain_scores_gemma":[0.9971102,0.0009922915,0.00028647686,0.00026830722,0.0007892278,0.0005534777],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0034235616,0.0002790188,0.00022426622,0.0013167139,0.002424724,0.003253453,0.0008753864,0.00037590112,0.0047610207],"category_scores_gemma":[0.006989176,0.00015053252,0.000107308835,0.0012152855,0.0024476128,0.0015489189,0.0028037133,0.0007868336,0.00056612684],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017885,0.00072253286,0.09500466,0.00035189904,0.000016182415,0.0007259386,0.0892044,0.0022178665,0.0048044412,0.018507406,0.016920615,0.7713452],"study_design_scores_gemma":[0.000032192038,0.0005905799,0.54021,0.00132709,0.0000370731,0.0007766691,0.20498581,0.0036846392,0.0072155455,0.0125148045,0.22847755,0.0001479411],"about_ca_topic_score_codex":0.34288985,"about_ca_topic_score_gemma":0.77095026,"teacher_disagreement_score":0.65711015,"about_ca_system_score_codex":0.013003123,"about_ca_system_score_gemma":0.020075427,"threshold_uncertainty_score":0.68178797},"labels":[],"label_agreement":null},{"id":"W2910202428","doi":"10.1007/s40037-018-0492-z","title":"Giving feedback on others’ writing","year":2019,"lang":"en","type":"editorial","venue":"Perspectives on Medical Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Computer science; Medical education; Psychology; Data science; Medicine","score_opus":0.01407736540808381,"score_gpt":0.3876558373560515,"score_spread":0.3735784719479677,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2910202428","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000014640636,0.0019276274,0.00006197376,0.047592264,0.94907403,0.000016501115,0.000026116164,0.000027474083,0.0012593118],"genre_scores_gemma":[0.00046784218,0.001979895,0.00009565862,0.02409032,0.96289825,0.000042593107,0.000019643783,0.00004767932,0.010358148],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.96619153,0.009725275,0.0048954855,0.0024906571,0.014966048,0.0017310372],"domain_scores_gemma":[0.83367103,0.07716364,0.0072064307,0.0044865133,0.061604228,0.015868159],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.030149642,0.0045461957,0.0062983898,0.006695905,0.00600289,0.015747609,0.006601657,0.038192473,0.031632423],"category_scores_gemma":[0.15297785,0.0016278498,0.004690846,0.0030301576,0.0050797747,0.0052574347,0.0043286053,0.029248038,0.019815579],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028281444,0.000008396197,0.000013946239,0.00021932743,0.000019022116,0.00008865264,0.000035508245,0.000010372073,0.000027972033,0.00027302117,0.9954301,0.0038454328],"study_design_scores_gemma":[0.00011250569,0.000026628593,0.0001878285,0.0012504759,0.00008727018,0.00017272445,0.00011167382,0.0001479645,0.000111676694,0.0010792153,0.99667597,0.000036142603],"about_ca_topic_score_codex":0.0035285668,"about_ca_topic_score_gemma":0.010202013,"teacher_disagreement_score":0.038192473,"about_ca_system_score_codex":0.0075094476,"about_ca_system_score_gemma":0.0072785714,"threshold_uncertainty_score":0.15944844},"labels":[],"label_agreement":null},{"id":"W2910283173","doi":"10.53841/bpsptr.2018.24.2.64","title":"Using the Immediate Feedback Assessment Technique (IFAT) for non-assessments: Student perceptions and performance","year":2018,"lang":"en","type":"article","venue":"Psychology Teaching Review","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Durham College","funders":"","keywords":"Psychology; Lottery; Class (philosophy); Mathematics education; Perception; Reading (process); Medical education; Computer science; Statistics; Mathematics; Medicine; Linguistics","score_opus":0.0840307749180396,"score_gpt":0.5186797314255001,"score_spread":0.43464895650746044,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2910283173","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9943171,0.0001489555,0.0031269449,0.00008862042,0.000051742147,0.00019932525,0.000021504718,0.000061002505,0.001984729],"genre_scores_gemma":[0.98969156,0.00016593206,0.0077528055,0.00010510904,0.000029075984,0.00021204844,0.000047557787,0.000020264884,0.001975643],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98591983,0.00779875,0.0007963092,0.000902531,0.004126164,0.0004565096],"domain_scores_gemma":[0.94467676,0.03527034,0.0072506475,0.0034449296,0.0069065653,0.0024507637],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010592289,0.0005588958,0.00072466384,0.0006371618,0.0007075493,0.0014465027,0.0008250204,0.0006663355,0.002045909],"category_scores_gemma":[0.046585727,0.00020298366,0.00039386872,0.00035850346,0.00045994384,0.0008064551,0.0009150526,0.0010917312,0.0009485359],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003733092,0.023231756,0.24581008,0.0012964228,0.0002051304,0.00031142466,0.027536308,0.00059707084,0.06329194,0.00044125432,0.0021742294,0.6313713],"study_design_scores_gemma":[0.00049759273,0.086898275,0.8116134,0.0004850197,0.0002737377,0.0016774466,0.027386973,0.003183523,0.05105417,0.0008527632,0.015774967,0.00030210038],"about_ca_topic_score_codex":0.0006679934,"about_ca_topic_score_gemma":0.0012032138,"teacher_disagreement_score":0.010592289,"about_ca_system_score_codex":0.00033291613,"about_ca_system_score_gemma":0.00081403996,"threshold_uncertainty_score":0.056018114},"labels":[],"label_agreement":null},{"id":"W2910439838","doi":"10.20381/ruor-22955","title":"Large-scale Assessment and Mathematics Teacher Practice: A Case Study with Ontario Grade 9 Applied Teachers","year":2019,"lang":"en","type":"dissertation","venue":"uO Research (University of Ottawa)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Mathematics education; Scale (ratio); Pedagogy; Mathematics; Psychology; Geography; Cartography","score_opus":0.05698183760826345,"score_gpt":0.410490315276935,"score_spread":0.35350847766867155,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2910439838","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9902625,0.00022254273,0.00060848007,0.001162804,0.00002143133,0.0001781726,0.000049262428,0.000011049127,0.007483637],"genre_scores_gemma":[0.99174786,0.00037762173,0.0006752643,0.0002442459,0.000007890363,0.00011090768,0.000023425955,0.000013005649,0.00679974],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9914637,0.00451325,0.00030170078,0.0005883683,0.0016927844,0.0014401922],"domain_scores_gemma":[0.98730904,0.0068887053,0.0011955032,0.0005481566,0.0019805282,0.0020780526],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0055010533,0.00037085492,0.0006135956,0.0012092717,0.017061535,0.0036037657,0.001990379,0.0014565762,0.0028299678],"category_scores_gemma":[0.014370532,0.0006557492,0.0003070573,0.0020906606,0.009235368,0.0015498446,0.004225971,0.0020831632,0.00030946897],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019461391,0.000072047915,0.005239196,0.0000509823,0.0000023128332,0.00161033,0.98817843,0.000040305134,0.00049682584,0.00044762454,0.00038428046,0.0034582755],"study_design_scores_gemma":[0.0000066761945,0.00007205638,0.009228244,0.0000757607,0.0000044361723,0.00031070327,0.9771978,0.00007170258,0.00018787,0.000096749805,0.012733774,0.000014206478],"about_ca_topic_score_codex":0.7441616,"about_ca_topic_score_gemma":0.90058464,"teacher_disagreement_score":0.2558384,"about_ca_system_score_codex":0.032383185,"about_ca_system_score_gemma":0.030992996,"threshold_uncertainty_score":0.51469016},"labels":[],"label_agreement":null},{"id":"W2914965366","doi":"10.1002/9780470690048.ch10","title":"The Role of Assessment in a Learning Culture","year":2002,"lang":"en","type":"other","venue":"Teaching and Learning","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":13,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Curriculum; Reading (process); Section (typography); Mathematics education; Psychology; Process (computing); Pedagogy; Computer science; Political science","score_opus":0.012356049490881798,"score_gpt":0.32887429515767197,"score_spread":0.31651824566679015,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2914965366","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020204782,0.006507241,0.020197105,0.012152062,0.0005555708,0.00003068105,0.000045819605,0.00016269252,0.940144],"genre_scores_gemma":[0.7080061,0.010809844,0.019393852,0.0013362889,0.00055142585,0.0001553832,0.00006625771,0.00024083532,0.2594401],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9956403,0.0028357764,0.00016751836,0.000232519,0.0010039586,0.00011996959],"domain_scores_gemma":[0.9742639,0.017207466,0.0007687655,0.0015715274,0.004174971,0.0020134042],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005315774,0.0005899871,0.0003686761,0.0023104697,0.0022430408,0.013265728,0.0010788152,0.0017185229,0.015916688],"category_scores_gemma":[0.018690716,0.00019009005,0.0001718543,0.0028443336,0.007187419,0.010497236,0.002891644,0.0027135632,0.0015739085],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003256526,0.00014367633,0.002186171,0.0001583966,0.000007668661,0.000118054806,0.0067509464,0.000914981,0.00020772385,0.60703504,0.015205576,0.36723933],"study_design_scores_gemma":[0.000014890406,0.00007452421,0.00796897,0.00078092585,0.000022249487,0.00051311677,0.01105722,0.0051933536,0.0009355613,0.7133879,0.26001686,0.000034383665],"about_ca_topic_score_codex":0.0061010886,"about_ca_topic_score_gemma":0.007313699,"teacher_disagreement_score":0.015916688,"about_ca_system_score_codex":0.003726457,"about_ca_system_score_gemma":0.0039858804,"threshold_uncertainty_score":0.053246558},"labels":[],"label_agreement":null},{"id":"W2919446416","doi":"10.18162/ritpu.2009.159","title":"10.18162/ritpu.2009.159","year":2016,"lang":"fr","type":"dataset","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Saint Mary's University","funders":"","keywords":"Pencil (optics); Multiple choice; Test (biology); Significant difference; Psychology; Cognition; Mathematics education; Computer science; Statistics; Mathematics; Engineering","score_opus":0.03289347138127198,"score_gpt":0.34694202684143716,"score_spread":0.3140485554601652,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2919446416","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0013087617,0.0004589198,0.00056137756,0.00016492463,0.0000970157,0.00006741867,0.986568,0.0028111173,0.007962536],"genre_scores_gemma":[0.002971744,0.0004533735,0.0018793674,0.00013946394,0.0000478717,0.0002575248,0.98177576,0.0005962393,0.011878755],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9990588,0.00017868413,0.00017921439,0.0002518656,0.00021833122,0.00011313326],"domain_scores_gemma":[0.9974706,0.0008370264,0.00031457416,0.00085974653,0.00031558258,0.00020237715],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.001988745,0.0016520693,0.0012435468,0.007330793,0.00063243636,0.0033479182,0.0017933046,0.0011142535,0.39137775],"category_scores_gemma":[0.007816743,0.00087062543,0.0016377394,0.007870062,0.0002739718,0.0010875413,0.0021972698,0.0010552759,0.4804615],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026319633,0.00013432118,0.0066715614,0.0023585097,0.00023449588,0.000078062,0.000066828135,0.0003960918,0.00045140294,0.00067201245,0.9218591,0.06681448],"study_design_scores_gemma":[0.00051748595,0.000071171045,0.009238606,0.00064826367,0.00013375266,0.00018630276,0.000061806,0.00074397406,0.0005502931,0.00076974917,0.98704904,0.0000295919],"about_ca_topic_score_codex":0.0065701106,"about_ca_topic_score_gemma":0.009607628,"teacher_disagreement_score":0.60862225,"about_ca_system_score_codex":0.00094251457,"about_ca_system_score_gemma":0.0017781266,"threshold_uncertainty_score":0.8681258},"labels":[],"label_agreement":null},{"id":"W2923578044","doi":"10.1186/s40468-019-0078-7","title":"The language assessment literacy needs of Iranian EFL teachers with a focus on reformed assessment policies","year":2019,"lang":"en","type":"article","venue":"Language Testing in Asia","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":59,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Rubric; Psychology; Literacy; Curriculum; Pedagogy; Active listening; Mathematics education; Language assessment; Alternative assessment; Perception; Focus group; Sociology","score_opus":0.016486939779852855,"score_gpt":0.3597537479867195,"score_spread":0.3432668082068666,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2923578044","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9967217,0.00015775772,0.00006030128,0.0015661052,0.000006430713,0.000009949355,0.000014030252,0.0000034721643,0.0014602217],"genre_scores_gemma":[0.9990589,0.00012593348,0.00013245428,0.00021348016,0.000004504955,0.0000120731665,0.000015322961,0.0000012037613,0.00043616307],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.997486,0.00067053316,0.00020398683,0.00014069487,0.00069567596,0.00080321066],"domain_scores_gemma":[0.99199706,0.0020704805,0.0020372777,0.00017931557,0.0027901523,0.0009256622],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003266443,0.00013949341,0.00027468058,0.0007862643,0.00136874,0.0017656697,0.0004048916,0.0008837045,0.0011923789],"category_scores_gemma":[0.013325224,0.00019501218,0.00015295127,0.00072168483,0.0010380455,0.0018206025,0.0009734715,0.0009819649,0.0002046536],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019710383,0.0006450421,0.5118874,0.0003284755,0.000013316358,0.0022253285,0.37258172,0.0004047985,0.0037561376,0.0015951028,0.002323462,0.10404214],"study_design_scores_gemma":[0.00002139716,0.00041223245,0.41187942,0.00021470779,0.000012426173,0.0012072541,0.5721058,0.0007444667,0.0009969135,0.00080845854,0.011544034,0.000052965603],"about_ca_topic_score_codex":0.018954339,"about_ca_topic_score_gemma":0.023349416,"teacher_disagreement_score":0.018954339,"about_ca_system_score_codex":0.0028143574,"about_ca_system_score_gemma":0.0056414404,"threshold_uncertainty_score":0.037688017},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.07905727411628827,"score_gpt":0.4421515498552321,"score_spread":0.3630942757389438,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2923740196","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17688383,0.014725224,0.56537503,0.0845071,0.0010217563,0.00040189983,0.000051896513,0.00011234197,0.15692092],"genre_scores_gemma":[0.9659733,0.0012639746,0.03027358,0.0011333204,0.00016372815,0.00015038559,0.00000934343,0.000021164218,0.0010111178],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.92918247,0.057778794,0.0016877895,0.0018974914,0.007637205,0.0018163425],"domain_scores_gemma":[0.8795193,0.10270623,0.0052090506,0.004364857,0.0058338298,0.0023667829],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.052763622,0.00056488416,0.0010955626,0.00401221,0.005696093,0.014909508,0.00298669,0.004119467,0.0025402678],"category_scores_gemma":[0.09571839,0.00039292817,0.00071360084,0.002635494,0.03781327,0.016124867,0.013678789,0.0077295196,0.00022301327],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026291356,0.00011629466,0.0038825825,0.00022937491,0.000019363431,0.000075961936,0.036736887,0.0017251553,0.00014906038,0.9147874,0.00059576856,0.04165575],"study_design_scores_gemma":[0.000012766865,0.000047639984,0.001803405,0.00067059445,0.000013903389,0.0000785082,0.015513748,0.0049208663,0.00021482188,0.9650324,0.011660699,0.000030673473],"about_ca_topic_score_codex":0.0058271484,"about_ca_topic_score_gemma":0.0055174134,"teacher_disagreement_score":0.052763622,"about_ca_system_score_codex":0.010135305,"about_ca_system_score_gemma":0.013371337,"threshold_uncertainty_score":0.27904403},"labels":[],"label_agreement":null},{"id":"W2929902524","doi":"10.1021/acs.jchemed.9b00072","title":"Writing as a Mode of Learning: Staged Approaches to Chromatography and Writing in the Undergraduate Organic Lab","year":2019,"lang":"en","type":"article","venue":"Journal of Chemical Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Winnipeg; University of Waterloo","funders":"Korea Electrotechnology Research Institute; University of Winnipeg","keywords":"TUTOR; Craft; Scientific writing; Mathematics education; Reflection (computer programming); Process (computing); Professional writing; Computer science; Peer tutor; Report writing; Chemistry; Psychology; Visual arts; Literature; Art; Library science","score_opus":0.03764289474911719,"score_gpt":0.3391362368971839,"score_spread":0.3014933421480667,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2929902524","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.74868876,0.00054149807,0.22940479,0.0011362183,0.00015363938,0.003248499,0.000072003015,0.0006528413,0.016101819],"genre_scores_gemma":[0.5906764,0.00042781146,0.39799598,0.00032376905,0.000036023153,0.0018547138,0.00006207888,0.00007218782,0.008550984],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9870003,0.008850416,0.00045902855,0.00094965316,0.0024002946,0.00034040952],"domain_scores_gemma":[0.97542506,0.015063523,0.0016070118,0.0024180857,0.0028108852,0.002675426],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0108803315,0.00053506554,0.0004349279,0.00095834106,0.0013077635,0.003776974,0.001934191,0.0008308205,0.0021870784],"category_scores_gemma":[0.023108613,0.00043774545,0.00049364474,0.000616707,0.0021831016,0.0014061681,0.0032787337,0.0013928999,0.00055806356],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016640628,0.00497631,0.01077568,0.0008991563,0.00003828098,0.00048635772,0.075463116,0.0035105064,0.10760852,0.008441952,0.002314837,0.78382117],"study_design_scores_gemma":[0.0035110847,0.07641772,0.14599748,0.0020372833,0.0003433859,0.0064722444,0.09071382,0.08051321,0.32117766,0.07876779,0.19287926,0.0011689843],"about_ca_topic_score_codex":0.0005334619,"about_ca_topic_score_gemma":0.0011133676,"teacher_disagreement_score":0.0108803315,"about_ca_system_score_codex":0.0013391759,"about_ca_system_score_gemma":0.004305028,"threshold_uncertainty_score":0.05754143},"labels":[],"label_agreement":null},{"id":"W2930362096","doi":"10.5539/hes.v9n2p117","title":"Using Digital Tools to Assess and Improve College Student Writing","year":2019,"lang":"en","type":"article","venue":"Higher Education Studies","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Formative assessment; Summative assessment; Grading (engineering); Higher education; Computer science; Learning analytics; Workload; Sophistication; Curriculum; Mathematics education; Medical education; Pedagogy; Psychology; Data science; Engineering; Sociology","score_opus":0.1686309663595367,"score_gpt":0.47804219324124064,"score_spread":0.30941122688170397,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2930362096","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8966972,0.00087458,0.04687653,0.0015103123,0.00030201956,0.001321387,0.0014318421,0.0041258507,0.046860296],"genre_scores_gemma":[0.8134748,0.0010688355,0.17086856,0.00030189322,0.00011172387,0.00058865757,0.00087592157,0.0001909509,0.012518706],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9931238,0.002828094,0.00077950093,0.0004596179,0.0025267322,0.00028221877],"domain_scores_gemma":[0.9616479,0.020023584,0.0044170055,0.0027647768,0.009768278,0.0013784647],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007599509,0.0007170478,0.00038116743,0.0069212294,0.0006570159,0.003046815,0.00079909805,0.0004125377,0.0059761875],"category_scores_gemma":[0.049598407,0.00025546804,0.00035357373,0.0032328363,0.0003843441,0.0024271046,0.0017492389,0.0006747915,0.0026408203],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019801584,0.0008103789,0.07632437,0.00017890109,0.00002202779,0.00004499587,0.001244075,0.00037835044,0.0024324923,0.00031201742,0.004721064,0.91333336],"study_design_scores_gemma":[0.00036373525,0.008296106,0.7883959,0.001695871,0.00029232106,0.0010557726,0.020241914,0.022765158,0.05654213,0.0065409006,0.09334637,0.00046389783],"about_ca_topic_score_codex":0.0018023512,"about_ca_topic_score_gemma":0.003808239,"teacher_disagreement_score":0.007599509,"about_ca_system_score_codex":0.00087250676,"about_ca_system_score_gemma":0.001366056,"threshold_uncertainty_score":0.040190518},"labels":[],"label_agreement":null},{"id":"W2930367903","doi":"","title":"Preparing for the exam vs. developing the language proficiency: A washback study on the learners","year":2018,"lang":"en","type":"article","venue":"2019 Conference of the Canadian Society for the Study of Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Mathematics education; Certificate; Psychology; Test (biology); School Certificate; Pedagogy; Focus group; Argument (complex analysis); English language; Medical education; Sociology; Medicine; Mathematics","score_opus":0.06936604890178882,"score_gpt":0.37074523631046336,"score_spread":0.30137918740867453,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2930367903","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9985569,0.00008766799,0.00016372433,0.00013322478,0.0000150301275,0.00007480542,0.000015175483,0.0000052148066,0.00094828964],"genre_scores_gemma":[0.9952036,0.0001800763,0.00052313734,0.00026790734,0.000020999601,0.00024467285,0.000033801436,0.000015765398,0.0035101206],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.99520326,0.0024901738,0.00035411984,0.00042718678,0.0008376418,0.000687582],"domain_scores_gemma":[0.986537,0.008152519,0.0012896749,0.00086190377,0.00197124,0.0011876499],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011756239,0.0008285958,0.0013984332,0.0016752484,0.0045033772,0.0044938317,0.0018210531,0.002011301,0.0041421014],"category_scores_gemma":[0.027726563,0.0006670878,0.00072018505,0.00063370855,0.0034555213,0.0037084755,0.00413635,0.0036638163,0.0009579759],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00068882696,0.0060471445,0.072040565,0.0003606912,0.000033825898,0.0018317497,0.87507415,0.00006831585,0.004997716,0.00064066827,0.00061960175,0.03759677],"study_design_scores_gemma":[0.00007814304,0.0052433047,0.059686642,0.00023423816,0.00004990873,0.0007206764,0.92076606,0.00015711285,0.0043222774,0.00046930453,0.008184319,0.000087930755],"about_ca_topic_score_codex":0.002668104,"about_ca_topic_score_gemma":0.004381569,"teacher_disagreement_score":0.011756239,"about_ca_system_score_codex":0.0016401706,"about_ca_system_score_gemma":0.0016001436,"threshold_uncertainty_score":0.062173665},"labels":[],"label_agreement":null},{"id":"W2935437723","doi":"","title":"Teacher candidates' approaches to assessment: A latent class analysis","year":2019,"lang":"en","type":"article","venue":"2019 Conference of the Canadian Society for the Study of Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Class (philosophy); Context (archaeology); Certification; Psychology; Teacher education; Relevance (law); Pedagogy; Mathematics education; Latent class model; Computer science; Political science","score_opus":0.08837553336067248,"score_gpt":0.3379940463399017,"score_spread":0.2496185129792292,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2935437723","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98998916,0.000035436053,0.007326565,0.00019654476,0.000014698742,0.00033553393,0.00015678494,0.000029579394,0.0019156183],"genre_scores_gemma":[0.9968227,0.000021104433,0.0018190366,0.000012690326,0.000007835435,0.0002538581,0.00025446308,0.0000128467245,0.00079545047],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9863505,0.0063826633,0.00076286035,0.0008784016,0.004114338,0.001511318],"domain_scores_gemma":[0.9832429,0.0069354856,0.003001336,0.0014216165,0.003899431,0.0014992654],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011771923,0.00048468274,0.0007871654,0.0038317828,0.0029396915,0.00418308,0.0011174898,0.00066380895,0.005141494],"category_scores_gemma":[0.029436465,0.00036264764,0.0012025939,0.0022540113,0.001372053,0.0015194671,0.0023093324,0.0013374964,0.0009007903],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011349088,0.0015982457,0.8627068,0.00013417535,0.00019388605,0.00021631779,0.061298728,0.0010494959,0.0020519358,0.005768326,0.0017590253,0.06208814],"study_design_scores_gemma":[0.00018430297,0.0011516422,0.8652999,0.00014969699,0.00012764077,0.0002691695,0.08752672,0.0319945,0.0012625933,0.004696885,0.0071798903,0.0001571896],"about_ca_topic_score_codex":0.007615071,"about_ca_topic_score_gemma":0.0076222024,"teacher_disagreement_score":0.011771923,"about_ca_system_score_codex":0.0017008972,"about_ca_system_score_gemma":0.0027182063,"threshold_uncertainty_score":0.062256575},"labels":[],"label_agreement":null},{"id":"W2941199026","doi":"10.1187/cbe.17-07-0137","title":"Retention following Two-Stage Collaborative Exams Depends on Timing and Student Performance","year":2019,"lang":"en","type":"article","venue":"CBE—Life Sciences Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":22,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Knowledge retention; Retention rate; Retention time; Collaborative learning; Psychology; Content (measure theory); Computer science; Medical education; Mathematics education; Medicine; Chemistry; Mathematics; Chromatography","score_opus":0.042398828372233945,"score_gpt":0.403120116642093,"score_spread":0.36072128826985905,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2941199026","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99532,0.00031782812,0.0019149089,0.00011031558,0.000026285214,0.00006922108,0.00006542524,0.000050898394,0.0021250981],"genre_scores_gemma":[0.99615604,0.00017247949,0.0010518187,0.00005050439,0.000026340784,0.000071142225,0.00016741538,0.000021925252,0.0022823848],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99311066,0.0020686607,0.0007585505,0.0007917182,0.002671119,0.00059933646],"domain_scores_gemma":[0.9082439,0.059045933,0.012476734,0.004971794,0.009683725,0.005577844],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0110328775,0.00052797137,0.00083380414,0.0010020469,0.00056796,0.0019656576,0.0008975446,0.0007853826,0.003214233],"category_scores_gemma":[0.0758766,0.00023266418,0.0007362517,0.0006469276,0.00036058438,0.0008862102,0.0018256666,0.0010930601,0.0011889514],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0042131618,0.006260933,0.44461313,0.000725517,0.0006225156,0.0002615336,0.0055993856,0.0019101404,0.059119176,0.00031115778,0.0013286065,0.47503474],"study_design_scores_gemma":[0.00007140478,0.010547409,0.9653719,0.00013293624,0.00018705975,0.00012212337,0.0010656453,0.0020328143,0.018239846,0.00043196933,0.0017233515,0.00007359922],"about_ca_topic_score_codex":0.001494076,"about_ca_topic_score_gemma":0.0018262741,"teacher_disagreement_score":0.0110328775,"about_ca_system_score_codex":0.00041371776,"about_ca_system_score_gemma":0.0009919027,"threshold_uncertainty_score":0.05834812},"labels":[],"label_agreement":null},{"id":"W2942832874","doi":"10.3138/cmlr.2018-0197","title":"Self-Assessment in the Primary L2 Writing Classroom","year":2019,"lang":"fr","type":"article","venue":"Canadian Modern Language Review/ La Revue canadienne des langues vivantes","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Humanities; Philosophy","score_opus":0.013911688384095337,"score_gpt":0.27811199888622334,"score_spread":0.264200310502128,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2942832874","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9884071,0.00026630596,0.0006323373,0.00027374673,0.000025096739,0.000050190873,0.000014480799,0.00005084002,0.010279801],"genre_scores_gemma":[0.99357396,0.00013715816,0.00056837365,0.00006267927,0.000009571134,0.000044947155,0.000021562795,0.000008803747,0.0055728806],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.9961133,0.0016722477,0.00018083454,0.00058214046,0.00096266036,0.0004888128],"domain_scores_gemma":[0.9908546,0.003002247,0.0012867905,0.00060453406,0.0014051669,0.0028466373],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0035139685,0.00041390143,0.0006177194,0.0011722713,0.0014989354,0.0051425644,0.0007145154,0.0006303834,0.004584754],"category_scores_gemma":[0.009667622,0.0002751647,0.0004067518,0.0005151844,0.0015037382,0.0017606968,0.0025756594,0.0015560212,0.0011192712],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00035598304,0.0062300344,0.46296105,0.0005144202,0.00006984564,0.0009416905,0.2131213,0.00057121593,0.0067619486,0.004386122,0.006087905,0.29799846],"study_design_scores_gemma":[0.00010885621,0.0022934484,0.79912084,0.000447892,0.00006395477,0.0006896716,0.15113685,0.0025262735,0.005940719,0.006084912,0.031429537,0.00015702452],"about_ca_topic_score_codex":0.004666312,"about_ca_topic_score_gemma":0.006919964,"teacher_disagreement_score":0.0051425644,"about_ca_system_score_codex":0.0021309734,"about_ca_system_score_gemma":0.0023553171,"threshold_uncertainty_score":0.018583834},"labels":[],"label_agreement":null},{"id":"W2943008257","doi":"10.55016/ojs/jet.v40i2.52563","title":"Standardized Testing and the Classroom","year":2018,"lang":"en","type":"article","venue":"Journal of educational thought.","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Standardized test; Psychology; Mathematics education; Pedagogy","score_opus":0.04197803242966986,"score_gpt":0.3914393847025016,"score_spread":0.34946135227283176,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2943008257","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.118701845,0.035916217,0.038755663,0.1742585,0.0061889277,0.0002544588,0.00025363237,0.0006808269,0.62498987],"genre_scores_gemma":[0.94014853,0.00696753,0.012509856,0.011650125,0.0011668878,0.0003809548,0.00014646482,0.00012205738,0.026907448],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98477757,0.01107975,0.00043928166,0.0006930942,0.002424496,0.00058578316],"domain_scores_gemma":[0.9758775,0.015651086,0.0016267431,0.0017298012,0.002762985,0.0023518442],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009034224,0.00035981278,0.00040789184,0.0014032798,0.0012889525,0.0040868623,0.0009745822,0.0013106845,0.0077420594],"category_scores_gemma":[0.0473318,0.00016676055,0.00021743534,0.00091782404,0.010310261,0.0033117207,0.0036623634,0.0037673817,0.00087563164],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008526665,0.0006534975,0.011069275,0.0002590695,0.00002180102,0.00042488019,0.015716592,0.00040128795,0.00042959183,0.4686115,0.06122596,0.4411012],"study_design_scores_gemma":[0.00013218944,0.00058087904,0.031249056,0.002029841,0.000017201442,0.001101306,0.025804246,0.0010313895,0.0010049429,0.57752436,0.35945,0.000074642885],"about_ca_topic_score_codex":0.00739727,"about_ca_topic_score_gemma":0.0053101624,"teacher_disagreement_score":0.009034224,"about_ca_system_score_codex":0.0031193618,"about_ca_system_score_gemma":0.0068333945,"threshold_uncertainty_score":0.04777813},"labels":[],"label_agreement":null},{"id":"W2943955341","doi":"10.4300/jgme-d-18-01003.1","title":"Faculty and Resident Perspectives on Using Entrustment Anchors for Workplace-Based Assessment","year":2019,"lang":"en","type":"article","venue":"Journal of Graduate Medical Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":30,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Normative; Medical education; Data collection; Grounded theory; Psychology; Computer science; Medicine; Qualitative research; Sociology; Political science","score_opus":0.07086773104654848,"score_gpt":0.45126005979494244,"score_spread":0.38039232874839396,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2943955341","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97884136,0.00052546035,0.00936592,0.0038850603,0.000081735954,0.00008836888,0.0000337516,0.00012418207,0.007054166],"genre_scores_gemma":[0.99509996,0.00026130344,0.0033239264,0.00032888548,0.000015628377,0.00003713497,0.000014119951,0.000018848456,0.000900304],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9632107,0.0273929,0.0013110555,0.00077858166,0.0053586056,0.0019481424],"domain_scores_gemma":[0.9316652,0.038925357,0.008022024,0.0028771826,0.01249554,0.0060147992],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.03249574,0.00037677257,0.00035440052,0.0011467137,0.0035023503,0.004218916,0.0010311833,0.0010800919,0.0021868537],"category_scores_gemma":[0.07703413,0.00035892,0.00038817103,0.00095179403,0.0036477803,0.0029194772,0.0054991078,0.0018367828,0.00038640437],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002529061,0.00032224017,0.05499475,0.00048399408,0.00003413174,0.0012983574,0.7942001,0.00047993596,0.005275619,0.0026066704,0.0032946516,0.1367566],"study_design_scores_gemma":[0.000029986675,0.0014974126,0.04278694,0.0008462923,0.00005607134,0.001500011,0.8826125,0.0013974442,0.0062728208,0.0025427162,0.060258158,0.00019954346],"about_ca_topic_score_codex":0.0038545541,"about_ca_topic_score_gemma":0.0071220794,"teacher_disagreement_score":0.96750426,"about_ca_system_score_codex":0.0029575373,"about_ca_system_score_gemma":0.006049781,"threshold_uncertainty_score":0.17185593},"labels":[],"label_agreement":null},{"id":"W2945827673","doi":"10.31542/r.gm:1624","title":"Effects of feedback templates on student performance","year":2018,"lang":"en","type":"dissertation","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"MacEwan University","funders":"","keywords":"Template; Feedback control; Computer science; Control (management); Work (physics); Artificial intelligence; Engineering; Control engineering; Programming language","score_opus":0.014219661856784999,"score_gpt":0.3529219634070954,"score_spread":0.33870230155031045,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2945827673","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9958591,0.000144347,0.00097045983,0.00014967844,0.0000974043,0.00025802694,0.000115170966,0.00022699896,0.0021789302],"genre_scores_gemma":[0.99543864,0.00007343795,0.0025425146,0.000060019993,0.00004412945,0.0004197616,0.00017472637,0.00005900371,0.0011878175],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9721531,0.013828825,0.0032417262,0.0024856634,0.0070881275,0.0012024796],"domain_scores_gemma":[0.5969298,0.31126305,0.039853826,0.015290202,0.014544985,0.022118064],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.017369738,0.001173303,0.0010707976,0.0010523214,0.00062556576,0.0025493854,0.0012157081,0.0015392496,0.0036352386],"category_scores_gemma":[0.2150257,0.0005506182,0.00080274424,0.00073697267,0.0006336663,0.0012877678,0.0018228672,0.0014695592,0.000932851],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.071879,0.032223,0.38280052,0.0014016285,0.0012308878,0.00043664384,0.006370228,0.013517169,0.030694325,0.00092311803,0.004456412,0.45406708],"study_design_scores_gemma":[0.0030720844,0.07712786,0.87543684,0.0005419542,0.00086562254,0.00024740002,0.0013453929,0.017479863,0.017594572,0.0015269517,0.004428379,0.00033304366],"about_ca_topic_score_codex":0.0011953128,"about_ca_topic_score_gemma":0.0012160607,"teacher_disagreement_score":0.017369738,"about_ca_system_score_codex":0.0010154417,"about_ca_system_score_gemma":0.0016352354,"threshold_uncertainty_score":0.09186101},"labels":[],"label_agreement":null},{"id":"W2946729216","doi":"10.55016/ojs/jet.v51i2.58451","title":"Alberta’s New Teaching Quality Standard and Its Implications for Teacher Education","year":2019,"lang":"en","type":"article","venue":"Journal of educational thought.","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Quality (philosophy); Teacher quality; Psychology; Mathematics education; Pedagogy; Epistemology; Economics; Operations management; Philosophy","score_opus":0.05178738373696707,"score_gpt":0.4593764704320529,"score_spread":0.4075890866950858,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2946729216","genre_codex":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.060430378,0.009285766,0.012378182,0.715064,0.0044602123,0.0001810324,0.0012965921,0.0005176434,0.19638617],"genre_scores_gemma":[0.78363204,0.0065654786,0.038785663,0.081429265,0.0010163888,0.00017260507,0.0012495675,0.00014870804,0.087000325],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9769711,0.0027377768,0.00068875006,0.001320368,0.014992605,0.0032893168],"domain_scores_gemma":[0.96927816,0.0066734506,0.0012173346,0.0011722713,0.016488092,0.00517072],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.016065083,0.00033824344,0.00040308133,0.0019802717,0.008346491,0.010334467,0.0028283831,0.003551961,0.0035121276],"category_scores_gemma":[0.028021336,0.00037309286,0.0007326171,0.0031186205,0.008757197,0.0022718452,0.0033203647,0.0056842035,0.0002675744],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019304227,0.00019596225,0.029733527,0.00044636606,0.000046686615,0.00044031793,0.0075196666,0.0069782194,0.00198298,0.61649626,0.20041838,0.1355486],"study_design_scores_gemma":[0.00007920354,0.00014184964,0.105509885,0.0008017593,0.000062174215,0.00015583012,0.010594156,0.0039326935,0.0013665251,0.0636928,0.81340814,0.00025499184],"about_ca_topic_score_codex":0.98421836,"about_ca_topic_score_gemma":0.98911184,"teacher_disagreement_score":0.17386673,"about_ca_system_score_codex":0.17386673,"about_ca_system_score_gemma":0.33143374,"threshold_uncertainty_score":0.9581975},"labels":[],"label_agreement":null},{"id":"W2948214676","doi":"10.1002/9781118784235.eelt0321","title":"Preparing Students to Take Tests","year":2018,"lang":"en","type":"other","venue":"The TESOL Encyclopedia of English Language Teaching","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Test (biology); Context (archaeology); Mathematics education; Test preparation; Academic achievement; Student achievement; Psychology; Achievement test; Scale (ratio); Empirical research; Teacher preparation; Pedagogy; Medical education; Standardized test; Teacher education; Engineering; Medicine; Mathematics","score_opus":0.011415522042493593,"score_gpt":0.33989004920855964,"score_spread":0.32847452716606607,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2948214676","genre_codex":"empirical","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6188783,0.0010300472,0.062249966,0.012267007,0.001879423,0.0047132852,0.0018831316,0.0064681065,0.2906307],"genre_scores_gemma":[0.6912468,0.0016423145,0.12648733,0.003400854,0.00040037377,0.0024568378,0.003224261,0.0009912229,0.17015],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9972683,0.00071306515,0.00019855754,0.0002827543,0.00111572,0.00042159652],"domain_scores_gemma":[0.990195,0.0017281964,0.0009654668,0.0010086336,0.0034981247,0.0026045858],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0033731482,0.00067215966,0.00054570637,0.0011941168,0.0011334713,0.0032876595,0.0016015711,0.0009739445,0.021933693],"category_scores_gemma":[0.022437278,0.00025491064,0.00049040397,0.00058139,0.0004779848,0.001371752,0.0023287847,0.002110019,0.019541655],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017357609,0.0020808594,0.03779118,0.00032946965,0.000012807947,0.00058415544,0.008477094,0.00078679726,0.014567479,0.008022553,0.104831636,0.8223424],"study_design_scores_gemma":[0.00010412659,0.003033647,0.14103477,0.00087476295,0.00004551493,0.0018733783,0.020733016,0.0021170871,0.0457808,0.024906516,0.75925505,0.00024131854],"about_ca_topic_score_codex":0.00062500796,"about_ca_topic_score_gemma":0.0014156827,"teacher_disagreement_score":0.021933693,"about_ca_system_score_codex":0.0007917925,"about_ca_system_score_gemma":0.0030859695,"threshold_uncertainty_score":0.07337552},"labels":[],"label_agreement":null},{"id":"W2948450036","doi":"10.11575/pplt.v3i1.53146","title":"Conversations and Perspectives on Peer Feedback for Problem Solving","year":2018,"lang":"en","type":"article","venue":"University of Calgary","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Conversation; Peer feedback; Session (web analytics); Leverage (statistics); Computer science; Context (archaeology); Peer review; Mathematics education; Psychology; Pedagogy; World Wide Web; Artificial intelligence; Political science","score_opus":0.028446742653643012,"score_gpt":0.2801169388451335,"score_spread":0.2516701961914905,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2948450036","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.30270562,0.038579863,0.07695834,0.28771275,0.0061964835,0.00039423493,0.00018727595,0.0003609067,0.28690454],"genre_scores_gemma":[0.9784279,0.005967193,0.004929185,0.003443077,0.0011443207,0.0001827574,0.000027667655,0.00018248745,0.0056953635],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.8163312,0.16554485,0.0018977271,0.0025317883,0.009771434,0.003922979],"domain_scores_gemma":[0.797061,0.17428027,0.0067901467,0.004020181,0.012653327,0.0051950812],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.060631033,0.0012635787,0.0008723817,0.0038031896,0.01871155,0.01751164,0.0023933083,0.0069389967,0.002934568],"category_scores_gemma":[0.127211,0.00052991015,0.00084533845,0.0026924862,0.030678933,0.015859675,0.013793296,0.012023358,0.00049969315],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000049214043,0.00002414884,0.0005373807,0.00025631904,0.000014297553,0.00070369185,0.90746254,0.00017588044,0.0004958214,0.073877506,0.0031352881,0.013267982],"study_design_scores_gemma":[0.000020982054,0.00013983615,0.0015370386,0.0013792536,0.000023600458,0.0012623986,0.6932673,0.0007926399,0.0010698215,0.035716604,0.2647132,0.00007733098],"about_ca_topic_score_codex":0.0038089172,"about_ca_topic_score_gemma":0.003197441,"teacher_disagreement_score":0.060631033,"about_ca_system_score_codex":0.008096437,"about_ca_system_score_gemma":0.0071789105,"threshold_uncertainty_score":0.3206514},"labels":[],"label_agreement":null},{"id":"W2952420433","doi":"10.21083/ajote.v7i3.4325","title":"FORMATIVE ASSESSMENT PRACTICES AMONG DISTANCE EDUCATION TUTORS IN GHANA","year":2018,"lang":"en","type":"article","venue":"African Journal of Teacher Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Formative assessment; TUTOR; Knowledge survey; Medical education; Data collection; Test (biology); Psychology; Mathematics education; Medicine; Summative assessment; Statistics; Mathematics","score_opus":0.028596621851778078,"score_gpt":0.41710532518256394,"score_spread":0.38850870333078585,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2952420433","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9963863,0.00074159645,0.0013949143,0.0002683534,0.000022045233,0.000080476006,0.00002471922,0.00004419826,0.0010374659],"genre_scores_gemma":[0.996181,0.0004582069,0.0021035396,0.00010031842,0.00001102199,0.00003770464,0.000022513934,0.000008040339,0.0010777103],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9932454,0.003981242,0.0007362208,0.00045675292,0.0013026964,0.00027773515],"domain_scores_gemma":[0.9700455,0.012797634,0.006054455,0.0018395898,0.007020853,0.0022419256],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006969724,0.00021362014,0.00036884518,0.0011906315,0.00092082814,0.0015021926,0.0007477914,0.0005200449,0.0014643136],"category_scores_gemma":[0.043605115,0.0002068309,0.00015726253,0.0009119058,0.0005803024,0.0010913678,0.0012392929,0.00044651923,0.0003223403],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003030212,0.0008130908,0.5034075,0.0005882531,0.000034627465,0.001942725,0.16276273,0.0003350221,0.01020418,0.000330587,0.001073652,0.31820455],"study_design_scores_gemma":[0.000101378464,0.006614156,0.6341497,0.0016020637,0.00012148454,0.008486793,0.28609195,0.0030436842,0.014063525,0.0014571704,0.044082902,0.00018515473],"about_ca_topic_score_codex":0.0013156214,"about_ca_topic_score_gemma":0.0026846053,"teacher_disagreement_score":0.006969724,"about_ca_system_score_codex":0.0010497861,"about_ca_system_score_gemma":0.0014311738,"threshold_uncertainty_score":0.03685987},"labels":[],"label_agreement":null},{"id":"W2954027589","doi":"10.7202/1071418ar","title":"Beyond the Competencies Agenda in Large-Scale International Assessments: A Confucian Alternative","year":2020,"lang":"en","type":"article","venue":"Philosophical Inquiry in Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Competence (human resources); Judgement; Rationality; Sociology; Epistemology; Social psychology; Psychology; Pedagogy","score_opus":0.11006403246162254,"score_gpt":0.42963915418185183,"score_spread":0.3195751217202293,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2954027589","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.039870977,0.006242126,0.25578907,0.11994139,0.0012226765,0.00020026304,0.000089529945,0.00014259048,0.57650137],"genre_scores_gemma":[0.9453747,0.0013718548,0.038379744,0.0058784396,0.00073488103,0.0003970239,0.000039674553,0.000106692576,0.0077168276],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9569389,0.029606672,0.0015643481,0.003265086,0.0073216497,0.0013034028],"domain_scores_gemma":[0.9617946,0.020949105,0.0026332166,0.006045206,0.0071687484,0.0014091025],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.037841942,0.0010414138,0.001035327,0.0038731382,0.0044828146,0.014346689,0.0023383119,0.005174315,0.0031292066],"category_scores_gemma":[0.051971193,0.00041733385,0.0006821381,0.0034183152,0.07143152,0.024944833,0.01170995,0.010891981,0.0006791963],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000063561743,0.0000060053494,0.000109797256,0.000017138267,0.0000016172384,0.000015372534,0.002203386,0.00014180677,0.0000187066,0.9927477,0.00034126575,0.0043907994],"study_design_scores_gemma":[0.0000098957535,0.000019921365,0.00030745676,0.00018797717,0.0000030336082,0.00004673997,0.0029119877,0.00097502995,0.00009147081,0.9704165,0.025015539,0.000014556571],"about_ca_topic_score_codex":0.0065536047,"about_ca_topic_score_gemma":0.004690668,"teacher_disagreement_score":0.037841942,"about_ca_system_score_codex":0.008200392,"about_ca_system_score_gemma":0.006806903,"threshold_uncertainty_score":0.20012975},"labels":[],"label_agreement":null},{"id":"W2954748270","doi":"10.1117/12.2523795","title":"Error detection tasks and peer feedback for engaging physics students","year":2019,"lang":"en","type":"article","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dawson College; John Abbott College; Vanier College","funders":"","keywords":"Peer instruction; Peer feedback; Asynchronous communication; Computer science; Class (philosophy); Peer-to-peer; Error detection and correction; Control (management); Peer assessment; Mathematics education; Multimedia; World Wide Web; Artificial intelligence; Algorithm; Psychology","score_opus":0.03869756151750285,"score_gpt":0.37844820519967604,"score_spread":0.33975064368217317,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2954748270","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92659324,0.00020814194,0.0633563,0.00036571914,0.00015121291,0.0009821316,0.00014351409,0.0015416129,0.006658132],"genre_scores_gemma":[0.90962803,0.00016919083,0.08500825,0.00013659391,0.0000658668,0.0011158506,0.00023792204,0.00013095868,0.003507363],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9919917,0.0040821233,0.0005733305,0.0008473151,0.0020794433,0.00042618724],"domain_scores_gemma":[0.9471185,0.03855684,0.004200734,0.0034645307,0.0034965416,0.0031627598],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0056185364,0.0011819787,0.00085549464,0.001185027,0.0005954385,0.0013689884,0.0012702777,0.0011965015,0.004515701],"category_scores_gemma":[0.057890356,0.00028801244,0.00045664815,0.00043996138,0.0005834425,0.0016101013,0.0025608235,0.0011767593,0.0011378061],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0034921004,0.017547876,0.032803964,0.0014836678,0.00013326161,0.00056595827,0.009045144,0.00783247,0.057165153,0.0013923481,0.0060652136,0.8624729],"study_design_scores_gemma":[0.00340991,0.08262134,0.35993686,0.0014732223,0.00055594905,0.0045908466,0.009769905,0.16948874,0.278363,0.020647218,0.06810082,0.0010422235],"about_ca_topic_score_codex":0.0006160479,"about_ca_topic_score_gemma":0.000933036,"teacher_disagreement_score":0.0056185364,"about_ca_system_score_codex":0.00042141837,"about_ca_system_score_gemma":0.0010350039,"threshold_uncertainty_score":0.029714048},"labels":[],"label_agreement":null},{"id":"W2956152746","doi":"10.1109/icse-companion.2019.00103","title":"Comparing the Popularity of Testing Careers Among Canadian, Chinese, and Indian Students","year":2019,"lang":"en","type":"article","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Western University","funders":"","keywords":"Popularity; Dimension (graph theory); Relevance (law); Vitality; Human Dimension; Software; Process (computing); Focus (optics)","score_opus":0.03566238364825517,"score_gpt":0.3338372350683909,"score_spread":0.2981748514201357,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2956152746","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99146336,0.00040183988,0.000057511763,0.0011192731,0.000044300905,0.000017898055,0.00041892464,0.000017772836,0.0064590015],"genre_scores_gemma":[0.9965546,0.00031191207,0.000060319584,0.00014858549,0.000016931772,0.000008430457,0.0001960111,0.000010396711,0.0026926878],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99780065,0.00019452065,0.00009652751,0.0001730614,0.00082591525,0.0009092414],"domain_scores_gemma":[0.98354614,0.0018313398,0.0028007783,0.00030932904,0.0046425364,0.006869873],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018692493,0.00025481175,0.00029832884,0.004881867,0.003701011,0.0026071537,0.001353713,0.00076871115,0.005784597],"category_scores_gemma":[0.010281254,0.00019808595,0.00042471616,0.004770384,0.0016911888,0.0009580275,0.0012861437,0.0013378666,0.0007321837],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010426887,0.00010694583,0.947617,0.0000540503,0.000016183589,0.000192616,0.022303842,0.00004803983,0.0002785777,0.0007033372,0.002964346,0.02561085],"study_design_scores_gemma":[0.0000034839773,0.00006137744,0.95829326,0.0000553149,0.000009974945,0.00011819681,0.037408844,0.00019280541,0.0000912246,0.00006620232,0.0036682982,0.000031032338],"about_ca_topic_score_codex":0.71185845,"about_ca_topic_score_gemma":0.80634934,"teacher_disagreement_score":0.71185845,"about_ca_system_score_codex":0.007506218,"about_ca_system_score_gemma":0.012544264,"threshold_uncertainty_score":0.5796769},"labels":[],"label_agreement":null},{"id":"W2967888896","doi":"10.1186/s40468-019-0089-4","title":"Critical review of validation models and practices in language testing: their limitations and future directions for validation research","year":2019,"lang":"en","type":"article","venue":"Language Testing in Asia","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":46,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Argument (complex analysis); Empirical research; Construct (python library); Computer science; Test (biology); Construct validity; Language assessment; Management science; Psychology; Data science; Psychometrics; Statistics; Mathematics education; Mathematics; Engineering","score_opus":0.2871225134574545,"score_gpt":0.4973541369068704,"score_spread":0.21023162344941593,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2967888896","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0048391228,0.8135438,0.043423664,0.114996694,0.010075686,0.0022562377,0.0004166136,0.0002141802,0.010233916],"genre_scores_gemma":[0.1050491,0.73127675,0.10563485,0.04156501,0.005088027,0.008264305,0.00066071353,0.0004891545,0.0019721275],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.5562592,0.31613237,0.06128142,0.008355281,0.055803195,0.00216854],"domain_scores_gemma":[0.11774201,0.70557404,0.027631246,0.023806734,0.123523556,0.0017224522],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.447146,0.0019351265,0.0044118306,0.03158281,0.005530765,0.015263579,0.006665227,0.00573032,0.0032001443],"category_scores_gemma":[0.7135997,0.001975636,0.0038540876,0.023809375,0.016306981,0.023742698,0.007797544,0.010353054,0.0013213954],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026552155,0.00009912292,0.0032671406,0.1231972,0.0009448603,0.00045379682,0.03095689,0.0008516443,0.00060319743,0.09072774,0.0700017,0.67863125],"study_design_scores_gemma":[0.00012051671,0.00021786032,0.0040289257,0.47346228,0.0013057304,0.0006501459,0.019912424,0.001425595,0.0016883989,0.054177996,0.44277218,0.00023788032],"about_ca_topic_score_codex":0.008780839,"about_ca_topic_score_gemma":0.00958327,"teacher_disagreement_score":0.552854,"about_ca_system_score_codex":0.022100002,"about_ca_system_score_gemma":0.06731454,"threshold_uncertainty_score":0.68176746},"labels":[],"label_agreement":null},{"id":"W2969685073","doi":"10.3389/feduc.2019.00094","title":"Toward a Differential and Situated View of Assessment Literacy: Studying Teachers' Responses to Classroom Assessment Scenarios","year":2019,"lang":"en","type":"article","venue":"Frontiers in Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":44,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Situated; Literacy; Mathematics education; Situated learning; Computer science; Pedagogy; Psychology; Artificial intelligence","score_opus":0.022140024713449183,"score_gpt":0.3697810083821209,"score_spread":0.34764098366867174,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2969685073","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98756635,0.00009301856,0.00914063,0.00035684262,0.000009172289,0.000072313094,0.00002601472,0.000024243736,0.0027113934],"genre_scores_gemma":[0.9973124,0.00009001076,0.0020748537,0.000050828345,0.000003098737,0.00007090858,0.000027277065,0.000007665551,0.0003629562],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.978144,0.016778165,0.0012164742,0.0011763988,0.0019944527,0.0006904163],"domain_scores_gemma":[0.9370636,0.050894227,0.0059141517,0.0021674884,0.0026892778,0.0012713295],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0097453445,0.00040040986,0.0005277447,0.0017665025,0.0019017308,0.0039238464,0.0008902191,0.0017086042,0.0012696824],"category_scores_gemma":[0.07652348,0.00049189833,0.00040752185,0.0009226011,0.0037109163,0.0038664737,0.0048105856,0.0020325137,0.00028991033],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014435747,0.00013646223,0.07657654,0.00022119335,0.00002675262,0.00089598005,0.8875366,0.0008986452,0.0065086535,0.0029302798,0.000286784,0.023837725],"study_design_scores_gemma":[0.000021840942,0.0003499984,0.060238384,0.0002606835,0.000021835922,0.0015374059,0.9140701,0.003841049,0.0036258998,0.006302823,0.009597299,0.0001327698],"about_ca_topic_score_codex":0.0015392834,"about_ca_topic_score_gemma":0.002455323,"teacher_disagreement_score":0.0097453445,"about_ca_system_score_codex":0.0013482538,"about_ca_system_score_gemma":0.0011009008,"threshold_uncertainty_score":0.051538944},"labels":[],"label_agreement":null},{"id":"W2969964033","doi":"10.1111/jedm.12237","title":"Students’ Interpretation of Formative Assessment Feedback: Three Claims for Why We Know So Little About Something So Important","year":2019,"lang":"en","type":"article","venue":"Journal of Educational Measurement","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":45,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Formative assessment; Psychology; Interpretation (philosophy); Cognition; Process (computing); Mathematics education; Cognitive psychology; Computer science","score_opus":0.044221159940934986,"score_gpt":0.39151100053294274,"score_spread":0.34728984059200774,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2969964033","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7810838,0.0038344292,0.07590194,0.11321128,0.0011800526,0.00031016622,0.00010309841,0.00037771874,0.023997579],"genre_scores_gemma":[0.9909039,0.00038403049,0.0049053784,0.003014287,0.00008412426,0.00012920407,0.00001925099,0.000031066458,0.00052877615],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.82357866,0.104013816,0.014593094,0.007272645,0.047078315,0.003463482],"domain_scores_gemma":[0.39959356,0.44673845,0.054775428,0.04046233,0.05357383,0.004856498],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.16298364,0.00087573676,0.0012022514,0.0032321804,0.0031632232,0.011701284,0.004797573,0.006133221,0.0016648823],"category_scores_gemma":[0.45110956,0.0009209597,0.00111679,0.0016323373,0.037860185,0.012059464,0.009296358,0.009498495,0.00039989545],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014448323,0.0006019319,0.090501696,0.0015757732,0.00031123517,0.0007102685,0.70345336,0.00057890895,0.003211124,0.06146973,0.004617074,0.13152416],"study_design_scores_gemma":[0.00042704245,0.0018583636,0.08856123,0.006809203,0.0005060669,0.0023560068,0.51605445,0.010410075,0.018067623,0.3194277,0.0346782,0.00084399804],"about_ca_topic_score_codex":0.0020134193,"about_ca_topic_score_gemma":0.002004466,"teacher_disagreement_score":0.16298364,"about_ca_system_score_codex":0.0054032393,"about_ca_system_score_gemma":0.006995072,"threshold_uncertainty_score":0.86195016},"labels":[],"label_agreement":null},{"id":"W2970699927","doi":"10.5539/ells.v9n3p20","title":"Investigating Chinese EFL College Students’ Writing Through the Web-Automatic Writing Evaluation Program","year":2019,"lang":"en","type":"article","venue":"English Language and Literature Studies","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Sichuan University","keywords":"Spelling; Punctuation; Grammar; Vocabulary; Mathematics education; Computer science; Psychology; Linguistics; Artificial intelligence","score_opus":0.019044630644175522,"score_gpt":0.38818521807161305,"score_spread":0.36914058742743755,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2970699927","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.998285,0.000015866206,0.00036747076,0.00002869431,0.000003908756,0.00008065951,0.000048528,0.000022157326,0.0011476559],"genre_scores_gemma":[0.99394727,0.000055894863,0.0027059722,0.000043525815,0.000009307232,0.00022960031,0.00018141154,0.000011572327,0.0028152554],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99831307,0.0005512799,0.00022709505,0.00026593637,0.0004895775,0.00015306157],"domain_scores_gemma":[0.99219704,0.0024993569,0.0010060011,0.0005216878,0.0030391135,0.0007369237],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0032244101,0.00042777698,0.00036505595,0.0013643177,0.00065541896,0.0008698384,0.00044798,0.00034196774,0.002481866],"category_scores_gemma":[0.010464928,0.00015424156,0.00021660022,0.00086330634,0.00034441098,0.0008006251,0.00091012067,0.00045849578,0.0005806056],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005459285,0.0048119216,0.5118322,0.00057353673,0.00006075085,0.00070619857,0.04188354,0.0007305055,0.02411747,0.00043929942,0.0029908621,0.4113078],"study_design_scores_gemma":[0.00009672,0.0020881004,0.9536911,0.00007108335,0.00006308732,0.00027277163,0.019317597,0.0051202225,0.013095243,0.00036562822,0.005746676,0.000071739996],"about_ca_topic_score_codex":0.0027274885,"about_ca_topic_score_gemma":0.0059620524,"teacher_disagreement_score":0.0032244101,"about_ca_system_score_codex":0.0005231961,"about_ca_system_score_gemma":0.0011127674,"threshold_uncertainty_score":0.017052531},"labels":[],"label_agreement":null},{"id":"W2975545495","doi":"10.1080/10627197.2019.1670056","title":"Toward a Teacher Professional Learning Continuum in Assessment for Learning","year":2019,"lang":"en","type":"article","venue":"Educational Assessment","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":52,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Council of Ministers of Education; Queen's University","funders":"","keywords":"Mathematics education; Assessment for learning; Professional learning community; Psychology; Pedagogy; Professional development; Observational study; Empirical research; Epistemology; Mathematics; Formative assessment","score_opus":0.033801063854011035,"score_gpt":0.43057365010553394,"score_spread":0.3967725862515229,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2975545495","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.87484074,0.00051947124,0.06165882,0.012097061,0.000076058735,0.00040146758,0.00008001733,0.00037850227,0.049947884],"genre_scores_gemma":[0.9613699,0.0001060921,0.035403416,0.0004674648,0.000012141065,0.00022968161,0.000037454396,0.00003789091,0.0023359794],"study_design_codex":"qualitative","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9834599,0.009704266,0.0011398343,0.0012342974,0.0035096314,0.00095216656],"domain_scores_gemma":[0.96588945,0.015916003,0.00351245,0.0038391289,0.006361803,0.0044812365],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.017388906,0.00016276124,0.0002504753,0.0017457985,0.0040564546,0.008004634,0.0011553685,0.0016953044,0.0016640059],"category_scores_gemma":[0.032350212,0.0005196913,0.0002965005,0.0011026826,0.007727739,0.006788302,0.008038673,0.0043521896,0.00073528057],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018791339,0.0013222891,0.117604285,0.0004200417,0.000014224592,0.0017761218,0.5055659,0.001008339,0.0114137065,0.1326165,0.0031841742,0.22488657],"study_design_scores_gemma":[0.000109951194,0.0010138722,0.15712236,0.00081468705,0.000009832429,0.004280857,0.49639496,0.0070038624,0.007870055,0.19565524,0.12954569,0.00017868895],"about_ca_topic_score_codex":0.0020043594,"about_ca_topic_score_gemma":0.0036081276,"teacher_disagreement_score":0.017388906,"about_ca_system_score_codex":0.0050151953,"about_ca_system_score_gemma":0.010427457,"threshold_uncertainty_score":0.09196246},"labels":[],"label_agreement":null},{"id":"W2975877382","doi":"10.1080/0142159x.2019.1656804","title":"Meaningful feedback through a sociocultural lens","year":2019,"lang":"en","type":"article","venue":"Medical Teacher","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":52,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"The Wilson Centre; University of Toronto","funders":"","keywords":"Sociocultural evolution; Set (abstract data type); Psychology; Sociocultural perspective; Perspective (graphical); Politeness; Pedagogy; Mathematics education; Sociology; Computer science; Political science","score_opus":0.04063133680797009,"score_gpt":0.3572131293742551,"score_spread":0.316581792566285,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2975877382","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.018869456,0.021502392,0.39888054,0.14442345,0.005547242,0.0011012566,0.00025754396,0.001954085,0.4074641],"genre_scores_gemma":[0.5237107,0.025989717,0.33524728,0.017205276,0.0023909085,0.0036259324,0.00020923017,0.0011260759,0.090494804],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.9607601,0.031718887,0.0016335075,0.0007130239,0.0041867234,0.0009877022],"domain_scores_gemma":[0.9730907,0.019289192,0.0010830146,0.0016573465,0.0031229854,0.0017567833],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.026961273,0.002321883,0.00080258056,0.005174553,0.008147104,0.01676667,0.003050306,0.0053675943,0.008877319],"category_scores_gemma":[0.02819227,0.00071896135,0.00095481315,0.002119348,0.024525167,0.019469302,0.014225233,0.008429186,0.002242805],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004464337,0.00012820393,0.0005443901,0.0010075244,0.00001358726,0.0008513433,0.18268321,0.0006476499,0.001737529,0.68849444,0.020856824,0.102990605],"study_design_scores_gemma":[0.000013705664,0.000099864,0.0004551148,0.0022524574,0.000010208835,0.0006293129,0.100756295,0.0006465728,0.0011952082,0.15965609,0.7342404,0.0000447368],"about_ca_topic_score_codex":0.0030745745,"about_ca_topic_score_gemma":0.00575592,"teacher_disagreement_score":0.026961273,"about_ca_system_score_codex":0.00623104,"about_ca_system_score_gemma":0.010326997,"threshold_uncertainty_score":0.14258653},"labels":[],"label_agreement":null},{"id":"W2979056522","doi":"10.18806/tesl.v36i1.1308","title":"Sitting at 6.5: Problematizing IELTS and Admissions to Canadian Universities","year":2019,"lang":"en","type":"article","venue":"TESL Canada Journal","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"University of British Columbia; University of Prince Edward Island; University of Ontario Institute of Technology; University of Northern British Columbia","keywords":"Humanities; Psychology; Curriculum; Library science; Pedagogy; Philosophy; Computer science","score_opus":0.011861015996786954,"score_gpt":0.27159693781048505,"score_spread":0.2597359218136981,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2979056522","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.54039896,0.0035593966,0.010019562,0.16304961,0.0033591783,0.0012608037,0.006270088,0.0015297026,0.2705527],"genre_scores_gemma":[0.92276263,0.0019460968,0.015748097,0.007823244,0.00032225976,0.00023551432,0.0031417308,0.00045008902,0.04757028],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9551843,0.005594381,0.0026249457,0.00200911,0.025429005,0.009158301],"domain_scores_gemma":[0.89308906,0.011579627,0.0068730693,0.0021950759,0.066368386,0.019894762],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.022054663,0.0007789559,0.000916353,0.009225988,0.019980567,0.016453924,0.005525037,0.002260032,0.013130531],"category_scores_gemma":[0.11573942,0.00078863633,0.0012978313,0.01231348,0.005263291,0.0048699216,0.008659142,0.0058986996,0.0026055225],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.00037582693,0.00029011926,0.29192302,0.00051477394,0.000104819606,0.0010871439,0.06071092,0.0021458818,0.0010460975,0.03008077,0.25427252,0.35744804],"study_design_scores_gemma":[0.000055195662,0.00020066908,0.4955202,0.001433468,0.000107981,0.00036906844,0.1891293,0.0061388374,0.0018673957,0.011548936,0.29275262,0.0008763925],"about_ca_topic_score_codex":0.9737552,"about_ca_topic_score_gemma":0.98528314,"teacher_disagreement_score":0.85454524,"about_ca_system_score_codex":0.14545476,"about_ca_system_score_gemma":0.16937377,"threshold_uncertainty_score":0.99115133},"labels":[],"label_agreement":null},{"id":"W2979335464","doi":"10.31468/cjsdwr.737","title":"Reflecting on Assessment: Strategies and Tools for Measuring the Impact of a Canadian WAC Program","year":2019,"lang":"en","type":"article","venue":"Discourse and Writing/Rédactologie","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Writing assessment; Exposition (narrative); Context (archaeology); Variety (cybernetics); Process (computing); Computer science; Engineering ethics; Reflection (computer programming); Engineering management; Pedagogy; Engineering; Sociology; Artificial intelligence; History","score_opus":0.27463465058214864,"score_gpt":0.5338785316821187,"score_spread":0.2592438810999701,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2979335464","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6420145,0.0011384579,0.17084748,0.0026894938,0.00028714974,0.020187017,0.002903087,0.0034328639,0.15649997],"genre_scores_gemma":[0.5785301,0.0011353801,0.39466366,0.00032390334,0.000042444874,0.010112471,0.0011471659,0.00027889424,0.013765987],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9587576,0.012721857,0.0028296148,0.0016051978,0.022544092,0.0015416249],"domain_scores_gemma":[0.93434966,0.017359344,0.0064934907,0.0038376593,0.03454018,0.0034196628],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03369981,0.001517591,0.0008375527,0.015111589,0.0052934517,0.005948291,0.0030329016,0.0009905933,0.0031181076],"category_scores_gemma":[0.09140019,0.00056935137,0.00072394527,0.009108273,0.00238492,0.002674569,0.0054305275,0.0021045853,0.0009574326],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000156125,0.00052381225,0.12141026,0.0008714658,0.00006433159,0.00017214597,0.048568174,0.0015437771,0.008482665,0.0066816933,0.0063284407,0.8051971],"study_design_scores_gemma":[0.00011801289,0.001822612,0.7215925,0.0017422596,0.00026451398,0.00039828932,0.09775471,0.016706921,0.028272886,0.008660306,0.12194037,0.0007266564],"about_ca_topic_score_codex":0.3992654,"about_ca_topic_score_gemma":0.561711,"teacher_disagreement_score":0.6007346,"about_ca_system_score_codex":0.01589696,"about_ca_system_score_gemma":0.03651832,"threshold_uncertainty_score":0.79388285},"labels":[],"label_agreement":null},{"id":"W2980323187","doi":"10.26855/er.2018.09.002","title":"A Brief Review of Washback Studies in the South Asian Countries","year":2018,"lang":"en","type":"review","venue":"The Educational Review USA","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"South asia; Sri lanka; Test (biology); Political science; Psychology; Sociology; Ecology","score_opus":0.20937722329914993,"score_gpt":0.5278685289246098,"score_spread":0.31849130562545985,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2980323187","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0003142173,0.99851733,0.0000470002,0.00039829823,0.00012065167,0.000019434437,0.00004039286,0.0000025687402,0.00054007984],"genre_scores_gemma":[0.0022084517,0.99717426,0.00013375629,0.00025668828,0.0000613608,0.000026271498,0.000027194332,0.0000013984532,0.00011063699],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.9970817,0.0010403997,0.0009183938,0.00025450176,0.0005947912,0.000110115805],"domain_scores_gemma":[0.9833945,0.01238675,0.0016807825,0.000223434,0.00207554,0.0002388934],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0051867277,0.0010095619,0.001775454,0.008560892,0.0007992339,0.0025184625,0.0012646569,0.001269579,0.0044417074],"category_scores_gemma":[0.019718094,0.000578638,0.0017624233,0.010619535,0.0010164977,0.0023910122,0.0013581436,0.00145977,0.0005672849],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012037877,0.00008243167,0.0016443018,0.3770459,0.00075924944,0.0003767953,0.0024825106,0.00020460565,0.00037821033,0.0033782932,0.016546456,0.5969808],"study_design_scores_gemma":[0.00003150957,0.0002244588,0.0100755505,0.41240913,0.0023994516,0.0014122041,0.0033498323,0.000067477005,0.00046873002,0.0013278183,0.5681745,0.000059341048],"about_ca_topic_score_codex":0.009321031,"about_ca_topic_score_gemma":0.01970323,"teacher_disagreement_score":0.009321031,"about_ca_system_score_codex":0.0024648916,"about_ca_system_score_gemma":0.010367451,"threshold_uncertainty_score":0.027430356},"labels":[],"label_agreement":null},{"id":"W2980647847","doi":"10.4102/sajce.v9i1.739","title":"Formative assessment as ‘formative pedagogy’ in Grade 3 mathematics","year":2019,"lang":"en","type":"article","venue":"South African Journal of Childhood Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Education and Early Childhood Development","funders":"University of Johannesburg; National Research Foundation","keywords":"Formative assessment; Mathematics education; Curriculum; Pedagogy; Psychology; Focus group; Sociology","score_opus":0.014615595148406657,"score_gpt":0.36736591523537826,"score_spread":0.3527503200869716,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2980647847","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5366438,0.025837319,0.18793115,0.018967621,0.001336496,0.0015711552,0.00016724557,0.00043215652,0.22711305],"genre_scores_gemma":[0.95672107,0.0034932923,0.033868507,0.00082772697,0.00013626045,0.0005934523,0.00004490188,0.000054991226,0.004259792],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.98073304,0.014340567,0.0010718077,0.0007274612,0.0024733634,0.000653609],"domain_scores_gemma":[0.9548952,0.032053303,0.0058153807,0.0028740026,0.0029539475,0.0014082621],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.017655311,0.0006516551,0.000342299,0.0033927485,0.002366527,0.007815109,0.0015448947,0.0015869878,0.0019160341],"category_scores_gemma":[0.034482908,0.00032419624,0.00044033123,0.0030935174,0.012983886,0.0062694,0.0047667813,0.0033753836,0.0002514204],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000084077634,0.000412717,0.039293256,0.0011105702,0.000038070924,0.0012934773,0.5232388,0.0008197118,0.0030878827,0.123510756,0.0023082609,0.30480245],"study_design_scores_gemma":[0.00004667779,0.0009286038,0.11756296,0.008999942,0.00010425981,0.006963589,0.36016452,0.0026821946,0.007064609,0.12361546,0.3716712,0.00019606108],"about_ca_topic_score_codex":0.004709461,"about_ca_topic_score_gemma":0.006546378,"teacher_disagreement_score":0.017655311,"about_ca_system_score_codex":0.006012611,"about_ca_system_score_gemma":0.008809976,"threshold_uncertainty_score":0.09337133},"labels":[],"label_agreement":null},{"id":"W2980773015","doi":"10.4018/978-1-7998-0323-2.ch017","title":"Assessment in 21st Century Learning","year":2019,"lang":"en","type":"book-chapter","venue":"Advances in early childhood and K-12 education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Western University","funders":"","keywords":"Formative assessment; Situated; Improvisation; Narrative; Divergence (linguistics); Pedagogy; Situated learning; Assessment for learning; Space (punctuation); Curriculum; Literacy; Mathematics education; Sociology; Psychology; Computer science; Visual arts; Art; Artificial intelligence","score_opus":0.007753887984675155,"score_gpt":0.30720618080539824,"score_spread":0.2994522928207231,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2980773015","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013513307,0.071250014,0.012559257,0.00849261,0.0011650793,0.00007667555,0.00005495339,0.00011655155,0.89277154],"genre_scores_gemma":[0.37391797,0.061531484,0.014585315,0.0016364302,0.0005975503,0.00008931602,0.000082822466,0.00010356157,0.5474556],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99925286,0.00021225026,0.000030989606,0.000045400157,0.0003958745,0.00006272073],"domain_scores_gemma":[0.99906963,0.00059555576,0.000031100506,0.000051767216,0.00019198009,0.00006000917],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0009413532,0.00031951172,0.0001903545,0.0010665308,0.0016008636,0.0035286527,0.00052554073,0.0006594292,0.0046583037],"category_scores_gemma":[0.001961806,0.000095872114,0.000099122284,0.0013543088,0.0057297545,0.0022495193,0.0014151548,0.0011814046,0.00054265134],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000010210682,0.00003028914,0.0011534283,0.00029131045,0.000002236059,0.00014570907,0.031829853,0.0006971068,0.000530812,0.6090201,0.031306688,0.32498226],"study_design_scores_gemma":[0.000001365524,0.000012366713,0.0016111487,0.00042159957,0.0000011906928,0.00016038454,0.0039490336,0.0003243616,0.00022424139,0.07952547,0.91376096,0.000007942492],"about_ca_topic_score_codex":0.0981001,"about_ca_topic_score_gemma":0.19400582,"teacher_disagreement_score":0.0981001,"about_ca_system_score_codex":0.010463279,"about_ca_system_score_gemma":0.0076788026,"threshold_uncertainty_score":0.19505817},"labels":[],"label_agreement":null},{"id":"W2981392404","doi":"10.5539/elt.v12n11p64","title":"Using Self-Assessment as a Tool for English Language Learning","year":2019,"lang":"en","type":"article","venue":"English Language Teaching","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":45,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Universiti Putra Malaysia","keywords":"Formative assessment; Psychology; Learner autonomy; Context (archaeology); Self-assessment; Mathematics education; Language acquisition; Autonomy; Quality (philosophy); Class (philosophy); Pedagogy; Language education; Comprehension approach; Computer science; Artificial intelligence","score_opus":0.013233138124479972,"score_gpt":0.3512337609470111,"score_spread":0.3380006228225311,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2981392404","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.20975056,0.06465167,0.5400691,0.014204549,0.0037754222,0.0076669157,0.0011982315,0.004729679,0.1539539],"genre_scores_gemma":[0.50617605,0.019819802,0.45722345,0.0015003185,0.00041781546,0.004258634,0.0006665894,0.00018779315,0.009749561],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.95281523,0.029813321,0.0033056878,0.000959246,0.012783387,0.0003232023],"domain_scores_gemma":[0.9381792,0.040422257,0.0037003874,0.0024057622,0.013948471,0.0013439121],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.035854314,0.0005740183,0.00078793394,0.006726263,0.0009955885,0.0053136866,0.0012188044,0.0007643889,0.0018517025],"category_scores_gemma":[0.0559228,0.0002795596,0.00062130165,0.0030476376,0.0019531855,0.004478382,0.0029576512,0.0018805687,0.0009877147],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000066584755,0.0003306101,0.023559982,0.0015554682,0.00008009648,0.0001223474,0.009915529,0.0004305339,0.001403678,0.009341595,0.00820572,0.9449877],"study_design_scores_gemma":[0.00021342887,0.0041430173,0.18721703,0.02448034,0.00042510944,0.005864379,0.049805216,0.016659569,0.018985564,0.07834643,0.6129618,0.000898109],"about_ca_topic_score_codex":0.0010710311,"about_ca_topic_score_gemma":0.0017636637,"teacher_disagreement_score":0.035854314,"about_ca_system_score_codex":0.0017020702,"about_ca_system_score_gemma":0.0044993195,"threshold_uncertainty_score":0.18961799},"labels":[],"label_agreement":null},{"id":"W2984367764","doi":"10.1186/s40468-019-0094-7","title":"Assessing peer review pattern and the effect of face-to-face and mobile-mediated modes on students’ academic writing development","year":2019,"lang":"en","type":"article","venue":"Language Testing in Asia","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":15,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Psychology; Academic writing; English for academic purposes; Peer feedback; Mathematics education; Cohesion (chemistry); Task (project management); Second language writing; Face-to-face; Pedagogy; Medical education; Second language; Linguistics","score_opus":0.032727561803754454,"score_gpt":0.399730670787874,"score_spread":0.36700310898411953,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2984367764","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9960078,0.00014901425,0.001869552,0.000118426804,0.000025628817,0.00017819708,0.000024486226,0.00007220599,0.0015546577],"genre_scores_gemma":[0.9953999,0.00008798263,0.0032345532,0.000039425762,0.000029895871,0.00021197922,0.00002737712,0.000018637234,0.0009502279],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.97239673,0.015456316,0.0026280321,0.0023121613,0.0066151563,0.0005916316],"domain_scores_gemma":[0.80783755,0.12968504,0.025277263,0.011345122,0.020386286,0.0054686978],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.015401662,0.00040196278,0.0008098075,0.0015209927,0.0007787039,0.0017541727,0.001127828,0.0005401295,0.0024847265],"category_scores_gemma":[0.15419523,0.0003104045,0.00035819225,0.00062355085,0.00061114546,0.0013878292,0.0017822753,0.00059482653,0.00083849626],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0028453756,0.0019073712,0.45699933,0.00064887793,0.00030094985,0.0005502063,0.019994166,0.00074927096,0.02742742,0.0002049456,0.0012510278,0.48712105],"study_design_scores_gemma":[0.0002608212,0.0060189096,0.9556075,0.00018850512,0.00022545666,0.0010590535,0.01633329,0.0045891157,0.011604193,0.000458079,0.0035199313,0.00013510916],"about_ca_topic_score_codex":0.0008066833,"about_ca_topic_score_gemma":0.0016507454,"teacher_disagreement_score":0.98459834,"about_ca_system_score_codex":0.00053458684,"about_ca_system_score_gemma":0.0007746325,"threshold_uncertainty_score":0.08145273},"labels":[],"label_agreement":null},{"id":"W2989650653","doi":"10.5539/elt.v12n12p132","title":"The Reality of Continuous Assessment Strategies on Saudi Students&amp;#39; Performance at University Level","year":2019,"lang":"en","type":"article","venue":"English Language Teaching","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology; Continuous assessment; Medical education; Sample (material); Mathematics education; Medicine","score_opus":0.02738941493298204,"score_gpt":0.3477198042507374,"score_spread":0.32033038931775537,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2989650653","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99738365,0.00018185723,0.00026930895,0.00017798638,0.0000080347445,0.000009432304,0.00000869835,0.0000089883915,0.0019520075],"genre_scores_gemma":[0.9993661,0.00009594909,0.00026321446,0.000022031301,0.0000034929728,0.0000046552746,0.0000056545246,0.000001726848,0.00023724472],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9933565,0.0029551457,0.0004586468,0.0003025652,0.002451027,0.0004760863],"domain_scores_gemma":[0.9638537,0.014400861,0.006462878,0.0012247013,0.010081947,0.0039758277],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0055319685,0.00027373785,0.00028241507,0.0010306534,0.0008390549,0.0030983768,0.00054844574,0.00051856664,0.0012767517],"category_scores_gemma":[0.03195312,0.0001426262,0.0002128701,0.00063178665,0.00083001266,0.0010413815,0.0013148655,0.000560128,0.00034529268],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004902814,0.00086872093,0.60459375,0.00037693614,0.00007204405,0.00042290296,0.07017755,0.00055133016,0.00635675,0.00088085426,0.0009212291,0.31428757],"study_design_scores_gemma":[0.000026050375,0.0026357637,0.8461729,0.00038569947,0.0000630696,0.00048432095,0.13190784,0.0023307898,0.004790872,0.0006825589,0.010399411,0.00012075131],"about_ca_topic_score_codex":0.005116889,"about_ca_topic_score_gemma":0.0070472592,"teacher_disagreement_score":0.0055319685,"about_ca_system_score_codex":0.0013060233,"about_ca_system_score_gemma":0.0022549897,"threshold_uncertainty_score":0.029256165},"labels":[],"label_agreement":null},{"id":"W2989744490","doi":"10.22329/jtl.v13i2.5971","title":"Finnish Upper Secondary School Students’ Perceptions of Their Teachers’ Assessment Practices","year":2020,"lang":"en","type":"article","venue":"Journal of Teaching and Learning","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Perception; Literacy; Mathematics education; Psychology; School teachers; Medical education; Pedagogy; Medicine","score_opus":0.03752627490038453,"score_gpt":0.3973500381577403,"score_spread":0.35982376325735577,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2989744490","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99870884,0.00008072893,0.000045058576,0.00005833299,0.000002900608,0.0000034761815,0.0000083320665,0.0000023528673,0.0010900293],"genre_scores_gemma":[0.9994173,0.00006163769,0.000036666705,0.000019357833,0.0000012951277,0.0000041737126,0.000010263713,0.0000011571306,0.00044810504],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99637055,0.00084966654,0.00044876043,0.00031757067,0.0012644309,0.0007491166],"domain_scores_gemma":[0.9907025,0.00353312,0.0017685668,0.0003173378,0.0013050423,0.0023735035],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003489327,0.00027382924,0.00053683226,0.0015217606,0.0021262618,0.00465768,0.00047337147,0.0009699626,0.0022487382],"category_scores_gemma":[0.009665414,0.00030658516,0.00043704457,0.0010746748,0.0018898975,0.0011284084,0.0018572138,0.0010431067,0.00047374502],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001351043,0.00033425886,0.40705907,0.00013145195,0.000029280114,0.0009699192,0.566275,0.000121536556,0.00369177,0.00043077808,0.00041087065,0.020410914],"study_design_scores_gemma":[0.000010922173,0.0004802057,0.58936536,0.00014651466,0.00003193755,0.00053622824,0.40114427,0.00024116639,0.0013040542,0.00026553893,0.0063926326,0.000081271304],"about_ca_topic_score_codex":0.017976921,"about_ca_topic_score_gemma":0.020931255,"teacher_disagreement_score":0.017976921,"about_ca_system_score_codex":0.0015473445,"about_ca_system_score_gemma":0.0015092826,"threshold_uncertainty_score":0.035744548},"labels":[],"label_agreement":null},{"id":"W2990008878","doi":"10.7202/1065164ar","title":"Quel feedback les élèves du primaire en difficulté d’apprentissage reçoivent-ils dans leur bulletin scolaire ? Vers une typologie des commentaires laissés par leurs enseignants","year":2019,"lang":"fr","type":"article","venue":"Mesure et évaluation en éducation","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Humanities; Political science; Art","score_opus":0.08092896404244351,"score_gpt":0.3593135500961273,"score_spread":0.27838458605368377,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2990008878","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.88095963,0.0019770283,0.010355205,0.021002509,0.0012488777,0.00048555623,0.0003511015,0.0006027323,0.08301728],"genre_scores_gemma":[0.9454149,0.0012554037,0.003559027,0.0013358084,0.00022567903,0.00034035757,0.00021971657,0.00014392883,0.047505118],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9908049,0.004092435,0.000506284,0.00052613637,0.0033077209,0.0007625744],"domain_scores_gemma":[0.93839943,0.024288736,0.0075215735,0.0030013446,0.019546947,0.00724203],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009826835,0.0005130458,0.00059029675,0.0023187855,0.0038407338,0.0062855994,0.001026193,0.0015461235,0.013737333],"category_scores_gemma":[0.07357631,0.00034858746,0.00033065924,0.0018486399,0.0029674075,0.0036030568,0.0034747005,0.0025782762,0.0037953316],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00054868753,0.0005372453,0.13487013,0.0012034269,0.00008883323,0.0011324848,0.46818662,0.00037926924,0.0074963477,0.011217938,0.03737416,0.3369649],"study_design_scores_gemma":[0.00007027094,0.0010572692,0.17288129,0.0011524695,0.00010153564,0.000646027,0.44448942,0.0011591614,0.0049561504,0.005038881,0.36825305,0.00019440897],"about_ca_topic_score_codex":0.01420876,"about_ca_topic_score_gemma":0.028835066,"teacher_disagreement_score":0.01420876,"about_ca_system_score_codex":0.003451217,"about_ca_system_score_gemma":0.006576578,"threshold_uncertainty_score":0.051969886},"labels":[],"label_agreement":null},{"id":"W2993413569","doi":"10.5539/elt.v13n1p43","title":"Research on the Effect of Supervisor Feedback for Undergraduate Thesis Writing","year":2019,"lang":"en","type":"article","venue":"English Language Teaching","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Supervisor; Peer feedback; Psychology; Focus (optics); Corrective feedback; Expression (computer science); Negative feedback; Mathematics education; Computer science; Management; Engineering","score_opus":0.03487369127801464,"score_gpt":0.39149926914608824,"score_spread":0.3566255778680736,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2993413569","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9938822,0.0011068333,0.0019492279,0.00019483776,0.00004247261,0.00007883133,0.000030506219,0.000063067106,0.0026522013],"genre_scores_gemma":[0.9968029,0.00034669216,0.002217218,0.00003778835,0.000029776505,0.00003782578,0.000024739276,0.00001709973,0.00048586354],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.97395825,0.018435992,0.0011472217,0.001079302,0.004855876,0.00052339927],"domain_scores_gemma":[0.5395802,0.39755663,0.025805898,0.006126449,0.02339016,0.007540553],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.016438065,0.0005356863,0.0005828342,0.0011567583,0.00068765227,0.0014193545,0.00070770906,0.00063155004,0.0024050681],"category_scores_gemma":[0.21754779,0.00022234957,0.0004981124,0.0005893105,0.0006935843,0.0008387395,0.0008750015,0.00090420374,0.00042181587],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0060786176,0.0037908878,0.31095916,0.0028765006,0.0005558765,0.0003885291,0.038842954,0.0012080101,0.03910623,0.0003839092,0.0012990974,0.59451026],"study_design_scores_gemma":[0.00032226538,0.014418175,0.9501125,0.00070315157,0.0006136759,0.00053073326,0.010761724,0.0020120565,0.015852386,0.00049312034,0.004080401,0.00009983201],"about_ca_topic_score_codex":0.0010904684,"about_ca_topic_score_gemma":0.0019502233,"teacher_disagreement_score":0.016438065,"about_ca_system_score_codex":0.0009142539,"about_ca_system_score_gemma":0.0017162814,"threshold_uncertainty_score":0.08693385},"labels":[],"label_agreement":null},{"id":"W2994446456","doi":"10.47678/cjhe.v35i4.184475","title":"The Immediate Feedback Assessment Technique: A Learner-centered Multiple-choice Response Form","year":2013,"lang":"en","type":"article","venue":"Canadian Journal of Higher Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Brock University","funders":"","keywords":"Grading (engineering); Multiple choice; Computer science; Suite; Mathematics education; Psychology; Mathematics; Political science; Statistics; Engineering","score_opus":0.02670177446827649,"score_gpt":0.35239603585010404,"score_spread":0.32569426138182755,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2994446456","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.092009336,0.0011803657,0.8037192,0.0023371498,0.0023585497,0.037453562,0.004808207,0.006859989,0.049273703],"genre_scores_gemma":[0.12192182,0.0009712407,0.8074366,0.0008933932,0.000297154,0.04170146,0.0018933462,0.00084184157,0.024043197],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.977688,0.014154601,0.002221365,0.0009545002,0.004655615,0.00032601747],"domain_scores_gemma":[0.9437185,0.0352199,0.0031612443,0.0020560843,0.015261936,0.0005822711],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.019836646,0.0008816272,0.00082094024,0.0020043335,0.00050135655,0.0012726457,0.0012862093,0.0009873483,0.02121499],"category_scores_gemma":[0.06643177,0.00035281279,0.0008560613,0.001049674,0.00050050666,0.0012173105,0.001166404,0.001624609,0.0071703307],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016350411,0.0011068275,0.0050266315,0.0023831762,0.00008937512,0.00017798417,0.0027635286,0.0017687477,0.019588867,0.0039099506,0.06767659,0.8938733],"study_design_scores_gemma":[0.0025736042,0.0077709635,0.08520352,0.0042356844,0.00027208004,0.0017589229,0.004158067,0.04259399,0.06713191,0.016080856,0.76726884,0.00095169345],"about_ca_topic_score_codex":0.00045761527,"about_ca_topic_score_gemma":0.0010116253,"teacher_disagreement_score":0.02121499,"about_ca_system_score_codex":0.0007198516,"about_ca_system_score_gemma":0.0015946742,"threshold_uncertainty_score":0.10490745},"labels":[],"label_agreement":null},{"id":"W2994544299","doi":"","title":"The Degree of Using Alternative Assessment Strategies by the Teachers of the First Three Grades in the Tabuk Region: Survey Study","year":2016,"lang":"en","type":"article","venue":"Canadian social science","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Degree (music); Sample (material); Psychology; Mathematics education; Estimation; Statistics; Medical education; Mathematics; Medicine; Management; Economics","score_opus":0.15057878264938052,"score_gpt":0.3883937566217403,"score_spread":0.2378149739723598,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2994544299","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99961746,0.00006913246,0.00001875644,0.000019273557,0.000001151917,0.000007747568,0.000036767902,7.860817e-7,0.00022894716],"genre_scores_gemma":[0.9994936,0.00012852317,0.00006380618,0.000012060049,0.0000011568557,0.000010882034,0.000044688342,6.732208e-7,0.00024449753],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9988495,0.00025339943,0.00014629427,0.000108766035,0.00033479492,0.000307187],"domain_scores_gemma":[0.99699485,0.0004743053,0.001164631,0.00011094364,0.0008321393,0.00042303372],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0017126658,0.00023142854,0.00029331076,0.0014813247,0.0007626201,0.0010320776,0.00048335927,0.00041795615,0.0014178448],"category_scores_gemma":[0.0033103076,0.00031463828,0.00033494944,0.0012894204,0.0004990039,0.00064121984,0.00055227306,0.00053285365,0.0003302075],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029920042,0.00009216302,0.97961205,0.00006784751,0.000012209891,0.00014036856,0.0133104725,0.000029779188,0.0005340123,0.000039517363,0.00009952824,0.0060321926],"study_design_scores_gemma":[0.000001604123,0.00012799764,0.9680798,0.00004631746,0.0000066585567,0.00021278455,0.030665958,0.000080503065,0.00017542415,0.000011179456,0.00058304524,0.000008638715],"about_ca_topic_score_codex":0.031879902,"about_ca_topic_score_gemma":0.04928966,"teacher_disagreement_score":0.031879902,"about_ca_system_score_codex":0.0012097809,"about_ca_system_score_gemma":0.0011995021,"threshold_uncertainty_score":0.063388705},"labels":[],"label_agreement":null},{"id":"W2994689616","doi":"10.1080/0969594x.2019.1703171","title":"A cross-cultural comparison of German and Canadian student teachers’ assessment competence","year":2019,"lang":"en","type":"article","venue":"Assessment in Education Principles Policy and Practice","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Queen's University","funders":"","keywords":"Competence (human resources); German; Multitude; Psychology; Pedagogy; Cross-cultural; Mathematics education; Sociology; Social psychology; Political science; Geography","score_opus":0.06255569384159228,"score_gpt":0.5279710097896466,"score_spread":0.46541531594805435,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2994689616","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99280703,0.00027185443,0.00015073783,0.00013063897,0.000013120425,0.000017677936,0.00014188288,0.0000037482469,0.006463303],"genre_scores_gemma":[0.99841475,0.00019810884,0.00017370845,0.000042267027,0.0000018171064,0.000010292882,0.00014982033,0.000004014094,0.0010052266],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99690837,0.00046759428,0.00017963986,0.0003015148,0.0014424155,0.00070049905],"domain_scores_gemma":[0.99257267,0.0015029414,0.0005483448,0.0002849989,0.004225052,0.00086589734],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0036476415,0.00024626948,0.00038557168,0.003032211,0.0038397778,0.0021293468,0.0005950579,0.0003147577,0.0020390674],"category_scores_gemma":[0.008860679,0.00022993864,0.00034235528,0.0044149775,0.002149972,0.00059573003,0.0015865926,0.00062334194,0.00018079676],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00045397386,0.00021871523,0.54853684,0.0002801712,0.00014343846,0.00052698434,0.36012077,0.00033061617,0.0033230956,0.004211653,0.003057968,0.07879571],"study_design_scores_gemma":[0.0000096825515,0.00010557955,0.8485903,0.000101473,0.00003359132,0.00018783036,0.14220797,0.00018401672,0.00060828374,0.00013921091,0.0077843396,0.000047702844],"about_ca_topic_score_codex":0.95181054,"about_ca_topic_score_gemma":0.9812887,"teacher_disagreement_score":0.04818946,"about_ca_system_score_codex":0.016998116,"about_ca_system_score_gemma":0.018107701,"threshold_uncertainty_score":0.12333053},"labels":[],"label_agreement":null},{"id":"W2995076146","doi":"10.5539/ies.v13n1p1","title":"Not All Finns Think Alike: Varying Views of Assessment in Finland","year":2019,"lang":"en","type":"article","venue":"International Education Studies","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Narrative; Psychology; Socioeconomic status; Pedagogy; Standardized test; Narrative inquiry; Teacher education; Medical education; Educational assessment; Mathematics education; Sociology; Medicine","score_opus":0.13217833186897876,"score_gpt":0.501713879522738,"score_spread":0.3695355476537593,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2995076146","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9744377,0.002714535,0.00044907347,0.0051793633,0.00011299168,0.00001507678,0.000031388776,0.000008632721,0.017051209],"genre_scores_gemma":[0.99857605,0.0004993679,0.00008129567,0.0003403379,0.000011423888,0.0000054525617,0.00001007475,0.0000033499416,0.0004725642],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.990262,0.0047643553,0.00080413173,0.0007047807,0.0022873604,0.0011775115],"domain_scores_gemma":[0.98846895,0.0076957876,0.0013518119,0.00026565956,0.00087489706,0.0013428888],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013315402,0.000509348,0.00059621,0.0022149908,0.011443865,0.009909598,0.0009758375,0.002054064,0.0010505049],"category_scores_gemma":[0.018066095,0.0004389422,0.00047277805,0.0018947807,0.012617943,0.0054810755,0.0059632473,0.0030969046,0.00017088502],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000031147887,0.000013985532,0.019016447,0.000060343587,0.000013276793,0.0007497151,0.971548,0.000040893607,0.0003990528,0.001865065,0.0003958273,0.005866189],"study_design_scores_gemma":[0.0000036143122,0.000027191803,0.01037034,0.00021027363,0.00001555154,0.00042983922,0.98074925,0.000055447577,0.0001957739,0.0007433762,0.007168327,0.00003103477],"about_ca_topic_score_codex":0.032746494,"about_ca_topic_score_gemma":0.033375133,"teacher_disagreement_score":0.032746494,"about_ca_system_score_codex":0.005623198,"about_ca_system_score_gemma":0.0063802805,"threshold_uncertainty_score":0.07041937},"labels":[],"label_agreement":null},{"id":"W2996434871","doi":"10.1515/ijnes-2019-0061","title":"A, B, or C? A Quasi-experimental Multi-site Study Investigating Three Option Multiple Choice Questions","year":2019,"lang":"en","type":"article","venue":"International Journal of Nursing Education Scholarship","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Red River College; Northwestern Polytechnic; Dalhousie University","funders":"","keywords":"Replication (statistics); Multiple choice; Psychology; Item response theory; Actuarial science; Medicine; Psychometrics; Clinical psychology; Statistics; Significant difference; Economics; Mathematics; Internal medicine","score_opus":0.15817704518269934,"score_gpt":0.5024275049395138,"score_spread":0.34425045975681445,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2996434871","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9842345,0.000048158614,0.0014434597,0.00012362335,0.00007645367,0.012580232,0.00013508323,0.000020161182,0.0013383147],"genre_scores_gemma":[0.9125549,0.00018077322,0.019282851,0.0010155197,0.00012844757,0.060342368,0.00021373504,0.000021241958,0.006260095],"study_design_codex":"nonrandomized_trial","study_design_gemma":"nonrandomized_trial","domain_scores_codex":[0.9873892,0.008287472,0.00077868556,0.0014604158,0.0012681294,0.00081601884],"domain_scores_gemma":[0.9642638,0.024849888,0.0034905649,0.0025399013,0.002807985,0.0020478459],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.021245489,0.00069407164,0.0014216907,0.00089261093,0.0037841771,0.00160061,0.0016603961,0.0018334909,0.0092206765],"category_scores_gemma":[0.025292713,0.001525487,0.0007772134,0.0007722655,0.0026444423,0.0016477972,0.0008554706,0.0025058328,0.0019596936],"study_design_candidate":"nonrandomized_trial","study_design_consensus":"nonrandomized_trial","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.053191867,0.69048625,0.06985972,0.0021322554,0.0003048108,0.0006125316,0.06184093,0.0012764648,0.018245462,0.0036376885,0.0031103778,0.09530152],"study_design_scores_gemma":[0.03828886,0.7726675,0.11886332,0.00034340378,0.00022586089,0.00034048664,0.041320454,0.0039169313,0.00590691,0.0030387756,0.014861719,0.00022572972],"about_ca_topic_score_codex":0.0034295828,"about_ca_topic_score_gemma":0.006530238,"teacher_disagreement_score":0.9787545,"about_ca_system_score_codex":0.0015102064,"about_ca_system_score_gemma":0.004255268,"threshold_uncertainty_score":0.11235827},"labels":[],"label_agreement":null},{"id":"W2997403840","doi":"10.5539/elt.v13n1p180","title":"The Washback Effect of WAEC/SSCE English Test of Orals on Teachers Methodology in Senior Secondary Schools in Sokoto Metropolis","year":2019,"lang":"en","type":"article","venue":"English Language Teaching","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology; Test (biology); Mathematics education; Curriculum; Ranking (information retrieval); Simple random sample; Population; Medical education; Pedagogy; Computer science; Medicine","score_opus":0.018941388842862547,"score_gpt":0.36298388591822156,"score_spread":0.344042497075359,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2997403840","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9993783,0.000087574095,0.000033394877,0.00008639005,0.0000059465365,0.000014092475,0.0000058532382,0.000005545705,0.00038293822],"genre_scores_gemma":[0.9992774,0.00006367191,0.00010570739,0.000036147198,0.000004035464,0.000012221591,0.000008533452,0.0000019772824,0.0004902835],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99175256,0.0032392072,0.0007308865,0.0005314528,0.002746053,0.0009998964],"domain_scores_gemma":[0.97232676,0.011810642,0.007786026,0.0015944815,0.003060253,0.003421762],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005698492,0.00043936833,0.0004856685,0.0011846749,0.0010905587,0.0010741977,0.00089432247,0.00083629024,0.002225098],"category_scores_gemma":[0.027548756,0.0004060862,0.00043067432,0.00059410837,0.001163914,0.0006638726,0.0016099549,0.0010056285,0.0003379385],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001687715,0.004011181,0.7641816,0.0005701187,0.000099106925,0.0028855258,0.06903937,0.0003932851,0.012799688,0.0003512483,0.00094678276,0.1430343],"study_design_scores_gemma":[0.00003100207,0.0042391787,0.94904816,0.00015623924,0.00004989536,0.000380039,0.038678475,0.00033181117,0.0046482165,0.0001434391,0.0022651749,0.000028450511],"about_ca_topic_score_codex":0.006204623,"about_ca_topic_score_gemma":0.010824702,"teacher_disagreement_score":0.006204623,"about_ca_system_score_codex":0.0018535411,"about_ca_system_score_gemma":0.0020858382,"threshold_uncertainty_score":0.030136824},"labels":[],"label_agreement":null},{"id":"W2998316675","doi":"","title":"Examining Student Preparation for Certification Examination: An Exploratory Case Study","year":2019,"lang":"en","type":"dissertation","venue":"Brock University Digital Repository (Brock University)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Certification; Exploratory research; Medical education; Psychology; Mathematics education; Engineering; Medicine; Political science; Sociology","score_opus":0.046782753602780884,"score_gpt":0.3019578126824316,"score_spread":0.2551750590796507,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2998316675","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98637307,0.00028455327,0.0038274599,0.002471314,0.00004929807,0.0004674983,0.00007216692,0.000025387752,0.006429294],"genre_scores_gemma":[0.98209214,0.0011104875,0.009226772,0.0008487459,0.000047826423,0.0005347267,0.00010972371,0.00003386786,0.0059956065],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9875657,0.007966009,0.00049714156,0.0007063667,0.0016737784,0.0015911042],"domain_scores_gemma":[0.9750515,0.017127141,0.0021079183,0.00084279303,0.0025325373,0.002338098],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012846314,0.0006317484,0.00065932114,0.0026146774,0.012372988,0.004548933,0.0034841164,0.0036424806,0.0025742804],"category_scores_gemma":[0.02772159,0.0007036173,0.0007668849,0.0026555944,0.004644413,0.0030296089,0.005616064,0.003844384,0.0005097555],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006163509,0.0010995656,0.028909942,0.00026625732,0.000014488044,0.01817258,0.9180634,0.00037702505,0.0015989585,0.0038680595,0.0017758117,0.025792198],"study_design_scores_gemma":[0.000011131761,0.00035773765,0.0068384637,0.00022744911,0.000011475453,0.0030779208,0.9695774,0.00050954224,0.0010981244,0.0005915678,0.017668288,0.000030923744],"about_ca_topic_score_codex":0.011701952,"about_ca_topic_score_gemma":0.03383911,"teacher_disagreement_score":0.012846314,"about_ca_system_score_codex":0.0070685493,"about_ca_system_score_gemma":0.0111083025,"threshold_uncertainty_score":0.067938626},"labels":[],"label_agreement":null},{"id":"W2998551013","doi":"10.5539/ijel.v10n1p255","title":"EFL Students’ Perception of Classroom Assessment Environment in Translation Courses","year":2019,"lang":"en","type":"article","venue":"International Journal of English Linguistics","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Perception; Psychology; Class (philosophy); Mathematics education; Learning environment; Medical education; Pedagogy; Medicine; Computer science","score_opus":0.024074329695309166,"score_gpt":0.3684626835152612,"score_spread":0.34438835381995203,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2998551013","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99931,0.000030315763,0.000055792356,0.000050109913,0.000003016831,0.000004667928,0.000006229589,0.0000020542927,0.00053769705],"genre_scores_gemma":[0.9989557,0.000054123542,0.0001003114,0.00003635603,0.000002952514,0.000008167505,0.000012298212,0.000001716156,0.00082821934],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.9990276,0.00028380528,0.00007363697,0.00008740321,0.00031500089,0.0002126465],"domain_scores_gemma":[0.9960174,0.00085657585,0.0011739795,0.00009147179,0.0007778855,0.0010827436],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012953904,0.00022253962,0.0003527697,0.00057145266,0.0007462963,0.0020063224,0.00025707675,0.00046716703,0.0031328502],"category_scores_gemma":[0.0048842747,0.0001546539,0.0002447216,0.00032640123,0.0005584169,0.00065848435,0.00083297753,0.0007770268,0.00058886915],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025360892,0.0023163115,0.8156847,0.00022265394,0.000028185055,0.0012370619,0.11483103,0.00024376424,0.01437383,0.00038374742,0.0009043834,0.049520798],"study_design_scores_gemma":[0.000017378408,0.001558136,0.7751791,0.00010754353,0.000024426912,0.0006430343,0.21347024,0.00053281256,0.002615619,0.00030131746,0.005493836,0.00005659649],"about_ca_topic_score_codex":0.001649904,"about_ca_topic_score_gemma":0.0026883306,"teacher_disagreement_score":0.0031328502,"about_ca_system_score_codex":0.0005033557,"about_ca_system_score_gemma":0.00064768124,"threshold_uncertainty_score":0.010480404},"labels":[],"label_agreement":null},{"id":"W3001300584","doi":"10.24908/pceea.vi0.13858","title":"THE EFFECT OF STUDENT REFLECTION QUALITY ON A TECHNICAL WRITING ASSIGNMENT RESUBMISSION","year":2019,"lang":"en","type":"article","venue":"Proceedings of the Canadian Engineering Education Association (CEEA)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"McGill University","funders":"McGill University","keywords":"Rubric; Grading (engineering); Reflection (computer programming); Computer science; Mathematics education; Quality (philosophy); Graduate students; Psychology; Medical education; Pedagogy; Engineering; Medicine","score_opus":0.013022911278381157,"score_gpt":0.34177096006534985,"score_spread":0.32874804878696867,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3001300584","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99493873,0.00010522615,0.0023104982,0.00022678096,0.00006190406,0.00024725965,0.000047963837,0.0001665446,0.0018951087],"genre_scores_gemma":[0.9927799,0.000058343696,0.004932621,0.00007699695,0.00003334745,0.00023327711,0.00009269544,0.000038470265,0.0017543117],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.97240645,0.015490101,0.00264814,0.00179071,0.006459991,0.0012046003],"domain_scores_gemma":[0.67940897,0.24988616,0.027105935,0.016239021,0.017675856,0.009684092],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.023480384,0.0006520893,0.00076858955,0.0006773869,0.00051035546,0.0017849598,0.0011395714,0.000896656,0.0036661618],"category_scores_gemma":[0.14745432,0.00036901102,0.00096247566,0.00050788966,0.0007230386,0.000959416,0.001652266,0.0012573746,0.0006448999],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.025282389,0.026988598,0.26098537,0.0009707243,0.00070147094,0.00022594599,0.00786052,0.0054662926,0.03825445,0.00045498405,0.0033403528,0.629469],"study_design_scores_gemma":[0.00089371565,0.058161926,0.89532167,0.00019740919,0.0003669974,0.0001690404,0.0019653046,0.008002263,0.031762328,0.0003891364,0.0025922249,0.00017794016],"about_ca_topic_score_codex":0.00092026143,"about_ca_topic_score_gemma":0.0012847217,"teacher_disagreement_score":0.023480384,"about_ca_system_score_codex":0.0008180599,"about_ca_system_score_gemma":0.0011237192,"threshold_uncertainty_score":0.124177635},"labels":[],"label_agreement":null},{"id":"W3006441709","doi":"10.19173/irrodl.v20i5.4333","title":"A Systematic Review of Technology-Supported Peer Assessment Research","year":2019,"lang":"en","type":"review","venue":"The International Review of Research in Open and Distributed Learning","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":26,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Ministry of Science and Technology, Taiwan","keywords":"Peer assessment; Anonymity; Peer feedback; Peer review; Computer science; Assessment for learning; Educational technology; Technical peer review; Psychology; Formative assessment; Mathematics education","score_opus":0.2510590947545748,"score_gpt":0.602044607008705,"score_spread":0.3509855122541302,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3006441709","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0009466748,0.9957196,0.0006573087,0.00035383727,0.00024437587,0.00095333875,0.0005255536,0.000019282294,0.0005799733],"genre_scores_gemma":[0.012438123,0.9829472,0.001756786,0.00044309266,0.00010118797,0.0016499393,0.0004412023,0.000011941228,0.00021058916],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.9746738,0.009322197,0.008646144,0.0014954762,0.0054814103,0.00038100648],"domain_scores_gemma":[0.92656916,0.05361324,0.00913901,0.0015299116,0.008414631,0.00073403405],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.018710343,0.001779261,0.0066805473,0.021543177,0.0012719254,0.003355129,0.0028418351,0.0018971845,0.0050146794],"category_scores_gemma":[0.09904147,0.0011592767,0.0049530594,0.020467173,0.00150611,0.0035654623,0.002435719,0.0015032493,0.0006302155],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000091933434,0.000015429912,0.0004597792,0.934399,0.003060635,0.00013284336,0.0003758079,0.00008968903,0.00017618903,0.00043405226,0.00242728,0.058337394],"study_design_scores_gemma":[0.000107749205,0.00012988175,0.0022523492,0.9413986,0.019464443,0.00040621258,0.000430905,0.00007070241,0.00020118285,0.00050191686,0.035003416,0.00003255366],"about_ca_topic_score_codex":0.0063489703,"about_ca_topic_score_gemma":0.019431653,"teacher_disagreement_score":0.9812897,"about_ca_system_score_codex":0.0049960753,"about_ca_system_score_gemma":0.023541272,"threshold_uncertainty_score":0.09895092},"labels":[],"label_agreement":null},{"id":"W3007758995","doi":"10.1080/0969594x.2020.1728908","title":"Making feedback effective?","year":2020,"lang":"en","type":"article","venue":"Assessment in Education Principles Policy and Practice","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kellogg's (Canada)","funders":"","keywords":"Computer science; Psychology","score_opus":0.09632089257636077,"score_gpt":0.48106678362533445,"score_spread":0.38474589104897366,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3007758995","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026804011,0.024142802,0.040364005,0.7860187,0.012691897,0.00055831706,0.00017940467,0.0015422738,0.10769851],"genre_scores_gemma":[0.7565559,0.02505055,0.075075045,0.11118805,0.007897443,0.0013709604,0.00019375549,0.00097046315,0.021697806],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.86509293,0.08764392,0.0057533374,0.004702753,0.031002143,0.005804846],"domain_scores_gemma":[0.7039152,0.18336879,0.020660916,0.014270932,0.06266631,0.015117802],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.096601814,0.0010701199,0.0011396463,0.0022819454,0.0039629363,0.012845359,0.002000519,0.007339032,0.01456862],"category_scores_gemma":[0.38123378,0.00072602835,0.00092754577,0.0011638846,0.006621133,0.018497882,0.005901547,0.0066248192,0.0059613143],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023044366,0.00036356744,0.006821586,0.0023375354,0.00016000959,0.00026450184,0.016911557,0.00023401417,0.0012616925,0.03923567,0.17929852,0.7528809],"study_design_scores_gemma":[0.0005023488,0.0008901375,0.013348445,0.01696025,0.0004385887,0.0017501421,0.042202104,0.0020406593,0.0051033245,0.15742135,0.7591079,0.00023470905],"about_ca_topic_score_codex":0.0025421858,"about_ca_topic_score_gemma":0.0033015262,"teacher_disagreement_score":0.096601814,"about_ca_system_score_codex":0.004683778,"about_ca_system_score_gemma":0.013941105,"threshold_uncertainty_score":0.51088536},"labels":[],"label_agreement":null},{"id":"W3009011090","doi":"10.7330/9781607329329.c011","title":"Framing Graduate Teaching Assistant Preparation Around Threshold Concepts of Writing Studies","year":2020,"lang":"en","type":"book-chapter","venue":"Utah State University Press eBooks","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"York University; Harvard University; University of Cambridge; Utah State University","keywords":"Framing (construction); Graduate students; Graduate education; Computer science; Mathematics education; Psychology; Pedagogy; Engineering","score_opus":0.1107655094268788,"score_gpt":0.3561919206657548,"score_spread":0.24542641123887599,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3009011090","genre_codex":"commentary","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.034955747,0.0066013727,0.25986946,0.3717362,0.009196398,0.0005284436,0.000060854323,0.001112654,0.31593883],"genre_scores_gemma":[0.74216497,0.0025627161,0.10546407,0.04060273,0.004676211,0.001406362,0.00004969125,0.0009879407,0.102085285],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.96645063,0.020901233,0.0012147389,0.002770068,0.0066565406,0.0020066774],"domain_scores_gemma":[0.9207867,0.058960598,0.0027881514,0.004106703,0.00821464,0.005143163],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.038871236,0.0008708104,0.00075024244,0.003958273,0.013147477,0.029749611,0.004288888,0.008399933,0.0064593633],"category_scores_gemma":[0.0690314,0.00074613176,0.0007025714,0.0025720655,0.042258732,0.017612457,0.014126,0.024962144,0.0017962646],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000017668675,0.000063013154,0.000488259,0.0001239144,0.0000036437143,0.00011865814,0.03672261,0.00019249815,0.0005459672,0.91794026,0.012389219,0.031394284],"study_design_scores_gemma":[0.00003223243,0.000079496844,0.0012887814,0.00091434625,0.000015584934,0.0001929081,0.047434717,0.0011561335,0.0014415248,0.74356896,0.20382285,0.000052489366],"about_ca_topic_score_codex":0.0037598226,"about_ca_topic_score_gemma":0.0077502476,"teacher_disagreement_score":0.038871236,"about_ca_system_score_codex":0.013863935,"about_ca_system_score_gemma":0.015629169,"threshold_uncertainty_score":0.20557326},"labels":[],"label_agreement":null},{"id":"W3009513072","doi":"10.3138/jvme.0418-045r","title":"Using the Digital Platform ExamSoft in Veterinary Anatomy and Parasitology Assessments in Written and Laboratory Components","year":2020,"lang":"en","type":"article","venue":"Journal of Veterinary Medical Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Grading (engineering); Veterinary parasitology; Standardization; Medical education; Test (biology); Process (computing); Computer science; Medical physics; Veterinary medicine; Medicine; Engineering; Biology","score_opus":0.1472560376084991,"score_gpt":0.47630665501173014,"score_spread":0.32905061740323105,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3009513072","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6354879,0.00087982253,0.22551556,0.0050909957,0.0013056144,0.0033372762,0.0043462473,0.0277501,0.09628658],"genre_scores_gemma":[0.6573627,0.00065256393,0.29327658,0.0012759637,0.00019471253,0.0016322316,0.002192654,0.001531172,0.041881334],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99686277,0.0012447082,0.0002676843,0.00047543074,0.0009024301,0.00024689085],"domain_scores_gemma":[0.9844396,0.006508057,0.0012302641,0.002103276,0.0034157634,0.002303114],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0052259183,0.00082047953,0.00039876753,0.0017355507,0.0005508153,0.0022789608,0.0009605157,0.0005907867,0.02125306],"category_scores_gemma":[0.02167129,0.00038674191,0.00051032525,0.0011490138,0.00041614764,0.0018944048,0.0030718413,0.00132766,0.008442086],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00070036424,0.0023527802,0.03362038,0.00032646867,0.000024289693,0.00050844456,0.0027955815,0.0016888914,0.017103698,0.001797255,0.037023053,0.9020588],"study_design_scores_gemma":[0.00045815328,0.010072977,0.29459155,0.0016383271,0.0001304675,0.0039968486,0.006507087,0.027645225,0.07967394,0.017485484,0.55725205,0.0005478553],"about_ca_topic_score_codex":0.00059040904,"about_ca_topic_score_gemma":0.0016905064,"teacher_disagreement_score":0.02125306,"about_ca_system_score_codex":0.0006756516,"about_ca_system_score_gemma":0.0015357726,"threshold_uncertainty_score":0.07109851},"labels":[],"label_agreement":null},{"id":"W3010193995","doi":"","title":"Reform Through Assessment in Ontario Schools","year":2001,"lang":"en","type":"dissertation","venue":"OpenBU (Boston University)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Political science; Mathematics education; Pedagogy; Public administration; Psychology","score_opus":0.034477647699919275,"score_gpt":0.3333817733728638,"score_spread":0.2989041256729445,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3010193995","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8743034,0.0009382387,0.0006816075,0.025583345,0.0001356016,0.0005394402,0.0010506688,0.00014697097,0.09662072],"genre_scores_gemma":[0.96240765,0.0002924159,0.00087384594,0.00049022946,0.0000210757,0.0001065353,0.00019896733,0.00002489689,0.035584353],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98406065,0.003975039,0.0006536073,0.00106272,0.0057731657,0.004474884],"domain_scores_gemma":[0.94939023,0.0058188452,0.0032760082,0.0014606792,0.02391776,0.016136553],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009846262,0.00028868296,0.0006084209,0.0026531075,0.017707106,0.008256271,0.0021157104,0.0020444004,0.007991339],"category_scores_gemma":[0.0389077,0.00059706956,0.0003978543,0.0072483765,0.0046557575,0.0026286058,0.0060297316,0.0019863783,0.00073257944],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.0011144014,0.001142635,0.39336756,0.0006064971,0.00009440545,0.00077422603,0.1504916,0.0043903138,0.0012797009,0.06532126,0.1076608,0.27375653],"study_design_scores_gemma":[0.00021415335,0.00044593244,0.7025158,0.00047505109,0.00009199173,0.00006296985,0.088413015,0.0033854472,0.0018591359,0.0065638158,0.19580436,0.00016833904],"about_ca_topic_score_codex":0.9852336,"about_ca_topic_score_gemma":0.9951351,"teacher_disagreement_score":0.77149355,"about_ca_system_score_codex":0.22850643,"about_ca_system_score_gemma":0.412862,"threshold_uncertainty_score":0.8948232},"labels":[],"label_agreement":null},{"id":"W3011346301","doi":"10.3138/jvme.2019-0058","title":"Developing Miller’s Pyramid to Support Students’ Assessment Literacy","year":2020,"lang":"en","type":"article","venue":"Journal of Veterinary Medical Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Pyramid (geometry); Curriculum; Literacy; Miller; Relevance (law); Needs assessment; Work (physics); Computer science; Psychology; Engineering ethics; Medical education; Mathematics education; Pedagogy; Sociology; Engineering; Medicine; Political science; Social science","score_opus":0.1434371480127097,"score_gpt":0.5190844493078557,"score_spread":0.375647301295146,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3011346301","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14992976,0.00019887942,0.74551713,0.0116241565,0.00021488537,0.0026404734,0.00030132572,0.0056462972,0.083927035],"genre_scores_gemma":[0.30281222,0.00017804498,0.68907577,0.0005584936,0.000024564077,0.0009917353,0.00019186149,0.00010814247,0.006059155],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99554944,0.0013092832,0.00029133263,0.0003367129,0.0022113908,0.0003018413],"domain_scores_gemma":[0.98682016,0.0060884613,0.0010543058,0.0011073418,0.0037453142,0.001184415],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0074203606,0.00052563165,0.0004402458,0.0015014161,0.001082691,0.0029226744,0.0015483504,0.0011290062,0.0049514617],"category_scores_gemma":[0.022374056,0.0003671208,0.00061432936,0.00082384126,0.0010601362,0.0042831963,0.00396441,0.0018959173,0.0016294135],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016298606,0.0024067666,0.023153089,0.00063988223,0.000024279814,0.00040835975,0.01584187,0.009614794,0.019439757,0.11276417,0.032029055,0.78351486],"study_design_scores_gemma":[0.00024091578,0.0032868697,0.051461186,0.0018136019,0.00013524451,0.0014994937,0.018249229,0.35507017,0.034237478,0.23871374,0.29488626,0.0004058026],"about_ca_topic_score_codex":0.0038275188,"about_ca_topic_score_gemma":0.006519481,"teacher_disagreement_score":0.0074203606,"about_ca_system_score_codex":0.0028416838,"about_ca_system_score_gemma":0.009566423,"threshold_uncertainty_score":0.039243102},"labels":[],"label_agreement":null},{"id":"W3013727910","doi":"10.4018/978-1-7998-2943-0.ch001","title":"Innovation, Critical Pedagogy, and Appreciative Feedback","year":2020,"lang":"en","type":"book-chapter","venue":"Advances in higher education and professional development book series","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Royal Roads University","funders":"","keywords":"Dialogic; Scope (computer science); Dyad; Power (physics); Pedagogy; Process (computing); Critical pedagogy; Appreciative inquiry; Through-the-lens metering; Psychology; Sociology; Engineering; Computer science; Lens (geology); Social psychology","score_opus":0.04357742160523497,"score_gpt":0.4046063351145801,"score_spread":0.36102891350934513,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3013727910","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009962394,0.0702809,0.060246825,0.03016169,0.0041064476,0.0004136459,0.00004375695,0.00030258505,0.82448167],"genre_scores_gemma":[0.42457038,0.09836841,0.077466436,0.013353138,0.0050081005,0.0019005017,0.00013442455,0.0003779878,0.37882066],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9949927,0.0027444067,0.00015264795,0.00029313425,0.0015721807,0.00024498263],"domain_scores_gemma":[0.9906094,0.0072724363,0.0004864714,0.00036078328,0.0007496707,0.0005212142],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004281094,0.0008270465,0.00042841936,0.001954411,0.00224423,0.007138343,0.000979348,0.0019135852,0.005773222],"category_scores_gemma":[0.010442741,0.00024200314,0.00031358955,0.001546404,0.01634843,0.0075558536,0.0038161017,0.0045107175,0.0009985232],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000018911378,0.000059166323,0.0001868814,0.0004795888,0.000003847642,0.00011593665,0.02142479,0.000284827,0.00037032348,0.8395289,0.021449847,0.1160771],"study_design_scores_gemma":[0.000016282595,0.000081960636,0.00043235777,0.001295431,0.0000055146143,0.00046978742,0.007531057,0.0004268205,0.0006046278,0.46207583,0.52703625,0.000023973591],"about_ca_topic_score_codex":0.0014789087,"about_ca_topic_score_gemma":0.0016820264,"teacher_disagreement_score":0.007138343,"about_ca_system_score_codex":0.004762377,"about_ca_system_score_gemma":0.0062128166,"threshold_uncertainty_score":0.034553647},"labels":[],"label_agreement":null},{"id":"W3016349227","doi":"10.17632/hfkt24zxcw.1","title":"2012-2018 Direct Writing Assessment Scores for an international school (K-12) in Bangkok, Thailand","year":2020,"lang":"en","type":"article","venue":"Data Archiving and Networked Services (DANS)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Psychology; Political science; Geography","score_opus":0.06343688411253688,"score_gpt":0.3663497340823161,"score_spread":0.3029128499697792,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3016349227","genre_codex":"empirical","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98193914,0.00004261955,0.00027825384,0.00011760388,0.000024053583,0.00026025725,0.008114772,0.00006949298,0.009153804],"genre_scores_gemma":[0.9622624,0.0001539193,0.0017735689,0.000057607664,0.000016182026,0.0007297241,0.010693954,0.000033089058,0.024279553],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.999223,0.0001240032,0.00013037195,0.00018081166,0.00020194387,0.0001400036],"domain_scores_gemma":[0.99545175,0.00020798836,0.0008937687,0.00015828731,0.0018925576,0.0013957407],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0012709214,0.0004959955,0.00025394736,0.0011643359,0.00079720234,0.0011780922,0.0006426625,0.00022901643,0.0067972937],"category_scores_gemma":[0.0036430294,0.00032270345,0.00028067167,0.001219967,0.00038573417,0.0006432802,0.0011182538,0.0007684705,0.003287366],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002684709,0.00036212528,0.93426234,0.00016781472,0.000021901626,0.00043824143,0.008702076,0.00023920306,0.0009692251,0.000108161126,0.009472775,0.04498754],"study_design_scores_gemma":[0.0000095923715,0.00019015325,0.9873984,0.000043449352,0.000008048935,0.0001417986,0.0071287015,0.00012501313,0.000680704,0.000032672167,0.0042236014,0.000017942783],"about_ca_topic_score_codex":0.037582185,"about_ca_topic_score_gemma":0.1258934,"teacher_disagreement_score":0.037582185,"about_ca_system_score_codex":0.0015573491,"about_ca_system_score_gemma":0.0032532644,"threshold_uncertainty_score":0.07472688},"labels":[],"label_agreement":null},{"id":"W3028174053","doi":"10.37590/able.v41.abs78","title":"Examining the efficacy of peer feedback as part of the writing process in an introductory biology course","year":2020,"lang":"en","type":"article","venue":"Advances in Biology Laboratory Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Lethbridge","funders":"","keywords":"Course (navigation); Peer feedback; Writing process; Process (computing); Mathematics education; Computer science; Psychology; Physics; Programming language; Astronomy","score_opus":0.029020089710651183,"score_gpt":0.4120239851794286,"score_spread":0.38300389546877744,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3028174053","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9974137,0.000074793774,0.00038302538,0.00019621674,0.00003124518,0.00020978993,0.000015604686,0.000020554267,0.0016549373],"genre_scores_gemma":[0.99742246,0.00010400423,0.0013240346,0.00010030914,0.00003251347,0.00027299765,0.000027552991,0.000010906625,0.00070530304],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.929276,0.04797981,0.0046592895,0.0026381547,0.013713926,0.00173273],"domain_scores_gemma":[0.5876896,0.29780728,0.04607855,0.013496654,0.04381068,0.011117239],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.06981675,0.00054469897,0.0008228171,0.0018827997,0.0019869665,0.0026029167,0.0013503684,0.0012890097,0.0014361652],"category_scores_gemma":[0.2712984,0.0006432361,0.00094011676,0.0007705755,0.0015548645,0.0019514821,0.0018172425,0.0021456655,0.00058347255],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.006274956,0.0215648,0.555615,0.0011774006,0.00068406516,0.00041130898,0.11703635,0.0008808174,0.008712022,0.0005318246,0.002483821,0.2846275],"study_design_scores_gemma":[0.0005411936,0.046427354,0.8974556,0.00072490214,0.00042387153,0.00036776162,0.038447823,0.0035646313,0.0076399907,0.00048421125,0.0037216113,0.00020105699],"about_ca_topic_score_codex":0.0014105815,"about_ca_topic_score_gemma":0.0021479228,"teacher_disagreement_score":0.06981675,"about_ca_system_score_codex":0.0015156615,"about_ca_system_score_gemma":0.0026251588,"threshold_uncertainty_score":0.3692307},"labels":[],"label_agreement":null},{"id":"W3033487789","doi":"10.1186/s41039-020-00134-8","title":"Can automated item generation be used to develop high quality MCQs that assess application of knowledge?","year":2020,"lang":"en","type":"article","venue":"Research and Practice in Technology Enhanced Learning","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":43,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta; University of Ottawa; Ottawa Hospital; Medical Council of Canada","funders":"","keywords":"Quality (philosophy); Multiple choice; Cognition; Recall; Item analysis; Wilcoxon signed-rank test; Sample (material); Computer science; Test (biology); Modalities; Psychology; Psychometrics; Significant difference; Statistics; Clinical psychology; Mathematics; Cognitive psychology","score_opus":0.2606414184306209,"score_gpt":0.5297904732686232,"score_spread":0.2691490548380023,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3033487789","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.84545594,0.0022369504,0.13570732,0.0018614208,0.00041770935,0.005261413,0.0009607819,0.0016228147,0.006475618],"genre_scores_gemma":[0.8174748,0.00063572556,0.17715408,0.000688999,0.00017957749,0.0027727499,0.00053202285,0.00010586436,0.0004561275],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9288949,0.05319733,0.0040096347,0.0020596904,0.011251279,0.0005871926],"domain_scores_gemma":[0.5636616,0.33847493,0.03340413,0.021938259,0.04097394,0.0015472098],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.11042037,0.0007186647,0.0011802893,0.0039079795,0.00030396608,0.0015309192,0.0014379326,0.0010789555,0.0022090129],"category_scores_gemma":[0.29336393,0.00041214383,0.0008613601,0.0022734422,0.00090109167,0.0017618865,0.0012161818,0.0006849696,0.000956236],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.003593423,0.0010173749,0.2045776,0.0014979528,0.00048450497,0.00010663319,0.0028197123,0.0029298246,0.007329383,0.0005509155,0.004932938,0.7701597],"study_design_scores_gemma":[0.002731303,0.017222796,0.847783,0.002680758,0.00084680953,0.001433309,0.003323862,0.06446222,0.028688857,0.0049849376,0.025386088,0.00045602684],"about_ca_topic_score_codex":0.0010845383,"about_ca_topic_score_gemma":0.0016784511,"teacher_disagreement_score":0.11042037,"about_ca_system_score_codex":0.000771681,"about_ca_system_score_gemma":0.0009653654,"threshold_uncertainty_score":0.5839657},"labels":[],"label_agreement":null},{"id":"W3036912581","doi":"10.18438/eblip29709","title":"Using Assessment Tools to Develop a Workshop for Library Staff: Establishing a Culture of Assessment","year":2020,"lang":"en","type":"article","venue":"Evidence Based Library and Information Practice","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"University of Illinois at Chicago; University of Illinois at Urbana-Champaign","keywords":"Computer science; Library science; Data science; Engineering management; World Wide Web; Medical education; Medicine; Engineering","score_opus":0.08634915348694418,"score_gpt":0.391862556407179,"score_spread":0.3055134029202348,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3036912581","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.43145183,0.002948307,0.34294868,0.048402056,0.0041838083,0.01773797,0.00055652007,0.0052791913,0.14649169],"genre_scores_gemma":[0.6710523,0.0011750021,0.30565977,0.0030625474,0.0001845984,0.0074752485,0.0002496897,0.00030897852,0.010831808],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.80858463,0.15084551,0.0113024255,0.0026515562,0.023763433,0.0028524306],"domain_scores_gemma":[0.6652491,0.2014888,0.021857796,0.018215511,0.07758273,0.015606041],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.16908537,0.0008558835,0.000873173,0.0037933635,0.004557801,0.010256968,0.0036818378,0.0023602557,0.0033540875],"category_scores_gemma":[0.32541567,0.0006687167,0.0010280199,0.0021189728,0.003221212,0.008688807,0.013835989,0.0046022967,0.002679516],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034638608,0.0025780597,0.02891723,0.0044283243,0.00009915888,0.00040366172,0.13228516,0.0012821807,0.004796195,0.006367404,0.02619734,0.79229885],"study_design_scores_gemma":[0.00069715,0.009612873,0.113052785,0.033128712,0.00057367794,0.0019446904,0.40321413,0.01875401,0.048632566,0.0383366,0.33044592,0.0016068463],"about_ca_topic_score_codex":0.0012034172,"about_ca_topic_score_gemma":0.0030895758,"teacher_disagreement_score":0.16908537,"about_ca_system_score_codex":0.0043137847,"about_ca_system_score_gemma":0.01841674,"threshold_uncertainty_score":0.8942196},"labels":[],"label_agreement":null},{"id":"W3046538170","doi":"10.1111/emip.12382","title":"Synergy and Tension between Large‐Scale and Classroom Assessment: International Trends","year":2020,"lang":"en","type":"article","venue":"Educational Measurement Issues and Practice","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":21,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Queen's University; Brock University","funders":"","keywords":"Scale (ratio); Test (biology); Political science; Mathematics education; Pedagogy; Sociology; Psychology; Geography; Geology; Cartography","score_opus":0.09632131387335943,"score_gpt":0.42067691106516314,"score_spread":0.32435559719180374,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3046538170","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6923557,0.08575698,0.012100718,0.10650138,0.0005356059,0.00008126989,0.0004144431,0.00017276227,0.102081224],"genre_scores_gemma":[0.9889381,0.007133181,0.0019861474,0.0010626396,0.00013192648,0.000022465767,0.0000621931,0.000026247964,0.00063706114],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9779327,0.009496402,0.0020225488,0.003315778,0.005945744,0.0012868799],"domain_scores_gemma":[0.79710925,0.12863964,0.018206926,0.008969309,0.04136628,0.005708543],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.046076596,0.00019608988,0.0005050337,0.004356804,0.00096165075,0.006938803,0.0012651858,0.00094193954,0.0025724433],"category_scores_gemma":[0.05747416,0.00031086826,0.00021280577,0.009207913,0.006573258,0.008068855,0.005446479,0.0026973805,0.00023732554],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021067033,0.00020170554,0.2032793,0.002084328,0.00011087031,0.00022036758,0.041262157,0.0013057038,0.0017646984,0.09733063,0.0064678746,0.64576167],"study_design_scores_gemma":[0.000023682322,0.0004931898,0.7198912,0.004646169,0.000078776975,0.0009358522,0.10282808,0.0022121358,0.0020133997,0.02183255,0.14489502,0.00014998252],"about_ca_topic_score_codex":0.014271814,"about_ca_topic_score_gemma":0.013667175,"teacher_disagreement_score":0.046076596,"about_ca_system_score_codex":0.004967979,"about_ca_system_score_gemma":0.007635783,"threshold_uncertainty_score":0.24367923},"labels":[],"label_agreement":null},{"id":"W3046571216","doi":"10.5430/jct.v9n3p33","title":"The Effect of Formative Assessment on the Academic Achievement Levels of Prospective Teachers","year":2020,"lang":"en","type":"article","venue":"Journal of Curriculum and Teaching","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Formative assessment; Psychology; Qualitative property; Mathematics education; Data collection; Qualitative research; Test (biology); Documentation; Research design; Academic year; Academic achievement; Affect (linguistics); Medical education; Computer science; Mathematics; Medicine; Statistics","score_opus":0.024088470971229545,"score_gpt":0.3627800769070531,"score_spread":0.33869160593582354,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3046571216","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9955024,0.00023126238,0.0023919663,0.00012454059,0.0000401588,0.00017979431,0.000024317458,0.000037293972,0.0014683525],"genre_scores_gemma":[0.9950112,0.00018993858,0.0039731455,0.000055300112,0.000036339025,0.00021483692,0.000039423747,0.0000071851323,0.0004726683],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.97071236,0.016328566,0.0025374491,0.0018277414,0.007793099,0.00080072763],"domain_scores_gemma":[0.8296387,0.11660551,0.025137609,0.011257922,0.013835554,0.0035247433],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.027881505,0.0007887769,0.0005357716,0.0010833029,0.00091633294,0.0021915836,0.0011337369,0.0006339475,0.00084774464],"category_scores_gemma":[0.10687324,0.00041959426,0.00076294795,0.0006235428,0.00090381486,0.0014903034,0.0014779324,0.0011388601,0.0001980924],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0029181743,0.010181853,0.5337041,0.0010445217,0.00058162236,0.00027934927,0.03353981,0.0011674261,0.017202832,0.00049378077,0.0005729233,0.39831373],"study_design_scores_gemma":[0.00027039068,0.026370358,0.92908275,0.00050520163,0.00046950462,0.00042352022,0.015597953,0.0017821763,0.02111716,0.0006521949,0.0035754787,0.00015328416],"about_ca_topic_score_codex":0.0009855198,"about_ca_topic_score_gemma":0.0013206727,"teacher_disagreement_score":0.027881505,"about_ca_system_score_codex":0.00085153314,"about_ca_system_score_gemma":0.0020097492,"threshold_uncertainty_score":0.14745325},"labels":[],"label_agreement":null},{"id":"W3076472937","doi":"10.5539/elt.v13n9p10","title":"A Review of the Washback of English Language Tests on Classroom Teaching","year":2020,"lang":"en","type":"review","venue":"English Language Teaching","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Syllabus; Psychology; Mathematics education; English language; Test (biology); Empirical research; Language education; Teaching method; Language assessment; Pedagogy; Mathematics","score_opus":0.02859189116016439,"score_gpt":0.3774667469147653,"score_spread":0.34887485575460087,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3076472937","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00014425616,0.99939156,0.0000446958,0.00010641408,0.00006891504,0.000008362559,0.000011974335,0.0000024222538,0.00022139608],"genre_scores_gemma":[0.0013186857,0.9983311,0.00012339198,0.00010287931,0.000039753144,0.000012548001,0.00001557712,0.0000013027508,0.000054847464],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99745923,0.0007931975,0.00068365963,0.00028109644,0.00071098574,0.00007183387],"domain_scores_gemma":[0.98452526,0.011964867,0.0012702151,0.00024110342,0.0018103388,0.00018814475],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0048153,0.00089888915,0.0021221146,0.005955736,0.00045212728,0.0013920459,0.0014229476,0.0012770644,0.0024701594],"category_scores_gemma":[0.013738095,0.00066554215,0.0015668068,0.005890982,0.0009218217,0.0019540286,0.00093467627,0.0012690998,0.00055815553],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011803405,0.00008026908,0.0004392018,0.19439057,0.0004399983,0.000100711004,0.0003620558,0.00014898094,0.00054797356,0.0012347922,0.0074063023,0.79473114],"study_design_scores_gemma":[0.000087878674,0.0007274963,0.0140725,0.3547641,0.004979433,0.0020787138,0.0008749309,0.00018272901,0.0015699569,0.0016712161,0.61889493,0.00009605176],"about_ca_topic_score_codex":0.005103676,"about_ca_topic_score_gemma":0.010373447,"teacher_disagreement_score":0.005955736,"about_ca_system_score_codex":0.0013871725,"about_ca_system_score_gemma":0.004514983,"threshold_uncertainty_score":0.025466025},"labels":[],"label_agreement":null},{"id":"W3084220926","doi":"","title":"Exploring science teachers’ conceptions and efficacy of assessment in Manitoba schools: A case study.","year":2019,"lang":"en","type":"dissertation","venue":"Mspace (University of Manitoba)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Mathematics education; Pedagogy; Sociology; Psychology","score_opus":0.08932588436502209,"score_gpt":0.33666609939273756,"score_spread":0.24734021502771547,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3084220926","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9940718,0.00030471836,0.00040530955,0.0011514684,0.00001108108,0.00007576163,0.000015187204,0.0000065485015,0.0039581014],"genre_scores_gemma":[0.99408543,0.00046979185,0.00086842495,0.0002712027,0.0000033331694,0.00007942253,0.000015417021,0.0000070930973,0.004199869],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9956768,0.002423442,0.00015667418,0.00030332225,0.00063489494,0.0008048204],"domain_scores_gemma":[0.9930681,0.0031419375,0.00082727295,0.00026328603,0.0016021528,0.0010972157],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0060790004,0.0005240548,0.00046158672,0.0017480786,0.018189097,0.0044241734,0.0018772475,0.0015987502,0.0013646316],"category_scores_gemma":[0.00724473,0.00093246007,0.00027699326,0.0022096583,0.0069698654,0.0014640738,0.0039856816,0.0027848606,0.00020713818],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000030431287,0.00022669513,0.04735497,0.00007750097,0.000007434876,0.0037532803,0.93845624,0.00011909491,0.0010250927,0.0016604749,0.00037294987,0.006915809],"study_design_scores_gemma":[0.0000075020967,0.00009239726,0.04019498,0.00012270441,0.000014342581,0.00048101507,0.94852823,0.0003127277,0.00049120537,0.00024323966,0.009490855,0.000020925092],"about_ca_topic_score_codex":0.582316,"about_ca_topic_score_gemma":0.84372556,"teacher_disagreement_score":0.41768402,"about_ca_system_score_codex":0.028448202,"about_ca_system_score_gemma":0.028440103,"threshold_uncertainty_score":0.8402877},"labels":[],"label_agreement":null},{"id":"W3084713209","doi":"10.4018/978-1-7998-5030-4.ch008","title":"Chinese International Graduate Students' Perceptions of Classroom Assessment at a Canadian University","year":2020,"lang":"en","type":"book-chapter","venue":"Advances in higher education and professional development book series","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Windsor","funders":"","keywords":"Data collection; Medical education; Perception; Psychology; Graduate students; Qualitative property; Diversity (politics); Transparency (behavior); Pedagogy; Mathematics education; Medicine; Sociology; Political science; Computer science; Social science","score_opus":0.027426370367356873,"score_gpt":0.37094936101189274,"score_spread":0.34352299064453584,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3084713209","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9785144,0.00052514084,0.0001340526,0.0007314126,0.000022830412,0.000023352837,0.00003982656,0.000011107994,0.019997735],"genre_scores_gemma":[0.9935783,0.00067996193,0.00015992828,0.00017291612,0.0000042690717,0.000011008289,0.000037394093,0.000005800297,0.005350292],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99801457,0.0002970246,0.000067375666,0.00013714509,0.0010043451,0.0004795634],"domain_scores_gemma":[0.9964232,0.00057283044,0.00027489933,0.000060865048,0.0014632425,0.0012049794],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021533936,0.00029647336,0.00027242614,0.0012031754,0.0055569243,0.0040974184,0.00055358483,0.0004305495,0.0027077522],"category_scores_gemma":[0.004141501,0.00013971864,0.00020294846,0.002245686,0.002526989,0.000984105,0.0018136427,0.0012472811,0.00020065259],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000055617737,0.00011043811,0.1034726,0.00013718355,0.000009762618,0.0004206521,0.84031487,0.00008425262,0.002659677,0.0024103562,0.00414526,0.046179447],"study_design_scores_gemma":[0.000004691629,0.00010890864,0.14341597,0.00015625845,0.000012824812,0.00018172272,0.8275764,0.0001394393,0.00048535143,0.00020112969,0.027662612,0.000054787677],"about_ca_topic_score_codex":0.7887835,"about_ca_topic_score_gemma":0.87981385,"teacher_disagreement_score":0.21121651,"about_ca_system_score_codex":0.012924693,"about_ca_system_score_gemma":0.01527962,"threshold_uncertainty_score":0.4249208},"labels":[],"label_agreement":null},{"id":"W3088489015","doi":"","title":"Critical Education: Increasing Student Achievement through Formative Assessments","year":2020,"lang":"en","type":"article","venue":"Scholarship@Western (Western University)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Formative assessment; Mathematics education; Academic achievement; Student achievement; Pedagogy; Psychology; Medical education; Political science; Medicine","score_opus":0.1605869940978424,"score_gpt":0.4477805437303521,"score_spread":0.28719354963250965,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3088489015","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4186999,0.00086064806,0.17734107,0.020847244,0.0012177012,0.010689127,0.0023112965,0.011782297,0.3562506],"genre_scores_gemma":[0.71488804,0.00093540974,0.23659788,0.0019168092,0.00023328855,0.0062695355,0.0011152312,0.0006118339,0.03743199],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9893695,0.0039550946,0.0006611363,0.00078944874,0.0043596337,0.0008651702],"domain_scores_gemma":[0.97529227,0.007007937,0.0035631706,0.0026642645,0.0080447905,0.0034275667],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013665208,0.00084359397,0.00042410765,0.004559069,0.0022889485,0.0053993203,0.0022718615,0.00083945034,0.008428366],"category_scores_gemma":[0.036948495,0.0004755972,0.0006427538,0.002058908,0.001361315,0.0048071737,0.0058415197,0.0023885202,0.0024022062],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015080241,0.0032252788,0.028853089,0.000447202,0.000038120277,0.00010446983,0.0140704205,0.0005147232,0.0026623742,0.008613113,0.03757116,0.90374917],"study_design_scores_gemma":[0.0005191434,0.006563918,0.31565312,0.0047375034,0.00029094133,0.00092715386,0.037116293,0.008663311,0.054231428,0.07223845,0.4983975,0.0006613466],"about_ca_topic_score_codex":0.005490938,"about_ca_topic_score_gemma":0.009229707,"teacher_disagreement_score":0.013665208,"about_ca_system_score_codex":0.0032296297,"about_ca_system_score_gemma":0.010292715,"threshold_uncertainty_score":0.07226944},"labels":[],"label_agreement":null},{"id":"W3090347405","doi":"10.16986/huje.2020063705","title":"Guidelines for Generating Effective Feedback from E-Assessments","year":2020,"lang":"en","type":"article","venue":"Hacettepe University Journal of Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Computer science; Psychology","score_opus":0.07753533092986926,"score_gpt":0.39255052791016115,"score_spread":0.3150151969802919,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3090347405","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.029283023,0.005029759,0.752343,0.018613523,0.0014996302,0.07468755,0.003195616,0.016953185,0.09839474],"genre_scores_gemma":[0.0330909,0.0028352756,0.9276616,0.0011482455,0.00017255414,0.022646794,0.0013043088,0.00048922823,0.010651089],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9097169,0.057132795,0.012470212,0.0016735148,0.017433744,0.001572828],"domain_scores_gemma":[0.790224,0.09585362,0.013016641,0.014448495,0.08074578,0.00571148],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.07586309,0.0021101364,0.0012278343,0.007056892,0.0020920478,0.006543008,0.0043003433,0.004870391,0.016696997],"category_scores_gemma":[0.18564615,0.0012660109,0.0014381785,0.0036358263,0.0013528481,0.0049771545,0.004086102,0.0032185288,0.017997386],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00050291925,0.0024944125,0.006293266,0.005135175,0.000064788466,0.0009833111,0.011342289,0.0032574206,0.008438207,0.009660516,0.10039429,0.8514335],"study_design_scores_gemma":[0.0014527814,0.0039343527,0.048396442,0.03631695,0.00024012524,0.0034458044,0.020695481,0.021112544,0.026910145,0.048660714,0.78795755,0.0008771308],"about_ca_topic_score_codex":0.00483306,"about_ca_topic_score_gemma":0.012022321,"teacher_disagreement_score":0.07586309,"about_ca_system_score_codex":0.0028921184,"about_ca_system_score_gemma":0.01436029,"threshold_uncertainty_score":0.4012072},"labels":[],"label_agreement":null},{"id":"W3092500786","doi":"10.47670/wuwijar201821lh","title":"Direct assessment of second language writing: Holistic and analytic scoring","year":2018,"lang":"en","type":"article","venue":"Westcliff International Journal of Applied Research","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Wycliffe College","funders":"","keywords":"Rubric; Writing assessment; Language assessment; Task (project management); Test (biology); Mathematics education; Standards-based assessment; Reliability (semiconductor); Peer assessment; Psychology; Educational assessment; Computer science","score_opus":0.09942307377488162,"score_gpt":0.5055932593544762,"score_spread":0.40617018557959456,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3092500786","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.36252895,0.028168624,0.45311987,0.0033642256,0.0013680079,0.0062201745,0.00095388823,0.0016276898,0.14264855],"genre_scores_gemma":[0.52145064,0.01236416,0.4524756,0.00045003253,0.00023444863,0.0036031061,0.00051396166,0.00016085076,0.008747091],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.97320175,0.007825904,0.0028641613,0.0011273117,0.014682858,0.00029808353],"domain_scores_gemma":[0.9673738,0.011528684,0.0044393134,0.001664513,0.01414482,0.00084890326],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.019752024,0.00087705156,0.0014708415,0.008483659,0.0008798594,0.0032789116,0.0012849804,0.0006562821,0.0028194285],"category_scores_gemma":[0.059764605,0.00043553967,0.0009237697,0.0049524577,0.002391607,0.00344912,0.0040156296,0.0010372308,0.0010161032],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018789808,0.00017947548,0.030566221,0.0017402013,0.00008286125,0.00007692548,0.003467667,0.0004864152,0.0041846484,0.0067017167,0.0028703178,0.9494557],"study_design_scores_gemma":[0.00040480413,0.007045375,0.6145904,0.013190687,0.0007307819,0.009585685,0.03596938,0.03504802,0.03738033,0.093861535,0.15129125,0.0009017129],"about_ca_topic_score_codex":0.0011855694,"about_ca_topic_score_gemma":0.0041460586,"teacher_disagreement_score":0.019752024,"about_ca_system_score_codex":0.0016057028,"about_ca_system_score_gemma":0.003717713,"threshold_uncertainty_score":0.10445994},"labels":[],"label_agreement":null},{"id":"W3094750526","doi":"10.5539/ijel.v10n6p381","title":"Promoted Peer Review in EFL Writing: Development in Students’ Perceptions and Feedback","year":2020,"lang":"en","type":"article","venue":"International Journal of English Linguistics","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"King Saud University","keywords":"Psychology; Medical education; Session (web analytics); Perception; Peer feedback; Promotion (chess); Mathematics education; Medicine; Computer science","score_opus":0.051053419853868846,"score_gpt":0.3924193996363336,"score_spread":0.34136597978246475,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3094750526","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99611026,0.0003617868,0.0010969815,0.00039600045,0.00002849318,0.00010453539,0.000009094547,0.000030078641,0.0018627284],"genre_scores_gemma":[0.9975453,0.00023759087,0.0013363092,0.00014101059,0.00002423549,0.00007099254,0.00001052677,0.000009780563,0.00062418415],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.96047556,0.02234443,0.0022852444,0.0013390717,0.012477754,0.0010780152],"domain_scores_gemma":[0.8546026,0.08409467,0.026751904,0.0049752486,0.022251723,0.007323911],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.023994347,0.00035427994,0.00051523646,0.0013902964,0.0014185836,0.0030579679,0.00092324533,0.00083279336,0.0010408157],"category_scores_gemma":[0.12580962,0.0003566599,0.00048666922,0.0006482901,0.0016082298,0.0015995785,0.002641786,0.0012767239,0.00028065266],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00035346314,0.0019769801,0.38936406,0.0010429649,0.00014557748,0.001048083,0.34118345,0.00028643513,0.013899936,0.00048408983,0.0016273357,0.24858767],"study_design_scores_gemma":[0.00009847069,0.0042752656,0.7133824,0.00075769686,0.00014330816,0.0035048183,0.24922875,0.0022856572,0.008446145,0.0007221323,0.01690865,0.000246756],"about_ca_topic_score_codex":0.001109511,"about_ca_topic_score_gemma":0.0012019239,"teacher_disagreement_score":0.9760057,"about_ca_system_score_codex":0.0010248672,"about_ca_system_score_gemma":0.0022898244,"threshold_uncertainty_score":0.12689573},"labels":[],"label_agreement":null},{"id":"W3094847424","doi":"10.5539/ijel.v10n6p347","title":"The Practical Perceptions of Vietnamese Lecturers and Students Towards Written Peer Feedback","year":2020,"lang":"en","type":"article","venue":"International Journal of English Linguistics","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Vietnamese; Perception; Context (archaeology); Peer feedback; Mathematics education; Psychology; Medical education; Pedagogy; Medicine; Geography","score_opus":0.033070435731891674,"score_gpt":0.39738003538951,"score_spread":0.36430959965761833,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3094847424","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9973998,0.00014109333,0.00030240865,0.00031864294,0.000017225753,0.00003057556,0.000007344141,0.0000063428724,0.0017765393],"genre_scores_gemma":[0.99821186,0.0002064667,0.00022964398,0.0001575781,0.00001293539,0.000019442597,0.000009213913,0.0000032147125,0.001149641],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9894748,0.0065189213,0.00063766673,0.0005159986,0.0020012292,0.000851357],"domain_scores_gemma":[0.97718006,0.00988306,0.0036582479,0.0007393501,0.0042954297,0.0042438786],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008115711,0.00032191988,0.00035099077,0.00061102776,0.0017386904,0.0038537285,0.00051807525,0.0009289396,0.0021402054],"category_scores_gemma":[0.029053763,0.00028979094,0.0003956638,0.00033206725,0.0021838145,0.0010693098,0.0020426626,0.0016404158,0.00037092014],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023954616,0.00070377934,0.21506937,0.00037089468,0.00006643614,0.0020644777,0.7206832,0.0003097561,0.0129311895,0.0006758615,0.0011471678,0.045738306],"study_design_scores_gemma":[0.000034740453,0.0026721407,0.14552848,0.00027705205,0.000046732785,0.0016928723,0.833835,0.00069013546,0.002871424,0.00031196504,0.0119171385,0.00012228965],"about_ca_topic_score_codex":0.0031813083,"about_ca_topic_score_gemma":0.0030324617,"teacher_disagreement_score":0.9918843,"about_ca_system_score_codex":0.00091581745,"about_ca_system_score_gemma":0.0015544528,"threshold_uncertainty_score":0.04292047},"labels":[],"label_agreement":null},{"id":"W3095163032","doi":"10.37213/cjal.2020.31121","title":"Portfolio Based Language Assessment (PBLA) in Language Instruction for Newcomers to Canada (LINC) Programs: Taking Stock of Teachers' Experience","year":2020,"lang":"en","type":"article","venue":"Canadian Journal of Applied Linguistics","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Carleton University","funders":"","keywords":"Summative assessment; Formative assessment; Portfolio; Mathematics education; Psychological intervention; Psychology; Medical education; Medicine; Business","score_opus":0.03401772351194283,"score_gpt":0.34175259535421443,"score_spread":0.3077348718422716,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3095163032","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9811379,0.0011084372,0.0021537233,0.0036638076,0.00008963211,0.00020868272,0.00006367062,0.000087243556,0.011487077],"genre_scores_gemma":[0.98599875,0.0009249804,0.005434377,0.0005053064,0.000013069791,0.00008306552,0.00007491344,0.000032721204,0.006932793],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99354494,0.0024551956,0.00022462722,0.0005882978,0.0021583356,0.0010285748],"domain_scores_gemma":[0.98895776,0.0021086999,0.0008050273,0.00038325338,0.004011504,0.0037337395],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0061517176,0.00035316206,0.00040349364,0.00081019115,0.008797751,0.0033035919,0.0016666935,0.0007497886,0.0015442556],"category_scores_gemma":[0.014098831,0.00035951965,0.00020286604,0.0010907328,0.0031330748,0.0016139193,0.004816182,0.00238106,0.00024256378],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001907086,0.0006487107,0.08759871,0.00041743228,0.000019988385,0.001406706,0.5620207,0.0004921459,0.0047589224,0.001985049,0.008256017,0.33220485],"study_design_scores_gemma":[0.000050419836,0.00077632203,0.20719881,0.0007085112,0.00005719225,0.0011499132,0.63425595,0.0016669565,0.0049543586,0.00096706057,0.14797589,0.00023858335],"about_ca_topic_score_codex":0.81511676,"about_ca_topic_score_gemma":0.94719326,"teacher_disagreement_score":0.9647838,"about_ca_system_score_codex":0.035216223,"about_ca_system_score_gemma":0.07007941,"threshold_uncertainty_score":0.37194407},"labels":[],"label_agreement":null},{"id":"W3095324430","doi":"10.1080/00131881.2020.1839353","title":"From sea to sea: The Canadian landscape of assessment education","year":2020,"lang":"en","type":"article","venue":"Educational Research","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Queen's University","funders":"","keywords":"Syllabus; Documentation; Context (archaeology); Teacher education; Pace; Pedagogy; Assessment for learning; Psychology; Mathematics education; Focus group; Formative assessment; Sociology; Medical education; Geography; Medicine","score_opus":0.16246924222224482,"score_gpt":0.5141131410749168,"score_spread":0.351643898852672,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3095324430","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6150715,0.024785101,0.0043167803,0.10627453,0.0007559575,0.000290331,0.002171951,0.00026355166,0.24607028],"genre_scores_gemma":[0.9781294,0.0048380056,0.0024679455,0.0018389497,0.00003120647,0.00004927695,0.00030623743,0.00005424653,0.012284564],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.991088,0.0013820486,0.00024575717,0.0008678275,0.0032932062,0.0031232482],"domain_scores_gemma":[0.9859437,0.0015555413,0.00065103994,0.00031158482,0.006838236,0.004699985],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004045675,0.00040496682,0.00043109345,0.0036150373,0.027602468,0.011699398,0.0023261895,0.0011552584,0.0058963043],"category_scores_gemma":[0.00816572,0.0005207748,0.00040179116,0.009325237,0.011050446,0.0028362197,0.005692729,0.0026395204,0.00034232804],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.0002487293,0.000100292855,0.112116024,0.001026014,0.00005378508,0.0017260349,0.36188883,0.0014695808,0.0019731252,0.086181976,0.049053863,0.3841619],"study_design_scores_gemma":[0.000012931746,0.00006199098,0.24135275,0.0009970546,0.000044788732,0.00031303498,0.30995956,0.0006474617,0.00040275315,0.0044768476,0.44154027,0.0001905529],"about_ca_topic_score_codex":0.9976427,"about_ca_topic_score_gemma":0.99891865,"teacher_disagreement_score":0.7491433,"about_ca_system_score_codex":0.2508567,"about_ca_system_score_gemma":0.3782455,"threshold_uncertainty_score":0.86890006},"labels":[],"label_agreement":null},{"id":"W3095528190","doi":"10.1177/016146812012201115","title":"“The Tail Wagging the Dog”: High-Stakes Testing as a Mediating Context in Secondary Literacy-Related","year":2020,"lang":"en","type":"article","venue":"Teachers College Record The Voice of Scholarship in Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Context (archaeology); Psychology; Test (biology); Curriculum; Graduation (instrument); Focus group; Literacy; Qualitative research; Mathematics education; Standardized test; Distress; Pedagogy; Medical education; Medicine; Sociology; Clinical psychology","score_opus":0.03671470962516018,"score_gpt":0.340418104589002,"score_spread":0.30370339496384186,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3095528190","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9196767,0.0010588663,0.009711131,0.011453678,0.00014500757,0.00016495978,0.00008031405,0.00009900791,0.05761024],"genre_scores_gemma":[0.99753016,0.00012333567,0.0009813097,0.00037813524,0.000012028991,0.00004352764,0.00000825021,0.000020566591,0.00090273685],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.9792005,0.017583784,0.00025518754,0.0009899329,0.000620989,0.0013496291],"domain_scores_gemma":[0.9754166,0.017564908,0.0024296597,0.0014247493,0.00091120927,0.0022529666],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012374946,0.00047370416,0.0004310466,0.001311315,0.009393473,0.007068355,0.0016835235,0.001674413,0.0063498155],"category_scores_gemma":[0.021663133,0.00064619555,0.00050692743,0.0009056947,0.025958486,0.0058784625,0.011834146,0.0025750776,0.0004685397],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000094790674,0.00018419567,0.056123916,0.0002166606,0.000025805273,0.0031500645,0.8780311,0.00011196415,0.0017674573,0.043764602,0.0011843891,0.015345089],"study_design_scores_gemma":[0.00003245559,0.00024818952,0.042161096,0.00088508805,0.0000854813,0.001550675,0.8787499,0.00045186304,0.0021438922,0.02541657,0.04821539,0.00005940358],"about_ca_topic_score_codex":0.009084947,"about_ca_topic_score_gemma":0.011040798,"teacher_disagreement_score":0.012374946,"about_ca_system_score_codex":0.0040002535,"about_ca_system_score_gemma":0.005273727,"threshold_uncertainty_score":0.06544578},"labels":[],"label_agreement":null},{"id":"W3096093179","doi":"10.5206/cjsotl-rcacea.2020.2.8009","title":"Moving Forward or Holding Back? Creating a Culture of Academic Assessment","year":2020,"lang":"en","type":"article","venue":"The Canadian Journal for the Scholarship of Teaching and Learning","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Skepticism; Resistance (ecology); Liberal arts education; Perception; Space (punctuation); Psychology; Medical education; The arts; Higher education; Pedagogy; Sociology; Political science; Medicine; Computer science","score_opus":0.08040758083284723,"score_gpt":0.39121290642895906,"score_spread":0.31080532559611185,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3096093179","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9753921,0.00040112532,0.003515187,0.0076438766,0.00010230367,0.00008404427,0.000015301834,0.000042946045,0.012803134],"genre_scores_gemma":[0.997957,0.00012265916,0.0010009821,0.00036336575,0.000010436184,0.000014686882,0.000006092454,0.000008524323,0.00051624223],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9493206,0.028154004,0.0023011204,0.0016805985,0.014581959,0.0039616763],"domain_scores_gemma":[0.9111769,0.03652401,0.015349868,0.0050914986,0.018510593,0.013347146],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0312725,0.00029949952,0.0005241847,0.0019679703,0.011964265,0.013666879,0.0018128167,0.0012550983,0.0009583434],"category_scores_gemma":[0.07120063,0.00034456595,0.00031210927,0.0026137661,0.015094986,0.004561998,0.0069974377,0.003412263,0.00019594746],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008699149,0.00023821159,0.16138187,0.0001736863,0.00004833593,0.0004397796,0.7473477,0.00026142906,0.0033857047,0.009578441,0.0018144673,0.07524336],"study_design_scores_gemma":[0.000014741545,0.00021971407,0.084693104,0.00031059113,0.000025498277,0.00027900163,0.8846346,0.0006016644,0.0013577467,0.0032799144,0.024451522,0.00013190659],"about_ca_topic_score_codex":0.08820444,"about_ca_topic_score_gemma":0.092601456,"teacher_disagreement_score":0.98715246,"about_ca_system_score_codex":0.01284753,"about_ca_system_score_gemma":0.03672624,"threshold_uncertainty_score":0.17538208},"labels":[],"label_agreement":null},{"id":"W3096667251","doi":"10.1075/itl.20006.rez","title":"Peer and teacher assessment of second-language writing in high- and low-stakes conditions","year":2020,"lang":"en","type":"article","venue":"ITL Review of Applied Linguistics","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Psychology; Rasch model; Peer assessment; Writing assessment; Consistency (knowledge bases); Inter-rater reliability; Variation (astronomy); Rating scale; Mathematics education; English language; Peer evaluation; Medical education; Developmental psychology; Medicine; Higher education; Computer science","score_opus":0.025057942438654435,"score_gpt":0.3707478996727184,"score_spread":0.3456899572340639,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3096667251","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9992231,0.000041433406,0.000107685635,0.000015409338,0.0000046203027,0.000013656527,0.000011448496,0.0000062816694,0.00057624246],"genre_scores_gemma":[0.9995598,0.000019327017,0.00015349948,0.000005559268,0.000003893466,0.000017110253,0.000017993128,0.0000023678951,0.00022043844],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9878128,0.006139239,0.0010131783,0.0009144512,0.003701222,0.00041918166],"domain_scores_gemma":[0.94651526,0.02472812,0.011309142,0.0026412178,0.010776872,0.00402937],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009641112,0.00033205838,0.00076972414,0.0016177847,0.0008135678,0.0015349159,0.00049856916,0.00041207802,0.0016080345],"category_scores_gemma":[0.057417955,0.00019261151,0.00027278013,0.0004819273,0.00091928744,0.0008307323,0.0023041011,0.0005473731,0.0003651318],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0017925875,0.001424915,0.8560204,0.00028263286,0.0001537846,0.0008588213,0.03803905,0.00046087473,0.015299672,0.00015939468,0.0007286525,0.08477935],"study_design_scores_gemma":[0.000075935364,0.0025267592,0.9707347,0.00007800532,0.000048919155,0.00075167016,0.016846837,0.0011863023,0.0064884345,0.00023256127,0.0009789215,0.00005089893],"about_ca_topic_score_codex":0.0015026039,"about_ca_topic_score_gemma":0.0029127614,"teacher_disagreement_score":0.009641112,"about_ca_system_score_codex":0.00077665265,"about_ca_system_score_gemma":0.00073760323,"threshold_uncertainty_score":0.05098766},"labels":[],"label_agreement":null},{"id":"W3096866469","doi":"10.5539/ijel.v11n1p68","title":"Washback in Language Testing: An Exploration with a Focus on a Specific EFL Context in Oman","year":2020,"lang":"en","type":"article","venue":"International Journal of English Linguistics","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Context (archaeology); Tourism; Language assessment; Psychology; Focus (optics); Section (typography); Mathematics education; English language; Construct (python library); Language education; Pedagogy; Computer science; Political science; Geography","score_opus":0.07812477684966987,"score_gpt":0.3580429468002768,"score_spread":0.2799181699506069,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3096866469","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9784814,0.0026947102,0.00079640554,0.003762587,0.00004703893,0.000040448474,0.000020565038,0.000009753522,0.014147138],"genre_scores_gemma":[0.9936237,0.00196093,0.00074963656,0.0006285936,0.00002123063,0.000027878274,0.000016436705,0.000009493286,0.002962211],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9971022,0.0017561117,0.000085574495,0.00018515566,0.00032343654,0.0005475167],"domain_scores_gemma":[0.9976774,0.00142583,0.0003033728,0.00005725846,0.0002543594,0.00028179598],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027144097,0.0003683483,0.00041846826,0.0016204602,0.0064443215,0.003913372,0.0011357042,0.0015726755,0.0035491078],"category_scores_gemma":[0.0038320431,0.00028955645,0.00019345668,0.002392753,0.003963714,0.0038597796,0.0046153013,0.0017867014,0.00033880855],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009728826,0.00074726075,0.050490472,0.00097373244,0.000010361008,0.012628668,0.7609354,0.0002473961,0.002361045,0.01832931,0.002407118,0.15077189],"study_design_scores_gemma":[0.0000045567813,0.00013993181,0.046386763,0.00073830155,0.000008468273,0.0021905128,0.91216004,0.0002513942,0.0005750644,0.0022325497,0.035290245,0.00002224636],"about_ca_topic_score_codex":0.008443639,"about_ca_topic_score_gemma":0.036526468,"teacher_disagreement_score":0.008443639,"about_ca_system_score_codex":0.0063576126,"about_ca_system_score_gemma":0.0054172054,"threshold_uncertainty_score":0.046127915},"labels":[],"label_agreement":null},{"id":"W3108940771","doi":"10.4018/978-1-7998-3473-1.ch019","title":"Automating the Generation of Test Items","year":2020,"lang":"en","type":"book-chapter","venue":"Advances in logistics, operations, and management science book series","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Test (biology); Computer science; Domain (mathematical analysis); Data science; Machine learning; Artificial intelligence; Information retrieval; Mathematics","score_opus":0.04221560599566671,"score_gpt":0.3313379888908244,"score_spread":0.2891223828951577,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3108940771","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026807532,0.0008395455,0.8716841,0.0010047723,0.00066849403,0.0030953565,0.002216419,0.020233752,0.07345003],"genre_scores_gemma":[0.033629254,0.0006548705,0.9292161,0.00031384674,0.000080699036,0.0015221986,0.0032206753,0.0014525363,0.029909842],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9960622,0.0017964176,0.00021768322,0.00045113635,0.0013680757,0.0001044089],"domain_scores_gemma":[0.9833483,0.011140723,0.00034980814,0.0016227651,0.0033578523,0.0001805013],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0047571706,0.0014489023,0.0010383911,0.0023026054,0.0005847151,0.0024330912,0.0023213418,0.0011509197,0.024294196],"category_scores_gemma":[0.028323507,0.0006850248,0.00066665024,0.002575162,0.00049952173,0.001669758,0.0016276039,0.0014642515,0.022364661],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006839673,0.00017020592,0.0012944997,0.0003688332,0.000011981577,0.00011916481,0.00084361405,0.004441942,0.0075455788,0.006238141,0.033403758,0.945494],"study_design_scores_gemma":[0.00023370693,0.00082046876,0.013262801,0.0012340809,0.00010291234,0.0019003184,0.0022535527,0.21591863,0.07860183,0.06274243,0.6226789,0.00025042007],"about_ca_topic_score_codex":0.0024444563,"about_ca_topic_score_gemma":0.0031039773,"teacher_disagreement_score":0.024294196,"about_ca_system_score_codex":0.0009156714,"about_ca_system_score_gemma":0.001698728,"threshold_uncertainty_score":0.081272185},"labels":[],"label_agreement":null},{"id":"W3109481489","doi":"10.18806/tesl.v37i2.1333","title":"The Amount and Usefulness of Written Corrective Feedback Across Different Educational Contexts and Levels","year":2020,"lang":"en","type":"article","venue":"TESL Canada Journal","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Corrective feedback; Psychology; Mathematics education; Humanities; Art","score_opus":0.03637841302817352,"score_gpt":0.31789534108808604,"score_spread":0.2815169280599125,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3109481489","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9959335,0.0005263189,0.0008634152,0.000097597185,0.000016297687,0.000060445705,0.000060233142,0.00006626385,0.0023760477],"genre_scores_gemma":[0.9945359,0.00039985013,0.002575932,0.000056451718,0.000009871326,0.000033704266,0.00009205086,0.00002159788,0.00227464],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9916848,0.0027618504,0.0006719875,0.00083608145,0.0036237144,0.0004216165],"domain_scores_gemma":[0.9274056,0.03467228,0.011483174,0.0035162629,0.02047737,0.0024452677],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0050841575,0.00052341935,0.00040117343,0.0017924391,0.0010140892,0.0021185533,0.0008855661,0.0005073995,0.0010679379],"category_scores_gemma":[0.06095326,0.00026160726,0.00022097265,0.0008899481,0.0009484284,0.00063789124,0.0010484633,0.00054653845,0.00022490238],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008186862,0.00047026668,0.47126615,0.00090227113,0.00018383964,0.00079443224,0.07712579,0.0007606066,0.041075904,0.0001446908,0.0006998708,0.4057574],"study_design_scores_gemma":[0.000029310586,0.00073642936,0.97191316,0.00027245184,0.00009023373,0.0003788862,0.014609956,0.00059449824,0.005835169,0.000061777835,0.005404957,0.000073196046],"about_ca_topic_score_codex":0.16050453,"about_ca_topic_score_gemma":0.3383199,"teacher_disagreement_score":0.16050453,"about_ca_system_score_codex":0.0029763314,"about_ca_system_score_gemma":0.0049071494,"threshold_uncertainty_score":0.31914055},"labels":[],"label_agreement":null},{"id":"W3109962707","doi":"10.18806/tesl.v37i2.1339","title":"Dynamic Written Corrective Feedback among Graduate Students: The Effects of Feedback Timing","year":2020,"lang":"en","type":"article","venue":"TESL Canada Journal","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Brigham Young University","keywords":"Corrective feedback; Fluency; Grammar; Peer feedback; Psychology; Curriculum; Linguistics; Computer science; Mathematics education; Pedagogy; Philosophy","score_opus":0.023733882282623613,"score_gpt":0.3048955972167413,"score_spread":0.2811617149341177,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3109962707","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99815756,0.00012034657,0.0007234559,0.00010065177,0.00002752653,0.00013450722,0.00001830772,0.000042402517,0.000675227],"genre_scores_gemma":[0.9944417,0.00018898558,0.004218011,0.00014171655,0.000026263173,0.00030325787,0.000041518822,0.000018841574,0.00061966345],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99574333,0.0018543955,0.00043266886,0.0006591309,0.0010125352,0.00029797052],"domain_scores_gemma":[0.96713066,0.02031827,0.0051287264,0.0019370556,0.0024503474,0.0030348902],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004885037,0.0005987952,0.0005862251,0.00062767183,0.00057616236,0.0010916537,0.0008905754,0.0007559295,0.0023512524],"category_scores_gemma":[0.055716336,0.00030676002,0.00039957365,0.00040538845,0.00061222573,0.0007098233,0.0014841302,0.0013831827,0.0002787537],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.010734449,0.021954635,0.199239,0.0014103018,0.00036321132,0.0007910928,0.030730937,0.0015533617,0.053704992,0.0004651169,0.0015945752,0.67745835],"study_design_scores_gemma":[0.0026790684,0.07038314,0.8724763,0.0009864568,0.0006603399,0.0010129001,0.016727395,0.0036002586,0.020160476,0.0014698617,0.009654553,0.0001892361],"about_ca_topic_score_codex":0.0012571051,"about_ca_topic_score_gemma":0.0016898497,"teacher_disagreement_score":0.004885037,"about_ca_system_score_codex":0.0005645114,"about_ca_system_score_gemma":0.001404542,"threshold_uncertainty_score":0.025834858},"labels":[],"label_agreement":null},{"id":"W3109972545","doi":"10.20343/teachlearninqu.9.1.20","title":"Exploring the Emotional Responses of Undergraduate Students to Assessment Feedback: Implications for Instructors","year":2021,"lang":"en","type":"article","venue":"Teaching & Learning Inquiry The ISSOTL Journal","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":51,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"MacEwan University","funders":"MacEwan University; Ohio State University; University of Gloucestershire; Purdue University; Monash University; Leeds Beckett University","keywords":"Psychology; Summative assessment; Peer feedback; Psychological resilience; Variety (cybernetics); Social psychology; Cognition; Negative feedback; Formative assessment; Medical education; Pedagogy","score_opus":0.17912409354407574,"score_gpt":0.44624243943902614,"score_spread":0.2671183458949504,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3109972545","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9857451,0.0013860445,0.0023669251,0.005437937,0.00011419126,0.00008087162,0.000033238524,0.00003455192,0.004801093],"genre_scores_gemma":[0.99574065,0.0010906978,0.0011955241,0.00052907254,0.00003681869,0.000069394264,0.000016615262,0.00000938127,0.0013118448],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9947403,0.0036049406,0.00024842963,0.00013664599,0.0009190516,0.00035069056],"domain_scores_gemma":[0.9773946,0.015563726,0.001411889,0.00036055155,0.003396841,0.0018723623],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0112532005,0.0002728998,0.00045857576,0.0006541833,0.0013938871,0.0038134851,0.0005046504,0.00078603026,0.0013578144],"category_scores_gemma":[0.03836885,0.00012465764,0.0002683503,0.00074422505,0.0015377868,0.0014812244,0.001497155,0.001295166,0.00035619235],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00037559247,0.0009699048,0.17239942,0.0009091805,0.00003666528,0.0016380223,0.5297893,0.00032085986,0.007906271,0.0014870745,0.003060097,0.2811076],"study_design_scores_gemma":[0.000021600497,0.0012215215,0.22087474,0.0010365322,0.000036238318,0.00080694305,0.74811864,0.00082525314,0.0033510446,0.0029467728,0.020679297,0.00008139482],"about_ca_topic_score_codex":0.001397462,"about_ca_topic_score_gemma":0.0025908968,"teacher_disagreement_score":0.0112532005,"about_ca_system_score_codex":0.0011548041,"about_ca_system_score_gemma":0.0018842696,"threshold_uncertainty_score":0.05951327},"labels":[],"label_agreement":null},{"id":"W3113029542","doi":"10.1007/978-3-030-56838-2_2","title":"Mathematics Teacher Education in Ontario, Canada and Mainland China","year":2020,"lang":"en","type":"book-chapter","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Toronto; Institute for Christian Studies","funders":"","keywords":"Certification; Mainland China; Teacher education; China; Certificate in Education; Comparative education; Position (finance); Political science; Service (business); Pedagogy; Mainland; Professional development; Education policy; Mathematics education; Higher education; Medical education; Sociology; Geography; Education; Psychology; Medicine; Business; Marketing","score_opus":0.018091966074435667,"score_gpt":0.2767506281673541,"score_spread":0.25865866209291843,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3113029542","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4847443,0.02136454,0.0005702204,0.013213806,0.0003917461,0.00014215814,0.0054883896,0.00021071595,0.47387412],"genre_scores_gemma":[0.62282443,0.0072820056,0.0009225597,0.0005568049,0.00003195564,0.00005035393,0.0013328819,0.00006212487,0.36693692],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9992705,0.000049986127,0.000022358185,0.00006201381,0.00018396122,0.00041113055],"domain_scores_gemma":[0.9990239,0.00006452705,0.00006538075,0.000017661316,0.00033665515,0.00049186667],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00033002935,0.00029863502,0.00044409625,0.0020655931,0.0099214325,0.0033938228,0.0011068519,0.00059977017,0.011672518],"category_scores_gemma":[0.0008215244,0.00030484196,0.0003301716,0.009356137,0.0018348702,0.0009918923,0.0013852596,0.0009303267,0.00085033715],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033838846,0.00014618758,0.18921134,0.001127089,0.000057471007,0.0027708067,0.091501065,0.0019428189,0.0017822104,0.15818387,0.19960274,0.35333604],"study_design_scores_gemma":[0.00002821488,0.000050429968,0.4529734,0.00045345048,0.000028816376,0.00023723865,0.051826548,0.00078064686,0.00038371852,0.0020665198,0.4911354,0.000035549114],"about_ca_topic_score_codex":0.99694306,"about_ca_topic_score_gemma":0.9996141,"teacher_disagreement_score":0.10143344,"about_ca_system_score_codex":0.10143344,"about_ca_system_score_gemma":0.17357154,"threshold_uncertainty_score":0.7359546},"labels":[],"label_agreement":null},{"id":"W3116449517","doi":"10.31002/ijome.v3i2.3079","title":"Challenges with Implementing Oral Exams in Post-Secondary Mathematics Courses","year":2020,"lang":"en","type":"article","venue":"Indonesian Journal of Mathematics Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Span (engineering); Mathematics education; Attention span; Life span; Mathematics; Psychology; Medicine; Gerontology; Engineering; Cognition","score_opus":0.06228160648665003,"score_gpt":0.3619901061220255,"score_spread":0.29970849963537544,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3116449517","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97211933,0.0005069527,0.0013508301,0.0077403234,0.00030385374,0.0002963347,0.00007945154,0.0001786678,0.017424352],"genre_scores_gemma":[0.98821706,0.00041415228,0.0022838716,0.0013390934,0.000054695083,0.00013716827,0.00007031124,0.00003143104,0.007452158],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.97302026,0.008704097,0.002242022,0.0015391172,0.010206601,0.004287886],"domain_scores_gemma":[0.9329839,0.014993526,0.011172952,0.0028889233,0.021140955,0.016819784],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.017674698,0.0003637799,0.0004919115,0.0010312953,0.0046322877,0.006480565,0.0027608306,0.0018443589,0.0055771],"category_scores_gemma":[0.07879802,0.00052907714,0.0006558604,0.0007713292,0.001468196,0.001984997,0.0045854133,0.0029323965,0.0016350112],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00036808022,0.0025129586,0.35583606,0.00069862505,0.00007545352,0.003158079,0.16280177,0.0008902574,0.006981373,0.0027496568,0.02166611,0.44226158],"study_design_scores_gemma":[0.000080923586,0.0021666845,0.3545845,0.0011843992,0.00008335021,0.0017176538,0.5209427,0.0014006727,0.0066565867,0.0015507899,0.10941634,0.00021537804],"about_ca_topic_score_codex":0.023891764,"about_ca_topic_score_gemma":0.040416088,"teacher_disagreement_score":0.023891764,"about_ca_system_score_codex":0.0060787606,"about_ca_system_score_gemma":0.018514762,"threshold_uncertainty_score":0.09347385},"labels":[],"label_agreement":null},{"id":"W3117672137","doi":"10.3968/11905","title":"Backwash in Higher Education: Calibrating assessment and swinging the pendulum From Summative Assessment","year":2020,"lang":"en","type":"article","venue":"Canadian social science","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Summative assessment; Phenomenon; Affect (linguistics); Higher education; Pedagogy; Mathematics education; Sociology; Psychology; Formative assessment; Epistemology; Philosophy; Political science; Law","score_opus":0.059165992595048456,"score_gpt":0.3728504895420151,"score_spread":0.31368449694696665,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3117672137","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7491261,0.0021754596,0.18170892,0.011092036,0.00063432835,0.0013199341,0.00011834917,0.0014814704,0.05234345],"genre_scores_gemma":[0.94348395,0.00038911897,0.052717295,0.0007091535,0.000053748292,0.00030472648,0.000040517323,0.000110677014,0.0021908784],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9495953,0.03168761,0.0020616322,0.0024591507,0.012659934,0.0015364336],"domain_scores_gemma":[0.8947484,0.069137365,0.008157738,0.009832844,0.01583438,0.0022893138],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.05892587,0.00093692663,0.00082224066,0.0041081067,0.0030270119,0.0075423494,0.0026168048,0.0018330563,0.00207612],"category_scores_gemma":[0.22648819,0.0006947277,0.00046604176,0.0023107752,0.0052299504,0.0062358375,0.00989468,0.002777893,0.00085234],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00048712626,0.0005087819,0.06171715,0.00072080665,0.00007120242,0.00037019138,0.09954886,0.0033079581,0.008786785,0.018527605,0.0037278133,0.80222577],"study_design_scores_gemma":[0.0002704755,0.005727698,0.36830974,0.0081416825,0.00042509648,0.0016305952,0.21273713,0.077094615,0.058239497,0.15035924,0.11595048,0.0011137268],"about_ca_topic_score_codex":0.0059626205,"about_ca_topic_score_gemma":0.0074386457,"teacher_disagreement_score":0.05892587,"about_ca_system_score_codex":0.004798613,"about_ca_system_score_gemma":0.005698832,"threshold_uncertainty_score":0.31163347},"labels":[],"label_agreement":null},{"id":"W3117676024","doi":"10.1002/jee.20376","title":"Peer review as developmental: Exploring the ripple effects of the <scp><i>JEE</i></scp> Mentored Reviewer Program","year":2020,"lang":"en","type":"article","venue":"Journal of Engineering Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Peer mentoring; Ripple; Psychology; Medical education; Engineering; Pedagogy; Medicine","score_opus":0.039213288960016884,"score_gpt":0.3378162465782725,"score_spread":0.2986029576182556,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3117676024","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8527722,0.00091617426,0.014534812,0.019039998,0.00039427058,0.0012397356,0.0003387667,0.00048139176,0.11028274],"genre_scores_gemma":[0.98858196,0.00017579831,0.0045867846,0.0008289309,0.00008321454,0.00054923067,0.00005914412,0.000074934855,0.005060028],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9272674,0.052174356,0.0015335861,0.0026844393,0.014018513,0.0023216903],"domain_scores_gemma":[0.31348002,0.57709426,0.038178787,0.024302075,0.033744283,0.013200599],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.068257675,0.00035225454,0.0005720532,0.001837479,0.0045296294,0.007578134,0.0035769204,0.0022789629,0.00879204],"category_scores_gemma":[0.43449262,0.00054765906,0.00059631944,0.0019161808,0.0036725595,0.00615001,0.0061780997,0.0029598102,0.0011761122],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0038621295,0.006847071,0.33412927,0.0017163374,0.0006711804,0.0009375438,0.06905254,0.0034523667,0.0026505159,0.05589399,0.02263393,0.49815315],"study_design_scores_gemma":[0.001398513,0.008715914,0.68975556,0.0020478265,0.0015497927,0.00085886364,0.1091095,0.0222821,0.0072345063,0.079129785,0.07741636,0.00050136074],"about_ca_topic_score_codex":0.009053168,"about_ca_topic_score_gemma":0.017188843,"teacher_disagreement_score":0.9317423,"about_ca_system_score_codex":0.00494769,"about_ca_system_score_gemma":0.014444913,"threshold_uncertainty_score":0.3609854},"labels":[],"label_agreement":null},{"id":"W3117986551","doi":"10.22215/etd/2019-13853","title":"An Investigation of Jordanian English as a Foreign Language (EFL) Teachers' Perceptions of and Practices in Classroom Assessment","year":2019,"lang":"en","type":"dissertation","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Active listening; Perception; Psychology; Variety (cybernetics); English as a foreign language; Mathematics education; Reading (process); Foreign language; Pedagogy; English language; Medical education; Computer science; Medicine; Political science","score_opus":0.02351437807181366,"score_gpt":0.4057533098005282,"score_spread":0.38223893172871454,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3117986551","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99837863,0.00015087995,0.00008139704,0.00020245556,0.0000032619794,0.000006995312,0.0000059709296,0.0000020873122,0.0011683519],"genre_scores_gemma":[0.99849033,0.00026324578,0.00019317823,0.00017043433,0.000004169698,0.000010641707,0.000009291861,0.0000017910232,0.0008568881],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99750715,0.0011888428,0.00017697384,0.00014985295,0.00067118905,0.00030614494],"domain_scores_gemma":[0.9922742,0.0017722978,0.002058431,0.00018044934,0.002745601,0.0009689419],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0039525395,0.0001594559,0.00025704099,0.0006780499,0.0017427249,0.0018610344,0.00035666398,0.0003377364,0.0010667101],"category_scores_gemma":[0.0064932015,0.00020277708,0.000101625665,0.0005956017,0.001318271,0.0009879576,0.0009786433,0.00066152436,0.00023915408],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000863044,0.00033912307,0.30597115,0.0001791845,0.000013083883,0.00082723796,0.65449005,0.000060535964,0.005118777,0.0004851577,0.0006802929,0.03174913],"study_design_scores_gemma":[0.0000098885885,0.00036817888,0.19639903,0.00013160313,0.000009850318,0.0006198309,0.7887155,0.00016623476,0.00091330643,0.00011547923,0.012529685,0.000021425021],"about_ca_topic_score_codex":0.010134639,"about_ca_topic_score_gemma":0.020298054,"teacher_disagreement_score":0.010134639,"about_ca_system_score_codex":0.0012834338,"about_ca_system_score_gemma":0.0028456878,"threshold_uncertainty_score":0.02090323},"labels":[],"label_agreement":null},{"id":"W3118099899","doi":"10.5539/ijel.v11n1p206","title":"A Study on APSACS Karachi Zone ESL Teachers’ Notion About Assessment and Its Numerous Employment in English Pedagogy","year":2020,"lang":"en","type":"article","venue":"International Journal of English Linguistics","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Formative assessment; Psychology; Likert scale; Summative assessment; Pedagogy; Mathematics education; Medical education; Medicine","score_opus":0.05076778133382033,"score_gpt":0.4085462471080892,"score_spread":0.35777846577426886,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3118099899","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9970446,0.00012205401,0.00011396045,0.00032412895,0.0000082108345,0.000015008783,0.000009255491,0.000001330824,0.0023613987],"genre_scores_gemma":[0.9981317,0.00018469292,0.00009261135,0.00008849341,0.0000038255753,0.000015682705,0.000006504136,0.0000010369238,0.0014755134],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9986337,0.000580815,0.00009819994,0.00015825537,0.000314402,0.00021459848],"domain_scores_gemma":[0.99624497,0.0016993084,0.00062374235,0.00011761851,0.00074042426,0.000573863],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002342563,0.0001659962,0.00019809956,0.00068708166,0.0029533696,0.0021377443,0.00036550497,0.0005929018,0.0021521787],"category_scores_gemma":[0.004396609,0.00027840232,0.00014646215,0.00064964587,0.0029311073,0.0014541057,0.0011961898,0.0013158193,0.00022504246],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000028413875,0.00016140014,0.050615996,0.00012214556,0.0000021990309,0.0011136619,0.9369211,0.000022831582,0.0021028353,0.0010796494,0.00037474514,0.0074549997],"study_design_scores_gemma":[0.0000017765947,0.00010630306,0.050284255,0.000098104276,0.000003635278,0.0003459969,0.9414662,0.000037265454,0.00036030295,0.00012785401,0.00715895,0.000009308228],"about_ca_topic_score_codex":0.009564366,"about_ca_topic_score_gemma":0.01789074,"teacher_disagreement_score":0.009564366,"about_ca_system_score_codex":0.0019500453,"about_ca_system_score_gemma":0.0027478533,"threshold_uncertainty_score":0.019017398},"labels":[],"label_agreement":null},{"id":"W3119940242","doi":"10.5539/ijel.v11n1p266","title":"The Practice of Cross-Grading in Assessing Writing: The Case of EFL Teachers and Students in a Saudi Arabian Context","year":2021,"lang":"en","type":"article","venue":"International Journal of English Linguistics","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Grading (engineering); Psychology; English as a foreign language; Mathematics education; English language; Context (archaeology); Perception; Pedagogy; Medical education; Medicine","score_opus":0.03303773342466218,"score_gpt":0.43774144187120445,"score_spread":0.40470370844654224,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3119940242","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9932995,0.00045174386,0.0024199786,0.0013509926,0.0000441226,0.000089056855,0.000007231966,0.00002642726,0.0023108693],"genre_scores_gemma":[0.99381894,0.0002739788,0.0038238505,0.00044778435,0.000023217612,0.000037502945,0.0000074631002,0.000018574336,0.0015486795],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.96697885,0.024234265,0.0015829286,0.002223226,0.0030395896,0.001941086],"domain_scores_gemma":[0.9471763,0.027230576,0.008351055,0.003378757,0.008398008,0.005465295],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02766512,0.0006709497,0.00076297927,0.0018582189,0.010616339,0.0061815754,0.002522103,0.002698729,0.0014340373],"category_scores_gemma":[0.059937015,0.00073022285,0.00042029246,0.0012574447,0.0059583597,0.0036755183,0.007488154,0.0026174306,0.0004788239],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007249097,0.0002685267,0.02812589,0.00017194166,0.000014078583,0.0043485714,0.9250771,0.000097308286,0.0029712496,0.0004281773,0.00042126296,0.038003515],"study_design_scores_gemma":[0.00001758226,0.00047158924,0.022391178,0.00028353446,0.000023004508,0.005892739,0.9526662,0.0007546094,0.0025538967,0.00069898064,0.014165101,0.00008156141],"about_ca_topic_score_codex":0.005163318,"about_ca_topic_score_gemma":0.012850089,"teacher_disagreement_score":0.02766512,"about_ca_system_score_codex":0.0035200566,"about_ca_system_score_gemma":0.004129524,"threshold_uncertainty_score":0.1463089},"labels":[],"label_agreement":null},{"id":"W3122537597","doi":"10.5430/jnep.v11n5p54","title":"Nursing student perception and performance with collaborative testing","year":2021,"lang":"en","type":"article","venue":"Journal of Nursing Education and Practice","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Perception; Psychology; Medical education; Test (biology); Nursing; Medicine","score_opus":0.08733587536504024,"score_gpt":0.48235061016355796,"score_spread":0.39501473479851773,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3122537597","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9989723,0.00003750442,0.00017726558,0.000082135986,0.000007802274,0.000013895481,0.000011877798,0.0000066399925,0.0006905751],"genre_scores_gemma":[0.9995158,0.000031371048,0.00014810561,0.00003288178,0.0000054537804,0.000014292999,0.000024017443,0.0000028930244,0.00022523936],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9917744,0.002759634,0.00075012085,0.00037713358,0.003663168,0.0006755261],"domain_scores_gemma":[0.95902765,0.016124493,0.010386915,0.0012876008,0.007165953,0.0060074246],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0056207776,0.00027362825,0.00035912602,0.00083708676,0.000537113,0.0017035917,0.0005288354,0.0005902869,0.002875239],"category_scores_gemma":[0.049833212,0.00017215281,0.0005988465,0.00052663113,0.0006421693,0.0007418858,0.0014548919,0.0008629021,0.0006326706],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020483455,0.0011648242,0.9658056,0.000049297378,0.000049939026,0.00017028605,0.0061483164,0.00026343527,0.0008503713,0.000035616435,0.00035766102,0.024899751],"study_design_scores_gemma":[0.000022848637,0.0034180454,0.9811323,0.000044568063,0.00003381653,0.0006662326,0.010782562,0.0014864943,0.0011990735,0.000134505,0.0010395104,0.00004006433],"about_ca_topic_score_codex":0.001666154,"about_ca_topic_score_gemma":0.001248157,"teacher_disagreement_score":0.0056207776,"about_ca_system_score_codex":0.0005843129,"about_ca_system_score_gemma":0.0007649296,"threshold_uncertainty_score":0.02972585},"labels":[],"label_agreement":null},{"id":"W3128610517","doi":"10.1016/j.stueduc.2021.100977","title":"The long-term washback effects of the National Matriculation English Test on college English learning in China: Tertiary student perspectives","year":2021,"lang":"en","type":"article","venue":"Studies In Educational Evaluation","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":31,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Matriculation; Active listening; Competence (human resources); Psychology; Test (biology); College English; Curriculum; Perception; Mathematics education; China; Medical education; Pedagogy; Medicine; Political science","score_opus":0.031240674061682346,"score_gpt":0.419786253443572,"score_spread":0.38854557938188966,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3128610517","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9982646,0.00035499144,0.00001883549,0.0004816446,0.000014368723,0.000013837267,0.00003073175,0.0000022870556,0.00081861735],"genre_scores_gemma":[0.9995789,0.000080930906,0.000016335003,0.00006223969,0.000012572828,0.0000076219385,0.000030081681,8.14016e-7,0.00021038395],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.99647236,0.001296135,0.00026966757,0.00023770386,0.00096069946,0.0007635829],"domain_scores_gemma":[0.97766805,0.0072433725,0.003860228,0.00095970574,0.004833297,0.00543532],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009496037,0.00024421114,0.00071884005,0.0011130775,0.0014864964,0.001189498,0.0010148213,0.0009780076,0.00194772],"category_scores_gemma":[0.031687226,0.00013025544,0.00073730736,0.0009764917,0.0010759194,0.0010617089,0.0014470808,0.0011897513,0.00020472503],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0022453002,0.0032216853,0.9122018,0.000090587484,0.00013663569,0.00043454798,0.0058540325,0.00022369935,0.00087918754,0.00031708955,0.00092382217,0.07347168],"study_design_scores_gemma":[0.000048326398,0.0022951558,0.9930386,0.00004275153,0.00010097034,0.000049111215,0.0032249033,0.00025318423,0.00044754625,0.000084966625,0.00039585735,0.000018655577],"about_ca_topic_score_codex":0.04799857,"about_ca_topic_score_gemma":0.058846485,"teacher_disagreement_score":0.04799857,"about_ca_system_score_codex":0.0037282226,"about_ca_system_score_gemma":0.005394956,"threshold_uncertainty_score":0.09543836},"labels":[],"label_agreement":null},{"id":"W3128960566","doi":"10.18733/cpi29569","title":"All that Glitters is not Gold: Culturally responsive online Assessment and Pedagogy in uncertain times","year":2021,"lang":"en","type":"article","venue":"Cultural and Pedagogical Inquiry","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Pedagogy; Psychology","score_opus":0.5374877977163827,"score_gpt":0.554900221389048,"score_spread":0.017412423672665378,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3128960566","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0018692357,0.007976265,0.002337337,0.8166964,0.16003013,0.00011260223,0.000061910294,0.00028294406,0.010633164],"genre_scores_gemma":[0.07096394,0.035036325,0.018025719,0.4749188,0.3105826,0.0011266933,0.00028303775,0.0016738779,0.087389],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.97141695,0.016597481,0.0021225798,0.0009924026,0.007735657,0.001134906],"domain_scores_gemma":[0.8373628,0.10452146,0.0055554355,0.0033806372,0.026672207,0.02250743],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.036732513,0.0006993355,0.0010500756,0.001373127,0.0067935926,0.015497521,0.0021734952,0.0090942625,0.014829726],"category_scores_gemma":[0.13805574,0.00060710654,0.00050461746,0.0010646568,0.0073638,0.012959866,0.009487972,0.01713278,0.004457133],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027379116,0.00004319994,0.00034585487,0.000163781,0.0000057692932,0.00016516162,0.002822699,0.000026213884,0.00009231503,0.001664593,0.94507396,0.049568966],"study_design_scores_gemma":[0.000024058918,0.000084755986,0.001808953,0.0011253451,0.000016571967,0.00037594268,0.016429476,0.0001830258,0.00034397747,0.010771062,0.968752,0.00008482229],"about_ca_topic_score_codex":0.0033939567,"about_ca_topic_score_gemma":0.014365069,"teacher_disagreement_score":0.036732513,"about_ca_system_score_codex":0.0022447414,"about_ca_system_score_gemma":0.010806198,"threshold_uncertainty_score":0.19426239},"labels":[],"label_agreement":null},{"id":"W3131800560","doi":"10.29173/isotl532","title":"Conversations and Reflections on Authentic Assessment","year":2021,"lang":"en","type":"article","venue":"Imagining SoTL","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"ROWE; Taxonomy (biology); Point (geometry); Computer science; Sociology; Mathematics education; Pedagogy; Knowledge management; Engineering ethics; Psychology; Management; Engineering","score_opus":0.061162770415292445,"score_gpt":0.44456000084983166,"score_spread":0.3833972304345392,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3131800560","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.40443465,0.012103338,0.1668263,0.1937079,0.009528827,0.0007364985,0.00025324224,0.0008448274,0.2115644],"genre_scores_gemma":[0.9635229,0.0024560867,0.0105104055,0.008398586,0.00082386174,0.00035553,0.00007905898,0.0004270881,0.013426466],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.8179302,0.1570124,0.0029241648,0.004455658,0.012715598,0.004961969],"domain_scores_gemma":[0.8280985,0.13846427,0.005180575,0.007393543,0.01327287,0.007590243],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.06205434,0.0018552912,0.0012203818,0.0029890323,0.02239833,0.017046493,0.004146307,0.009429985,0.00395229],"category_scores_gemma":[0.18316893,0.0009294009,0.0013412685,0.0023346683,0.041141562,0.021081362,0.028900085,0.029086057,0.0015861848],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000063517924,0.000079388934,0.0004932105,0.00015137596,0.0000131560555,0.0009254932,0.9135041,0.00039671306,0.00087218086,0.06798802,0.004833913,0.01067896],"study_design_scores_gemma":[0.000020061363,0.00011589878,0.0004977429,0.00087839336,0.000013747704,0.0013672054,0.67115605,0.0014561856,0.0020768216,0.045102865,0.27719486,0.00012013699],"about_ca_topic_score_codex":0.0025374566,"about_ca_topic_score_gemma":0.0020078276,"teacher_disagreement_score":0.06205434,"about_ca_system_score_codex":0.009182772,"about_ca_system_score_gemma":0.0046396963,"threshold_uncertainty_score":0.32817864},"labels":[],"label_agreement":null},{"id":"W3133706844","doi":"10.1017/9781108589789.027","title":"Teachers’ and Students’ Beliefs and Perspectives about Corrective Feedback","year":2021,"lang":"en","type":"book-chapter","venue":"Cambridge University Press eBooks","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University; University of Victoria","funders":"","keywords":"Corrective feedback; Situational ethics; Psychology; Mathematics education; Social psychology","score_opus":0.03148769182241588,"score_gpt":0.26908976789327804,"score_spread":0.23760207607086217,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3133706844","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91331255,0.009125981,0.004014363,0.005244682,0.0000984764,0.00003157708,0.00007982219,0.000045078257,0.068047486],"genre_scores_gemma":[0.9911724,0.0030837168,0.00061620306,0.00017984888,0.00001413054,0.00001756186,0.000018857449,0.000008987882,0.0048883143],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99588627,0.0018264095,0.00018216805,0.00022603024,0.0016328169,0.0002462748],"domain_scores_gemma":[0.9892838,0.007876759,0.0011777132,0.00021468061,0.0010092866,0.00043784338],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0041367784,0.00017971585,0.00025688077,0.0011151843,0.00078280445,0.003745369,0.00041016136,0.0008211718,0.0018524138],"category_scores_gemma":[0.010065902,0.00017584514,0.00019529408,0.0008013044,0.0020426374,0.0019944203,0.0009315494,0.0016811978,0.00027605577],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010298807,0.00022233903,0.08038807,0.00085466745,0.000029751103,0.0012784789,0.68516195,0.00069217966,0.004940969,0.023311386,0.0034590408,0.19955817],"study_design_scores_gemma":[0.000027079046,0.00035011276,0.17119184,0.0023212964,0.000063114814,0.0026684508,0.6738096,0.0011917077,0.004026809,0.015315214,0.1288975,0.00013727476],"about_ca_topic_score_codex":0.0032115804,"about_ca_topic_score_gemma":0.0037064373,"teacher_disagreement_score":0.0041367784,"about_ca_system_score_codex":0.0015537958,"about_ca_system_score_gemma":0.0013980125,"threshold_uncertainty_score":0.021877646},"labels":[],"label_agreement":null},{"id":"W3135544085","doi":"10.5430/elr.v10n1p1","title":"Construction and Application of OBE-based Multiple Formative Assessment System in the “Micro-lecture + PAD Class”","year":2021,"lang":"en","type":"article","venue":"English Linguistics Research","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Formative assessment; Enthusiasm; Construct (python library); Class (philosophy); Computer science; Mathematics education; Curriculum; Quality (philosophy); Psychology; Pedagogy; Artificial intelligence","score_opus":0.038455158807855175,"score_gpt":0.4054706823467402,"score_spread":0.36701552353888506,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3135544085","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3368108,0.00012364956,0.6497235,0.0002688148,0.00023500304,0.0021733586,0.00024605828,0.0043237507,0.0060949977],"genre_scores_gemma":[0.45597625,0.00007447016,0.5389483,0.00008756573,0.000060183906,0.0014923614,0.00035107203,0.00010692231,0.0029029024],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99379855,0.003171642,0.0006590445,0.0008979787,0.0012538832,0.00021890782],"domain_scores_gemma":[0.9892021,0.004252217,0.0006262747,0.001620491,0.0037909048,0.00050796435],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009184898,0.0006048391,0.00073775894,0.0015283725,0.00055060454,0.001209278,0.0009915554,0.00081182644,0.002167497],"category_scores_gemma":[0.012838558,0.00029033076,0.00059598044,0.000544536,0.0005441404,0.0016666823,0.0015705252,0.0008756104,0.0007167865],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010874312,0.0028354072,0.052179154,0.00061959785,0.00010242604,0.00024275627,0.0031980556,0.0042125783,0.11125103,0.0040377816,0.0025233198,0.8177106],"study_design_scores_gemma":[0.00060341484,0.01523461,0.219292,0.0006242232,0.0007397703,0.0019527897,0.0059600845,0.2776847,0.414127,0.0064233085,0.05644666,0.00091139914],"about_ca_topic_score_codex":0.00048873544,"about_ca_topic_score_gemma":0.00074901554,"teacher_disagreement_score":0.009184898,"about_ca_system_score_codex":0.00043528064,"about_ca_system_score_gemma":0.0010962861,"threshold_uncertainty_score":0.048574984},"labels":[],"label_agreement":null},{"id":"W3135578950","doi":"10.1016/j.tate.2021.103316","title":"Toward a pedagogy for slow and significant learning about assessment in teacher education","year":2021,"lang":"en","type":"article","venue":"Teaching and Teacher Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":22,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Coursework; Mathematics education; Teacher preparation; Teacher education; Psychology; Pedagogy; Higher education; Institution; Taxonomy (biology); Sociology; Political science","score_opus":0.04098595074252736,"score_gpt":0.4212046423058825,"score_spread":0.38021869156335514,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3135578950","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.11246048,0.0013511176,0.7375745,0.05324153,0.0012970011,0.000843687,0.000043115364,0.0034309134,0.08975766],"genre_scores_gemma":[0.5126192,0.00056154205,0.4626415,0.0033978743,0.00018937184,0.00081870845,0.00002457306,0.0002780064,0.01946916],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.99261945,0.004055338,0.00027764036,0.0005014831,0.002347833,0.00019834681],"domain_scores_gemma":[0.9827617,0.0109080095,0.0010580085,0.0010993031,0.0030932932,0.001079672],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009172959,0.00049345824,0.00032074287,0.0014360552,0.0019073925,0.0037867003,0.0013695445,0.0017818682,0.0022573434],"category_scores_gemma":[0.028382957,0.00035326963,0.0003214874,0.0003784032,0.0036296574,0.0033803838,0.0052889166,0.0045465822,0.00084458163],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001516749,0.0015263208,0.0157921,0.0005173048,0.000032102394,0.00027704588,0.030166933,0.0019242574,0.011660813,0.21145603,0.026151953,0.70034355],"study_design_scores_gemma":[0.00031274356,0.0018467056,0.032358605,0.0018099614,0.0001582296,0.0024737115,0.041639972,0.035887744,0.031612307,0.5054907,0.34618485,0.0002245251],"about_ca_topic_score_codex":0.0018580527,"about_ca_topic_score_gemma":0.004717113,"teacher_disagreement_score":0.009172959,"about_ca_system_score_codex":0.0015635578,"about_ca_system_score_gemma":0.008083121,"threshold_uncertainty_score":0.048511863},"labels":[],"label_agreement":null},{"id":"W3136573347","doi":"10.1177/21582440211016838","title":"A Baseline for Multiple-Choice Testing in the University Classroom","year":2021,"lang":"en","type":"preprint","venue":"SAGE Open","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Trent University","funders":"","keywords":"Baseline (sea); Reliability (semiconductor); Context (archaeology); Test (biology); Multiple choice; Variety (cybernetics); Psychometrics; Item response theory; Psychology; Quality (philosophy); Applied psychology; Standardized test; Computer science; Medical education; Mathematics education; Statistics; Clinical psychology; Artificial intelligence; Medicine; Significant difference","score_opus":0.12406051353992756,"score_gpt":0.38601464641380895,"score_spread":0.26195413287388136,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3136573347","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4346073,0.0018855946,0.44558898,0.012473822,0.0013277648,0.0035580648,0.004673991,0.002173988,0.09371057],"genre_scores_gemma":[0.72343,0.00032028873,0.26121992,0.0016902763,0.000298481,0.0049055396,0.0029698224,0.00058595557,0.004579721],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9386607,0.02785555,0.0050540376,0.0053247884,0.021473879,0.0016310822],"domain_scores_gemma":[0.78334486,0.07176012,0.009295452,0.034013487,0.094913445,0.006672698],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.058539327,0.0006210666,0.0010637277,0.004445956,0.0037266198,0.005899357,0.002464111,0.0016176946,0.005977901],"category_scores_gemma":[0.24171314,0.00039980587,0.00070359017,0.0043933666,0.003715457,0.0050830212,0.0036954735,0.0040921136,0.0021821961],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010585032,0.002137603,0.14342739,0.0011030113,0.000099796314,0.00036238212,0.037875902,0.0023343447,0.01593984,0.11799827,0.030414507,0.6472485],"study_design_scores_gemma":[0.00028776657,0.0039947727,0.5261893,0.0028587766,0.00009661419,0.000910323,0.027534261,0.01026817,0.023676608,0.11631631,0.287533,0.00033408095],"about_ca_topic_score_codex":0.01442381,"about_ca_topic_score_gemma":0.01527942,"teacher_disagreement_score":0.058539327,"about_ca_system_score_codex":0.006893489,"about_ca_system_score_gemma":0.009742243,"threshold_uncertainty_score":0.30958927},"labels":[],"label_agreement":null},{"id":"W3138121929","doi":"10.1080/13803611.2021.1902354","title":"Linking personality to teachers’ literacy in classroom assessment: a cross-cultural study","year":2020,"lang":"en","type":"article","venue":"Educational Research and Evaluation","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Queen's University","funders":"","keywords":"Summative assessment; Formative assessment; Psychology; Literacy; Competence (human resources); Personality; Pedagogy; Big Five personality traits; Empathy; Mathematics education; Social psychology","score_opus":0.3451683761205265,"score_gpt":0.6177916604486202,"score_spread":0.27262328432809374,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3138121929","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.999579,0.000029083465,0.000058415335,0.000010839006,0.0000022487627,0.000006576371,0.000004375384,5.026183e-7,0.00030895788],"genre_scores_gemma":[0.9996525,0.000031165368,0.00009844555,0.00001581761,0.0000015692564,0.000007852511,0.0000073899882,0.0000014175712,0.00018385524],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9974485,0.001310888,0.00020037216,0.0002115111,0.0005720363,0.0002566551],"domain_scores_gemma":[0.9905607,0.0042456775,0.0015325117,0.0008205076,0.0018571195,0.0009835528],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0051872637,0.000258854,0.00039841165,0.0010778804,0.0012969836,0.0017827274,0.00030957905,0.0003857165,0.00077716267],"category_scores_gemma":[0.011368546,0.00038867793,0.0003591048,0.0006672865,0.0015641527,0.0007021299,0.0016656045,0.00092215114,0.00015227954],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011683168,0.00045343526,0.8566695,0.00005658869,0.000072566036,0.00046388942,0.124944925,0.00007524662,0.0015030592,0.00013088684,0.00011511948,0.01539802],"study_design_scores_gemma":[0.000007663623,0.0002728932,0.942017,0.000033306762,0.000026300344,0.00060423184,0.0555878,0.00015822853,0.00036056066,0.000063825326,0.00084957154,0.000018691937],"about_ca_topic_score_codex":0.0138731245,"about_ca_topic_score_gemma":0.025664542,"teacher_disagreement_score":0.0138731245,"about_ca_system_score_codex":0.0008834692,"about_ca_system_score_gemma":0.00081452617,"threshold_uncertainty_score":0.027584732},"labels":[],"label_agreement":null},{"id":"W3148929026","doi":"10.5430/elr.v10n1p10","title":"Is Peer Feedback Helpful When Learning Literature Review Writing? A Study of Feedback Features and Quantity","year":2021,"lang":"en","type":"review","venue":"English Linguistics Research","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Formative assessment; Peer feedback; Constructive; Reading (process); Psychology; Quality (philosophy); Process (computing); Writing process; Peer review; Mathematics education; Peer assessment; Computer science; Linguistics","score_opus":0.1447313827313703,"score_gpt":0.4989814303663223,"score_spread":0.35425004763495205,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3148929026","genre_codex":"empirical","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.67099124,0.27254787,0.024383401,0.010338254,0.0009939059,0.0021479796,0.00026101273,0.0002476813,0.0180886],"genre_scores_gemma":[0.93242,0.042721935,0.021575777,0.0007709348,0.000456533,0.0010000711,0.00008449683,0.000059400845,0.00091081206],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.70731425,0.22138798,0.021785958,0.0039951093,0.044233628,0.0012830305],"domain_scores_gemma":[0.28787833,0.6171294,0.042360548,0.0067971484,0.042786032,0.0030485766],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.17444995,0.00045709714,0.0019416902,0.0061191753,0.0009821679,0.0047362903,0.0013040222,0.0011757122,0.00093274],"category_scores_gemma":[0.51028,0.0006285851,0.0011757571,0.0056299367,0.0018138327,0.0057422454,0.0023910222,0.0011166013,0.0003099275],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013746021,0.0003017468,0.0513461,0.022263145,0.0011568506,0.00035262507,0.02338437,0.0002166772,0.0031235802,0.0008175737,0.001330179,0.8943326],"study_design_scores_gemma":[0.0015448007,0.018430764,0.67442,0.08720463,0.008639665,0.01019995,0.086315416,0.0052741766,0.013137038,0.011353037,0.082842074,0.00063841435],"about_ca_topic_score_codex":0.00063293474,"about_ca_topic_score_gemma":0.0023258685,"teacher_disagreement_score":0.8255501,"about_ca_system_score_codex":0.0017343533,"about_ca_system_score_gemma":0.0046274336,"threshold_uncertainty_score":0.92259055},"labels":[],"label_agreement":null},{"id":"W3153021973","doi":"","title":"International trends in the implementation of assessment for learning : Implications for policy and practice","year":2015,"lang":"en","type":"article","venue":"Research Bank (Australian Catholic University)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Brock University; Queen's University","funders":"","keywords":"Summative assessment; Globe; Policy learning; Political science; Assessment for learning; Impact assessment; Public administration; Regional science; Economic growth; Public relations; Formative assessment; Sociology; Pedagogy; Economics; Psychology; Computer science","score_opus":0.25869321118650285,"score_gpt":0.5606460194164312,"score_spread":0.30195280822992837,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3153021973","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0551158,0.048206992,0.004937456,0.8123204,0.0020151392,0.00010963086,0.00045182064,0.0001425854,0.07670025],"genre_scores_gemma":[0.8640216,0.05754795,0.012627372,0.05599572,0.0014109155,0.00024652208,0.00054626586,0.00015134417,0.0074522877],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9735293,0.011127015,0.0034034394,0.0029025334,0.005746466,0.003291267],"domain_scores_gemma":[0.843766,0.081778675,0.01983894,0.005831628,0.037239563,0.011545209],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.051288843,0.00030019478,0.00061141804,0.003890455,0.0025135572,0.012758641,0.0021385206,0.004338349,0.0074121575],"category_scores_gemma":[0.096295245,0.0003532284,0.00056158606,0.010353445,0.008990258,0.013795223,0.006881894,0.008577108,0.0009050093],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014583764,0.00040767895,0.049883153,0.002431701,0.000038056107,0.0001498341,0.017330293,0.0012035078,0.00054562656,0.41805628,0.035356957,0.47445095],"study_design_scores_gemma":[0.000055788212,0.0004208337,0.19072574,0.012775242,0.000039169794,0.0005373944,0.07693926,0.0016379314,0.0011661715,0.097025506,0.6185219,0.0001550499],"about_ca_topic_score_codex":0.040635344,"about_ca_topic_score_gemma":0.026343567,"teacher_disagreement_score":0.051288843,"about_ca_system_score_codex":0.018890038,"about_ca_system_score_gemma":0.034153063,"threshold_uncertainty_score":0.2712446},"labels":[],"label_agreement":null},{"id":"W3153702187","doi":"10.7202/1076184ar","title":"L’apport d’une communauté de pratique au développement professionnel de superviseurs de stage en enseignement","year":2021,"lang":"fr","type":"article","venue":"Phronesis","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Trois-Rivières","funders":"","keywords":"Political science; Humanities; Philosophy","score_opus":0.0733994065175714,"score_gpt":0.35655211090586114,"score_spread":0.28315270438828977,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3153702187","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.5969934,0.005681873,0.18904674,0.016756728,0.0007812244,0.0010365495,0.0005046057,0.0003323581,0.18886651],"genre_scores_gemma":[0.9436875,0.0017730558,0.030678386,0.0009196965,0.00011131864,0.0006108574,0.00016657174,0.00010693705,0.021945672],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.97714955,0.015070229,0.0008851147,0.001988351,0.0038850529,0.0010217235],"domain_scores_gemma":[0.964805,0.018646747,0.0037395118,0.0029176695,0.007820631,0.0020704218],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015467489,0.000549879,0.0004711474,0.0021883962,0.005134837,0.006794156,0.0013725883,0.0013881259,0.006999701],"category_scores_gemma":[0.02891197,0.0004511971,0.00057118176,0.0019711505,0.009290084,0.006123922,0.0049331984,0.0027889207,0.000964176],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017610616,0.00013247477,0.03256299,0.00097146694,0.00007855093,0.0005438447,0.7228004,0.00043143542,0.0039901882,0.1366946,0.003723642,0.09789441],"study_design_scores_gemma":[0.00007196368,0.0005510487,0.111898735,0.0027630378,0.00014174657,0.0017165435,0.48875633,0.0024230287,0.0059145265,0.061996654,0.32350823,0.00025809946],"about_ca_topic_score_codex":0.022844255,"about_ca_topic_score_gemma":0.0333759,"teacher_disagreement_score":0.022844255,"about_ca_system_score_codex":0.0068564937,"about_ca_system_score_gemma":0.01144824,"threshold_uncertainty_score":0.08180094},"labels":[],"label_agreement":null},{"id":"W3156065537","doi":"10.24908/iqurcp.10488","title":"3 Minute Thesis: “One slide, no props, 3 minutes”","year":2018,"lang":"en","type":"article","venue":"Inquiry Queen s Undergraduate Research Conference Proceedings","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer graphics (images); Engineering drawing; Computer science; Engineering","score_opus":0.1767653312492937,"score_gpt":0.424596863444695,"score_spread":0.2478315321954013,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3156065537","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0056496244,0.0022628442,0.009577406,0.09171011,0.27252522,0.0050351745,0.008958185,0.0067186486,0.5975628],"genre_scores_gemma":[0.008573419,0.00061242405,0.0033990266,0.010551567,0.023700586,0.0027360697,0.0027990136,0.0016470896,0.94598085],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982332,0.0003082537,0.000077187135,0.00019460738,0.00088081113,0.00030584697],"domain_scores_gemma":[0.99097013,0.0007439189,0.0002500963,0.00055413676,0.004466884,0.0030147973],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0019309756,0.0016039708,0.0014517254,0.0009830648,0.0035394211,0.006511879,0.0016345893,0.0026917886,0.59911346],"category_scores_gemma":[0.012007045,0.000722752,0.0010828457,0.0007616611,0.0008502387,0.0021264863,0.005218321,0.004442382,0.53285474],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007394379,0.00004298624,0.000030538664,0.000044906228,0.000001458286,0.000016122376,0.00006544032,0.000018090746,0.00042082855,0.00037086115,0.9874385,0.011476354],"study_design_scores_gemma":[0.000081538856,0.00023217962,0.0010841243,0.00013836446,0.0000041280623,0.000055004206,0.00060517003,0.00012051156,0.0003493917,0.0014038625,0.9959046,0.000021053387],"about_ca_topic_score_codex":0.001639913,"about_ca_topic_score_gemma":0.0034387836,"teacher_disagreement_score":0.59911346,"about_ca_system_score_codex":0.0014015756,"about_ca_system_score_gemma":0.00174914,"threshold_uncertainty_score":0.57181597},"labels":[],"label_agreement":null},{"id":"W3158042421","doi":"10.1080/01587919.2021.1910494","title":"Revisioning the potential of Freire’s principles of assessment: Influences on the art of assessment in open and online learning through blogging","year":2021,"lang":"en","type":"article","venue":"Distance Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lakehead University; University of Calgary; Thompson Rivers University; University of British Columbia","funders":"","keywords":"Dialogical self; Critical consciousness; Pedagogy; Sociology; Craft; Consciousness; Critical thinking; Distance education; Critical pedagogy; Psychology; Epistemology; Social psychology; Visual arts","score_opus":0.04593780520966546,"score_gpt":0.41824886776978143,"score_spread":0.372311062560116,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3158042421","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.28572288,0.004781525,0.30850118,0.0715551,0.0016175357,0.0005572524,0.000054654498,0.00036891544,0.32684103],"genre_scores_gemma":[0.9582261,0.0006320324,0.032717813,0.0017253256,0.00017846191,0.00023847136,0.000009132662,0.00014567596,0.006127083],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.9561904,0.030172506,0.001672605,0.0033707654,0.0074937404,0.001099914],"domain_scores_gemma":[0.85364455,0.11974699,0.003909615,0.008981752,0.012220745,0.0014963998],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.051596284,0.0009432143,0.00054793607,0.0039433986,0.006853784,0.016031096,0.0019826198,0.0039525884,0.0021465775],"category_scores_gemma":[0.11873336,0.00056303904,0.00062778307,0.0015598217,0.04016163,0.022498097,0.009756616,0.008553695,0.00044192138],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012516156,0.0001232096,0.004764058,0.00026755605,0.000026222582,0.00045225048,0.23820907,0.000645864,0.0014232029,0.6341913,0.0034701019,0.11630196],"study_design_scores_gemma":[0.0000788817,0.00018939491,0.005347159,0.0013022228,0.000049852264,0.0011943546,0.07324575,0.003934511,0.0037979158,0.7533581,0.15728655,0.00021527629],"about_ca_topic_score_codex":0.0024760845,"about_ca_topic_score_gemma":0.0032980964,"teacher_disagreement_score":0.051596284,"about_ca_system_score_codex":0.0055321604,"about_ca_system_score_gemma":0.005075867,"threshold_uncertainty_score":0.27287048},"labels":[],"label_agreement":null},{"id":"W3158490995","doi":"10.18733/cpi29603","title":"All that Glitters is not Gold:","year":2021,"lang":"en","type":"article","venue":"Cultural and Pedagogical Inquiry","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Psychology","score_opus":0.7089623333028044,"score_gpt":0.527925278176974,"score_spread":0.18103705512583046,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3158490995","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00081829086,0.0035497355,0.0007931271,0.5978409,0.35206196,0.00035410206,0.0005761429,0.0013456852,0.042659983],"genre_scores_gemma":[0.004913356,0.0031300548,0.0018412508,0.37652785,0.12996934,0.00094786653,0.0009319871,0.0018238756,0.47991452],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.98887676,0.002558751,0.00076540525,0.00096590293,0.00541606,0.0014171265],"domain_scores_gemma":[0.90822,0.02005728,0.0028362335,0.0041428627,0.027238386,0.037505317],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.017173875,0.0016452271,0.0020742205,0.0017853269,0.010507285,0.01692393,0.0038713047,0.023496052,0.21116216],"category_scores_gemma":[0.07240338,0.0010870601,0.0014144004,0.0011222648,0.005271536,0.013458572,0.012667692,0.0179026,0.13443929],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008975081,0.000013543091,0.00003043774,0.000019587755,0.0000010080753,0.00002380818,0.00004529483,0.0000035514788,0.00002436771,0.00019125185,0.996258,0.0033802383],"study_design_scores_gemma":[0.000017959816,0.000034948513,0.00044959036,0.00017239295,0.000002695973,0.000046133664,0.0007338906,0.00003091976,0.00005198892,0.0012667209,0.9971661,0.000026657117],"about_ca_topic_score_codex":0.0051820283,"about_ca_topic_score_gemma":0.014056376,"teacher_disagreement_score":0.21116216,"about_ca_system_score_codex":0.003718425,"about_ca_system_score_gemma":0.01374576,"threshold_uncertainty_score":0.7064078},"labels":[],"label_agreement":null},{"id":"W3159797685","doi":"10.5430/ijhe.v11n1p1","title":"University Academics’ Perceptions Regarding the Use of Information Technology Tools for Effective Formative Assessment: Implications for Quality Assessment through Professional Development","year":2021,"lang":"en","type":"article","venue":"International Journal of Higher Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Formative assessment; Cronbach's alpha; Medical education; Perception; Quality (philosophy); Psychology; Reliability (semiconductor); Consistency (knowledge bases); Data collection; Sample (material); Knowledge management; Pedagogy; Computer science; Sociology; Medicine; Psychometrics","score_opus":0.10811282267608271,"score_gpt":0.47594031694344857,"score_spread":0.36782749426736583,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3159797685","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9943415,0.00065337366,0.0007893511,0.0015313503,0.000020113494,0.000033574335,0.0000143706,0.00000887446,0.0026074995],"genre_scores_gemma":[0.9987093,0.00045790238,0.00044303146,0.0001294619,0.000008956379,0.0000120102695,0.000006727334,0.0000013867196,0.00023125786],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.98970515,0.0049327854,0.0010707044,0.00026581576,0.002879828,0.0011457956],"domain_scores_gemma":[0.9505791,0.02329533,0.009883647,0.0011787189,0.009318136,0.0057449485],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.019237863,0.00021082697,0.00036278283,0.0014757786,0.0014730092,0.0046099024,0.00040195955,0.0006790235,0.0014306512],"category_scores_gemma":[0.043227825,0.00020181842,0.00028742268,0.0017412779,0.0013921871,0.0019134587,0.0013263526,0.00090628595,0.00020384403],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002473618,0.0010788669,0.6252862,0.0007905349,0.000063165,0.0009596163,0.19144425,0.0004360738,0.004446303,0.0025366459,0.0014581736,0.17125277],"study_design_scores_gemma":[0.000021323038,0.0012969872,0.4936826,0.00081965735,0.000056755405,0.0007224929,0.48725325,0.000910439,0.0023442796,0.001958618,0.010828473,0.00010529874],"about_ca_topic_score_codex":0.001762108,"about_ca_topic_score_gemma":0.0020592099,"teacher_disagreement_score":0.019237863,"about_ca_system_score_codex":0.0016358069,"about_ca_system_score_gemma":0.0035847265,"threshold_uncertainty_score":0.10174078},"labels":[],"label_agreement":null},{"id":"W3160530669","doi":"10.5539/elt.v14n6p12","title":"Research on the Effect of Peer Feedback Training in English Writing Teaching—A Case Study of Students in Business English Major","year":2021,"lang":"en","type":"article","venue":"English Language Teaching","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Peer feedback; Psychology; Quality (philosophy); Perspective (graphical); Mathematics education; Point (geometry); Teaching method; Pedagogy; Computer science","score_opus":0.04366160629069881,"score_gpt":0.4157351404646889,"score_spread":0.3720735341739901,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3160530669","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99588925,0.000218933,0.0007261417,0.00019266948,0.000019928782,0.00012636128,0.000006373553,0.0000070095175,0.002813392],"genre_scores_gemma":[0.9976599,0.00023241476,0.00085789885,0.000043465854,0.000009047711,0.000059994087,0.0000069460643,0.00000427922,0.0011260243],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9914097,0.006361477,0.00029391082,0.00037095178,0.0009119002,0.00065206346],"domain_scores_gemma":[0.9849754,0.009534029,0.0012396331,0.0005541067,0.0016771386,0.0020198172],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006040481,0.00036912606,0.0004936149,0.0009410981,0.0033522137,0.0015861819,0.0011035632,0.0008401493,0.0027862592],"category_scores_gemma":[0.018730342,0.00022543075,0.00049479824,0.00070076785,0.0012467032,0.0011779324,0.001389606,0.0010979996,0.00036597028],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004345712,0.011585507,0.12829678,0.0022870316,0.00015060605,0.009528431,0.5541476,0.0009407377,0.01054223,0.0025001743,0.0018885899,0.27769762],"study_design_scores_gemma":[0.00028635247,0.008550964,0.24956554,0.0008656127,0.00029082815,0.00505004,0.6800804,0.003627503,0.013018899,0.0010987701,0.037400033,0.00016515199],"about_ca_topic_score_codex":0.0035687946,"about_ca_topic_score_gemma":0.009339089,"teacher_disagreement_score":0.006040481,"about_ca_system_score_codex":0.0013242131,"about_ca_system_score_gemma":0.004319511,"threshold_uncertainty_score":0.031945527},"labels":[],"label_agreement":null},{"id":"W3160550689","doi":"10.1080/2331186x.2021.1921903","title":"Exploring assessment across cultures: Teachers’ approaches to assessment in the U.S., China, and Canada","year":2021,"lang":"en","type":"article","venue":"Cogent Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":35,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Queen's University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Context (archaeology); Assessment for learning; Educational assessment; Psychology; China; Scale (ratio); Latent class model; Pedagogy; Class (philosophy); Mathematics education; Formative assessment; Geography; Computer science","score_opus":0.20288863404547883,"score_gpt":0.4023957242216135,"score_spread":0.1995070901761347,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3160550689","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99069715,0.00042127052,0.00042057564,0.0011418092,0.0000119114175,0.000056450364,0.000089669375,0.000009135797,0.0071520535],"genre_scores_gemma":[0.9980646,0.00025244517,0.00040394018,0.00010447173,0.0000012571087,0.000027110946,0.00004931729,0.0000050980584,0.0010915948],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9947695,0.0014463143,0.00028642293,0.0005275454,0.0016570305,0.0013132001],"domain_scores_gemma":[0.98706645,0.0025003375,0.0009615191,0.00045470046,0.006313743,0.002703414],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0068315184,0.00036225058,0.0005086212,0.0030940187,0.012243853,0.00520065,0.0013006167,0.00046065619,0.0009825957],"category_scores_gemma":[0.012812284,0.0003306523,0.00036326423,0.0065112063,0.0047256723,0.0015970956,0.0050653694,0.001436287,0.000076330114],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012225697,0.00007886196,0.42456514,0.00010241931,0.000043980068,0.00031069826,0.50002676,0.0006137329,0.0007827587,0.00504266,0.0019324333,0.066378325],"study_design_scores_gemma":[0.000013831632,0.000051978626,0.40948102,0.00019825506,0.000040700284,0.00006549431,0.5783873,0.0015008068,0.00057616824,0.00095410645,0.008662874,0.000067523775],"about_ca_topic_score_codex":0.9903578,"about_ca_topic_score_gemma":0.99632215,"teacher_disagreement_score":0.08511083,"about_ca_system_score_codex":0.08511083,"about_ca_system_score_gemma":0.1555027,"threshold_uncertainty_score":0.61752516},"labels":[],"label_agreement":null},{"id":"W3161754782","doi":"10.3968/12015","title":"Moroccan EFL Secondary School Teachers’ Current Practices and Challenges of Formative Assessment","year":2021,"lang":"en","type":"article","venue":"Canadian social science","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Formative assessment; Mathematics education; Psychology; Pedagogy; Medical education; Medicine","score_opus":0.06726235339531093,"score_gpt":0.4018378190155934,"score_spread":0.33457546562028245,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3161754782","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97323567,0.0060939747,0.0032957369,0.0057142293,0.00006969583,0.000093605406,0.00010238578,0.00007469231,0.011320056],"genre_scores_gemma":[0.99411064,0.0017308634,0.002611246,0.00035037802,0.000021200154,0.00008215646,0.00003147219,0.0000131173965,0.001048863],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.98016584,0.010610491,0.0018752587,0.0018787369,0.0040892595,0.0013805339],"domain_scores_gemma":[0.94494635,0.029553205,0.007328118,0.0039870148,0.012677427,0.0015078993],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.025934327,0.00034543476,0.0004512289,0.0018109366,0.003295289,0.004130346,0.0013892356,0.00075534836,0.0010744019],"category_scores_gemma":[0.047147427,0.00034643008,0.00014368205,0.0019336509,0.0031950788,0.0020351463,0.0020897943,0.0005392619,0.0002985092],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020895289,0.00019352039,0.21915267,0.0014185901,0.00004221409,0.0008264744,0.37852213,0.0004138811,0.0065448727,0.0037199243,0.0016095066,0.38734734],"study_design_scores_gemma":[0.000029850762,0.00048177794,0.46726376,0.0025317713,0.000049325117,0.0016633207,0.43796003,0.000795952,0.0046135946,0.0026786905,0.08176507,0.00016685613],"about_ca_topic_score_codex":0.05065202,"about_ca_topic_score_gemma":0.08351387,"teacher_disagreement_score":0.05065202,"about_ca_system_score_codex":0.006920738,"about_ca_system_score_gemma":0.007616855,"threshold_uncertainty_score":0.13715547},"labels":[],"label_agreement":null},{"id":"W3161805550","doi":"10.4018/978-1-7998-7106-4.ch014","title":"Appreciative Assessment in Graphic Design Education Using UDL Strategies","year":2021,"lang":"en","type":"book-chapter","venue":"Advances in educational technologies and instructional design book series","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Royal Roads University","funders":"","keywords":"Formative assessment; Universal Design for Learning; Class (philosophy); Computer science; Face (sociological concept); Appreciative inquiry; Best practice; Mathematics education; Pedagogy; Human–computer interaction; Engineering ethics; Psychology; Engineering; Sociology; Artificial intelligence; Political science","score_opus":0.03732473664692976,"score_gpt":0.3524010662162964,"score_spread":0.31507632956936665,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3161805550","genre_codex":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06602505,0.011354056,0.2879103,0.0060193636,0.00058037817,0.0012200428,0.00007122472,0.0018068866,0.6250127],"genre_scores_gemma":[0.32056746,0.01132898,0.48280963,0.0026574123,0.00014077873,0.0013861157,0.00020096192,0.0004965677,0.18041216],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99693334,0.0018331904,0.00010209855,0.00018907536,0.0008220594,0.000120247816],"domain_scores_gemma":[0.9957112,0.0034912718,0.00013586464,0.00021816256,0.0003050638,0.0001384227],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0033354391,0.000797153,0.00043536216,0.0017223107,0.000863737,0.0044293534,0.001536607,0.0012492529,0.0068916674],"category_scores_gemma":[0.007358999,0.0002921606,0.00034742398,0.0011165092,0.0029967085,0.0028577596,0.0033854835,0.0019860277,0.002251558],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000033031924,0.00034419005,0.0010739331,0.0011040183,0.000006085135,0.00052106753,0.031930827,0.0014194098,0.0047576316,0.11824183,0.01252494,0.8280431],"study_design_scores_gemma":[0.000048918366,0.00050890853,0.003737583,0.002759512,0.000017075545,0.0041547986,0.02101092,0.0070159053,0.0115943365,0.09881241,0.8502535,0.00008610688],"about_ca_topic_score_codex":0.00052813924,"about_ca_topic_score_gemma":0.001510343,"teacher_disagreement_score":0.0068916674,"about_ca_system_score_codex":0.001816031,"about_ca_system_score_gemma":0.0017259291,"threshold_uncertainty_score":0.023054898},"labels":[],"label_agreement":null},{"id":"W3163600682","doi":"10.48325/rleee.001.06","title":"L'articulation de l’évaluation dans une recherche collaborative sur l’évaluation des compétences en formation à distance (FAD) en enseignement supérieur","year":2020,"lang":"fr","type":"article","venue":"DOAJ (DOAJ: Directory of Open Access Journals)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"General partnership; Articulation (sociology); Valuation (finance); Context (archaeology); Sociology; Empirical research; Structuring; Higher education; Political science; Epistemology; Business; Accounting; Law; Philosophy","score_opus":0.46832230800859775,"score_gpt":0.5787659544646687,"score_spread":0.11044364645607097,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3163600682","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24835289,0.015732216,0.11472882,0.11737875,0.0023029693,0.0010433827,0.0002578387,0.0003493781,0.4998537],"genre_scores_gemma":[0.90091175,0.0052927854,0.028404452,0.004204506,0.00018600628,0.0005233672,0.00012280695,0.00012826435,0.06022615],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9242872,0.054085102,0.0022420264,0.0034736444,0.0127203455,0.00319165],"domain_scores_gemma":[0.92097515,0.030712124,0.004035693,0.0045125517,0.031876314,0.007888191],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.05255512,0.0006703496,0.00083388836,0.0030940187,0.010659795,0.015632506,0.002028527,0.003220679,0.009010184],"category_scores_gemma":[0.050237793,0.0004524972,0.0009202378,0.0029269948,0.014780227,0.0074360375,0.009837465,0.0049584745,0.0016418033],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018507113,0.00020649207,0.010933671,0.0014493292,0.00010139572,0.0007371931,0.38909513,0.0010883309,0.0036105327,0.33415928,0.017616097,0.24081743],"study_design_scores_gemma":[0.00005096192,0.00041033278,0.036736887,0.0045960024,0.00013378031,0.0005591134,0.29481855,0.0023584373,0.005114197,0.05075209,0.6041655,0.0003041174],"about_ca_topic_score_codex":0.18030173,"about_ca_topic_score_gemma":0.23191732,"teacher_disagreement_score":0.18030173,"about_ca_system_score_codex":0.04310295,"about_ca_system_score_gemma":0.08122877,"threshold_uncertainty_score":0.35850453},"labels":[],"label_agreement":null},{"id":"W316755295","doi":"","title":"A Triumph of Politics over Pedagogy? The Case of the Ontario Teacher Qualifying Test, 2000-2005","year":2005,"lang":"en","type":"article","venue":"Canadian Journal of Educational Administration and Policy","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Certification; Bachelor; Test (biology); Teacher preparation; Government (linguistics); Teacher education; Politics; Pedagogy; Alternative teacher certification; Political science; Medical education; Psychology; Mathematics education; Sociology; Medicine; Law","score_opus":0.0407775116742853,"score_gpt":0.4037780738310834,"score_spread":0.3630005621567981,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W316755295","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.17044422,0.0038561951,0.0005886717,0.6696183,0.00061004295,0.000073474745,0.0003690496,0.000043080196,0.1543969],"genre_scores_gemma":[0.9215579,0.0014909003,0.0006194795,0.03441476,0.00021883937,0.000056906814,0.00012527699,0.00006607812,0.041449837],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.98520815,0.002532355,0.00036759785,0.0009520139,0.005630942,0.0053089145],"domain_scores_gemma":[0.9803801,0.005744121,0.0012086944,0.0006825588,0.006032025,0.00595243],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013897805,0.00021689408,0.0004935206,0.0015005714,0.028878152,0.010575651,0.002167852,0.0075211697,0.005230784],"category_scores_gemma":[0.027922349,0.0004802164,0.0004434591,0.0026064175,0.015343548,0.0052261013,0.0036465463,0.007978018,0.00045681334],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":true,"study_design_scores_codex":[0.00024346123,0.00018652422,0.060785033,0.00017502639,0.00004456884,0.0032868537,0.17354675,0.0005653106,0.0015075605,0.42325425,0.25433978,0.08206486],"study_design_scores_gemma":[0.00014235759,0.000104304614,0.19589873,0.00059719395,0.00006768524,0.00059269916,0.18245243,0.00060110114,0.0010352993,0.021974629,0.5963333,0.00020028211],"about_ca_topic_score_codex":0.9750171,"about_ca_topic_score_gemma":0.9903368,"teacher_disagreement_score":0.8464757,"about_ca_system_score_codex":0.15352425,"about_ca_system_score_gemma":0.14163293,"threshold_uncertainty_score":0.9817919},"labels":[],"label_agreement":null},{"id":"W3167671009","doi":"10.1007/s40037-021-00670-z","title":"Don’t be reviewer&amp;nbsp;2! Reflections on writing effective peer review comments","year":2021,"lang":"en","type":"editorial","venue":"Perspectives on Medical Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":43,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"The Wilson Centre; Sinai Health System; University of Toronto; Western University","funders":"","keywords":"Medical education; Peer review; Psychology; Computer science; Medicine; Chemistry; Biochemistry","score_opus":0.05392581346621207,"score_gpt":0.5045142607564723,"score_spread":0.45058844729026026,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3167671009","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000054552285,0.0008609011,0.00031288643,0.38807797,0.6069797,0.00007836927,0.000091914466,0.00016528128,0.003378418],"genre_scores_gemma":[0.0021482725,0.0017916969,0.0017305776,0.3981361,0.53830045,0.00040262906,0.00019132605,0.0006482855,0.056650646],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.8655345,0.036183715,0.0149648795,0.006390924,0.070121594,0.0068043885],"domain_scores_gemma":[0.34912908,0.1161915,0.023833912,0.0153220175,0.45605275,0.039470755],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.10051651,0.0025729537,0.0044630063,0.004517855,0.012433851,0.025468474,0.0069265445,0.036344796,0.058397863],"category_scores_gemma":[0.5320133,0.0022280833,0.0036607701,0.0026538393,0.0073039117,0.013369293,0.007334212,0.04285478,0.06370663],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009034163,0.000003665505,0.000021131476,0.000051010684,0.000004437533,0.000030216028,0.000057966132,0.0000046185305,0.00001582599,0.00021798053,0.9980744,0.0015096414],"study_design_scores_gemma":[0.00009189349,0.000021235895,0.00028852862,0.00075024215,0.00004234777,0.00016240512,0.00053744524,0.00015228958,0.000111681264,0.0020437324,0.9957211,0.00007694936],"about_ca_topic_score_codex":0.011651511,"about_ca_topic_score_gemma":0.027173094,"teacher_disagreement_score":0.8994835,"about_ca_system_score_codex":0.011746283,"about_ca_system_score_gemma":0.03103932,"threshold_uncertainty_score":0.5315885},"labels":[],"label_agreement":null},{"id":"W3169110767","doi":"10.5539/elt.v14n7p21","title":"The Impact of Language Testing Washback in Promoting Teaching and Learning Processes: A Theoretical Review","year":2021,"lang":"en","type":"review","venue":"English Language Teaching","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology; Context (archaeology); Mathematics education; Test (biology); Government (linguistics); Pedagogy; Language assessment; Process (computing); Language change; Foreign language; Language education; Teaching method; Linguistics; Computer science","score_opus":0.026372066115280254,"score_gpt":0.40898340271917705,"score_spread":0.3826113366038968,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3169110767","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00008710048,0.99945146,0.000037883336,0.0001234712,0.00003198834,0.000008876667,0.000008488184,0.0000016244725,0.00024901514],"genre_scores_gemma":[0.0008231361,0.9989453,0.00009532237,0.00006471078,0.000017069444,0.000010034943,0.000007980011,5.6788315e-7,0.000035940215],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99892104,0.0003252919,0.00023635133,0.00015163011,0.00031271414,0.000053028158],"domain_scores_gemma":[0.9906369,0.0073976624,0.00065513316,0.000103469414,0.0010649515,0.0001418168],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0035652234,0.0008656555,0.0022310428,0.006698874,0.0004928274,0.0017602133,0.001580484,0.0017131813,0.0035349808],"category_scores_gemma":[0.008648233,0.00058087514,0.0014332347,0.0071615106,0.00095555984,0.0024275295,0.0010141622,0.0013339231,0.00079898763],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000089052504,0.00010641867,0.00042402808,0.2151868,0.00040514598,0.000111768575,0.00026540933,0.00024969532,0.00025644441,0.0027536908,0.0058253235,0.7743262],"study_design_scores_gemma":[0.000095994095,0.00054816756,0.0084701,0.38860413,0.0047912057,0.0016249127,0.0010244825,0.0003436235,0.0008698962,0.0034096895,0.590113,0.00010476657],"about_ca_topic_score_codex":0.005353322,"about_ca_topic_score_gemma":0.010921086,"teacher_disagreement_score":0.006698874,"about_ca_system_score_codex":0.0017784348,"about_ca_system_score_gemma":0.005514996,"threshold_uncertainty_score":0.018854916},"labels":[],"label_agreement":null},{"id":"W3170208555","doi":"10.5430/wjel.v11n2p1","title":"Students’ Perspectives as Providers and Receivers of Peer Formative Feedback on Writing","year":2021,"lang":"en","type":"article","venue":"World Journal of English Language","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Peer feedback; Formative assessment; Feeling; Quality (philosophy); Certainty; Peer review; Technical peer review; Computer science; Psychology; Medical education; Mathematics education; Social psychology; Medicine; Political science","score_opus":0.013191724688976893,"score_gpt":0.3307774514420382,"score_spread":0.3175857267530613,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3170208555","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9907368,0.00037559695,0.0021586758,0.0021855717,0.00007913151,0.0000573606,0.00002435929,0.000032115095,0.0043504206],"genre_scores_gemma":[0.9973385,0.00031017096,0.00062809413,0.00027370587,0.00006256857,0.000043193253,0.000016067757,0.000016959642,0.0013107251],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9346801,0.051827196,0.0019103144,0.0014762969,0.007352998,0.002753065],"domain_scores_gemma":[0.8964234,0.065951385,0.013189442,0.0028836539,0.012067998,0.009484135],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.028469222,0.000563199,0.0006907834,0.001631945,0.004872305,0.007592262,0.0010835293,0.001956785,0.002246871],"category_scores_gemma":[0.10076386,0.0005264545,0.00052671396,0.00089777046,0.0033420443,0.0037592833,0.00490704,0.003307631,0.00050998],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017496689,0.0001964877,0.039000828,0.00017659986,0.000029941813,0.0010212149,0.92512184,0.00008958381,0.0033022475,0.0009088073,0.0007626615,0.029214846],"study_design_scores_gemma":[0.000033904053,0.00093470834,0.02032675,0.00022992353,0.00005936273,0.0013737241,0.9596815,0.0004603049,0.002882918,0.0005317135,0.013422647,0.00006239991],"about_ca_topic_score_codex":0.0012139821,"about_ca_topic_score_gemma":0.0018525912,"teacher_disagreement_score":0.028469222,"about_ca_system_score_codex":0.0015788632,"about_ca_system_score_gemma":0.0035149774,"threshold_uncertainty_score":0.15056145},"labels":[],"label_agreement":null},{"id":"W3170640792","doi":"10.18806/tesl.v37i1.1333","title":"Does the Quality of Source Notes Matter? An Exploratory Study of Source-based Academic Writing","year":2020,"lang":"en","type":"article","venue":"TESL Canada Journal","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Copying; Redaction; Quality (philosophy); Popularity; Exploratory research; Humanities; Face (sociological concept); Psychology; Linguistics; Mathematics education; Pedagogy; Sociology; Literature; Art; Philosophy; Political science; Social psychology; Epistemology","score_opus":0.08123880349729176,"score_gpt":0.36819923467237226,"score_spread":0.2869604311750805,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3170640792","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99904376,0.000053561253,0.00015875019,0.00006285464,0.0000022109373,0.000014605915,0.000022249833,0.0000021517894,0.00063977245],"genre_scores_gemma":[0.99913675,0.00006826234,0.00023141575,0.000027732218,0.000004079115,0.000026426027,0.00003754592,0.0000060433695,0.0004617613],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9870935,0.0075231944,0.0011562351,0.0008943459,0.002830644,0.0005019935],"domain_scores_gemma":[0.76059353,0.17384267,0.04601223,0.0055557727,0.010190359,0.0038054504],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.016625905,0.000316029,0.0005519113,0.0017025693,0.0011201671,0.0056289625,0.00096917467,0.0007353734,0.0021666493],"category_scores_gemma":[0.1332441,0.00035831996,0.00031483962,0.0023066006,0.0021121358,0.0030349828,0.0022109908,0.0012435693,0.0004590376],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003401431,0.0009542578,0.80675054,0.00019620112,0.00010951304,0.00055093825,0.15326299,0.00012616684,0.0017633026,0.00057724264,0.0002567841,0.035111967],"study_design_scores_gemma":[0.000024739718,0.0008977564,0.9062646,0.0001288612,0.000042336236,0.00044880822,0.08817199,0.0005285909,0.0011942236,0.00058253837,0.0016806724,0.000034756224],"about_ca_topic_score_codex":0.0013072516,"about_ca_topic_score_gemma":0.0023782605,"teacher_disagreement_score":0.9833741,"about_ca_system_score_codex":0.00095460156,"about_ca_system_score_gemma":0.0010584595,"threshold_uncertainty_score":0.08792728},"labels":[],"label_agreement":null},{"id":"W3172002384","doi":"10.3968/12122","title":"A Review Research of Washback in Language Testing","year":2021,"lang":"en","type":"review","venue":"Studies in literature and language","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Phenomenon; Empirical research; Psychology; Test (biology); Mathematics education; Mathematics; Physics","score_opus":0.2682666067829474,"score_gpt":0.5816010816506939,"score_spread":0.3133344748677465,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3172002384","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00016142313,0.99873537,0.00008461536,0.00027662012,0.00010472715,0.00001267412,0.000023991232,0.000002828874,0.0005978019],"genre_scores_gemma":[0.0014075353,0.99798644,0.00020851259,0.0001822174,0.00006428746,0.000016254988,0.000020377789,0.0000015104707,0.00011281327],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9976871,0.0006295564,0.0006706069,0.00027068006,0.00067306537,0.000068946734],"domain_scores_gemma":[0.98621935,0.011025777,0.0010680619,0.0001714244,0.0013256627,0.00018973973],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028789516,0.0008029784,0.00158193,0.0070201675,0.0005975614,0.002362371,0.0010678312,0.0016507927,0.0046720956],"category_scores_gemma":[0.0123576205,0.00046394582,0.0014449492,0.008657108,0.0008414481,0.002810081,0.00086838636,0.0014115369,0.00073230895],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000083554776,0.00009152252,0.00075419684,0.36029705,0.00046567927,0.00029588776,0.00084164424,0.00019885036,0.00064721395,0.00395961,0.014930401,0.6174343],"study_design_scores_gemma":[0.000033233307,0.00019144171,0.0054996475,0.36101916,0.0028826506,0.0023209106,0.0012833274,0.0001085584,0.000596839,0.0029209382,0.62308955,0.000053804873],"about_ca_topic_score_codex":0.0037200153,"about_ca_topic_score_gemma":0.007710201,"teacher_disagreement_score":0.0070201675,"about_ca_system_score_codex":0.0016714424,"about_ca_system_score_gemma":0.006801966,"threshold_uncertainty_score":0.015629768},"labels":[],"label_agreement":null},{"id":"W3172290871","doi":"10.1139/cjc-2020-0398","title":"Examining chemistry students’ perceptions toward multiple-choice assessment tools that vary in feedback and partial credit","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Chemistry","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Wilfrid Laurier University","funders":"","keywords":"Psychology; Multiple choice; Preference; Test anxiety; Perception; Anxiety; Test (biology); Mathematics education; Statistics; Mathematics; Significant difference","score_opus":0.07628932059813516,"score_gpt":0.34230333238870675,"score_spread":0.2660140117905716,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3172290871","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99893886,0.000043429696,0.0003614914,0.000094664145,0.000009301453,0.000032162705,0.000011882227,0.0000065549957,0.000501704],"genre_scores_gemma":[0.9977568,0.00010859587,0.0012948985,0.00009838412,0.0000079444635,0.00003563298,0.000031262098,0.0000047209746,0.00066180166],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9918385,0.0026497534,0.0006153782,0.00038659095,0.003972281,0.0005374708],"domain_scores_gemma":[0.969315,0.013357894,0.0065960092,0.00068757724,0.0068593207,0.0031841996],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00992699,0.00041517068,0.0005279809,0.001140035,0.0006875811,0.0021280372,0.0004597113,0.0006248953,0.0020645396],"category_scores_gemma":[0.03815114,0.00023300452,0.0007059506,0.00068455643,0.00069119723,0.00076612114,0.0010169399,0.0010096283,0.00042687837],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015783968,0.0040200227,0.7846313,0.00037598165,0.00017919803,0.0005125326,0.040534075,0.0009929243,0.027910525,0.00043668906,0.0016394772,0.13718885],"study_design_scores_gemma":[0.00016248628,0.011732867,0.9066004,0.00022022332,0.00011603381,0.00069906237,0.05757876,0.005275937,0.0106968125,0.0005027389,0.0061587845,0.00025577797],"about_ca_topic_score_codex":0.0039154817,"about_ca_topic_score_gemma":0.0056069065,"teacher_disagreement_score":0.00992699,"about_ca_system_score_codex":0.0009803707,"about_ca_system_score_gemma":0.0011757559,"threshold_uncertainty_score":0.052499592},"labels":[],"label_agreement":null},{"id":"W3176463368","doi":"10.5539/elt.v14n7p107","title":"Teachers’ Perception towards Formative Assessment in Saudi Universities’ Context: A Review of Literature","year":2021,"lang":"en","type":"review","venue":"English Language Teaching","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Formative assessment; Psychology; Summative assessment; Context (archaeology); Perception; Knowledge survey; Medical education; Pedagogy; Medicine","score_opus":0.02417926377044678,"score_gpt":0.3972648817651881,"score_spread":0.3730856179947413,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3176463368","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015070259,0.99770975,0.000047289457,0.00029087314,0.00006443651,0.000009974255,0.000021525271,0.0000015818631,0.00034755652],"genre_scores_gemma":[0.013005641,0.9865218,0.00016139708,0.00016143742,0.00004349482,0.000013441891,0.000027824208,0.0000010143979,0.00006403936],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9980166,0.00058721885,0.00053945824,0.00017130357,0.00060945854,0.00007596651],"domain_scores_gemma":[0.9895455,0.0066274134,0.0014220469,0.00009719154,0.0021123681,0.00019545277],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0045278342,0.0006064909,0.0011863218,0.0054367688,0.0004497317,0.0022972298,0.00080940337,0.0010857163,0.0015243392],"category_scores_gemma":[0.010712379,0.00036636912,0.0010951097,0.005866971,0.00072288915,0.0018557204,0.0007792424,0.00087018084,0.00024076151],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017196068,0.00010902138,0.005826661,0.24621378,0.00087165425,0.00035277783,0.0028195593,0.00021789175,0.00053499354,0.0011126109,0.004952482,0.7368165],"study_design_scores_gemma":[0.000120070734,0.00083475915,0.09217429,0.43508112,0.009350231,0.0051643113,0.019566981,0.00040142157,0.0015837832,0.0020142854,0.43352947,0.00017913862],"about_ca_topic_score_codex":0.009667357,"about_ca_topic_score_gemma":0.0212605,"teacher_disagreement_score":0.009667357,"about_ca_system_score_codex":0.001899889,"about_ca_system_score_gemma":0.0064342115,"threshold_uncertainty_score":0.023945749},"labels":[],"label_agreement":null},{"id":"W3183541999","doi":"10.1002/prp2.833","title":"Answering questions in a co‐created formative exam question bank improves summative exam performance, while students perceive benefits from answering, authoring, and peer discussion: A mixed methods analysis of PeerWise","year":2021,"lang":"en","type":"article","venue":"Pharmacology Research & Perspectives","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Summative assessment; Formative assessment; Test (biology); Medical education; Multiple choice; Peer assessment; Class (philosophy); Psychology; Mathematics education; Computer science; Medicine; Internal medicine; Artificial intelligence","score_opus":0.0832141660436603,"score_gpt":0.5168632575806068,"score_spread":0.43364909153694653,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3183541999","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9927677,0.00024739583,0.004441394,0.00017894832,0.00002958156,0.00068231975,0.0002784609,0.000032510256,0.0013417004],"genre_scores_gemma":[0.98816085,0.00016656067,0.0075374404,0.00016554796,0.000023466844,0.0020037608,0.00023919066,0.000023474722,0.0016796663],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98435587,0.009338977,0.0016269891,0.0011164359,0.0028298069,0.0007319273],"domain_scores_gemma":[0.9578112,0.025231445,0.0065536737,0.0024462095,0.0063086255,0.0016487871],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.022133373,0.00043637663,0.00052494975,0.001117271,0.0010538268,0.0022488635,0.0009804995,0.00067262555,0.0027270115],"category_scores_gemma":[0.04848852,0.00037052133,0.0015174565,0.0007400418,0.0007534106,0.0010870964,0.0015748349,0.00070327235,0.00046889897],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0045836954,0.009443257,0.60733545,0.001854398,0.0018370887,0.00021011589,0.045964964,0.00096511556,0.012234459,0.002080207,0.0022127475,0.31127852],"study_design_scores_gemma":[0.0003961563,0.017786123,0.90912724,0.0009069098,0.0015964634,0.00027568673,0.022043694,0.004207032,0.023374986,0.0016821155,0.018416224,0.00018745454],"about_ca_topic_score_codex":0.0019052984,"about_ca_topic_score_gemma":0.004876623,"teacher_disagreement_score":0.022133373,"about_ca_system_score_codex":0.0012269457,"about_ca_system_score_gemma":0.0034971584,"threshold_uncertainty_score":0.11705381},"labels":[],"label_agreement":null},{"id":"W3183841095","doi":"10.5539/elt.v14n8p58","title":"Online Proctoring of High-Stakes English Language Examinations: A Survey of Past Candidates’ Attitudes and Perceptions","year":2021,"lang":"en","type":"article","venue":"English Language Teaching","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Cheating; Psychology; Perception; Constructive; Test (biology); Medical education; Mathematics education; Social psychology; Pedagogy; Medicine; Computer science; Process (computing)","score_opus":0.020986810649177012,"score_gpt":0.33866034351838115,"score_spread":0.31767353286920413,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3183841095","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9988372,0.00004216881,0.00007308093,0.00017806601,0.000006933362,0.000013242356,0.00002491386,0.0000029316127,0.00082157506],"genre_scores_gemma":[0.997603,0.00012500696,0.00017032996,0.000120589706,0.000010667014,0.000016228922,0.000052384752,0.0000039251076,0.0018977713],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9975038,0.0010614397,0.00023387064,0.00016128541,0.0005815328,0.00045804237],"domain_scores_gemma":[0.98433566,0.0037132795,0.004631023,0.00055343215,0.0024493565,0.0043172017],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0044014165,0.00021176376,0.000334869,0.0010606828,0.0014807717,0.001649008,0.00032220175,0.0006693026,0.0037680748],"category_scores_gemma":[0.013123186,0.00029184602,0.00032519858,0.00078645017,0.00075923384,0.0009096972,0.0009184662,0.001135682,0.0013476933],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021357747,0.0012099815,0.9215047,0.00011405995,0.000024726358,0.00089556613,0.03947427,0.00012753013,0.0033697928,0.00020878381,0.001251981,0.031605102],"study_design_scores_gemma":[0.0000087899225,0.0021782257,0.90199244,0.0000710563,0.000018065875,0.00087455066,0.08736042,0.0005931314,0.0012980838,0.00004856245,0.005509642,0.00004701352],"about_ca_topic_score_codex":0.003161756,"about_ca_topic_score_gemma":0.0046955366,"teacher_disagreement_score":0.0044014165,"about_ca_system_score_codex":0.00043623312,"about_ca_system_score_gemma":0.00057205564,"threshold_uncertainty_score":0.023277164},"labels":[],"label_agreement":null},{"id":"W3185590891","doi":"10.22034/elt.2021.43932.2334","title":"A New Dilemma for Language Teachers and Students: Self-assessment or Teacher Assessment (Research Article)","year":2021,"lang":"en","type":"article","venue":"DOAJ (DOAJ: Directory of Open Access Journals)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Dilemma; Self-assessment; Likert scale; Reading (process); Psychology; Reading comprehension; Mathematics education; Comprehension; Set (abstract data type); Test (biology); Medical education; Pedagogy; Computer science; Medicine","score_opus":0.32538256722417375,"score_gpt":0.6670082438301432,"score_spread":0.3416256766059695,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3185590891","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.1909465,0.07204178,0.3345343,0.3205077,0.014561827,0.0014389511,0.00036220567,0.0013247519,0.064281985],"genre_scores_gemma":[0.8163628,0.0085164225,0.14658742,0.018837906,0.0026208423,0.0016808811,0.00011775796,0.00024817968,0.0050277887],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.82987374,0.13941215,0.008410388,0.005238059,0.016212875,0.000852661],"domain_scores_gemma":[0.8429657,0.10869415,0.008291474,0.011750143,0.020881604,0.007416994],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.13481976,0.0004796135,0.0018539098,0.0029566698,0.0021217542,0.008887448,0.0018242802,0.0022192998,0.0020701105],"category_scores_gemma":[0.17015378,0.00040367158,0.0005231415,0.0016130636,0.0148992725,0.0111650415,0.006035287,0.004677589,0.001024936],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00038653958,0.00066321756,0.033882808,0.0017992526,0.0001529463,0.00030962456,0.055197604,0.00028117746,0.0021351506,0.08002491,0.028253255,0.7969135],"study_design_scores_gemma":[0.00048018308,0.003769354,0.061261285,0.010554245,0.00024619343,0.0074538714,0.18955411,0.008287851,0.0030752309,0.4022994,0.31212047,0.0008977659],"about_ca_topic_score_codex":0.0009246653,"about_ca_topic_score_gemma":0.0015375621,"teacher_disagreement_score":0.13481976,"about_ca_system_score_codex":0.0018207585,"about_ca_system_score_gemma":0.0064075664,"threshold_uncertainty_score":0.7130036},"labels":[],"label_agreement":null},{"id":"W3186678687","doi":"10.3390/educsci11070366","title":"Generative Unit Assessment: Authenticity in Mathematics Classroom Assessment Practices","year":2021,"lang":"en","type":"article","venue":"Education Sciences","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Lethbridge; University of Alberta","funders":"University of Alberta","keywords":"Unit (ring theory); Generative grammar; Mathematics education; Task (project management); Action (physics); Authentic assessment; Citizen journalism; Alternative assessment; Process (computing); Computer science; Dynamic assessment; Generative model; Pedagogy; Psychology; Artificial intelligence; Engineering; Curriculum","score_opus":0.141037056081307,"score_gpt":0.5097772346579433,"score_spread":0.3687401785766363,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3186678687","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.41624075,0.00048572774,0.52391636,0.0049840817,0.0001712748,0.0011924473,0.000044876182,0.0005510805,0.052413356],"genre_scores_gemma":[0.92763627,0.00008004506,0.06987243,0.00019758924,0.000018322784,0.00038426882,0.000019349707,0.00007039056,0.0017212998],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.8662498,0.11313822,0.0027328306,0.004918783,0.01151703,0.001443346],"domain_scores_gemma":[0.8506733,0.103202194,0.0071420833,0.026398543,0.009366396,0.0032174827],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.06460234,0.0007034309,0.0006529319,0.0026020044,0.005468748,0.011257048,0.0031769865,0.0025760466,0.0026650121],"category_scores_gemma":[0.15347451,0.00071350933,0.00070254225,0.0010937648,0.021836225,0.009802793,0.016209394,0.0037538067,0.0005356174],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012131798,0.0002725915,0.013155228,0.00046325725,0.000032251908,0.0006606653,0.724852,0.0018673053,0.0069644875,0.13861887,0.0010054559,0.11198654],"study_design_scores_gemma":[0.00011077846,0.001564179,0.017147986,0.002249981,0.000083192666,0.0042391378,0.36132762,0.022517938,0.022647113,0.36632493,0.20134242,0.00044471413],"about_ca_topic_score_codex":0.00083803176,"about_ca_topic_score_gemma":0.0011650316,"teacher_disagreement_score":0.06460234,"about_ca_system_score_codex":0.0026862526,"about_ca_system_score_gemma":0.004584186,"threshold_uncertainty_score":0.34165388},"labels":[],"label_agreement":null},{"id":"W3187362732","doi":"10.3390/educsci11080400","title":"Teacher Education during the COVID-19 Lockdown: Insights from a Formative Intervention Approach Involving Online Feedback","year":2021,"lang":"en","type":"article","venue":"Education Sciences","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":20,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Fundação para a Ciência e a Tecnologia; Universidade do Minho; Ministério da Ciência, Tecnologia e Ensino Superior; International Council for Canadian Studies","keywords":"Formative assessment; CLARITY; Psychology; Intervention (counseling); Mathematics education; Meaning (existential); Computer-mediated communication; Coronavirus disease 2019 (COVID-19); Teacher education; Higher education; Pedagogy; Medical education; Computer science; The Internet; Medicine","score_opus":0.06289100403871921,"score_gpt":0.4044985134050234,"score_spread":0.3416075093663042,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3187362732","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9754431,0.00033670003,0.009800965,0.0033041511,0.00019643584,0.0005359833,0.000044299406,0.0001737327,0.01016464],"genre_scores_gemma":[0.9924672,0.00019023092,0.0040916298,0.0004956385,0.00003325185,0.0002848852,0.000023157061,0.000047553014,0.0023664318],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.97614163,0.018132687,0.00054622244,0.00086372666,0.0023132167,0.0020024416],"domain_scores_gemma":[0.9451464,0.041314036,0.0034164952,0.002202958,0.0037403493,0.004179808],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.019462265,0.0005470265,0.0006256173,0.0011151858,0.00669037,0.00479291,0.0019695556,0.0021030097,0.0019700704],"category_scores_gemma":[0.06084505,0.00042832093,0.0003744087,0.0006523178,0.0056471117,0.002781134,0.0062136757,0.0041759433,0.00044331208],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004186062,0.002575727,0.012279812,0.0004328116,0.00002125063,0.0015550044,0.84689796,0.00031253343,0.0069077797,0.002883936,0.002321877,0.123392746],"study_design_scores_gemma":[0.00017224807,0.003396798,0.03523534,0.0010273776,0.00003944721,0.0010340326,0.8879977,0.0009735605,0.009108404,0.0027605619,0.058120564,0.00013389118],"about_ca_topic_score_codex":0.0030856996,"about_ca_topic_score_gemma":0.00835694,"teacher_disagreement_score":0.019462265,"about_ca_system_score_codex":0.003532036,"about_ca_system_score_gemma":0.005797841,"threshold_uncertainty_score":0.102927566},"labels":[],"label_agreement":null},{"id":"W3188171252","doi":"10.1007/s10459-021-10063-w","title":"Implicit and inferred: on the philosophical positions informing assessment science","year":2021,"lang":"en","type":"article","venue":"Advances in Health Sciences Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":8,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Sciences Centre; Sunnybrook Health Science Centre; St. Michael's Hospital; The Wilson Centre; Centre for Global Health Research; University of Toronto; University Health Network","funders":"","keywords":"Philosophical methodology; Competence (human resources); Epistemology; Construct (python library); Philosophical analysis; Psychology; Computer science; Social psychology; Philosophy","score_opus":0.037830304246417173,"score_gpt":0.4821125215118375,"score_spread":0.4442822172654203,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3188171252","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07386945,0.017669464,0.5192342,0.3160247,0.0024342153,0.0001930591,0.00032094095,0.00023738864,0.07001662],"genre_scores_gemma":[0.90586305,0.0034315197,0.08015788,0.006925778,0.0012629016,0.00023327388,0.00012634014,0.00011952009,0.001879716],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9233945,0.051956676,0.0054090284,0.0047616633,0.013387907,0.0010902061],"domain_scores_gemma":[0.6551881,0.28012598,0.012493911,0.02054689,0.028403658,0.0032415604],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.07558765,0.000925395,0.0015785551,0.005668218,0.0044752387,0.015390604,0.00611681,0.010350319,0.004717919],"category_scores_gemma":[0.23770577,0.0014672469,0.0011629848,0.003132585,0.073096365,0.03617933,0.011457764,0.020285547,0.0008100665],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013939588,0.000060506918,0.0020919049,0.00039501998,0.000054241355,0.00007526839,0.011501018,0.001033271,0.00028299892,0.95285213,0.0010699219,0.03044426],"study_design_scores_gemma":[0.000024867379,0.000027472654,0.00063816074,0.0003444164,0.000031037453,0.0000745069,0.0012795974,0.0033599678,0.00028753543,0.99038005,0.0035215688,0.000030758758],"about_ca_topic_score_codex":0.0036639278,"about_ca_topic_score_gemma":0.0032766433,"teacher_disagreement_score":0.92441237,"about_ca_system_score_codex":0.0063136704,"about_ca_system_score_gemma":0.006167577,"threshold_uncertainty_score":0.39975047},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_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","score_opus":0.07826089378203037,"score_gpt":0.4097405264132591,"score_spread":0.3314796326312287,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3191701502","genre_codex":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0030377705,0.062332477,0.15680656,0.5145002,0.0572215,0.029799042,0.01889674,0.0023785923,0.15502723],"genre_scores_gemma":[0.063763864,0.04369012,0.55081224,0.10298308,0.0057971384,0.07985347,0.029226309,0.002400986,0.121472746],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.71502525,0.13741636,0.06237194,0.00745107,0.065731704,0.012003666],"domain_scores_gemma":[0.56844056,0.10233402,0.02022155,0.017611278,0.27197108,0.019421494],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.21442145,0.0021201305,0.004524002,0.010803844,0.007263087,0.014269285,0.01862385,0.01926865,0.012601557],"category_scores_gemma":[0.3071682,0.004027469,0.009620917,0.008445152,0.011992956,0.0047349376,0.013228771,0.026171414,0.011895524],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00035826347,0.00015489756,0.0016680522,0.011071481,0.0002830783,0.0003435674,0.003306563,0.0015201989,0.00047753594,0.047243297,0.7994764,0.13409674],"study_design_scores_gemma":[0.00017036016,0.00008450548,0.003794283,0.02919088,0.00022839448,0.00027132296,0.0016215198,0.00062417134,0.0006254831,0.019047415,0.9441017,0.00023990612],"about_ca_topic_score_codex":0.19329098,"about_ca_topic_score_gemma":0.15573588,"teacher_disagreement_score":0.78557855,"about_ca_system_score_codex":0.049199242,"about_ca_system_score_gemma":0.21535671,"threshold_uncertainty_score":0.9687582},"labels":[],"label_agreement":null},{"id":"W3191913029","doi":"10.20343/teachlearninqu.9.2.18","title":"Can Relational Feed-Forward Enhance Students’ Cognitive and Affective Responses to Assessment?","year":2021,"lang":"en","type":"article","venue":"Teaching & Learning Inquiry The ISSOTL Journal","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"MacEwan University","funders":"","keywords":"Psychology; Thematic analysis; Rubric; Cognition; Qualitative research; Medical education; Pedagogy","score_opus":0.04183766046924296,"score_gpt":0.41995587850686356,"score_spread":0.3781182180376206,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3191913029","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95166564,0.0005450306,0.021598842,0.0060081636,0.00019693126,0.00032099447,0.000040437564,0.00028640896,0.019337602],"genre_scores_gemma":[0.9881292,0.00035877177,0.009167047,0.0004345902,0.000029162777,0.00019456627,0.00001590235,0.000034702538,0.0016359586],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9903137,0.0070807063,0.0002098148,0.00046653574,0.0012766299,0.00065261003],"domain_scores_gemma":[0.9833535,0.011149524,0.0017034101,0.00097328675,0.0011740057,0.001646342],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009526741,0.00038444964,0.00044496532,0.000676653,0.0012491572,0.004218269,0.00089546887,0.0011419147,0.0034482665],"category_scores_gemma":[0.038046252,0.00024891098,0.00044384485,0.0004357323,0.0022804574,0.002537501,0.003990669,0.0017719935,0.0007148481],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000476824,0.003080572,0.05011235,0.0015522045,0.00011138429,0.000730275,0.43577433,0.0008394188,0.030258726,0.00896448,0.0041329283,0.46396655],"study_design_scores_gemma":[0.0003313604,0.0059836186,0.25533625,0.0022892326,0.00032471475,0.0016277211,0.51432204,0.006840334,0.026410999,0.044698432,0.14134875,0.00048652667],"about_ca_topic_score_codex":0.0006929233,"about_ca_topic_score_gemma":0.00184505,"teacher_disagreement_score":0.009526741,"about_ca_system_score_codex":0.0010822584,"about_ca_system_score_gemma":0.0018308295,"threshold_uncertainty_score":0.050382853},"labels":[],"label_agreement":null},{"id":"W3192331548","doi":"10.5430/wjel.v11n2p107","title":"The Effects of Formative Evaluation on Students' Achievement in English for Specific Purposes (A Case Study of the Preparatory Year Students at Umm- Al-Qura University)","year":2021,"lang":"en","type":"article","venue":"World Journal of English Language","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Formative assessment; Summative assessment; Mathematics education; Medical education; Control (management); Psychology; Pedagogy; Medicine; Computer science","score_opus":0.016403695714600586,"score_gpt":0.33835593444764445,"score_spread":0.32195223873304385,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3192331548","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99718744,0.0001784037,0.00037614044,0.00017380062,0.00001894894,0.00006408504,0.000004294331,0.000010358367,0.0019866775],"genre_scores_gemma":[0.9982993,0.00016222517,0.00081588,0.000040145886,0.000013206314,0.00003790887,0.0000069537123,0.0000027012877,0.0006216444],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9884538,0.0076084244,0.00060502475,0.00039397524,0.0021569724,0.0007817485],"domain_scores_gemma":[0.9593392,0.024630208,0.004873564,0.001789935,0.005606111,0.00376093],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01609191,0.0005417113,0.00037607335,0.0009584858,0.0017014124,0.002661429,0.0008776313,0.0007398694,0.0011192994],"category_scores_gemma":[0.035190552,0.00020428063,0.00061220524,0.0005377869,0.0010229874,0.0010710567,0.0010407066,0.00081622147,0.00022881015],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010455657,0.011042777,0.3896963,0.0009967069,0.00017816042,0.003091304,0.15753171,0.00077395636,0.01778097,0.0010165458,0.0014774929,0.41536844],"study_design_scores_gemma":[0.00010496818,0.017053552,0.8259141,0.0004909371,0.00023107618,0.0018247417,0.12779638,0.0012894319,0.015801439,0.00059264817,0.008734995,0.00016579678],"about_ca_topic_score_codex":0.001420974,"about_ca_topic_score_gemma":0.0034930164,"teacher_disagreement_score":0.01609191,"about_ca_system_score_codex":0.001244269,"about_ca_system_score_gemma":0.0018586346,"threshold_uncertainty_score":0.085103214},"labels":[],"label_agreement":null},{"id":"W3194429716","doi":"10.1007/978-981-16-3603-5_4","title":"Global ESOL Assessment Practices: The Washback Effect and Automated Testing in China","year":2021,"lang":"en","type":"book-chapter","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Yorkville University","funders":"","keywords":"Language assessment; German; China; Foreign language; Test (biology); Language education; Computer science; Language industry; Mathematics education; Pedagogy; Comprehension approach; Psychology; Political science; Linguistics","score_opus":0.038857434390824924,"score_gpt":0.39103532223587484,"score_spread":0.3521778878450499,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3194429716","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96262676,0.002095842,0.001533293,0.0022688163,0.000047899604,0.00004562716,0.00018218797,0.00009322438,0.03110642],"genre_scores_gemma":[0.99260193,0.0004317076,0.000438538,0.00008518347,0.000010290961,0.000013370929,0.00007253385,0.000011036189,0.006335405],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99802303,0.0005430849,0.00012709177,0.00027683703,0.00071353203,0.00031646097],"domain_scores_gemma":[0.9971642,0.0009916537,0.00041463377,0.000330715,0.00066361023,0.00043517462],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027438942,0.00035618318,0.0003024121,0.002132226,0.0012524811,0.0016306402,0.0010712623,0.00037712077,0.00300542],"category_scores_gemma":[0.0042379634,0.00014899239,0.0002641001,0.0044979677,0.0021435297,0.0019379928,0.0014841703,0.0006002617,0.00018946234],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015086916,0.00020413921,0.45359388,0.0002232732,0.00004957684,0.000536359,0.022786962,0.0030090858,0.0014178545,0.021283153,0.006972352,0.48977256],"study_design_scores_gemma":[0.000016230762,0.00021705423,0.96502423,0.00010536573,0.00003602103,0.00012977324,0.009693056,0.004665163,0.00083288824,0.004610606,0.014636624,0.00003309238],"about_ca_topic_score_codex":0.14803842,"about_ca_topic_score_gemma":0.18014774,"teacher_disagreement_score":0.14803842,"about_ca_system_score_codex":0.005628615,"about_ca_system_score_gemma":0.009244754,"threshold_uncertainty_score":0.2943535},"labels":[],"label_agreement":null},{"id":"W3197741744","doi":"10.4018/978-1-7998-8275-6.ch012","title":"Beyond High-Stakes Assessment","year":2021,"lang":"en","type":"book-chapter","venue":"Advances in higher education and professional development book series","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Accreditation; Summative assessment; Certification; Medical education; Function (biology); Psychology; Standardized test; Measure (data warehouse); Mathematics education; Political science; Medicine; Computer science; Formative assessment","score_opus":0.027403880283262506,"score_gpt":0.3657024686300425,"score_spread":0.33829858834678,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3197741744","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0026571832,0.01853501,0.026077805,0.008840577,0.0013735392,0.00009471475,0.00026119727,0.0008123458,0.94134754],"genre_scores_gemma":[0.06471244,0.024572622,0.031483773,0.005460896,0.0013345338,0.0001753933,0.0005259529,0.00043360237,0.8713009],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9984546,0.00038063942,0.00004694627,0.00011275011,0.0009419263,0.000063205895],"domain_scores_gemma":[0.9960985,0.0023459063,0.00008331639,0.0003552428,0.000883044,0.00023382419],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0021445744,0.0005919523,0.00047965394,0.0012892068,0.0005232151,0.0046577025,0.0011523388,0.0012012356,0.035480242],"category_scores_gemma":[0.005368979,0.0001693644,0.00026706848,0.0013898349,0.001741903,0.005786259,0.0017638232,0.0029416615,0.0174758],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020968831,0.00007906395,0.00044217886,0.00036881818,0.0000052420082,0.00007698183,0.0008303471,0.0005458905,0.0005756484,0.2006644,0.13485065,0.6615398],"study_design_scores_gemma":[0.000007729056,0.00004603421,0.0013897616,0.0008556853,0.000005309271,0.00030973848,0.00047025786,0.0009650418,0.0006288864,0.1711939,0.824105,0.000022620368],"about_ca_topic_score_codex":0.0021465449,"about_ca_topic_score_gemma":0.0036188713,"teacher_disagreement_score":0.9978554,"about_ca_system_score_codex":0.0012830537,"about_ca_system_score_gemma":0.001923928,"threshold_uncertainty_score":0.11869317},"labels":[],"label_agreement":null},{"id":"W3200087034","doi":"10.5539/ies.v14n10p65","title":"Digital Assessment Literacy: The Need of Online Assessment Literacy and Online Assessment Literate Educators","year":2021,"lang":"en","type":"article","venue":"International Education Studies","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Literacy; Medical education; Digital literacy; Needs assessment; Psychology; Information literacy; Professional development; Mathematics education; Pedagogy; Sociology; Medicine","score_opus":0.041525946898013893,"score_gpt":0.48765904690363954,"score_spread":0.44613310000562567,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3200087034","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.68590635,0.004652951,0.038827404,0.10864439,0.00043876068,0.00040566712,0.0001446913,0.00036107335,0.16061877],"genre_scores_gemma":[0.97550493,0.0011812915,0.014726508,0.0029897166,0.000083844396,0.00014667514,0.0000521011,0.000022777656,0.0052921344],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99099606,0.004643061,0.00061002997,0.0006588308,0.0022934373,0.00079850544],"domain_scores_gemma":[0.96323746,0.020798396,0.0034584464,0.0018451628,0.005857549,0.004802924],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008491468,0.00015638176,0.00027189188,0.0013785121,0.0016359651,0.006282601,0.000575144,0.0014732925,0.005589827],"category_scores_gemma":[0.03498401,0.00018827055,0.00018316388,0.000795968,0.0020200585,0.0086340625,0.004086024,0.0018448136,0.0006799579],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011100477,0.0008469845,0.09635629,0.001665316,0.000015885305,0.001525276,0.1133468,0.0002443702,0.004571878,0.05643958,0.011547052,0.7133295],"study_design_scores_gemma":[0.00005231139,0.0012338866,0.16135281,0.0067933383,0.000078524645,0.009880759,0.35483217,0.0047670184,0.0074748085,0.07012175,0.3831964,0.00021619923],"about_ca_topic_score_codex":0.0014847366,"about_ca_topic_score_gemma":0.0022168297,"teacher_disagreement_score":0.008491468,"about_ca_system_score_codex":0.0013548158,"about_ca_system_score_gemma":0.0066754664,"threshold_uncertainty_score":0.04490775},"labels":[],"label_agreement":null},{"id":"W3202203794","doi":"","title":"An Integrated Design and Appraisal Framework for Ethical Writing Assessment","year":2016,"lang":"en","type":"article","venue":"eScholarship (California Digital Library)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":51,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"General partnership; Engineering ethics; Management science; Critical appraisal; Sociology; Psychology; Engineering; Political science; Medicine","score_opus":0.037488699228800985,"score_gpt":0.35270298762733926,"score_spread":0.31521428839853827,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3202203794","genre_codex":"methods","genre_gemma":"methods","domain_codex":"methods","domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0024125522,0.0034505308,0.93949056,0.019551596,0.0010543836,0.010553167,0.000162947,0.0004626689,0.02286158],"genre_scores_gemma":[0.021817826,0.0008688739,0.9644875,0.00070147467,0.00016970582,0.0111321695,0.00006325938,0.00004793922,0.00071122026],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.4095178,0.5195873,0.027904632,0.0071539376,0.03309678,0.0027395275],"domain_scores_gemma":[0.5396938,0.34965843,0.01695773,0.01844713,0.068825684,0.0064172563],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.4593206,0.0031209935,0.0033484194,0.01965883,0.007157013,0.022255795,0.0070133097,0.006952682,0.004737021],"category_scores_gemma":[0.29869547,0.0017902129,0.003404576,0.010669677,0.027792305,0.020197242,0.012911736,0.010357516,0.0017269992],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012956295,0.00026849573,0.0022465184,0.005770662,0.00018372876,0.00031437003,0.045811877,0.0053810235,0.00095211924,0.673162,0.011641288,0.25413838],"study_design_scores_gemma":[0.0002654548,0.0005415375,0.0016784405,0.009698651,0.00015528633,0.00033463727,0.020625087,0.015751934,0.0011752845,0.79349583,0.15605897,0.00021886271],"about_ca_topic_score_codex":0.0033516497,"about_ca_topic_score_gemma":0.004774839,"teacher_disagreement_score":0.4593206,"about_ca_system_score_codex":0.022922141,"about_ca_system_score_gemma":0.04625861,"threshold_uncertainty_score":0.666754},"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,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_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","score_opus":0.0578890967993076,"score_gpt":0.4468809123947186,"score_spread":0.388991815595411,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3202681787","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7248818,0.0025396333,0.038794316,0.14231977,0.0010985716,0.000550095,0.000058683174,0.00026462902,0.08949249],"genre_scores_gemma":[0.98790073,0.00030529703,0.006508812,0.003069345,0.00005537557,0.00009012926,0.00001487359,0.00003253478,0.0020228266],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.8991832,0.07838005,0.0035172387,0.0027037936,0.010239988,0.0059756893],"domain_scores_gemma":[0.90744543,0.05777471,0.007621267,0.005344026,0.009152693,0.0126618855],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.058114823,0.00043320737,0.0006505613,0.0017385854,0.014387872,0.015148496,0.0029179854,0.0061603296,0.0054805866],"category_scores_gemma":[0.0688181,0.0006909842,0.00065911224,0.0015724914,0.028426265,0.014345482,0.034457672,0.010926732,0.0006516923],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007367213,0.00018764565,0.010820663,0.00042054788,0.000014713755,0.0019085794,0.87592524,0.0004338141,0.001836347,0.052769057,0.004465989,0.05114376],"study_design_scores_gemma":[0.000013307246,0.00015897425,0.0046791174,0.0013361293,0.0000067805886,0.0007747915,0.8623982,0.0008033165,0.00080402545,0.017372815,0.11156589,0.0000867246],"about_ca_topic_score_codex":0.004379637,"about_ca_topic_score_gemma":0.0043530473,"teacher_disagreement_score":0.058114823,"about_ca_system_score_codex":0.013649246,"about_ca_system_score_gemma":0.018666854,"threshold_uncertainty_score":0.30734426},"labels":[],"label_agreement":null},{"id":"W3204027159","doi":"","title":"Implications of Standardized Testing in Teacher Education: A Look at Perceptions, Experiences and Impacts on Teacher Candidates","year":2020,"lang":"en","type":"article","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Queen's University","funders":"","keywords":"Standardized test; Certification; Psychology; Teacher education; Medical education; Perception; Teacher preparation; Test (biology); Mathematics education; Accreditation; Government (linguistics); Pedagogy; Medicine; Political science","score_opus":0.0457849572758282,"score_gpt":0.38077216744960946,"score_spread":0.33498721017378125,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3204027159","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9896646,0.0003380734,0.000077759694,0.0037224481,0.000036373847,0.00002412978,0.000026026371,0.0000059401104,0.00610457],"genre_scores_gemma":[0.99688476,0.00037821545,0.000083959385,0.00037725034,0.000013323661,0.000015354904,0.000029115152,0.0000045529127,0.0022133563],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.9909051,0.003336953,0.0003537346,0.00021226027,0.0030433906,0.002148528],"domain_scores_gemma":[0.98432946,0.0023708742,0.0022725915,0.0002606963,0.0029424208,0.007824016],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005554095,0.00020887454,0.0003533345,0.0008167381,0.0059529226,0.0032614016,0.00084029546,0.0007027736,0.0024393292],"category_scores_gemma":[0.012388451,0.0002956469,0.000350868,0.0010094706,0.0044339695,0.0011514588,0.0035313363,0.0016896526,0.00034036298],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017524866,0.00062528806,0.41781226,0.00016558176,0.000015530768,0.0020605167,0.5247443,0.00009994523,0.0012845915,0.0010272018,0.005397905,0.046591736],"study_design_scores_gemma":[0.00001287454,0.00045631433,0.2878463,0.00018546049,0.00000929468,0.0004883899,0.69171524,0.000089908484,0.00028825257,0.00013189476,0.018730467,0.000045527435],"about_ca_topic_score_codex":0.29996294,"about_ca_topic_score_gemma":0.39718089,"teacher_disagreement_score":0.29996294,"about_ca_system_score_codex":0.010026541,"about_ca_system_score_gemma":0.014081854,"threshold_uncertainty_score":0.5964339},"labels":[],"label_agreement":null},{"id":"W3209301443","doi":"10.5539/elt.v14n12p1","title":"Exploring Secondary School EFL Teachers’ Assessment Literacy in Practice: A Case Study in China","year":2021,"lang":"en","type":"article","venue":"English Language Teaching","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Guangdong University of Foreign Studies","keywords":"Psychology; Internship; Literacy; Pedagogy; Medical education; Focus group; Mathematics education; Sociology; Medicine","score_opus":0.03903641093597413,"score_gpt":0.40236822463480165,"score_spread":0.3633318136988275,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3209301443","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99827456,0.00010608723,0.00015276881,0.00037586555,0.000004678289,0.00004458645,0.000010242479,0.000004372292,0.0010268231],"genre_scores_gemma":[0.99729353,0.00020526437,0.00043606077,0.00019549085,0.000005546675,0.00004879745,0.000018295153,0.0000052144264,0.0017917184],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9972465,0.0010038737,0.00021020534,0.0002936733,0.00048131766,0.0007644662],"domain_scores_gemma":[0.9966055,0.0010021842,0.00044116276,0.00020194224,0.00040725974,0.0013419753],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0036462692,0.0005758472,0.00077986124,0.002245439,0.009422688,0.0023049398,0.001995364,0.0018484753,0.0023102479],"category_scores_gemma":[0.004536993,0.0006028604,0.00049955456,0.003255176,0.004572273,0.0019621733,0.0036490092,0.0014599867,0.0002780678],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006590871,0.00047064509,0.07041138,0.00029697086,0.000015507288,0.019876717,0.8881888,0.00029685424,0.0023073314,0.0017043075,0.0007436953,0.015621852],"study_design_scores_gemma":[0.00003287351,0.00038469885,0.0854371,0.00025611647,0.000025519377,0.0028848245,0.89805615,0.0011322023,0.0010142832,0.0004467245,0.010275296,0.000054167944],"about_ca_topic_score_codex":0.12200734,"about_ca_topic_score_gemma":0.17814216,"teacher_disagreement_score":0.12200734,"about_ca_system_score_codex":0.0104171885,"about_ca_system_score_gemma":0.008907393,"threshold_uncertainty_score":0.24259436},"labels":[],"label_agreement":null},{"id":"W3210068963","doi":"10.1080/0969594x.2021.1988510","title":"Formative assessment, growth mindset, and achievement: examining their relations in the East and the West","year":2021,"lang":"en","type":"article","venue":"Assessment in Education Principles Policy and Practice","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":50,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Mindset; Formative assessment; Psychology; Reading (process); Mainland China; Academic achievement; Pedagogy; Mathematics education; China; Political science; Computer science","score_opus":0.07796939436320567,"score_gpt":0.42193192942447144,"score_spread":0.3439625350612658,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3210068963","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99925095,0.00006910033,0.00010484408,0.00002123917,0.0000014200401,0.0000017002203,0.000026914457,0.0000011277203,0.0005227565],"genre_scores_gemma":[0.9996458,0.000059283215,0.00014038017,0.000006732942,0.0000017708203,0.0000022403012,0.00003035089,0.0000012846076,0.00011203233],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9994117,0.00019692093,0.000083034945,0.00009223673,0.00013966621,0.00007642159],"domain_scores_gemma":[0.9946791,0.0016212311,0.0020709813,0.0003556135,0.00077909423,0.0004939828],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014838835,0.00027666756,0.0004068755,0.0014838107,0.00033836195,0.0012583241,0.000190002,0.00015440269,0.00055812416],"category_scores_gemma":[0.0038120304,0.00015686669,0.00029478958,0.0015439271,0.00059819565,0.00075291615,0.0010268198,0.00042341326,0.00011061561],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006492984,0.000033590262,0.9881188,0.000016439708,0.000050575847,0.000043020988,0.002015837,0.000066746434,0.0006681212,0.00013025814,0.000021244678,0.008770436],"study_design_scores_gemma":[0.0000016179123,0.000045835033,0.99778855,0.0000102192325,0.000021285125,0.00003132317,0.0013606809,0.00026634548,0.0002881409,0.000059493963,0.00012321229,0.0000032241237],"about_ca_topic_score_codex":0.013181362,"about_ca_topic_score_gemma":0.02249004,"teacher_disagreement_score":0.013181362,"about_ca_system_score_codex":0.00039762395,"about_ca_system_score_gemma":0.0004951839,"threshold_uncertainty_score":0.026209295},"labels":[],"label_agreement":null},{"id":"W3210142070","doi":"10.1016/j.jslw.2021.100850","title":"What works may hurt: The negative side of feedback in second language writing","year":2021,"lang":"en","type":"article","venue":"Journal of Second Language Writing","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":56,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Negative feedback; Constructive; Quality (philosophy); Psychology; Corrective feedback; Peer feedback; Feedback loop; Positive feedback; Second language writing; Social psychology; Computer science; Second language; Mathematics education; Linguistics; Computer security","score_opus":0.01804869953246795,"score_gpt":0.33177635910815306,"score_spread":0.3137276595756851,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3210142070","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9181277,0.0013357651,0.00644553,0.03757853,0.0015194111,0.0001461986,0.00010367735,0.00050079636,0.034242336],"genre_scores_gemma":[0.99331576,0.00024977094,0.0022697453,0.001746619,0.00017332622,0.00008706159,0.000023105224,0.000086780834,0.0020478317],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.88229245,0.08060799,0.0035431965,0.0020920993,0.029148804,0.0023154956],"domain_scores_gemma":[0.49462613,0.40375075,0.02876433,0.00807862,0.052593704,0.012186486],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.05552578,0.00066835,0.0009352834,0.0015285136,0.003560707,0.006650273,0.0010178981,0.0031853379,0.0033488648],"category_scores_gemma":[0.3859012,0.00049848575,0.0005685881,0.0008651328,0.0036844453,0.0048056026,0.003792526,0.005047634,0.0010222091],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00323229,0.0025123288,0.18253241,0.0014739136,0.00032460224,0.0014899556,0.29066902,0.0014465101,0.008875457,0.006327162,0.035385475,0.4657309],"study_design_scores_gemma":[0.0010555002,0.010781385,0.3739334,0.005260085,0.00089826225,0.0036871645,0.43837562,0.020880654,0.02367972,0.03604188,0.084436,0.00097024173],"about_ca_topic_score_codex":0.0021308234,"about_ca_topic_score_gemma":0.0037888524,"teacher_disagreement_score":0.05552578,"about_ca_system_score_codex":0.002570483,"about_ca_system_score_gemma":0.0052572773,"threshold_uncertainty_score":0.29365188},"labels":[],"label_agreement":null},{"id":"W3211638126","doi":"10.1097/acm.0000000000004507","title":"Written-Based Progress Testing: A Scoping Review.","year":2022,"lang":"en","type":"article","venue":"PubMed","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Medical Council of Canada; Université de Sherbrooke","funders":"","keywords":"PsycINFO; Facilitator; CINAHL; MEDLINE; Formative assessment; Test (biology); Medical education; Psychology; Medicine; Nursing; Social psychology; Mathematics education; Psychological intervention","score_opus":0.09513950111257642,"score_gpt":0.3651457225609909,"score_spread":0.2700062214484145,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3211638126","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002238974,0.9731794,0.0049254913,0.0033108846,0.001444441,0.009915523,0.0010958827,0.00009621156,0.003793268],"genre_scores_gemma":[0.016665995,0.9455073,0.017546505,0.0014543238,0.00039158235,0.015654985,0.0014153388,0.000048660877,0.0013153089],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.9523975,0.01998969,0.015035296,0.0017453043,0.010196979,0.0006351693],"domain_scores_gemma":[0.8430703,0.103691034,0.019293902,0.0032983175,0.029707024,0.00093930843],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.06796251,0.002662619,0.0054239174,0.033857003,0.0020088914,0.0067119743,0.0036892758,0.0048558526,0.0048107775],"category_scores_gemma":[0.18600783,0.0018454696,0.0046701003,0.030159935,0.0022698499,0.007839798,0.0037173422,0.0028323976,0.0015015962],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016981344,0.00012578923,0.0010870574,0.58716536,0.0011842194,0.00034019595,0.0028755162,0.00046407108,0.0005700887,0.0026619348,0.01787377,0.38548228],"study_design_scores_gemma":[0.000057189944,0.00011816379,0.0015539369,0.94851726,0.001749877,0.00031941093,0.0014532427,0.0001992996,0.00032498763,0.0007948163,0.044871047,0.00004066051],"about_ca_topic_score_codex":0.006869277,"about_ca_topic_score_gemma":0.013002859,"teacher_disagreement_score":0.06796251,"about_ca_system_score_codex":0.006504054,"about_ca_system_score_gemma":0.03818283,"threshold_uncertainty_score":0.3594244},"labels":[],"label_agreement":null},{"id":"W3212616294","doi":"","title":"Ontario Elementary School Teachers' Approaches to Mathematics Assessment for Diverse Students","year":2021,"lang":"en","type":"dissertation","venue":"QSpace (Queen's University Library)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Mathematics education; Pedagogy; Mathematics; Psychology","score_opus":0.03906997615594648,"score_gpt":0.28939211954308985,"score_spread":0.25032214338714337,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3212616294","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9525129,0.00055718207,0.0021435586,0.0027215485,0.000026650707,0.00021191024,0.00016063011,0.00004706757,0.041618474],"genre_scores_gemma":[0.98649895,0.00052596437,0.0017350329,0.0001689661,0.000004108777,0.00009512369,0.000066353736,0.000015716461,0.010889726],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9956702,0.0011155991,0.00026762811,0.00060697267,0.0016295929,0.0007100423],"domain_scores_gemma":[0.9938333,0.0014476903,0.0006315877,0.00034087934,0.0020583265,0.0016881963],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0027269789,0.00034937664,0.00037459898,0.0014958327,0.012462669,0.0037271564,0.0011264322,0.00060935866,0.0026407936],"category_scores_gemma":[0.007821112,0.00041150313,0.00034426406,0.0019593383,0.004402286,0.0012852565,0.004339884,0.00089817675,0.00039830894],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006199041,0.00005860806,0.079446,0.00015446397,0.000008214232,0.0010132898,0.86125374,0.00027826487,0.0026523797,0.004094235,0.0026185063,0.04836027],"study_design_scores_gemma":[0.000016481601,0.00009416192,0.17231391,0.00023438701,0.000030287258,0.00027272367,0.7471604,0.00040640897,0.000984776,0.0016555793,0.07676071,0.00007021773],"about_ca_topic_score_codex":0.81665623,"about_ca_topic_score_gemma":0.9539113,"teacher_disagreement_score":0.9646942,"about_ca_system_score_codex":0.035305794,"about_ca_system_score_gemma":0.049271718,"threshold_uncertainty_score":0.368847},"labels":[],"label_agreement":null},{"id":"W3213817778","doi":"","title":"Conrad, Dianne; Openo, Jason. Assessment strategies for online learning. Engagement and authenticity. Edmonton: Athabasca University Press, 2018, ISBN:978-1-77199-233-6","year":2021,"lang":"es","type":"article","venue":"Revista Latinoamericana de Difusión Científica","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Media studies; Sociology","score_opus":0.03236000520398399,"score_gpt":0.32440344464953874,"score_spread":0.2920434394455548,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3213817778","genre_codex":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.013482665,0.6818561,0.04941161,0.053971767,0.00843362,0.0005132002,0.0016215142,0.0011590335,0.1895505],"genre_scores_gemma":[0.15344432,0.5016986,0.05910098,0.0051349923,0.0019957293,0.0008056665,0.0011604435,0.0011462608,0.27551296],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9983858,0.00042078042,0.0001454142,0.00014622552,0.00080516434,0.00009665782],"domain_scores_gemma":[0.98734957,0.006627935,0.00049366837,0.00030881,0.004589417,0.00063060236],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0034941218,0.00078042626,0.00054614816,0.0051341453,0.0017788283,0.004395182,0.0014229171,0.001667772,0.020395998],"category_scores_gemma":[0.016423047,0.00043563763,0.00029711367,0.0048727533,0.001390709,0.007112877,0.0016802705,0.0021696638,0.008334237],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007274509,0.00008980267,0.0015052002,0.00092404115,0.000009380445,0.00011559958,0.004180928,0.0001097506,0.0007189117,0.0065066703,0.19079037,0.79497665],"study_design_scores_gemma":[0.000028203223,0.000074234566,0.009928388,0.0025081611,0.000054653203,0.0005013345,0.005253637,0.0003014993,0.0016973332,0.009263318,0.97035426,0.000034908666],"about_ca_topic_score_codex":0.01862692,"about_ca_topic_score_gemma":0.04219747,"teacher_disagreement_score":0.020395998,"about_ca_system_score_codex":0.0012966068,"about_ca_system_score_gemma":0.0036799368,"threshold_uncertainty_score":0.068231404},"labels":[],"label_agreement":null},{"id":"W3214027731","doi":"10.1177/02655322211052680","title":"Investigating and optimizing score dependability of a local ITA speaking test across language groups: A generalizability theory approach","year":2021,"lang":"en","type":"article","venue":"Language Testing","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Generalizability theory; Dependability; Language proficiency; Psychology; Variance (accounting); Test (biology); Construct (python library); Formative assessment; Computer science; Mathematics education; Developmental psychology; Accounting","score_opus":0.050868985531210546,"score_gpt":0.3497865942429446,"score_spread":0.29891760871173406,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3214027731","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6361603,0.00041987657,0.35266072,0.00062853436,0.000056910125,0.0011100963,0.00020248465,0.00043369824,0.0083274385],"genre_scores_gemma":[0.9507976,0.00006967164,0.047814503,0.000080312566,0.000025289792,0.00056433893,0.00015736393,0.0000704249,0.00042043568],"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","domain_scores_codex":[0.94186175,0.042277265,0.0023312175,0.005780945,0.006960205,0.00078858994],"domain_scores_gemma":[0.73534185,0.21294822,0.010937085,0.025207106,0.014718775,0.0008469287],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.08313917,0.0015327206,0.0014003136,0.003990026,0.0008686305,0.0025761104,0.0017621223,0.0010370555,0.0016551898],"category_scores_gemma":[0.24767268,0.0006271307,0.0026763245,0.0029654484,0.0028935762,0.0032575608,0.0035016646,0.0017916902,0.00029129005],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00093442044,0.0006063585,0.6727764,0.00038435456,0.002189075,0.00019474018,0.008351212,0.0154744,0.006535386,0.009704689,0.0005476653,0.28230137],"study_design_scores_gemma":[0.00023132478,0.005896743,0.8465566,0.00021669985,0.001621534,0.00038176344,0.004894767,0.097275615,0.01561534,0.02442326,0.0027327163,0.00015356738],"about_ca_topic_score_codex":0.0043842136,"about_ca_topic_score_gemma":0.0036465917,"teacher_disagreement_score":0.08313917,"about_ca_system_score_codex":0.0018039201,"about_ca_system_score_gemma":0.0019270694,"threshold_uncertainty_score":0.43968725},"labels":[],"label_agreement":null},{"id":"W3215227414","doi":"10.5539/elt.v14n12p183","title":"Teachers’ Practice and Perceptions of Self-Assessment and Peer Assessment of Presentation Skills","year":2021,"lang":"en","type":"article","venue":"English Language Teaching","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Rubric; Peer assessment; Psychology; Assessment for learning; Medical education; Presentation (obstetrics); Pedagogy; Self-assessment; Mathematics education; Medicine; Formative assessment","score_opus":0.009395595803848704,"score_gpt":0.38553344987276483,"score_spread":0.37613785406891614,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3215227414","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9954091,0.0002902475,0.000729518,0.00014881392,0.000018009843,0.000046383786,0.000012860526,0.000017404456,0.00332759],"genre_scores_gemma":[0.99784315,0.00029363553,0.0004924035,0.000039021645,0.000008136049,0.000030093031,0.000015417332,0.0000068786444,0.0012713013],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.9912881,0.0030062082,0.00082614855,0.0005787756,0.003853705,0.0004471544],"domain_scores_gemma":[0.95673954,0.020647082,0.008727997,0.0015764319,0.008620584,0.0036884148],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0092043895,0.00024525277,0.0005117379,0.001530528,0.0009423057,0.0026621912,0.0006193597,0.00066520035,0.0020347598],"category_scores_gemma":[0.04304711,0.00042324516,0.0004079358,0.00059818395,0.0016609296,0.0015557967,0.0018608732,0.00094526453,0.0005037764],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023041737,0.0007010906,0.46990427,0.00064924406,0.00009748376,0.0009996735,0.44810343,0.00033523532,0.008114383,0.000658086,0.00093734404,0.069269426],"study_design_scores_gemma":[0.00004901572,0.0020272508,0.5501713,0.00046470994,0.00008464821,0.0021297482,0.42434004,0.00143163,0.0028057566,0.00081858825,0.015513294,0.00016409514],"about_ca_topic_score_codex":0.0032044854,"about_ca_topic_score_gemma":0.0030725377,"teacher_disagreement_score":0.0092043895,"about_ca_system_score_codex":0.0009273487,"about_ca_system_score_gemma":0.0013604156,"threshold_uncertainty_score":0.04867804},"labels":[],"label_agreement":null},{"id":"W3216763624","doi":"10.37213/cjal.2021.31242","title":"Is Less Really More? The Case for Comprehensive Written Corrective Feedback","year":2021,"lang":"en","type":"article","venue":"Canadian Journal of Applied Linguistics","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Corrective feedback; Exploit; Focus (optics); Second-language acquisition; Psychology; Cognitive psychology; Computer science; Empirical research; Mathematics education; Linguistics; Epistemology","score_opus":0.05410565985707475,"score_gpt":0.3385950120407823,"score_spread":0.2844893521837075,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3216763624","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0729791,0.015863562,0.032810315,0.7763009,0.0023428944,0.00015578525,0.00014919088,0.00040895148,0.09898926],"genre_scores_gemma":[0.8867107,0.0046419012,0.025194215,0.07510946,0.0013972303,0.00027309768,0.000051330713,0.00031769378,0.006304355],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9234298,0.04471006,0.0029161966,0.0074149617,0.018952912,0.0025760538],"domain_scores_gemma":[0.7932518,0.15199006,0.011108461,0.013044615,0.022829749,0.007775164],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.052286725,0.00060288457,0.0011922738,0.0019790216,0.0034763373,0.010858631,0.0023204451,0.0071362895,0.007453253],"category_scores_gemma":[0.17803252,0.00055091793,0.000638893,0.0012288399,0.021386355,0.02069915,0.006711927,0.008702923,0.0010577061],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00080174586,0.00034386804,0.014945157,0.004033433,0.00019956566,0.0015245357,0.0903618,0.0007158082,0.0058854837,0.4742183,0.04697525,0.359995],"study_design_scores_gemma":[0.00023439458,0.0005760476,0.01763473,0.0059934156,0.00015463665,0.0028689979,0.059763342,0.0020995722,0.0024892185,0.6183895,0.28953782,0.00025831672],"about_ca_topic_score_codex":0.0033017115,"about_ca_topic_score_gemma":0.0032373522,"teacher_disagreement_score":0.052286725,"about_ca_system_score_codex":0.0044290153,"about_ca_system_score_gemma":0.0073683537,"threshold_uncertainty_score":0.27652198},"labels":[],"label_agreement":null},{"id":"W326428004","doi":"10.55016/ojs/jet.v26i1.52246","title":"The Decima Research English Curriculum","year":2018,"lang":"en","type":"article","venue":"Journal of educational thought.","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Curriculum; Psychology; Pedagogy; Mathematics education; Sociology","score_opus":0.06980221479026665,"score_gpt":0.4835671468002403,"score_spread":0.41376493200997366,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W326428004","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4963974,0.00215377,0.0022179312,0.016118072,0.0007882278,0.00032771114,0.0004356039,0.00020371308,0.48135754],"genre_scores_gemma":[0.78331256,0.0015020019,0.0030274675,0.002578698,0.00006215166,0.00008742507,0.00030339605,0.000062857776,0.2090634],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99844813,0.00015864118,0.000049978677,0.00016637887,0.00069653563,0.00048031792],"domain_scores_gemma":[0.9947371,0.00028660378,0.00021163734,0.0001879857,0.0025709784,0.0020056341],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020196664,0.0001848279,0.00018296506,0.00070197537,0.0034608438,0.0039746966,0.0007934202,0.00053333206,0.0092653865],"category_scores_gemma":[0.0049600275,0.00013601234,0.00012972555,0.00068674644,0.0018326534,0.0012512835,0.0022044175,0.0013754946,0.0010558919],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003444794,0.0005074764,0.031687118,0.0007096656,0.000010443,0.000819446,0.083556,0.0006600875,0.017338866,0.137071,0.088998854,0.6382964],"study_design_scores_gemma":[0.000022364604,0.00024816903,0.073947966,0.00042403204,0.000011208487,0.00018537947,0.037115306,0.00031828543,0.0034096227,0.0052204854,0.8790662,0.000031003485],"about_ca_topic_score_codex":0.506149,"about_ca_topic_score_gemma":0.7968532,"teacher_disagreement_score":0.506149,"about_ca_system_score_codex":0.023333726,"about_ca_system_score_gemma":0.076505445,"threshold_uncertainty_score":0.99351877},"labels":[],"label_agreement":null},{"id":"W339483823","doi":"10.12794/metadc271904","title":"The Politics of Grading: a Comparative Study of High School English Teachers' Personal Beliefs, Self-reported Systems, and Actual Practices","year":2013,"lang":"en","type":"dissertation","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Ministère de l’Éducation, Gouvernement de l’Ontario; University of Toronto; Harvard University","keywords":"Grading (engineering); Mathematics education; Psychology; Politics; Medical education; Pedagogy; Political science; Engineering; Medicine","score_opus":0.05246443031952186,"score_gpt":0.38897096461860875,"score_spread":0.3365065342990869,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W339483823","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.999424,0.000044715027,0.00004232759,0.0000313409,0.0000015253147,0.0000031322893,0.0000057542597,0.0000010111632,0.00044618122],"genre_scores_gemma":[0.9995863,0.00007252363,0.000053934782,0.000021983073,0.0000023450418,0.000005801898,0.000009740855,0.0000018588885,0.00024553903],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9958191,0.0024191593,0.00030168387,0.0002678101,0.0007171147,0.00047510173],"domain_scores_gemma":[0.9827989,0.009636054,0.0033562386,0.0006116007,0.0023592364,0.0012380385],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0063692355,0.00012674647,0.00039123476,0.002145151,0.0025250353,0.0025773973,0.0005527615,0.0004858512,0.0013596183],"category_scores_gemma":[0.020169113,0.00033883064,0.0002038248,0.0018206639,0.0021561987,0.0017866895,0.0012777926,0.00077610137,0.00017122719],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009177186,0.00033016686,0.3322759,0.000107133084,0.00002694511,0.00056257914,0.6492302,0.000042014133,0.0013024585,0.000362006,0.0001569345,0.01551186],"study_design_scores_gemma":[0.000006152207,0.00024094044,0.37431556,0.00006619724,0.000014588107,0.000250015,0.62270236,0.00010460822,0.0004374064,0.00008333876,0.0017596817,0.00001909712],"about_ca_topic_score_codex":0.008092145,"about_ca_topic_score_gemma":0.02334142,"teacher_disagreement_score":0.008092145,"about_ca_system_score_codex":0.0017468418,"about_ca_system_score_gemma":0.0014519306,"threshold_uncertainty_score":0.033684134},"labels":[],"label_agreement":null},{"id":"W36778657","doi":"10.1557/s43578-022-00764-2","title":"On-line formative assessment item banking and learning support","year":2001,"lang":"en","type":"article","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Formative assessment; Process (computing); Computer science; Curriculum; The Internet; Variation (astronomy); Line (geometry); Psychology; Medical education; Knowledge management; Mathematics education; Pedagogy; World Wide Web; Medicine","score_opus":0.04230765488828795,"score_gpt":0.3899345329517583,"score_spread":0.3476268780634703,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W36778657","genre_codex":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.15134495,0.0008285094,0.34550953,0.0045062574,0.0023045866,0.046187844,0.039512273,0.04790875,0.3618974],"genre_scores_gemma":[0.18231297,0.0012769869,0.53927696,0.0016676729,0.00092688395,0.028209966,0.028452858,0.0034428213,0.21443291],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9775214,0.010594468,0.0030041381,0.0014086921,0.0068128183,0.0006584744],"domain_scores_gemma":[0.88091654,0.044692393,0.006210973,0.018242493,0.04590618,0.00403132],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.021395419,0.0015188949,0.0015073911,0.0049262885,0.0008011058,0.0032784985,0.0035281142,0.0010270689,0.11206512],"category_scores_gemma":[0.100360096,0.00061925704,0.0011297372,0.0029778725,0.00041746878,0.0030853474,0.003155035,0.0016379824,0.06632437],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000817699,0.0022840751,0.00928621,0.0006025894,0.000050981154,0.00015590922,0.0013196022,0.00090360915,0.0028621056,0.0017728561,0.155703,0.82424134],"study_design_scores_gemma":[0.0013677097,0.0053923433,0.15707558,0.0016852326,0.0002101465,0.0016068323,0.0040271557,0.0336763,0.03176118,0.021112742,0.7414622,0.000622507],"about_ca_topic_score_codex":0.0018390679,"about_ca_topic_score_gemma":0.0027559092,"teacher_disagreement_score":0.11206512,"about_ca_system_score_codex":0.0010433795,"about_ca_system_score_gemma":0.0028193374,"threshold_uncertainty_score":0.37489516},"labels":[],"label_agreement":null},{"id":"W37481711","doi":"10.1093/rheumatology/kead362","title":"Self-Assessment in the Middle School Science Classroom","year":2014,"lang":"en","type":"article","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Canadian Institutes of Health Research; National Institute on Aging; National Institutes of Health; Arthritis Society; Mayo Clinic","keywords":"Mathematics education; Diversity (politics); Psychology; Set (abstract data type); Pedagogy; Self-assessment; Science education; Student achievement; Academic achievement; Computer science; Sociology","score_opus":0.032105416556750185,"score_gpt":0.3473892525693282,"score_spread":0.315283836012578,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W37481711","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9989612,0.0000344655,0.000055865512,0.000028126382,0.0000035677506,0.000006032508,0.000025720457,0.000010263413,0.0008748317],"genre_scores_gemma":[0.99901235,0.000034563578,0.00015953211,0.00002505551,0.0000024148615,0.000006069224,0.00006948404,0.0000030458489,0.0006875257],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9988398,0.00021183684,0.00011797142,0.00018237338,0.00049811695,0.00014996203],"domain_scores_gemma":[0.9947049,0.0009016751,0.0013384584,0.00028483052,0.0015496736,0.001220399],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015819293,0.00020238766,0.00031924376,0.0016486634,0.00052603544,0.00095303723,0.00037810547,0.00043057313,0.0019688827],"category_scores_gemma":[0.007062712,0.00018708146,0.00024888487,0.0004438034,0.00043433747,0.00068553217,0.0011027289,0.00055970956,0.00058970234],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000048967024,0.00027165964,0.9855483,0.0000112449,0.000009664227,0.00010633474,0.001192982,0.000025325478,0.0010131757,0.00003865396,0.00031270424,0.011420942],"study_design_scores_gemma":[0.000004690066,0.00019741124,0.99636793,0.000011473192,0.0000067885194,0.0002742695,0.0018246286,0.00017035758,0.0006407846,0.00006372121,0.00043046984,0.000007406745],"about_ca_topic_score_codex":0.004235891,"about_ca_topic_score_gemma":0.010119664,"teacher_disagreement_score":0.004235891,"about_ca_system_score_codex":0.0004152932,"about_ca_system_score_gemma":0.0005533464,"threshold_uncertainty_score":0.008422494},"labels":[],"label_agreement":null},{"id":"W4200080833","doi":"10.35542/osf.io/fmgv8","title":"A Short History of Grading Practices at Dalhousie University (1901-2021)","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Grading (engineering); Grading scale; Value (mathematics); Point (geometry); Psychology; Mathematics education; Statistics; Mathematics; Medicine; Engineering","score_opus":0.08511183768631214,"score_gpt":0.3450227982369392,"score_spread":0.25991096055062707,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200080833","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.037182316,0.07276382,0.022829035,0.04395161,0.022920156,0.0013305122,0.035067037,0.009330898,0.75462455],"genre_scores_gemma":[0.07716472,0.030790571,0.021407211,0.004921606,0.0029081013,0.00050862797,0.019049754,0.0011738501,0.8420756],"study_design_codex":"not_applicable","study_design_gemma":"qualitative","domain_scores_codex":[0.9932225,0.00044000204,0.00060906477,0.0007836676,0.00437614,0.00056864467],"domain_scores_gemma":[0.98299015,0.0005227242,0.0008125653,0.00083026243,0.012578942,0.0022653043],"candidate_categories":["sts"],"consensus_categories":[],"category_scores_codex":[0.0059961076,0.0009528474,0.00048014912,0.010325224,0.0033576905,0.005705591,0.0020514491,0.0012314245,0.067385666],"category_scores_gemma":[0.010341291,0.0005210345,0.00034310826,0.010467451,0.0012107914,0.0033744404,0.0030030478,0.002155699,0.041973624],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000050797426,0.00009129361,0.0033493422,0.0002831605,0.000006482196,0.000058141035,0.00031449067,0.00022454874,0.00078309834,0.0065114563,0.52737826,0.46094897],"study_design_scores_gemma":[0.000002372157,0.000022832432,0.014562487,0.00012545906,0.000001379143,0.00003845468,0.00012225336,0.00009275567,0.00047332468,0.00031809154,0.9842147,0.000025890751],"about_ca_topic_score_codex":0.12774628,"about_ca_topic_score_gemma":0.19414169,"teacher_disagreement_score":0.9966423,"about_ca_system_score_codex":0.017309906,"about_ca_system_score_gemma":0.014735168,"threshold_uncertainty_score":0.25400543},"labels":[],"label_agreement":null},{"id":"W4200186911","doi":"10.21083/ajote.v10i2.6762","title":"Analysis of Item Writing Flaws in a Communications Skills Test in a Ghanaian University","year":2021,"lang":"en","type":"article","venue":"African Journal of Teacher Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Test (biology); Psychology; Multiple choice; Multitude; Quality (philosophy); First language; Mathematics education; Descriptive statistics; Item analysis; Social psychology; Statistics; Linguistics; Psychometrics; Developmental psychology; Mathematics","score_opus":0.025276382341985728,"score_gpt":0.35590290993779317,"score_spread":0.33062652759580746,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200186911","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99921477,0.000054697433,0.00037484913,0.000036553356,0.0000034235682,0.00003474894,0.00004649155,0.000005624504,0.00022887501],"genre_scores_gemma":[0.99859875,0.00004934265,0.0010757894,0.0000141421115,0.00000239362,0.000029298886,0.00009253353,0.0000029225002,0.00013483543],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9957249,0.0013128371,0.0009234307,0.00026390256,0.0014982449,0.00027666066],"domain_scores_gemma":[0.9515698,0.021726016,0.017109096,0.0016243048,0.0068572857,0.0011135129],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006162721,0.00043779134,0.0006264001,0.0037167224,0.0005408721,0.0009000371,0.0005380038,0.00052562816,0.0009343931],"category_scores_gemma":[0.043130472,0.0003042479,0.0005375102,0.003986399,0.000983654,0.00088918314,0.00081590074,0.00077411596,0.0001954977],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012622218,0.00011602024,0.9724486,0.00007335156,0.000024301264,0.0005319879,0.0052857823,0.00019958215,0.0014832304,0.000081619764,0.00013992256,0.019489326],"study_design_scores_gemma":[0.0000070389588,0.00034318643,0.9923614,0.00003957853,0.000017360422,0.00093045627,0.0039209668,0.0007370444,0.0011788016,0.00008491532,0.00036766057,0.000011502806],"about_ca_topic_score_codex":0.0027393561,"about_ca_topic_score_gemma":0.0037045504,"teacher_disagreement_score":0.006162721,"about_ca_system_score_codex":0.0012602811,"about_ca_system_score_gemma":0.0010606884,"threshold_uncertainty_score":0.03259194},"labels":[],"label_agreement":null},{"id":"W4200222103","doi":"10.14221/ajte.2021v46n10.1","title":"The Role of Individual Preferences in the Efficacy of Written Corrective Feedback in an English for Academic Purposes Writing Course","year":2021,"lang":"en","type":"article","venue":"˜The œAustralian journal of teacher education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Capilano University","funders":"","keywords":"Corrective feedback; Psychology; Mathematics education; Qualitative research; Test (biology); Qualitative property; Control (management); English as a foreign language; Treatment and control groups; Medical education; Computer science; Medicine","score_opus":0.05189781943817671,"score_gpt":0.3935110894213582,"score_spread":0.3416132699831815,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200222103","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9993999,0.00003311145,0.00012148718,0.000014363144,0.0000024999304,0.0000061730057,0.0000055700107,0.0000028988363,0.00041400286],"genre_scores_gemma":[0.99966383,0.000012167297,0.00017590632,0.000007908567,0.0000013142534,0.000003004752,0.000005579314,0.0000015454798,0.00012871485],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9974644,0.0013570422,0.00022605986,0.00029816007,0.00052717066,0.00012726932],"domain_scores_gemma":[0.9742702,0.018640757,0.0035473388,0.000856028,0.0013876021,0.0012980899],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0030270102,0.00014466458,0.00022858512,0.00037662606,0.00023006275,0.00071905594,0.0002197643,0.00027486685,0.00086780323],"category_scores_gemma":[0.02625974,0.00010914288,0.00010983184,0.00019747214,0.00038393357,0.00031875353,0.00030496228,0.0003016893,0.00015532515],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0030858153,0.0020575712,0.79766256,0.00020038777,0.00018958334,0.0002582918,0.011845367,0.0006148508,0.025794577,0.00014104313,0.000201136,0.1579488],"study_design_scores_gemma":[0.00003349929,0.0015986428,0.98941666,0.000016617927,0.000043349613,0.0002381504,0.0032752133,0.0007739059,0.003973362,0.0001384395,0.00046831154,0.000023824956],"about_ca_topic_score_codex":0.0006392621,"about_ca_topic_score_gemma":0.0008933771,"teacher_disagreement_score":0.0030270102,"about_ca_system_score_codex":0.00026988747,"about_ca_system_score_gemma":0.00024944055,"threshold_uncertainty_score":0.016008556},"labels":[],"label_agreement":null},{"id":"W4205154527","doi":"10.1097/acm.0000000000004507","title":"Written-Based Progress Testing: A Scoping Review","year":2021,"lang":"en","type":"article","venue":"Academic Medicine","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":24,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Medical Council of Canada; Université de Sherbrooke","funders":"","keywords":"Facilitator; Formative assessment; Test (biology); Inclusion (mineral); Consistency (knowledge bases); Thematic analysis; MEDLINE; Data extraction","score_opus":0.14112124408067425,"score_gpt":0.46820543343452536,"score_spread":0.3270841893538511,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4205154527","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0020366132,0.9732871,0.0064428602,0.003840036,0.001514138,0.008092864,0.0006037642,0.000096056814,0.0040865163],"genre_scores_gemma":[0.012485475,0.9638129,0.011670985,0.0012397969,0.00039694936,0.008945682,0.00072834425,0.00004289408,0.0006770055],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.9307486,0.030299097,0.021853747,0.0027247889,0.013294215,0.0010796242],"domain_scores_gemma":[0.74740595,0.1824967,0.020036248,0.0047150613,0.04404162,0.0013044489],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.08415625,0.0031384826,0.007737767,0.040060945,0.002638509,0.008077148,0.0044075116,0.005337785,0.004545732],"category_scores_gemma":[0.24699883,0.0021939562,0.005859855,0.03246468,0.0035012471,0.009445819,0.0046714884,0.0037144064,0.0013032418],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013575926,0.000120411685,0.00092794694,0.6011644,0.001237406,0.00037212847,0.0028656938,0.0006419161,0.00047530505,0.003571044,0.012164096,0.37632394],"study_design_scores_gemma":[0.000032374857,0.000094699346,0.0008018113,0.95974696,0.0016133849,0.0002179316,0.0011589305,0.00020509852,0.0002530929,0.0010180848,0.034821298,0.00003626251],"about_ca_topic_score_codex":0.008089066,"about_ca_topic_score_gemma":0.012066244,"teacher_disagreement_score":0.9158437,"about_ca_system_score_codex":0.008137738,"about_ca_system_score_gemma":0.04780986,"threshold_uncertainty_score":0.4450661},"labels":[],"label_agreement":null},{"id":"W4205625260","doi":"10.20343/teachlearninqu.10.3","title":"Instructors’ Perspectives of Challenges and Barriers to Providing Effective Feedback","year":2022,"lang":"en","type":"article","venue":"Teaching & Learning Inquiry The ISSOTL Journal","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":31,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Capilano University; University of Calgary","funders":"Social Sciences and Humanities Research Council of Canada; Killam Trusts","keywords":"Context (archaeology); Thematic analysis; Workload; Class (philosophy); Focus group; Medical education; Coronavirus disease 2019 (COVID-19); Process (computing); Psychology; Computer science; Qualitative research; Medicine; Sociology","score_opus":0.031140960563814667,"score_gpt":0.34022756603078774,"score_spread":0.3090866054669731,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4205625260","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9589262,0.0009084932,0.008896962,0.017676124,0.0005432214,0.00014373579,0.000053808417,0.000180223,0.012671074],"genre_scores_gemma":[0.9935976,0.00044247633,0.0025635017,0.0011279499,0.00007049116,0.00007097021,0.00001959439,0.000033293913,0.002074083],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9704147,0.018578373,0.0016309927,0.0009803438,0.005723759,0.0026719125],"domain_scores_gemma":[0.8946691,0.057611886,0.007636977,0.0020198715,0.02558034,0.012481792],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.028000414,0.0002816791,0.00041927202,0.0009120587,0.004659719,0.0059322277,0.0012928083,0.0019950278,0.0021523426],"category_scores_gemma":[0.09915864,0.0003846665,0.00042775643,0.00065324845,0.0018429926,0.0025751488,0.0033260852,0.0027800114,0.0005168035],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020448217,0.00057462865,0.08309689,0.00065844436,0.000055111257,0.0025431889,0.7427428,0.00065782265,0.0066316677,0.0025779065,0.007867597,0.15238939],"study_design_scores_gemma":[0.000044686924,0.0011670797,0.032845862,0.0009827524,0.00005131518,0.0015416446,0.85455734,0.0022506479,0.0036998233,0.0017553875,0.10094097,0.0001625644],"about_ca_topic_score_codex":0.0041188467,"about_ca_topic_score_gemma":0.005680289,"teacher_disagreement_score":0.028000414,"about_ca_system_score_codex":0.00274394,"about_ca_system_score_gemma":0.00812605,"threshold_uncertainty_score":0.14808214},"labels":[],"label_agreement":null},{"id":"W4206800665","doi":"10.5206/cieeci.v50i1.14133","title":"Grading in a Dilemmatic Space : An Exploratory Cross-cultural Analysis of Mathematics and Language Secondary Teachers","year":2021,"lang":"en","type":"article","venue":"Comparative and International Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Queen's University","funders":"","keywords":"Grading (engineering); Negotiation; Mathematics education; Exploratory research; Psychology; Pedagogy; Sociology; Social science; Engineering","score_opus":0.09320390665256642,"score_gpt":0.4722633425067662,"score_spread":0.37905943585419977,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4206800665","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9982955,0.00008046581,0.00047409753,0.00013210616,0.0000051277466,0.000027390695,0.0000139793165,0.0000033130689,0.0009681436],"genre_scores_gemma":[0.9984895,0.00011752912,0.00059658807,0.000046288867,0.00000411291,0.000029581113,0.000033660745,0.000008059094,0.0006745764],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9915677,0.0052772886,0.00054039323,0.000531443,0.0012514784,0.0008317746],"domain_scores_gemma":[0.98197734,0.010131547,0.0025411749,0.00061110023,0.0034428295,0.0012960373],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009979956,0.00041438465,0.00053429016,0.0035783877,0.006235926,0.0053304858,0.0011752303,0.0009111306,0.0008675502],"category_scores_gemma":[0.027047424,0.00046073654,0.00029973892,0.0026556917,0.0061744465,0.0026501615,0.0039902837,0.0018748804,0.00014604545],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021855149,0.000061449675,0.017464716,0.000033750508,0.0000039836423,0.0004110801,0.97615844,0.000030348947,0.00059682573,0.00043821492,0.00012111052,0.0046581854],"study_design_scores_gemma":[0.0000019257038,0.000032758933,0.020745343,0.00003178986,0.000002701409,0.00027233653,0.9758706,0.00013607278,0.00032100498,0.0002416731,0.0023295244,0.000014366414],"about_ca_topic_score_codex":0.02400817,"about_ca_topic_score_gemma":0.0523591,"teacher_disagreement_score":0.02400817,"about_ca_system_score_codex":0.004504134,"about_ca_system_score_gemma":0.004158688,"threshold_uncertainty_score":0.052779615},"labels":[],"label_agreement":null},{"id":"W4207047314","doi":"10.1093/oxfordhb/9780199841332.013.28","title":"Classroom Assessment as a Source of Motivational Messages","year":2021,"lang":"en","type":"book-chapter","venue":"Oxford University Press eBooks","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Summative assessment; Extant taxon; Psychology; Task (project management); Theme (computing); Field (mathematics); Event (particle physics); Formative assessment; Mathematics education; Computer science; Engineering","score_opus":0.030881876982471478,"score_gpt":0.28154660866295145,"score_spread":0.25066473168048,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4207047314","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21543884,0.14753476,0.0649507,0.03140671,0.0060721315,0.0011399083,0.00046890683,0.00075453066,0.5322335],"genre_scores_gemma":[0.85609984,0.044775445,0.029225053,0.0040469705,0.0013865932,0.0010834242,0.00036208477,0.00023044631,0.0627901],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99633706,0.0022400953,0.00015188847,0.00016818997,0.0009974763,0.000105307634],"domain_scores_gemma":[0.9767876,0.020412717,0.0008872077,0.0003869903,0.0012764757,0.0002491264],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0042965556,0.00029144675,0.00039774965,0.0021372847,0.0006539807,0.004500789,0.00080290757,0.00090137153,0.0060204477],"category_scores_gemma":[0.015168662,0.00017761588,0.00038476277,0.0014247409,0.0011754737,0.0026199017,0.0019441553,0.0019610734,0.0009635331],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009773696,0.00028077743,0.0032126564,0.004526314,0.00004315374,0.000253959,0.025039256,0.0004469866,0.0019203324,0.05840851,0.02223276,0.8835376],"study_design_scores_gemma":[0.00007385209,0.0006455546,0.031366028,0.03787886,0.00017037173,0.00079066004,0.025538305,0.002261617,0.008549689,0.059070434,0.83353734,0.00011721354],"about_ca_topic_score_codex":0.00059482426,"about_ca_topic_score_gemma":0.001117659,"teacher_disagreement_score":0.0060204477,"about_ca_system_score_codex":0.0011205737,"about_ca_system_score_gemma":0.0017711502,"threshold_uncertainty_score":0.022722661},"labels":[],"label_agreement":null},{"id":"W4210351234","doi":"10.1364/etop.2021.f1b.1","title":"Fostering flow and feedback in the classroom: increasing the successful implementation of active learning instruction","year":2021,"lang":"en","type":"article","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; John Abbott College; Vanier College; Dawson College","funders":"","keywords":"Orchestration; Facilitation; Computer science; Active learning (machine learning); Mathematics education; Flow (mathematics); Multimedia; Knowledge management; Psychology; Artificial intelligence","score_opus":0.034210946651620396,"score_gpt":0.36427669572487414,"score_spread":0.33006574907325376,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210351234","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92419595,0.00016595038,0.0634163,0.0011029158,0.00004723586,0.00096602633,0.000026104011,0.0008468972,0.0092326375],"genre_scores_gemma":[0.94036114,0.00009772101,0.05812658,0.00005684951,0.000015170707,0.00025395726,0.000018135119,0.00003776628,0.0010327963],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9887184,0.0076620723,0.00033991988,0.000685277,0.0017154218,0.00087897625],"domain_scores_gemma":[0.97579646,0.017475221,0.001714577,0.001614647,0.0015439899,0.0018550969],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009419342,0.0007984263,0.00036628495,0.0012187342,0.0015419811,0.0028704621,0.001742919,0.0025403232,0.0024154314],"category_scores_gemma":[0.032794073,0.00033748697,0.0004045671,0.00035735386,0.0011251089,0.00275969,0.0030060587,0.0011256273,0.00056961057],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00063230156,0.013552358,0.04143599,0.0013631578,0.000062872794,0.001908101,0.04018788,0.0049088164,0.06041372,0.0053790365,0.0018919453,0.8282638],"study_design_scores_gemma":[0.0016408964,0.051853728,0.2763665,0.0033149535,0.00058779994,0.012277997,0.07820532,0.093585655,0.3310965,0.036937498,0.11341094,0.00072232884],"about_ca_topic_score_codex":0.0009570554,"about_ca_topic_score_gemma":0.0012667635,"teacher_disagreement_score":0.009419342,"about_ca_system_score_codex":0.0007300757,"about_ca_system_score_gemma":0.00226567,"threshold_uncertainty_score":0.04981482},"labels":[],"label_agreement":null},{"id":"W4210444891","doi":"10.18357/otessac.2021.1.1.44","title":"Comparison of English Teacher Feedback and Automated Writing Feedback on the Quality of English Language Learners’ Essay Revision","year":2021,"lang":"en","type":"article","venue":"The Open/Technology in Education Society and Scholarship Association Conference","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Ell; Quality (philosophy); Class (philosophy); Mathematics education; Psychology; English as a foreign language; English language; Strengths and weaknesses; Peer feedback; Computer science; Teaching method; Artificial intelligence; Social psychology","score_opus":0.07025106336337318,"score_gpt":0.4276535230342052,"score_spread":0.357402459670832,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210444891","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99851173,0.000107290376,0.0005670208,0.000032045427,0.000012941894,0.00003498326,0.000018936036,0.000024776487,0.0006900915],"genre_scores_gemma":[0.9986523,0.0000664919,0.0008450898,0.000021050117,0.000015414891,0.000036636717,0.000030239464,0.000010213768,0.0003226087],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9887937,0.0061934674,0.0008669985,0.00060678367,0.003230045,0.00030901405],"domain_scores_gemma":[0.8700168,0.09190422,0.01556699,0.004378181,0.014277264,0.0038566003],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0076489244,0.00039099896,0.00064702914,0.0007783055,0.00023944314,0.0009108871,0.00033199126,0.00043463547,0.0010552342],"category_scores_gemma":[0.083117,0.00017597144,0.00039790437,0.0003951847,0.0003694401,0.0006822704,0.0007014367,0.00044399654,0.00017275661],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.010437127,0.0037557583,0.4102082,0.0011307129,0.00056228484,0.0003424823,0.012884538,0.0015692766,0.033476017,0.000110097426,0.00074837904,0.52477515],"study_design_scores_gemma":[0.00045064834,0.013001095,0.9617753,0.00021011948,0.00036260858,0.00032053425,0.004072998,0.0050047333,0.0125438655,0.00016450306,0.001999469,0.000094081355],"about_ca_topic_score_codex":0.0009196032,"about_ca_topic_score_gemma":0.0014151987,"teacher_disagreement_score":0.0076489244,"about_ca_system_score_codex":0.00038814233,"about_ca_system_score_gemma":0.0005741382,"threshold_uncertainty_score":0.040451884},"labels":[],"label_agreement":null},{"id":"W4210921245","doi":"10.24124/2018/59229","title":"Analysis of portfolio-based language assessment (PBLA) guidelines for new immigrant language instruction in Canada: An action plan for teachers and administrators","year":2018,"lang":"en","type":"dissertation","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Division of Graduate Education","keywords":"Summative assessment; Formative assessment; Portfolio; Context (archaeology); Medical education; Computer science; Mathematics education; Medicine; Psychology","score_opus":0.0627993727201416,"score_gpt":0.44013063660281404,"score_spread":0.37733126388267246,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4210921245","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.70465195,0.011842593,0.104608774,0.06696223,0.00079318095,0.026598457,0.0040795286,0.0023037854,0.078159474],"genre_scores_gemma":[0.6211498,0.0063699484,0.34383094,0.0020420724,0.00004474404,0.0049908683,0.00250645,0.00017711672,0.01888801],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.97728306,0.0074422676,0.0017269895,0.00083712337,0.010831632,0.0018789804],"domain_scores_gemma":[0.94149494,0.005777911,0.0027499688,0.0012659903,0.04518004,0.0035311545],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.036355477,0.0005977537,0.0007712705,0.005536695,0.010327231,0.008857358,0.0032895054,0.0011779935,0.0011692262],"category_scores_gemma":[0.048718896,0.00050253764,0.00043810968,0.006134102,0.0020388782,0.0030323681,0.0037316016,0.0023483974,0.00033478026],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012001969,0.0010494059,0.04169445,0.0015921717,0.00003788466,0.00080226274,0.06861899,0.0042116977,0.0042635025,0.014420877,0.03764107,0.8255477],"study_design_scores_gemma":[0.00016232418,0.0011066229,0.19095337,0.0059972443,0.00017073954,0.00071626937,0.37375668,0.021083293,0.01909357,0.01217204,0.37421724,0.0005705426],"about_ca_topic_score_codex":0.82404554,"about_ca_topic_score_gemma":0.9079375,"teacher_disagreement_score":0.9121438,"about_ca_system_score_codex":0.08785618,"about_ca_system_score_gemma":0.2983917,"threshold_uncertainty_score":0.6374442},"labels":[],"label_agreement":null},{"id":"W4212780504","doi":"10.1080/13611267.2022.2030186","title":"Towards a better understanding of an academic success center in an EMI context","year":2022,"lang":"en","type":"article","venue":"Mentoring & Tutoring Partnership in Learning","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Context (archaeology); Mathematics education; Reading (process); Computer science; Point (geometry); Academic year; Psychology; Pedagogy; Mathematics","score_opus":0.13657375738084648,"score_gpt":0.41073488157990506,"score_spread":0.2741611241990586,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4212780504","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97921526,0.0011965103,0.007564223,0.0015498708,0.000026128728,0.000078913596,0.000033624845,0.000040421448,0.0102950465],"genre_scores_gemma":[0.99571437,0.0003049807,0.0034005796,0.00005933757,0.000005872347,0.00002662788,0.000010846493,0.0000056621084,0.000471882],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9958402,0.0027327163,0.00015516701,0.00041531143,0.00048327813,0.00037339708],"domain_scores_gemma":[0.99325305,0.0028642344,0.001414666,0.00026678777,0.0012063178,0.000994901],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0077297357,0.0005163178,0.00052307645,0.0025606274,0.0032220893,0.007992,0.00112106,0.0009900272,0.0015333388],"category_scores_gemma":[0.00849154,0.00024661087,0.00021053888,0.0015016304,0.0043354975,0.006788482,0.0046646246,0.0014709843,0.00013763888],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022725598,0.000677676,0.19167565,0.00077024254,0.00003778854,0.0012394895,0.65355057,0.0007025679,0.006581501,0.021879407,0.000651838,0.12200601],"study_design_scores_gemma":[0.000010270767,0.00053980976,0.22053269,0.00047863528,0.00003477307,0.00057392457,0.74835724,0.002136382,0.002431478,0.0047562737,0.020093923,0.000054661967],"about_ca_topic_score_codex":0.004785769,"about_ca_topic_score_gemma":0.007219563,"teacher_disagreement_score":0.007992,"about_ca_system_score_codex":0.0032136296,"about_ca_system_score_gemma":0.0029671774,"threshold_uncertainty_score":0.04087925},"labels":[],"label_agreement":null},{"id":"W4213156228","doi":"10.5430/ijhe.v11n3p158","title":"Pedagogical Strategies Used to Enact Formative Assessment in Science Classrooms: Physical Sciences Teachers' Perspectives","year":2022,"lang":"en","type":"article","venue":"International Journal of Higher Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Formative assessment; Science education; Pedagogy; Mathematics education; Qualitative research; Professional development; Sociology; Psychology; Social science","score_opus":0.0775854320361169,"score_gpt":0.5047785421790595,"score_spread":0.4271931101429426,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4213156228","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.90900254,0.008261999,0.039122347,0.010714507,0.00015459143,0.00030626095,0.000039692895,0.00008989864,0.032308113],"genre_scores_gemma":[0.9786758,0.004947463,0.01241657,0.00059344876,0.000024594012,0.00014937602,0.000019937914,0.000027119413,0.0031456836],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99054104,0.0063184747,0.0005873461,0.00051290286,0.0013353658,0.00070487213],"domain_scores_gemma":[0.98073614,0.013607038,0.002089503,0.0004993534,0.0022746455,0.0007932836],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012374823,0.00061964465,0.00040299102,0.0018473091,0.0027840023,0.0080777975,0.0013343407,0.0018115857,0.0005158259],"category_scores_gemma":[0.021450203,0.0005223981,0.00033804693,0.0011207504,0.006236567,0.003946616,0.0027669522,0.0022273818,0.00024955615],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000027612621,0.00009376127,0.015367188,0.0004348442,0.0000122145375,0.00089131325,0.92723656,0.00015061603,0.005242162,0.0042915414,0.00033656933,0.04591555],"study_design_scores_gemma":[0.000019393592,0.00023610689,0.022919059,0.0013851096,0.00005710731,0.0024333263,0.9022168,0.00056100875,0.007568514,0.00367971,0.058851827,0.00007205305],"about_ca_topic_score_codex":0.0051091313,"about_ca_topic_score_gemma":0.0084980065,"teacher_disagreement_score":0.012374823,"about_ca_system_score_codex":0.0026811182,"about_ca_system_score_gemma":0.005038725,"threshold_uncertainty_score":0.065445065},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"qualitative","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"},{"model":"gpt","categories":[],"domain":null,"study_design":"qualitative","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"agree"},{"id":"W4214555837","doi":"10.5206/cjsotl-rcacea.2017.1.1","title":"Tools and Questions: An Introduction to Volume 8, Issue 1","year":2017,"lang":"en","type":"article","venue":"The Canadian Journal for the Scholarship of Teaching and Learning","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Sociology; Psychology","score_opus":0.06214295486918278,"score_gpt":0.38785865685816706,"score_spread":0.32571570198898425,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4214555837","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0015121368,0.062175594,0.047378454,0.25774184,0.32185388,0.0018982966,0.002161554,0.0041842638,0.301094],"genre_scores_gemma":[0.015076548,0.07239279,0.0621154,0.15344198,0.18657376,0.0053480472,0.0052932897,0.006458576,0.49329954],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99003905,0.004145451,0.0013125613,0.00053498434,0.003527311,0.0004406852],"domain_scores_gemma":[0.94884515,0.03720688,0.0018116364,0.0020879826,0.0075607984,0.0024876269],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012383569,0.0014857874,0.0014962921,0.010668554,0.0041116606,0.016416093,0.0028597713,0.005378889,0.08978543],"category_scores_gemma":[0.04409436,0.0010894705,0.0014916373,0.007528289,0.006043605,0.0133535145,0.0069032926,0.009631874,0.053778242],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020358595,0.00009955735,0.00015567681,0.00062237884,0.000004739787,0.000054942946,0.0010689208,0.000079486905,0.00027444476,0.013463521,0.8852418,0.09891422],"study_design_scores_gemma":[0.0000039762144,0.000020327167,0.0001771734,0.00073076994,0.0000015160831,0.00006497303,0.00040286998,0.000059016103,0.00004107395,0.005063397,0.9934236,0.000011344682],"about_ca_topic_score_codex":0.0012805436,"about_ca_topic_score_gemma":0.0026647549,"teacher_disagreement_score":0.08978543,"about_ca_system_score_codex":0.0038815478,"about_ca_system_score_gemma":0.005816253,"threshold_uncertainty_score":0.30036217},"labels":[],"label_agreement":null},{"id":"W4214612186","doi":"10.52358/mm.vi9.244","title":"Évaluer des compétences : une articulation cubique","year":2022,"lang":"fr","type":"article","venue":"Médiations et médiatisations","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université du Québec à Trois-Rivières","funders":"","keywords":"Humanities; Political science; Valuation (finance); Library science; Philosophy; Computer science; Business","score_opus":0.06017867497735572,"score_gpt":0.35317604974977257,"score_spread":0.29299737477241683,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4214612186","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.037522238,0.04743198,0.18556547,0.07583512,0.0034865122,0.0007287964,0.00075453555,0.00043535314,0.64824],"genre_scores_gemma":[0.76165277,0.018590188,0.09076823,0.006647391,0.0009499893,0.0017952775,0.0005683177,0.00067490106,0.11835285],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.98644954,0.008622541,0.000692579,0.0010308464,0.0023729263,0.00083152053],"domain_scores_gemma":[0.9851141,0.0082156425,0.0008966849,0.00070782646,0.004310444,0.00075529795],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011369982,0.001261914,0.00094991503,0.007453648,0.0057775425,0.020362094,0.0015656704,0.0040182755,0.010163813],"category_scores_gemma":[0.01884323,0.0007351811,0.0008719957,0.0055256714,0.01669771,0.010218377,0.0070759295,0.005581381,0.001884632],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013437429,0.000033313874,0.0018131676,0.0007254281,0.00002515656,0.0003263401,0.08566229,0.0003757565,0.001357619,0.83673483,0.010482861,0.06232883],"study_design_scores_gemma":[0.000036248308,0.00008728135,0.0059094923,0.003307646,0.000054362972,0.0009135922,0.07744336,0.0017159169,0.0011681311,0.14967577,0.7595607,0.00012744566],"about_ca_topic_score_codex":0.065712474,"about_ca_topic_score_gemma":0.058724463,"teacher_disagreement_score":0.065712474,"about_ca_system_score_codex":0.020331047,"about_ca_system_score_gemma":0.014822435,"threshold_uncertainty_score":0.1475128},"labels":[],"label_agreement":null},{"id":"W4220932421","doi":"10.22158/selt.v10n2p27","title":"Formative Assessment is a Scaffold for ELs to Reach ZPD’s Second Layer: A Literature Review Study","year":2022,"lang":"en","type":"review","venue":"Studies in English Language Teaching","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"University of Manitoba","keywords":"Formative assessment; Zone of proximal development; Mathematics education; Function (biology); Process (computing); Scaffold; Computer science; sort; Psychology; Assessment for learning; Pedagogy","score_opus":0.09516354740164225,"score_gpt":0.4958929418848868,"score_spread":0.40072939448324457,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4220932421","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00037831202,0.9986663,0.0001589812,0.00032061775,0.000064521904,0.000014541366,0.000009943805,0.0000026994628,0.00038414792],"genre_scores_gemma":[0.006606944,0.99245197,0.0004184922,0.00028830575,0.00006992226,0.00003034958,0.000019113695,0.0000023387286,0.000112446],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.9971432,0.00095233065,0.0007621276,0.00030177663,0.00075482874,0.00008562291],"domain_scores_gemma":[0.97772914,0.018078573,0.0013717371,0.00025858523,0.0023769923,0.0001849099],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0058621615,0.00074594654,0.0018213808,0.0052637854,0.0004900168,0.0024158268,0.0011268299,0.001338588,0.0018607005],"category_scores_gemma":[0.019078365,0.00042997205,0.0013830661,0.005104739,0.0010137203,0.0027574177,0.00091160473,0.0013204393,0.00040257792],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001244166,0.00009124423,0.0011441148,0.25617176,0.0007989524,0.00018236296,0.00097110594,0.00022550882,0.0004948986,0.004558328,0.006563038,0.72867423],"study_design_scores_gemma":[0.00006145911,0.00040364897,0.009236572,0.49058402,0.0075079636,0.0023047104,0.0024219356,0.00042552754,0.001492753,0.0039567566,0.4815112,0.000093403454],"about_ca_topic_score_codex":0.0031314685,"about_ca_topic_score_gemma":0.0057243295,"teacher_disagreement_score":0.0058621615,"about_ca_system_score_codex":0.0014409072,"about_ca_system_score_gemma":0.0057989657,"threshold_uncertainty_score":0.031002462},"labels":[],"label_agreement":null},{"id":"W4221071532","doi":"10.51357/jei.v3i1.182","title":"Examining Online Course Evaluations and the Quality of Student Feedback","year":2022,"lang":"en","type":"article","venue":"Journal of Educational Informatics","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Constructive; Quality (philosophy); Online course; Usability; Coronavirus disease 2019 (COVID-19); Data collection; Computer science; Psychology; Medical education; Mathematics education; Medicine; Sociology","score_opus":0.1478109579851624,"score_gpt":0.49933037932117824,"score_spread":0.3515194213360159,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4221071532","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9030783,0.061738633,0.011312235,0.0030009034,0.00093239784,0.0009751905,0.0009844666,0.00026521535,0.017712645],"genre_scores_gemma":[0.9657359,0.020031331,0.008961304,0.0008012818,0.000562131,0.0007429504,0.00054005807,0.00008940339,0.0025355925],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.90962243,0.053270303,0.007817272,0.002408003,0.025679909,0.00120218],"domain_scores_gemma":[0.3981081,0.4541423,0.060614996,0.0053665703,0.07949605,0.0022719577],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.06502624,0.00055602845,0.0012518151,0.007288464,0.0007423922,0.0042635677,0.0011893989,0.0007322409,0.0021602549],"category_scores_gemma":[0.30719012,0.00029422884,0.0008442715,0.0066861245,0.00097562326,0.003021366,0.0015330762,0.00089846057,0.0006701918],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014060106,0.00085442286,0.19784439,0.010910375,0.000657966,0.00016137211,0.0115669565,0.00056077476,0.002530648,0.0003699455,0.003036297,0.77010095],"study_design_scores_gemma":[0.00021142761,0.006546169,0.9008387,0.01890014,0.00094661437,0.000778251,0.021677794,0.0021951336,0.0107625285,0.0009610346,0.035886094,0.0002961128],"about_ca_topic_score_codex":0.0020154524,"about_ca_topic_score_gemma":0.0032769782,"teacher_disagreement_score":0.06502624,"about_ca_system_score_codex":0.001910497,"about_ca_system_score_gemma":0.0027339892,"threshold_uncertainty_score":0.34389573},"labels":[],"label_agreement":null},{"id":"W4226190183","doi":"10.1504/ijlc.2022.119506","title":"Education quality comparing between official measurement scale and inter-counterparts' perception: a new horizon for learning assessment","year":2021,"lang":"en","type":"article","venue":"International Journal of Learning and Change","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Dalhousie University","funders":"","keywords":"Horizon; Scale (ratio); Perception; Quality (philosophy); Psychology; Item response theory; Mathematics education; Computer science; Psychometrics; Geography; Mathematics; Cartography","score_opus":0.14183940712578774,"score_gpt":0.44760455393451576,"score_spread":0.305765146808728,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4226190183","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8103942,0.004649488,0.08841782,0.011063029,0.00089504244,0.0006161814,0.00060256815,0.00023967326,0.083121896],"genre_scores_gemma":[0.98505276,0.00025091067,0.013559881,0.0001655307,0.000061028943,0.00014479997,0.00015215845,0.000010011112,0.00060286396],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98229086,0.009076213,0.0015545773,0.0010801643,0.005390805,0.00060734304],"domain_scores_gemma":[0.97077405,0.014340741,0.0030872426,0.0022782509,0.007965585,0.0015542058],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.019559082,0.0002579779,0.00042578045,0.003142222,0.0009135624,0.003138447,0.00084968517,0.00062164693,0.0021366053],"category_scores_gemma":[0.037663843,0.00013861696,0.00054607086,0.0028674053,0.0024013973,0.005917377,0.0023274138,0.0011158325,0.00020816019],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003760017,0.00043494487,0.56452006,0.0009834616,0.00014875928,0.00013697083,0.030960532,0.00054347556,0.0023792407,0.04057617,0.0049245115,0.35401574],"study_design_scores_gemma":[0.000051669922,0.0018069083,0.8006131,0.0012365286,0.00015224612,0.00033291275,0.109553546,0.009321524,0.0021902837,0.033869427,0.040691726,0.00018001856],"about_ca_topic_score_codex":0.0028772522,"about_ca_topic_score_gemma":0.0031435979,"teacher_disagreement_score":0.9804409,"about_ca_system_score_codex":0.0016459438,"about_ca_system_score_gemma":0.0023633353,"threshold_uncertainty_score":0.10343957},"labels":[],"label_agreement":null},{"id":"W4226402501","doi":"10.32038/ltrq.2021.25.02","title":"Teachers’ Beliefs and Practice about Written Corrective Feedback: A Case Study in a French as a Foreign Language Program","year":2021,"lang":"en","type":"article","venue":"Language Teaching Research Quarterly","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University; Université du Québec en Abitibi-Témiscamingue","funders":"","keywords":"Corrective feedback; Situated; Foreign language; English as a foreign language; Psychology; Class (philosophy); Pedagogy; Peer feedback; Second language writing; Mathematics education; Medical education; Second language; Computer science; Medicine; Linguistics","score_opus":0.04800438437751356,"score_gpt":0.4747548318168341,"score_spread":0.42675044743932056,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4226402501","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9982135,0.00007276992,0.00037220644,0.00045499884,0.000003801768,0.000035433586,0.0000062646845,0.000008795883,0.0008321492],"genre_scores_gemma":[0.9980413,0.00015433747,0.0006536658,0.00014065954,0.000004502852,0.00003745121,0.0000075798575,0.0000076245037,0.0009529257],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99311924,0.004777346,0.00023256769,0.00038465345,0.0006675143,0.0008187265],"domain_scores_gemma":[0.98525107,0.008510879,0.0018781081,0.00060564675,0.001885628,0.0018685752],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0065652104,0.0004979591,0.0004827409,0.0011573419,0.0078540575,0.0028014425,0.0015485162,0.0016655711,0.0014724699],"category_scores_gemma":[0.01803634,0.00045121086,0.00033357026,0.0008761453,0.0030302424,0.0011815373,0.0021552325,0.001989937,0.00022258332],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008882574,0.0010988875,0.029617406,0.00013059004,0.000013292202,0.008073088,0.9345855,0.000196546,0.0024906462,0.00035281072,0.00039391327,0.022958469],"study_design_scores_gemma":[0.000028811228,0.0009214315,0.034034885,0.00014825327,0.000022375596,0.003497233,0.95069236,0.0008682086,0.0017165089,0.00018579597,0.007839424,0.000044673907],"about_ca_topic_score_codex":0.036878917,"about_ca_topic_score_gemma":0.09200684,"teacher_disagreement_score":0.036878917,"about_ca_system_score_codex":0.006351022,"about_ca_system_score_gemma":0.0053916667,"threshold_uncertainty_score":0.073328495},"labels":[],"label_agreement":null},{"id":"W4230383360","doi":"10.5465/amle.9.4.zqr652","title":"Improving the Effectiveness of Students in Groups With a Centralized Peer Evaluation System","year":2010,"lang":"en","type":"article","venue":"Academy of Management Learning and Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":44,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Concordia University","funders":"","keywords":"Peer feedback; Peer evaluation; Peer assessment; Peer group; Computer science; Qualitative research; Psychology; Peer effects; Higher education; Mathematics education; Medical education; Multimedia; Knowledge management; Social psychology; Sociology","score_opus":0.015076458740300377,"score_gpt":0.3634936882704143,"score_spread":0.3484172295301139,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4230383360","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9935213,0.000067163346,0.0044542514,0.000096657874,0.000021723406,0.00021336532,0.000013316701,0.00015217326,0.0014601023],"genre_scores_gemma":[0.99092215,0.00003650063,0.008068557,0.00003757724,0.000039410963,0.0001579938,0.000031389172,0.000014524197,0.0006917605],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9792366,0.013936138,0.0009245129,0.0016679364,0.0032485304,0.0009862698],"domain_scores_gemma":[0.92026836,0.045349166,0.009255796,0.010275767,0.007908149,0.006942777],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.018631345,0.0006109847,0.0011534567,0.0010501477,0.0013965786,0.0020492852,0.0014482616,0.0007725099,0.0027090015],"category_scores_gemma":[0.06382896,0.0002730026,0.00044921093,0.0007020125,0.0008011631,0.0016702651,0.0027222924,0.00070395635,0.0006324032],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.005553875,0.023405397,0.14295343,0.00054251496,0.0003098939,0.0002694465,0.008562898,0.007109851,0.029296502,0.00054006244,0.0021420368,0.7793141],"study_design_scores_gemma":[0.0034467732,0.10080144,0.74806166,0.00038304232,0.0009387775,0.0007113219,0.013132188,0.058173887,0.058128033,0.0036515088,0.012111601,0.00045972184],"about_ca_topic_score_codex":0.0012126848,"about_ca_topic_score_gemma":0.0019723743,"teacher_disagreement_score":0.018631345,"about_ca_system_score_codex":0.0008955554,"about_ca_system_score_gemma":0.0019898412,"threshold_uncertainty_score":0.098533094},"labels":[],"label_agreement":null},{"id":"W4233654530","doi":"10.33137/incite.1.28913","title":"This Is a Test","year":2018,"lang":"en","type":"article","venue":"in cite journal","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Test (biology); Poetry; Word (group theory); Linguistics; History; Computer science; Psychology; Literature; Art; Philosophy; Biology; Ecology","score_opus":0.041965805483094615,"score_gpt":0.39616559617924996,"score_spread":0.35419979069615537,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4233654530","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.043168686,0.0014721939,0.03194279,0.058844987,0.013583345,0.0010417626,0.002186256,0.0057757217,0.84198433],"genre_scores_gemma":[0.35215056,0.0017645933,0.053907827,0.03673885,0.0026733929,0.0010285589,0.0027946148,0.0031322804,0.54580927],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9889227,0.00251313,0.00046255963,0.0008161693,0.006725581,0.0005598085],"domain_scores_gemma":[0.97148424,0.0062483777,0.000934953,0.0048501873,0.013270447,0.003211871],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0065029445,0.0007637365,0.0007538699,0.0010733533,0.0020295891,0.0043871347,0.0015384634,0.00228063,0.06417881],"category_scores_gemma":[0.043062672,0.0002915857,0.0006162734,0.0005537212,0.0022445663,0.005142977,0.002675121,0.0035377536,0.04239962],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003379511,0.0008948027,0.008926003,0.0004629884,0.00005789372,0.00032920303,0.004922213,0.00027408978,0.0058830273,0.048373867,0.52711993,0.40241805],"study_design_scores_gemma":[0.000074953175,0.0012534346,0.010811725,0.000703093,0.00005119764,0.0008119399,0.0050269146,0.00070771325,0.005242358,0.03461686,0.9405685,0.00013129225],"about_ca_topic_score_codex":0.0026609555,"about_ca_topic_score_gemma":0.0028004942,"teacher_disagreement_score":0.9358212,"about_ca_system_score_codex":0.0010081975,"about_ca_system_score_gemma":0.003564336,"threshold_uncertainty_score":0.2146995},"labels":[],"label_agreement":null},{"id":"W4239004152","doi":"10.37514/atd-b.2016.0933.3.2","title":"Epilogue","year":2016,"lang":"en","type":"book-chapter","venue":"The WAC Clearinghouse; University Press of Colorado eBooks","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Philosophy","score_opus":0.040058663557430124,"score_gpt":0.2596215988172264,"score_spread":0.21956293525979628,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4239004152","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00067470723,0.0046898527,0.0016385757,0.036872406,0.052617174,0.0006547809,0.00849616,0.001144057,0.8932123],"genre_scores_gemma":[0.0033448793,0.0026257904,0.0013340428,0.016514331,0.0045168707,0.00047848985,0.0037487801,0.00049964903,0.9669371],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99916935,0.00015649911,0.00005591505,0.00012262605,0.00037349953,0.00012214332],"domain_scores_gemma":[0.9976031,0.00047378274,0.00006477636,0.00018611619,0.0012462897,0.00042584245],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014379005,0.0005935053,0.000527057,0.001887671,0.002069627,0.0039906614,0.0014456015,0.0027201832,0.55787796],"category_scores_gemma":[0.0071922084,0.00031850353,0.0006117247,0.0013263312,0.0007737785,0.003995438,0.0023593723,0.0028862196,0.26040092],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026013115,0.000012450153,0.00007522229,0.00018591151,0.0000011009347,0.00007246692,0.00007957827,0.000015167544,0.00008230269,0.006580503,0.955898,0.036971416],"study_design_scores_gemma":[0.0000029631844,0.0000065796694,0.00013104836,0.00008730335,8.4359624e-7,0.00005172212,0.00005765014,0.000004585716,0.000027663822,0.0007710885,0.9988564,0.000002113778],"about_ca_topic_score_codex":0.006379192,"about_ca_topic_score_gemma":0.009708376,"teacher_disagreement_score":0.55787796,"about_ca_system_score_codex":0.0024907957,"about_ca_system_score_gemma":0.0032395164,"threshold_uncertainty_score":0},"labels":[],"label_agreement":null},{"id":"W4239409743","doi":"10.4018/9781591407324.ch020","title":"Effects of Anonymity and Accountability During Online Peer Assessment","year":2011,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Anonymity; Accountability; Internet privacy; Computer science; Psychology; Computer security; Political science; Law","score_opus":0.025561739298318783,"score_gpt":0.33107803161382754,"score_spread":0.30551629231550875,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4239409743","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99569595,0.000057689736,0.0013918438,0.00015149744,0.00004110317,0.0002634463,0.000016831795,0.000036386507,0.0023453666],"genre_scores_gemma":[0.99689025,0.000032590193,0.0021132731,0.00007856713,0.000033229655,0.00030865974,0.000016990702,0.000009363482,0.0005170811],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9031964,0.07222201,0.0061679096,0.0044925166,0.011044746,0.0028764033],"domain_scores_gemma":[0.45768198,0.4519785,0.051620185,0.019518238,0.009915738,0.009285373],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.035742834,0.00085969036,0.00089392887,0.00082101265,0.0018656339,0.0025536984,0.0013865253,0.0013741062,0.0032964651],"category_scores_gemma":[0.2110959,0.0007542529,0.0008368375,0.0004597584,0.0030099913,0.004146267,0.0037205047,0.0018306202,0.00029875178],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.10406081,0.046602767,0.35316616,0.0023120584,0.0010566165,0.0012841037,0.06660373,0.007092768,0.10886902,0.0048726834,0.0014811283,0.30259818],"study_design_scores_gemma":[0.008283778,0.13666241,0.72125083,0.00073277956,0.0012320507,0.0009989466,0.020941097,0.01593933,0.07134706,0.011389539,0.010299065,0.0009231049],"about_ca_topic_score_codex":0.0008087808,"about_ca_topic_score_gemma":0.0010709863,"teacher_disagreement_score":0.9642572,"about_ca_system_score_codex":0.0016553135,"about_ca_system_score_gemma":0.0020409042,"threshold_uncertainty_score":0.18902844},"labels":[],"label_agreement":null},{"id":"W4239550360","doi":"10.37514/atd-b.2016.0933.1.3","title":"Introduction","year":2016,"lang":"en","type":"book-chapter","venue":"The WAC Clearinghouse; University Press of Colorado eBooks","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Geology","score_opus":0.026302958385079643,"score_gpt":0.2468246126396398,"score_spread":0.22052165425456016,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4239550360","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0004754597,0.0025444063,0.00194097,0.0049499576,0.003564564,0.0001087645,0.0012622385,0.0005707701,0.9845829],"genre_scores_gemma":[0.0028619904,0.0016875409,0.0012232827,0.0016831731,0.00052537624,0.000068072586,0.0010417758,0.00024667114,0.99066216],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9987037,0.00015784019,0.00006378488,0.0003282151,0.0006094786,0.00013692825],"domain_scores_gemma":[0.9988299,0.00014286755,0.000046527213,0.00017590579,0.00058625423,0.00021842615],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0007574691,0.0007422193,0.0006490886,0.0012809797,0.002511479,0.006604788,0.0017090841,0.002558823,0.5323091],"category_scores_gemma":[0.0031003451,0.00032787112,0.0005297112,0.0014868382,0.0010698441,0.0043938984,0.0032885533,0.002473076,0.35186258],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020452755,0.000035708053,0.00022311404,0.00015440662,0.00000237845,0.00008174169,0.00050623686,0.00007339307,0.00024997076,0.039612364,0.8259727,0.13306756],"study_design_scores_gemma":[0.0000012020994,0.0000050408107,0.00012152966,0.00007305488,5.603882e-7,0.000052483443,0.000106767875,0.000013794806,0.000031437747,0.002231904,0.99736005,0.000002168735],"about_ca_topic_score_codex":0.004544472,"about_ca_topic_score_gemma":0.0071159787,"teacher_disagreement_score":0.46769089,"about_ca_system_score_codex":0.002454899,"about_ca_system_score_gemma":0.0027004725,"threshold_uncertainty_score":0.66710424},"labels":[],"label_agreement":null},{"id":"W4239565827","doi":"10.24124/2013/bpgub1571","title":"Inquiry for deep learning for all learners","year":2013,"lang":"en","type":"dissertation","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Northern British Columbia; University of British Columbia","funders":"","keywords":"Formative assessment; Pedagogy; Resource (disambiguation); The arts; Point (geometry); Mathematics education; Reflection (computer programming); Language arts; English language; Psychology; Computer science; Visual arts; Art","score_opus":0.06086780292602795,"score_gpt":0.4159079277008984,"score_spread":0.35504012477487046,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4239565827","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.026120186,0.01644365,0.100136586,0.101402655,0.0029541492,0.00067940797,0.0002297569,0.0020670858,0.7499667],"genre_scores_gemma":[0.27404988,0.01185069,0.15526666,0.01693644,0.00093483296,0.0014690803,0.00032804022,0.0012927075,0.5378716],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9980325,0.0011302567,0.00008333562,0.00012984584,0.00047313218,0.00015094462],"domain_scores_gemma":[0.99568707,0.0019151988,0.00018838912,0.00082458917,0.0004641077,0.00092068024],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0032960642,0.0003027326,0.00024375938,0.00041274104,0.0023882133,0.0071022743,0.00060089765,0.0012277786,0.018123558],"category_scores_gemma":[0.006370289,0.00017521766,0.0002955212,0.0003665726,0.003446089,0.004115556,0.0072894464,0.0042979447,0.006037358],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000043837623,0.00029203447,0.0012326017,0.00049708347,0.000011271141,0.00023045563,0.04025952,0.00013565461,0.003215946,0.29876933,0.15511319,0.5001991],"study_design_scores_gemma":[0.000012166657,0.00006522776,0.0009157838,0.00050969975,0.0000055736336,0.0003952694,0.0076672193,0.00018772672,0.000902893,0.099577084,0.88975126,0.000009998041],"about_ca_topic_score_codex":0.00040926068,"about_ca_topic_score_gemma":0.0012620474,"teacher_disagreement_score":0.018123558,"about_ca_system_score_codex":0.0012057102,"about_ca_system_score_gemma":0.004884942,"threshold_uncertainty_score":0.060629368},"labels":[],"label_agreement":null},{"id":"W4239768617","doi":"10.1007/978-94-6209-028-6_2","title":"Breakthrough","year":2012,"lang":"en","type":"book-chapter","venue":"SensePublishers eBooks","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Work (physics); Political science; Literacy; Public administration; Library science; Sociology; Media studies; Engineering; Law","score_opus":0.043099086111957674,"score_gpt":0.3064134650660748,"score_spread":0.26331437895411713,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4239768617","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00073607126,0.0031333293,0.0048975106,0.010014646,0.0048079398,0.00005806004,0.00041174033,0.0007037108,0.9752371],"genre_scores_gemma":[0.0058253775,0.0023382292,0.002624538,0.0026981109,0.00040453314,0.00004216096,0.0004502855,0.0005768254,0.98503995],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9979494,0.00036376587,0.00006677039,0.00035013413,0.0009208364,0.00034921803],"domain_scores_gemma":[0.9977514,0.00040850177,0.000051015384,0.0003287062,0.0007881846,0.0006721081],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018200489,0.00071925257,0.00042539038,0.0014678108,0.0029418964,0.00912102,0.001993606,0.0028140375,0.21313296],"category_scores_gemma":[0.0034662422,0.00043896146,0.00074606173,0.0016002518,0.0022834179,0.0064493306,0.004628534,0.0050962777,0.12105947],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000031995867,0.00002888464,0.00007427678,0.00015936962,0.0000029273697,0.00008316407,0.0008452518,0.00010640956,0.0003206848,0.1641752,0.74449414,0.08967764],"study_design_scores_gemma":[0.0000020204616,0.0000056333824,0.00002034283,0.000029572713,5.768836e-7,0.000055176704,0.000084069536,0.0000185984,0.000067365785,0.003931848,0.9957824,0.0000025476684],"about_ca_topic_score_codex":0.0050342698,"about_ca_topic_score_gemma":0.013936885,"teacher_disagreement_score":0.21313296,"about_ca_system_score_codex":0.0061687143,"about_ca_system_score_gemma":0.004688219,"threshold_uncertainty_score":0.7130008},"labels":[],"label_agreement":null},{"id":"W4241845040","doi":"10.1007/978-3-030-71363-8_26","title":"Giving Feedback on Others’ Writing","year":2021,"lang":"en","type":"book-chapter","venue":"Innovation and change in professional education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Conversation; Transformative learning; Rewriting; Action (physics); Computer science; Psychology; Human–computer interaction; Communication; Pedagogy","score_opus":0.09681976494152646,"score_gpt":0.41650593143806286,"score_spread":0.3196861664965364,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4241845040","genre_codex":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009131039,0.00092728983,0.012297436,0.0035102717,0.0018474481,0.00010242451,0.000079436686,0.0005914687,0.97151315],"genre_scores_gemma":[0.07753543,0.0011277725,0.013980571,0.0012086668,0.00065050676,0.000099521065,0.00016396408,0.00064662396,0.90458703],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9972254,0.0011953043,0.00011814862,0.00012810194,0.0012044174,0.00012867742],"domain_scores_gemma":[0.9885949,0.007735633,0.0002768867,0.0010030033,0.0019319386,0.00045778073],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029801344,0.00052916113,0.0003968732,0.0012500343,0.0012301948,0.0037144385,0.00093543704,0.0010168353,0.062678516],"category_scores_gemma":[0.017730644,0.00018192494,0.0004725496,0.0008800447,0.0010832658,0.0031198498,0.0016257378,0.0022777522,0.021982592],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000043586526,0.00019018013,0.00058717426,0.00017665933,0.000010098267,0.00016789598,0.016399566,0.00031400216,0.003416138,0.038021587,0.27817142,0.6625017],"study_design_scores_gemma":[0.000010611129,0.00014197343,0.0019185105,0.000326134,0.000010541966,0.0006920213,0.004996698,0.0008672631,0.003911586,0.021841817,0.9652506,0.000032228585],"about_ca_topic_score_codex":0.00068514067,"about_ca_topic_score_gemma":0.001505403,"teacher_disagreement_score":0.062678516,"about_ca_system_score_codex":0.00053390395,"about_ca_system_score_gemma":0.000751586,"threshold_uncertainty_score":0.2096805},"labels":[],"label_agreement":null},{"id":"W4244193584","doi":"10.1037/e642622013-015","title":"What's in a quarter: Adjusting and re-engaging with course aspirations after mid-quarter feedback","year":2013,"lang":"en","type":"dataset","venue":"PsycEXTRA Dataset","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Quarter (Canadian coin); Course (navigation); Short course; History; Engineering; Medicine; Pediatrics","score_opus":0.0382086263038963,"score_gpt":0.34316675102373695,"score_spread":0.30495812471984063,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4244193584","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001772824,0.00006291773,0.00009535786,0.0001947968,0.000045265722,0.00005257871,0.9966875,0.0003137369,0.0007750765],"genre_scores_gemma":[0.0046639293,0.000061308485,0.0005835923,0.00007438034,0.000018119554,0.0005808596,0.9908414,0.00006973713,0.0031066737],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99823964,0.00044910476,0.00024534416,0.00031329578,0.00047499238,0.0002775348],"domain_scores_gemma":[0.98847944,0.0038542682,0.0015518317,0.0019033741,0.003328724,0.0008823555],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028870667,0.0017187848,0.00103962,0.0030432655,0.0008718719,0.0020956036,0.0025959378,0.0020429785,0.040347572],"category_scores_gemma":[0.026540695,0.0005445124,0.0017114816,0.0045375763,0.00034357863,0.0009844393,0.0024938614,0.0024481588,0.043253142],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024462614,0.00008136854,0.008404037,0.00040110893,0.00004964519,0.000013349019,0.00011469978,0.00030022682,0.00004079428,0.00022607438,0.98348224,0.006641835],"study_design_scores_gemma":[0.0020564275,0.00019565258,0.16940372,0.0012722162,0.00022612784,0.000090118316,0.0011545864,0.0041477694,0.00092563557,0.0023108658,0.81805056,0.00016620598],"about_ca_topic_score_codex":0.094064966,"about_ca_topic_score_gemma":0.19525972,"teacher_disagreement_score":0.094064966,"about_ca_system_score_codex":0.0021574076,"about_ca_system_score_gemma":0.004701613,"threshold_uncertainty_score":0.18703485},"labels":[],"label_agreement":null},{"id":"W4244696859","doi":"10.24124/2015/bpgub1662","title":"Formative assessment strategies used in the University of Northern British Columbia School of Education","year":2015,"lang":"en","type":"dissertation","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"University of Northern British Columbia","keywords":"Formative assessment; Medical education; Knowledge survey; Psychology; Qualitative research; Phenomenology (philosophy); Pedagogy; Mathematics education; Summative assessment; Sociology; Medicine","score_opus":0.01935480869583143,"score_gpt":0.3475716144568128,"score_spread":0.32821680576098133,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4244696859","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9321956,0.0036388666,0.011027532,0.0050130635,0.00024470393,0.0014562637,0.00017254714,0.000329369,0.045922138],"genre_scores_gemma":[0.95675546,0.0020929459,0.01657146,0.00073806953,0.000033093187,0.00083160296,0.00013461772,0.00006327977,0.022779485],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.97293055,0.013482704,0.0012474406,0.0014413096,0.0090767555,0.0018213224],"domain_scores_gemma":[0.9515074,0.015663005,0.0033204642,0.002426224,0.021364726,0.0057181404],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.023080964,0.00047141788,0.00056500017,0.0035812554,0.008833947,0.008866568,0.0020568203,0.0009990418,0.0019239143],"category_scores_gemma":[0.0522882,0.0004368153,0.00018615316,0.00389572,0.0027716141,0.0022802392,0.0034732858,0.0016356199,0.0005670197],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015418019,0.0006818832,0.052438017,0.00046440473,0.000019893718,0.0004731005,0.49988112,0.0002629037,0.004811164,0.002679281,0.006466339,0.43166777],"study_design_scores_gemma":[0.0000608348,0.00067247584,0.19756974,0.0012636709,0.000042619453,0.00061789417,0.59070843,0.0007764141,0.008853277,0.002390883,0.19681677,0.0002270247],"about_ca_topic_score_codex":0.22476134,"about_ca_topic_score_gemma":0.45090985,"teacher_disagreement_score":0.22476134,"about_ca_system_score_codex":0.02455396,"about_ca_system_score_gemma":0.038464252,"threshold_uncertainty_score":0.44690615},"labels":[],"label_agreement":null},{"id":"W4245142731","doi":"10.24124/2013/bpgub918","title":"Implementing rubrics as formative assessment in English writing classes in Japan.","year":2013,"lang":"en","type":"dissertation","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Heritage; Library and Archives Canada","funders":"Vancouver Island University; University of Northern British Columbia","keywords":"Rubric; Formative assessment; Action research; Interpersonal communication; Psychology; Pedagogy; Mathematics education; Social psychology","score_opus":0.02393801657956783,"score_gpt":0.39175912016037673,"score_spread":0.3678211035808089,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4245142731","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9530774,0.0005987168,0.032082707,0.00060676126,0.00015290569,0.0022587988,0.000110271416,0.0006231836,0.010489196],"genre_scores_gemma":[0.84208345,0.00040741678,0.15174192,0.00020866263,0.00003549909,0.0011253316,0.00019667053,0.00010548299,0.0040956074],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9895778,0.006939982,0.0007880325,0.00064333406,0.0017133666,0.0003375732],"domain_scores_gemma":[0.982842,0.0065851486,0.002141615,0.0015640345,0.0057759807,0.0010911492],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.017897796,0.00053200714,0.00030939135,0.0011118646,0.0011006555,0.001373405,0.0009892725,0.00052221236,0.0007664089],"category_scores_gemma":[0.039766327,0.00029914253,0.0003479422,0.0007366187,0.00069210294,0.0013145681,0.0015300972,0.00076030643,0.00043749018],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00035649992,0.0022302293,0.057278503,0.0006686472,0.000033660428,0.0003258645,0.06006028,0.0006556768,0.034332428,0.0003763817,0.0024137169,0.8412682],"study_design_scores_gemma":[0.00043827592,0.014994257,0.67959565,0.0012129557,0.00034943837,0.001962869,0.10996907,0.012032566,0.10580771,0.0024255794,0.070665464,0.00054623],"about_ca_topic_score_codex":0.0036827056,"about_ca_topic_score_gemma":0.010862288,"teacher_disagreement_score":0.017897796,"about_ca_system_score_codex":0.0009410492,"about_ca_system_score_gemma":0.00266877,"threshold_uncertainty_score":0.094653726},"labels":[],"label_agreement":null},{"id":"W4246205618","doi":"10.1787/epa-2006-5-en","title":"Improving Learning through Formative Assessment","year":2007,"lang":"en","type":"book-chapter","venue":"Education policy analysis","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Formative assessment; German; Equity (law); Quality (philosophy); Medical education; Pedagogy; Political science; Mathematics education; Psychology; Geography; Medicine","score_opus":0.046278301571159114,"score_gpt":0.43819529058630224,"score_spread":0.39191698901514316,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4246205618","genre_codex":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010124608,0.031413607,0.23432556,0.014709938,0.0023643656,0.0006353562,0.000358592,0.0024635457,0.70360434],"genre_scores_gemma":[0.095750585,0.08110585,0.3251274,0.0054597342,0.0014575913,0.0009674279,0.00083499396,0.0008149881,0.4884814],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9976587,0.0006689399,0.00011128793,0.00018064797,0.0012741636,0.00010611252],"domain_scores_gemma":[0.9963529,0.0022536274,0.00015779337,0.00028149327,0.0008557754,0.00009840614],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0036508907,0.00079657853,0.00036721095,0.0017074024,0.0006316093,0.004138171,0.0015324535,0.0011749464,0.010174372],"category_scores_gemma":[0.0068170424,0.000240026,0.00042581273,0.0013348368,0.001507888,0.0063559893,0.0024079243,0.0020278117,0.004506204],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000014608835,0.000116052615,0.00041715478,0.000580953,0.000009196549,0.00006609459,0.0047655343,0.0013843561,0.0015826769,0.123164445,0.05194109,0.81595784],"study_design_scores_gemma":[0.0000104803385,0.000089805966,0.0007817929,0.0015920058,0.000013734704,0.0003483155,0.0011978395,0.0010427877,0.0038438174,0.07826346,0.9127844,0.00003153884],"about_ca_topic_score_codex":0.0014816865,"about_ca_topic_score_gemma":0.0021760075,"teacher_disagreement_score":0.010174372,"about_ca_system_score_codex":0.002007049,"about_ca_system_score_gemma":0.0023602275,"threshold_uncertainty_score":0.034036636},"labels":[],"label_agreement":null},{"id":"W4247519277","doi":"10.1007/978-3-030-16454-6","title":"Differentiated Teacher Evaluation and Professional Learning","year":2019,"lang":"en","type":"book","venue":"Palgrave studies on leadership and learning in teacher education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Mathematics education; Professional development; Psychology; Professional learning community; Pedagogy; Medical education; Medicine","score_opus":0.1085604436891531,"score_gpt":0.4125393468333608,"score_spread":0.3039789031442077,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4247519277","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.010174451,0.05357889,0.048280627,0.008016238,0.0015933075,0.000069555914,0.000052890326,0.00023499022,0.877999],"genre_scores_gemma":[0.4386233,0.0136989355,0.020692276,0.0016534376,0.0009424643,0.00016658168,0.000102750906,0.00019253837,0.52392775],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9974885,0.0011185982,0.00009269989,0.00017019807,0.0009844503,0.00014555186],"domain_scores_gemma":[0.99521106,0.0032875068,0.00014306414,0.00037559116,0.00076154654,0.0002212896],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002418538,0.00029490003,0.00045573886,0.0011499587,0.000563757,0.0027438446,0.00058334967,0.0009345564,0.009185926],"category_scores_gemma":[0.011064227,0.00018445907,0.00015358187,0.0008674796,0.0043270765,0.0028421516,0.0014561823,0.0016956992,0.0016152706],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000036720292,0.000039500763,0.00045079656,0.00010592416,0.0000026417613,0.00004781439,0.0009008145,0.0005662372,0.00024024719,0.6158731,0.033509184,0.34822705],"study_design_scores_gemma":[0.0000150578735,0.00007428785,0.0035049305,0.0002650724,0.000004373866,0.0003786468,0.001142813,0.0021916497,0.0007082606,0.7838644,0.20783292,0.000017576673],"about_ca_topic_score_codex":0.002531959,"about_ca_topic_score_gemma":0.004277908,"teacher_disagreement_score":0.009185926,"about_ca_system_score_codex":0.0027537567,"about_ca_system_score_gemma":0.0019814586,"threshold_uncertainty_score":0.03073001},"labels":[],"label_agreement":null},{"id":"W4249889919","doi":"10.24124/2001/bpgub1223","title":"Provinding [sic] authentic assessment for vocational programs","year":2001,"lang":"en","type":"dissertation","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Vocational education; Psychology; Computer science; Pedagogy","score_opus":0.04395059877584961,"score_gpt":0.4216020254307026,"score_spread":0.37765142665485296,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4249889919","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.020517668,0.0058921752,0.09929837,0.0042267335,0.0030426285,0.0013679671,0.002233623,0.007018514,0.8564024],"genre_scores_gemma":[0.14883801,0.0040845503,0.067943364,0.0006961913,0.0007958112,0.00058493577,0.0034906338,0.0009348108,0.77263176],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983171,0.00040667228,0.00008019636,0.00015674398,0.00091653096,0.000122752],"domain_scores_gemma":[0.99692816,0.00040910763,0.0000816471,0.0003776244,0.0019051434,0.00029825166],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023635982,0.0004299718,0.0005122415,0.0017982279,0.0018720173,0.0036551582,0.00071307126,0.0012003495,0.055187352],"category_scores_gemma":[0.0064308746,0.00028268367,0.0002750952,0.002182028,0.0006708746,0.0013729008,0.0012347308,0.0011848741,0.022371083],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011355716,0.0002657552,0.001108667,0.00024263724,0.00000743776,0.0000719968,0.0005693105,0.0008575256,0.0012894757,0.0190797,0.2641428,0.71225107],"study_design_scores_gemma":[0.00008873102,0.000539453,0.02345986,0.0007825615,0.00005462865,0.00039396936,0.0005800872,0.012181172,0.006063819,0.017411996,0.93837345,0.000070275215],"about_ca_topic_score_codex":0.009603183,"about_ca_topic_score_gemma":0.020306483,"teacher_disagreement_score":0.055187352,"about_ca_system_score_codex":0.0012511039,"about_ca_system_score_gemma":0.003284867,"threshold_uncertainty_score":0.18462008},"labels":[],"label_agreement":null},{"id":"W4250420280","doi":"10.4018/9781591407324.ch010","title":"Self-Assessment During Online Discussion","year":2011,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Psychology; Computer science","score_opus":0.026535787720943914,"score_gpt":0.32138575955527415,"score_spread":0.29484997183433026,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4250420280","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.40804744,0.0013395572,0.08297207,0.0016880857,0.0012649437,0.006511289,0.0027475958,0.0032072342,0.4922217],"genre_scores_gemma":[0.5978117,0.0010572571,0.08010559,0.00071266206,0.00019649437,0.006354905,0.0023872147,0.00082801934,0.31054616],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99421126,0.002322018,0.00030139333,0.00068070606,0.0022300577,0.0002545173],"domain_scores_gemma":[0.987223,0.0066295257,0.00074579567,0.0009284259,0.00394982,0.00052347773],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0044671777,0.0005484392,0.00044123083,0.0013557315,0.0013787058,0.0023274734,0.0009101505,0.0005487697,0.028460663],"category_scores_gemma":[0.01776604,0.0002137534,0.00032171095,0.0006480013,0.0005282384,0.0018328216,0.0021096969,0.001199043,0.013012184],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00031400804,0.0014321497,0.010138547,0.00093603134,0.000022515474,0.000238905,0.1037264,0.00045034432,0.017574703,0.009713374,0.0421473,0.81330574],"study_design_scores_gemma":[0.00008831708,0.0009939672,0.038559522,0.0014115353,0.000031881867,0.000675171,0.05510779,0.0030988543,0.035819292,0.015995655,0.84808594,0.00013206768],"about_ca_topic_score_codex":0.0003142881,"about_ca_topic_score_gemma":0.0005585417,"teacher_disagreement_score":0.028460663,"about_ca_system_score_codex":0.00067608827,"about_ca_system_score_gemma":0.0010046044,"threshold_uncertainty_score":0.09521037},"labels":[],"label_agreement":null},{"id":"W4254133157","doi":"10.4018/978-1-4666-0047-8.ch015","title":"Leveraging Technology to Promote Assessment for Learning in Higher Education","year":2011,"lang":"en","type":"book-chapter","venue":"IGI Global eBooks","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Queen's University","funders":"","keywords":"Peer assessment; Higher education; Computer science; Process (computing); Institution; Engineering management; Mathematics education; Medical education; Engineering; Knowledge management; Psychology; Sociology; Political science; Medicine","score_opus":0.05092252813267043,"score_gpt":0.3644200365005259,"score_spread":0.31349750836785545,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4254133157","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.027921068,0.035293434,0.110903375,0.008340484,0.0016377693,0.00046053168,0.00011739006,0.0015440864,0.813782],"genre_scores_gemma":[0.19383489,0.06532205,0.25864372,0.0031582133,0.001324699,0.0006892402,0.00028225215,0.0005770334,0.476168],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9988764,0.00038541356,0.00003687607,0.00009077635,0.00055160525,0.00005891723],"domain_scores_gemma":[0.99781966,0.0017171503,0.000064158456,0.00014200035,0.00014853662,0.000108495675],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015970842,0.00063550187,0.0003037992,0.0018066335,0.0005723845,0.004036601,0.0010946576,0.0011363584,0.010461333],"category_scores_gemma":[0.002983321,0.00016782692,0.00027156936,0.0018241474,0.0014452485,0.0046671135,0.0022285096,0.0016171148,0.004165665],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012854039,0.00016134181,0.0008000409,0.00052297686,0.000004044433,0.00010082619,0.0035897172,0.0004408096,0.0027500254,0.039369274,0.026370356,0.92587763],"study_design_scores_gemma":[0.000014867917,0.000171071,0.0061173937,0.0022984573,0.000010648182,0.001101633,0.0023388558,0.0016371532,0.0023919921,0.049487658,0.93439126,0.00003901806],"about_ca_topic_score_codex":0.0014153637,"about_ca_topic_score_gemma":0.0041680234,"teacher_disagreement_score":0.010461333,"about_ca_system_score_codex":0.0013209564,"about_ca_system_score_gemma":0.0015017735,"threshold_uncertainty_score":0.03499663},"labels":[],"label_agreement":null},{"id":"W4255235667","doi":"10.20343/9.1.20","title":"Exploring the Emotional Responses of Undergraduate Students to Assessment Feedback: Implications for Instructors","year":2021,"lang":"en","type":"article","venue":"Teaching & Learning Inquiry The ISSOTL Journal","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"MacEwan University","funders":"MacEwan University; Ohio State University; University of Gloucestershire; Purdue University; Monash University; Leeds Beckett University","keywords":"Psychology; Summative assessment; Peer feedback; Psychological resilience; Variety (cybernetics); Social psychology; Cognition; Negative feedback; Formative assessment; Medical education; Pedagogy","score_opus":0.17912409354407574,"score_gpt":0.44624243943902614,"score_spread":0.2671183458949504,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4255235667","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9857451,0.0013860445,0.0023669251,0.005437937,0.00011419126,0.00008087162,0.000033238524,0.00003455192,0.004801093],"genre_scores_gemma":[0.99574065,0.0010906978,0.0011955241,0.00052907254,0.00003681869,0.000069394264,0.000016615262,0.00000938127,0.0013118448],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9947403,0.0036049406,0.00024842963,0.00013664599,0.0009190516,0.00035069056],"domain_scores_gemma":[0.9773946,0.015563726,0.001411889,0.00036055155,0.003396841,0.0018723623],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0112532005,0.0002728998,0.00045857576,0.0006541833,0.0013938871,0.0038134851,0.0005046504,0.00078603026,0.0013578144],"category_scores_gemma":[0.03836885,0.00012465764,0.0002683503,0.00074422505,0.0015377868,0.0014812244,0.001497155,0.001295166,0.00035619235],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00037559247,0.0009699048,0.17239942,0.0009091805,0.00003666528,0.0016380223,0.5297893,0.00032085986,0.007906271,0.0014870745,0.003060097,0.2811076],"study_design_scores_gemma":[0.000021600497,0.0012215215,0.22087474,0.0010365322,0.000036238318,0.00080694305,0.74811864,0.00082525314,0.0033510446,0.0029467728,0.020679297,0.00008139482],"about_ca_topic_score_codex":0.001397462,"about_ca_topic_score_gemma":0.0025908968,"teacher_disagreement_score":0.0112532005,"about_ca_system_score_codex":0.0011548041,"about_ca_system_score_gemma":0.0018842696,"threshold_uncertainty_score":0.05951327},"labels":[],"label_agreement":null},{"id":"W4256693308","doi":"10.15760/nwjte.2012.9.2.7","title":"Towards Balanced Assessment of Student Teaching Performance","year":2012,"lang":"en","type":"article","venue":"Northwest Journal of Teacher Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Lethbridge","funders":"","keywords":"Summative assessment; Formative assessment; Context (archaeology); Knowledge survey; Process (computing); Medical education; Pedagogy; Mathematics education; Psychology; Computer science; Medicine","score_opus":0.0344671714649823,"score_gpt":0.4169282447697099,"score_spread":0.3824610733047276,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4256693308","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4809733,0.0015087011,0.42300296,0.014398815,0.00073667156,0.0024470028,0.000716042,0.0037069456,0.07250957],"genre_scores_gemma":[0.5277489,0.0007475845,0.46052718,0.0007854215,0.000083127634,0.0011417374,0.00044444486,0.00032671235,0.0081949495],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9273732,0.031869695,0.0056649833,0.0039509353,0.029936668,0.001204541],"domain_scores_gemma":[0.93235195,0.0156862,0.0069501386,0.0044431197,0.03849889,0.0020697846],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.057499893,0.0009167009,0.00096813554,0.0044112504,0.0015798926,0.007370987,0.001896271,0.00167592,0.0022113011],"category_scores_gemma":[0.10783651,0.00058901816,0.00041392155,0.0026834768,0.0018648666,0.005585855,0.008092206,0.002987562,0.0013605548],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00049214455,0.0007925676,0.06336692,0.0007959034,0.00007717615,0.00015167428,0.028332125,0.0023685053,0.022657108,0.011106436,0.0071316496,0.8627278],"study_design_scores_gemma":[0.00042502562,0.0072200624,0.4170316,0.0055621653,0.00033680155,0.001992096,0.07170996,0.0517774,0.11771273,0.10618343,0.21911594,0.0009327318],"about_ca_topic_score_codex":0.0036353269,"about_ca_topic_score_gemma":0.0055081244,"teacher_disagreement_score":0.057499893,"about_ca_system_score_codex":0.0029523193,"about_ca_system_score_gemma":0.007807463,"threshold_uncertainty_score":0.30409217},"labels":[],"label_agreement":null},{"id":"W4281488678","doi":"10.1097/acm.0000000000004755","title":"Narrative Assessments in Higher Education: A Scoping Review to Identify Evidence-Based Quality Indicators","year":2022,"lang":"en","type":"review","venue":"Academic Medicine","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Narrative; Thematic analysis; Quality (philosophy); Narrative inquiry; Psychology; Medical education; Descriptive statistics; Computer science; Inclusion (mineral); Qualitative research; Medicine; Social psychology; Sociology; Linguistics; Statistics; Social science","score_opus":0.5162953262998812,"score_gpt":0.6455581755914443,"score_spread":0.12926284929156318,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4281488678","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002356907,0.972809,0.006429166,0.0045833173,0.0012237258,0.008813902,0.0008433271,0.000061499035,0.0028791493],"genre_scores_gemma":[0.022232525,0.92598045,0.028600218,0.0019764467,0.00039308716,0.019438917,0.00088314945,0.000037776605,0.00045741335],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.8689294,0.060130678,0.0482255,0.0030420101,0.018502504,0.0011699118],"domain_scores_gemma":[0.5929996,0.29793635,0.048053075,0.00607241,0.0530278,0.0019107576],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.12676345,0.002808721,0.008035163,0.054187648,0.0032944023,0.010701166,0.0040709227,0.005285632,0.0052903495],"category_scores_gemma":[0.37417406,0.0022675854,0.009087802,0.039148156,0.0032669601,0.0132343555,0.0070431437,0.003852519,0.0010353388],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017565367,0.00006636137,0.0013126226,0.7865255,0.0019608445,0.00018237729,0.0030691975,0.0003357357,0.00023652797,0.002822924,0.005835008,0.19747722],"study_design_scores_gemma":[0.00004459471,0.000054577133,0.0007388756,0.9776734,0.0026866074,0.00011283663,0.0010346436,0.00013258608,0.00012737662,0.0009172997,0.01644831,0.000028800256],"about_ca_topic_score_codex":0.005530109,"about_ca_topic_score_gemma":0.013510175,"teacher_disagreement_score":0.12676345,"about_ca_system_score_codex":0.0126864035,"about_ca_system_score_gemma":0.05294573,"threshold_uncertainty_score":0.67039716},"labels":[],"label_agreement":null},{"id":"W4282946125","doi":"10.52214/jmetc.v13i1.8984","title":"Peer Feedback in the Mathematics Classroom","year":2022,"lang":"en","type":"article","venue":"Journal of Mathematics Education at Teachers College","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University; St. Francis Xavier University","funders":"","keywords":"Peer feedback; Mathematics education; Point (geometry); Psychology; Pedagogy; Mathematics","score_opus":0.03812704026720599,"score_gpt":0.3495190702609642,"score_spread":0.3113920299937582,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4282946125","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95622486,0.0021962232,0.012996032,0.0030140325,0.00025938154,0.00025065575,0.00006836352,0.00018760111,0.02480295],"genre_scores_gemma":[0.99596643,0.00031849404,0.001961691,0.00012851277,0.000054257885,0.00006834569,0.000016076057,0.00002405446,0.0014621421],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.91511685,0.06432609,0.0019213874,0.002437463,0.014076783,0.0021213663],"domain_scores_gemma":[0.85326725,0.09631803,0.018265156,0.006554138,0.019296024,0.0062993392],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.021958312,0.0005400996,0.0008688643,0.0027697126,0.0044905306,0.00455808,0.0012289352,0.0015383038,0.0025472243],"category_scores_gemma":[0.14355156,0.00033138035,0.0003773754,0.0013393073,0.0030838181,0.0034186076,0.0049041677,0.0017327813,0.00048276508],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000387715,0.0006659132,0.15388855,0.0009262605,0.00015700803,0.0017880208,0.57434094,0.0008357865,0.004759428,0.0064008194,0.004339137,0.2515104],"study_design_scores_gemma":[0.00014180403,0.001918357,0.23385412,0.0017773951,0.00019720876,0.004214676,0.6092197,0.0040795496,0.0064366143,0.013393408,0.12447538,0.00029175865],"about_ca_topic_score_codex":0.0030840072,"about_ca_topic_score_gemma":0.0046035615,"teacher_disagreement_score":0.021958312,"about_ca_system_score_codex":0.0023181327,"about_ca_system_score_gemma":0.0040238635,"threshold_uncertainty_score":0.11612803},"labels":[],"label_agreement":null},{"id":"W4283698056","doi":"10.1007/s11092-022-09389-9","title":"Mapping the constellation of assessment discourses: a scoping review study on assessment competence, literacy, capability, and identity","year":2022,"lang":"en","type":"review","venue":"Educational Assessment Evaluation and Accountability","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":31,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University; Memorial University of Newfoundland","funders":"","keywords":"Competence (human resources); Operationalization; Construct (python library); Authentic assessment; Literacy; Rubric; Pedagogy; Identity (music); Psychology; Engineering ethics; Sociology; Epistemology; Social psychology; Computer science; Engineering","score_opus":0.19602477827829456,"score_gpt":0.5663204934521253,"score_spread":0.37029571517383075,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283698056","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0054192077,0.9897786,0.0010793258,0.0012496868,0.00012762459,0.00029833784,0.00018248161,0.000008221212,0.0018565763],"genre_scores_gemma":[0.06338696,0.9300707,0.0045888233,0.0006039523,0.000064603264,0.00074389996,0.00026453758,0.000014243493,0.00026230505],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.9669871,0.017885856,0.0073160096,0.0019631896,0.005394739,0.00045322478],"domain_scores_gemma":[0.8583534,0.11983683,0.009114513,0.002287988,0.009898981,0.0005082685],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.043165293,0.0009562565,0.0039463607,0.023390202,0.0016378141,0.00789762,0.0015738702,0.0019117075,0.0018921107],"category_scores_gemma":[0.14486739,0.0011266582,0.0029445621,0.025607869,0.0032300702,0.008579675,0.005092536,0.0025264625,0.00027812933],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019800241,0.000075085605,0.0056491857,0.38395298,0.0037502032,0.00027378026,0.024586918,0.00026657633,0.0005545319,0.0111287525,0.0037590456,0.565805],"study_design_scores_gemma":[0.00005391262,0.00010628905,0.012244143,0.8786181,0.009775531,0.00064417144,0.020021072,0.00017900727,0.00052959507,0.004332902,0.073411845,0.00008352069],"about_ca_topic_score_codex":0.01214686,"about_ca_topic_score_gemma":0.03306799,"teacher_disagreement_score":0.043165293,"about_ca_system_score_codex":0.0053409,"about_ca_system_score_gemma":0.025122361,"threshold_uncertainty_score":0.22828263},"labels":[],"label_agreement":null},{"id":"W4283730835","doi":"10.1080/0142159x.2022.2083489","title":"Technology enhanced assessment: Ottawa consensus statement and recommendations","year":2022,"lang":"en","type":"article","venue":"Medical Teacher","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":33,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"National Institute for Health and Care Research","keywords":"Coronavirus disease 2019 (COVID-19); Medical education; Engineering ethics; Health technology; Computer science; Knowledge management; Health care; Engineering management; Political science; Medicine; Engineering","score_opus":0.027043108996454637,"score_gpt":0.3946262649641411,"score_spread":0.3675831559676865,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283730835","genre_codex":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00088546996,0.06835527,0.013369758,0.87817013,0.022924043,0.003999053,0.0017061753,0.00026152833,0.010328506],"genre_scores_gemma":[0.063859805,0.21198821,0.27089176,0.3823064,0.011865637,0.032581832,0.0081890505,0.00060502137,0.017712329],"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.63256454,0.16113278,0.09713395,0.011941044,0.08457608,0.012651591],"domain_scores_gemma":[0.33683407,0.23049186,0.038289025,0.014580351,0.35482943,0.024975212],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.3568218,0.0033183913,0.006523284,0.017837472,0.008755455,0.017191285,0.021817157,0.028060842,0.0089759305],"category_scores_gemma":[0.4503867,0.0030286196,0.010836481,0.011181357,0.012563677,0.017773239,0.01749306,0.033493135,0.0057628904],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00040327373,0.00038676875,0.0043949294,0.0514947,0.00095642224,0.00064341014,0.0067514647,0.0018570522,0.0005571279,0.028934704,0.61512583,0.28849432],"study_design_scores_gemma":[0.00034976602,0.00027985257,0.006153807,0.22594877,0.0011684569,0.00057218934,0.0081726005,0.0015130634,0.0010676166,0.03573048,0.7184633,0.00058019214],"about_ca_topic_score_codex":0.10337153,"about_ca_topic_score_gemma":0.09704115,"teacher_disagreement_score":0.3568218,"about_ca_system_score_codex":0.051160976,"about_ca_system_score_gemma":0.23142114,"threshold_uncertainty_score":0.7931532},"labels":[],"label_agreement":null},{"id":"W4283754310","doi":"10.21083/ajote.v11i1.6880","title":"The Use of Peers in Assessment for Learning: A Case Study of Trainee Teachers at Bindura University of Science Education (BUSE), Zimbabwe","year":2022,"lang":"en","type":"article","venue":"African Journal of Teacher Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Peer assessment; Psychology; Sincerity; Medical education; Population; Curriculum; Qualitative property; Mathematics education; Pedagogy; Social psychology; Medicine; Statistics","score_opus":0.06151002741819684,"score_gpt":0.3750338498474102,"score_spread":0.31352382242921334,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283754310","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9982632,0.00014740559,0.00025367178,0.00044323597,0.000006850111,0.000049730577,0.0000080243635,0.0000027916856,0.0008250772],"genre_scores_gemma":[0.99725467,0.0004644201,0.0004980735,0.00015573262,0.000008377819,0.000042368643,0.000008038159,0.0000059528993,0.0015624667],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99529773,0.0025653779,0.00017784568,0.00028052178,0.00048400348,0.0011945193],"domain_scores_gemma":[0.993606,0.003430481,0.0008359299,0.00021809447,0.00057631294,0.001333172],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003858311,0.00057411386,0.0006227974,0.0011273952,0.011531346,0.0032102924,0.0017689832,0.0023803068,0.0026204886],"category_scores_gemma":[0.01140065,0.00073121657,0.00033813363,0.00093831355,0.0039945543,0.0020309398,0.0034151475,0.0027013035,0.00037398346],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007788274,0.000653951,0.022116793,0.00019147852,0.0000109198045,0.023507223,0.9385785,0.000105839834,0.0016751629,0.0005475391,0.00041364197,0.012121048],"study_design_scores_gemma":[0.000011634724,0.00047549824,0.018042022,0.00015393797,0.000014844087,0.0065534604,0.9681916,0.00021123259,0.00076165335,0.00014711086,0.005413346,0.000023536028],"about_ca_topic_score_codex":0.021286298,"about_ca_topic_score_gemma":0.07010328,"teacher_disagreement_score":0.021286298,"about_ca_system_score_codex":0.0040613757,"about_ca_system_score_gemma":0.0032256455,"threshold_uncertainty_score":0.04232484},"labels":[],"label_agreement":null},{"id":"W4283778139","doi":"10.1117/12.2635510","title":"Fostering flow and feedback in the classroom: increasing the successful implementation of active learning instruction","year":2022,"lang":"en","type":"article","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University; John Abbott College; Vanier College; Dawson College","funders":"","keywords":"Orchestration; Facilitation; Active learning (machine learning); Computer science; Mathematics education; Flow (mathematics); Knowledge management; Multimedia; Psychology; Artificial intelligence","score_opus":0.03253108966307457,"score_gpt":0.356015431635151,"score_spread":0.32348434197207643,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4283778139","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92382854,0.00016521594,0.06378515,0.0010951154,0.00004763999,0.00096917356,0.000026306718,0.00086291746,0.0092198625],"genre_scores_gemma":[0.9401063,0.00009708793,0.058374077,0.00005735551,0.000015366331,0.0002554971,0.000018299696,0.000038191156,0.0010377677],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98876417,0.007597949,0.00034090842,0.0006896602,0.0017260103,0.0008813644],"domain_scores_gemma":[0.9758194,0.017423222,0.0017222886,0.0016215219,0.0015512081,0.0018622886],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0093668215,0.00080777874,0.00036732122,0.0012239278,0.0015357126,0.002873995,0.0017456756,0.0025555086,0.0024261002],"category_scores_gemma":[0.03272126,0.00033937732,0.00040651535,0.00035766177,0.0011182427,0.0027683778,0.003017711,0.0011269829,0.0005738633],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006356181,0.013685467,0.041353498,0.0013606837,0.0000632187,0.0019077375,0.039845094,0.0049229753,0.06146362,0.00533515,0.0018972667,0.82752967],"study_design_scores_gemma":[0.0016451336,0.052014574,0.27598688,0.003287576,0.00058961153,0.012249443,0.07666942,0.09349004,0.33378902,0.03655437,0.1130006,0.00072338467],"about_ca_topic_score_codex":0.00095663196,"about_ca_topic_score_gemma":0.0012596587,"teacher_disagreement_score":0.0093668215,"about_ca_system_score_codex":0.000725521,"about_ca_system_score_gemma":0.0022694934,"threshold_uncertainty_score":0.049537122},"labels":[],"label_agreement":null},{"id":"W4284711440","doi":"10.1108/qae-02-2022-0048","title":"Assuring online assessment quality: the case of unproctored online assessment","year":2022,"lang":"en","type":"article","venue":"Quality Assurance in Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Quality (philosophy); Quality assessment; Originality; Psychology; Alternative assessment; Online assessment; Higher education; Medical education; Mathematics education; Marketing; Social psychology; Political science; Formative assessment; Medicine; Business","score_opus":0.08445615915997876,"score_gpt":0.4978529657096593,"score_spread":0.4133968065496806,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4284711440","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9503308,0.0004736799,0.027394364,0.004827834,0.00017975176,0.00036727978,0.00007847008,0.00034960726,0.015998138],"genre_scores_gemma":[0.9918394,0.00008346406,0.0068293405,0.00025649255,0.00005051115,0.00008512307,0.000024065495,0.00003852086,0.00079296756],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.8820926,0.075155795,0.0071008997,0.004783666,0.02750519,0.0033618882],"domain_scores_gemma":[0.5721168,0.25630218,0.07077416,0.051949937,0.04052335,0.008333618],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.045592066,0.00040215693,0.0004702998,0.0016908242,0.0026657574,0.006604106,0.001956272,0.001403258,0.0019002018],"category_scores_gemma":[0.27287182,0.00045442482,0.0004849672,0.0017158623,0.0034879344,0.0053345934,0.004193322,0.0022890966,0.00046083474],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001091985,0.0011100813,0.26395255,0.0009637869,0.00014991072,0.004723723,0.12546773,0.0028256783,0.008014844,0.00685573,0.0046499767,0.58019406],"study_design_scores_gemma":[0.00024991774,0.0038764977,0.6007203,0.0039264425,0.000306902,0.012737037,0.197466,0.03935359,0.028719297,0.02266387,0.08947458,0.0005055752],"about_ca_topic_score_codex":0.004956134,"about_ca_topic_score_gemma":0.0052700755,"teacher_disagreement_score":0.045592066,"about_ca_system_score_codex":0.0038032148,"about_ca_system_score_gemma":0.005856992,"threshold_uncertainty_score":0.24111676},"labels":[],"label_agreement":null},{"id":"W4285051177","doi":"10.56498/21202092","title":"Genre-based Rubric for Peer Feedback","year":2020,"lang":"en","type":"article","venue":"Modern Journal of Studies in English Language Teaching and Literature","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Rubric; Argumentative; Peer feedback; Computer science; Peer assessment; Peer evaluation; Psychology; Mathematics education; Higher education; Linguistics; Political science","score_opus":0.038451028981926975,"score_gpt":0.3611125235187574,"score_spread":0.3226614945368304,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285051177","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.037168123,0.0061441935,0.73478615,0.004242513,0.008106616,0.024544608,0.0077743656,0.018448206,0.15878525],"genre_scores_gemma":[0.058343053,0.0019854836,0.87373716,0.001143986,0.00085323607,0.01928227,0.0043386417,0.0026092657,0.03770681],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.96149045,0.017401898,0.0054447176,0.0014953067,0.013473094,0.00069449947],"domain_scores_gemma":[0.9266659,0.022380559,0.0044549475,0.0077078235,0.036868334,0.00192251],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.020601405,0.0014857273,0.001284945,0.008461346,0.0021940742,0.0030147745,0.0021399793,0.0013422596,0.022947716],"category_scores_gemma":[0.08700616,0.0004322203,0.0011033072,0.0053558177,0.0015426178,0.0018388105,0.0035016928,0.0028125031,0.015160267],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00047091115,0.00040098146,0.0023039202,0.004202358,0.000043062235,0.00039641687,0.009616501,0.001173887,0.022842145,0.02064313,0.16734856,0.7705581],"study_design_scores_gemma":[0.00013314173,0.00071643124,0.011221307,0.0021081096,0.000052154373,0.0016014406,0.0037772537,0.0057937256,0.011572288,0.015147323,0.9476291,0.00024775902],"about_ca_topic_score_codex":0.0014799132,"about_ca_topic_score_gemma":0.002535631,"teacher_disagreement_score":0.022947716,"about_ca_system_score_codex":0.001954515,"about_ca_system_score_gemma":0.0044880332,"threshold_uncertainty_score":0.108951926},"labels":[],"label_agreement":null},{"id":"W4285677805","doi":"10.18733/cpi29639","title":"All that Glitters is not Gold: Culturally responsive online assessment and pedagogy in uncertain times","year":2022,"lang":"en","type":"article","venue":"Cultural and Pedagogical Inquiry","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of British Columbia; University of Calgary","funders":"","keywords":"Psychology; Pedagogy","score_opus":0.5267311310912989,"score_gpt":0.5478395655922317,"score_spread":0.021108434500932804,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285677805","genre_codex":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0049490267,0.0034964252,0.0029242674,0.8696216,0.079469554,0.00016375277,0.0001820752,0.00066445034,0.038528986],"genre_scores_gemma":[0.1545174,0.012756056,0.020346873,0.4370542,0.11595551,0.0018332128,0.0007035124,0.0025214597,0.25431177],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9734934,0.014479453,0.0014934236,0.0008384009,0.008185952,0.0015094159],"domain_scores_gemma":[0.82749647,0.107652284,0.00465324,0.0049020313,0.021274118,0.03402196],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.029042803,0.0005496494,0.0008449761,0.0012996664,0.011668376,0.019411772,0.0020283803,0.010728131,0.03368382],"category_scores_gemma":[0.13312954,0.00055902184,0.00051390653,0.0011543416,0.007638099,0.016552152,0.011698923,0.013452434,0.008744177],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026538612,0.000080309364,0.0005461265,0.00008439787,0.0000042729516,0.00011641153,0.004657285,0.000028078519,0.00009871835,0.004277961,0.9461034,0.043976486],"study_design_scores_gemma":[0.000018355016,0.00007151807,0.0024034746,0.00069427653,0.000009653411,0.00012955685,0.024515858,0.00016860408,0.00027330185,0.015038637,0.9565953,0.000081451566],"about_ca_topic_score_codex":0.0036455502,"about_ca_topic_score_gemma":0.01666222,"teacher_disagreement_score":0.03368382,"about_ca_system_score_codex":0.0031107645,"about_ca_system_score_gemma":0.011781352,"threshold_uncertainty_score":0.15359479},"labels":[],"label_agreement":null},{"id":"W4285723393","doi":"10.7202/1089053ar","title":"Toward the Consolidation of a Sociology of Classroom Assessment: A Narrative Review of the French-Language Literature","year":2020,"lang":"fr","type":"review","venue":"Mesure et évaluation en éducation","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Consolidation (business); Excellence; Sociology; Narrative; Presentation (obstetrics); Engineering ethics; Social science; Pedagogy; Political science; Linguistics; Engineering","score_opus":0.09067218176414672,"score_gpt":0.46036097831665657,"score_spread":0.36968879655250986,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4285723393","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0012739496,0.989287,0.0004439172,0.0062421034,0.00027670694,0.000012082742,0.000021370888,0.000005479821,0.0024373536],"genre_scores_gemma":[0.050494142,0.94305265,0.0012709785,0.0037019132,0.0006274785,0.00006638607,0.000050847957,0.000011309029,0.00072415895],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.990827,0.0063750083,0.00077968725,0.0005557828,0.0011458293,0.00031663067],"domain_scores_gemma":[0.95587695,0.037612997,0.0015713663,0.00043212902,0.0041523944,0.00035416268],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.014932188,0.0007388157,0.0013942217,0.011237596,0.001979679,0.0073972247,0.0010548738,0.0024030108,0.0015769438],"category_scores_gemma":[0.027223038,0.0003019716,0.00069964415,0.010825074,0.0034329807,0.005518127,0.0016511667,0.0022441372,0.00033508232],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013011131,0.000112143054,0.00249976,0.068781435,0.00032723456,0.001399717,0.03864998,0.0007830158,0.0012077155,0.12980792,0.038583886,0.71771705],"study_design_scores_gemma":[0.000013413764,0.00013853644,0.004721602,0.08902563,0.00021226489,0.0013501948,0.020216972,0.00020076243,0.00048188475,0.009206594,0.8743713,0.000060919167],"about_ca_topic_score_codex":0.017668415,"about_ca_topic_score_gemma":0.02534172,"teacher_disagreement_score":0.9850678,"about_ca_system_score_codex":0.008436779,"about_ca_system_score_gemma":0.015567249,"threshold_uncertainty_score":0.078969896},"labels":[],"label_agreement":null},{"id":"W4286213965","doi":"10.5296/ijssr.v10i2.19889","title":"Secondary School EFL Teachers’ Formative Assessment Practices and Their Impact on Learning","year":2022,"lang":"en","type":"article","venue":"International Journal of Social Science Research","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal","funders":"","keywords":"Formative assessment; Summative assessment; Psychology; Mathematics education; Strengths and weaknesses; Test (biology); Peer assessment; Medical education; The Internet; Pedagogy; Medicine; Computer science; Social psychology","score_opus":0.10155170101928927,"score_gpt":0.5545968960672434,"score_spread":0.4530451950479541,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4286213965","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9978109,0.00013799642,0.0001878619,0.000117220625,0.0000051715874,0.000015747495,0.000015216137,0.000010121461,0.0016998806],"genre_scores_gemma":[0.99836034,0.00013983632,0.00050576846,0.00004126311,0.0000054320576,0.00001881304,0.000019730775,0.000003267879,0.00090559205],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.996148,0.0017425718,0.00030210745,0.00035413032,0.001016889,0.00043632154],"domain_scores_gemma":[0.9859001,0.0062683066,0.002826588,0.0008914656,0.0030711277,0.0010424326],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0075039333,0.00035645053,0.00029122896,0.0012583319,0.0007571468,0.0027947049,0.0004935968,0.00044731714,0.0011847487],"category_scores_gemma":[0.017145045,0.0001549144,0.00025753773,0.0007094121,0.000900363,0.00096686254,0.001499777,0.00061068224,0.0002479992],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00036874952,0.0023492028,0.4778236,0.0005117322,0.000086038905,0.00068989675,0.108997524,0.0007932685,0.01107883,0.00074402866,0.0010101714,0.39554697],"study_design_scores_gemma":[0.00004046503,0.0020094116,0.9093102,0.00050053664,0.00006554826,0.00036582205,0.0630836,0.00077415805,0.009947859,0.00090810325,0.012934124,0.000060113758],"about_ca_topic_score_codex":0.0059333695,"about_ca_topic_score_gemma":0.008855797,"teacher_disagreement_score":0.0075039333,"about_ca_system_score_codex":0.0019463707,"about_ca_system_score_gemma":0.0018588852,"threshold_uncertainty_score":0.03968501},"labels":[],"label_agreement":null},{"id":"W4286390209","doi":"10.7202/1090461ar","title":"L’évaluation continue pour apprendre : enjeux de la pluralité des feedbacks entre pairs dans un cours universitaire","year":2021,"lang":"fr","type":"article","venue":"Mesure et évaluation en éducation","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Humanities; Political science; Sociology; Philosophy","score_opus":0.0497611882047252,"score_gpt":0.3633203714747588,"score_spread":0.3135591832700336,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4286390209","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9182743,0.001962267,0.039215423,0.0038055214,0.0004547148,0.0010338537,0.00014263774,0.00041642977,0.03469493],"genre_scores_gemma":[0.9625468,0.0004992512,0.02122404,0.0006131476,0.00009772944,0.0009233198,0.000096246215,0.00015623674,0.013843082],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.937944,0.043726686,0.0021509137,0.0040179244,0.01063726,0.0015232152],"domain_scores_gemma":[0.87684155,0.08199271,0.0071188463,0.007495399,0.020442821,0.0061086966],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.04137914,0.001005962,0.001477929,0.0016336379,0.0046020825,0.0072314795,0.0014014923,0.0019546482,0.0071310643],"category_scores_gemma":[0.12280625,0.00051701884,0.00079956034,0.0011446767,0.0030129377,0.004962014,0.006325816,0.002826947,0.0014001708],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0027990877,0.0016721912,0.03199158,0.0020133778,0.00022940905,0.00061355525,0.41971916,0.0012832327,0.02430006,0.013343729,0.005863291,0.49617127],"study_design_scores_gemma":[0.000760625,0.017993769,0.19809523,0.003757701,0.0006206078,0.0017284064,0.45101967,0.010496448,0.03996529,0.027926695,0.2467921,0.00084341463],"about_ca_topic_score_codex":0.0035787276,"about_ca_topic_score_gemma":0.0053242245,"teacher_disagreement_score":0.04137914,"about_ca_system_score_codex":0.0034682062,"about_ca_system_score_gemma":0.0056114546,"threshold_uncertainty_score":0.21883643},"labels":[],"label_agreement":null},{"id":"W4287658006","doi":"","title":"Guidelines for Generating Effective Feedback from E-Assessments","year":2020,"lang":"en","type":"article","venue":"DergiPark (Istanbul University)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Psychology","score_opus":0.08930957328236618,"score_gpt":0.36593272620510414,"score_spread":0.276623152922738,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4287658006","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021542452,0.0056742188,0.76794153,0.018817976,0.0016880194,0.058641054,0.0062341155,0.025436014,0.09402467],"genre_scores_gemma":[0.02579379,0.0019595083,0.9283605,0.0013321752,0.00014970286,0.022311363,0.0028323655,0.0008467869,0.016413804],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9035525,0.051188014,0.02077027,0.0017137239,0.020737635,0.002037868],"domain_scores_gemma":[0.7647234,0.09011,0.011193614,0.014366486,0.11526318,0.0043433076],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.06135189,0.0017855512,0.0013931732,0.007645125,0.0021842062,0.0055765132,0.0040998845,0.0052335165,0.01727516],"category_scores_gemma":[0.19783519,0.0015974483,0.0015248836,0.0034240203,0.0012284693,0.0035494214,0.003941505,0.003074266,0.02491032],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00051048904,0.001343985,0.0060072225,0.0038282713,0.00006665649,0.0010027225,0.0060951347,0.002053326,0.008565069,0.0072362744,0.13768664,0.82560426],"study_design_scores_gemma":[0.0009316416,0.0018221585,0.042137753,0.026180003,0.00032022892,0.0037957272,0.009684017,0.017576458,0.046370696,0.03181971,0.81880987,0.00055174204],"about_ca_topic_score_codex":0.005329887,"about_ca_topic_score_gemma":0.013205139,"teacher_disagreement_score":0.06135189,"about_ca_system_score_codex":0.002582412,"about_ca_system_score_gemma":0.012416368,"threshold_uncertainty_score":0.32446373},"labels":[],"label_agreement":null},{"id":"W4291926400","doi":"10.5539/elt.v15n9p9","title":"The Impact of Peer Feedback on Chinese EFL Junior High School Students’ Writing Performance","year":2022,"lang":"en","type":"article","venue":"English Language Teaching","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Peer feedback; Formative assessment; Psychology; Corrective feedback; Mathematics education; Class (philosophy); Grammar; Pedagogy; Computer science","score_opus":0.010141569157979632,"score_gpt":0.3475321059387549,"score_spread":0.33739053678077524,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4291926400","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9992238,0.000048145055,0.000031730393,0.00003397156,0.000005754501,0.000014558256,0.0000062761587,0.000004694211,0.0006310802],"genre_scores_gemma":[0.9995741,0.000036622867,0.00006681198,0.000010189647,0.0000047342523,0.000012173784,0.000009769363,0.0000013123484,0.00028416206],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9972475,0.0010567755,0.0002311375,0.00022935146,0.00087773794,0.0003575175],"domain_scores_gemma":[0.98776066,0.004418276,0.0021121337,0.0005724842,0.0025266912,0.0026097302],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0024334188,0.00037442672,0.0003831747,0.00067037385,0.0008882517,0.00077492965,0.00032713084,0.00030889033,0.0015514443],"category_scores_gemma":[0.015087025,0.00010738674,0.000414648,0.00027774693,0.0004059273,0.00032725531,0.00086081825,0.00039435847,0.00019967886],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011839111,0.0062515726,0.74252975,0.0003578658,0.00021610915,0.0009677326,0.024440799,0.00045668005,0.015817199,0.00015150377,0.0010229056,0.20660393],"study_design_scores_gemma":[0.000036753747,0.002055709,0.98653686,0.00004948333,0.00010521346,0.00012433251,0.007135872,0.0006656951,0.0025094815,0.000047214577,0.0007041237,0.000029267227],"about_ca_topic_score_codex":0.004649215,"about_ca_topic_score_gemma":0.0058216127,"teacher_disagreement_score":0.004649215,"about_ca_system_score_codex":0.00044778897,"about_ca_system_score_gemma":0.00094304176,"threshold_uncertainty_score":0.012869298},"labels":[],"label_agreement":null},{"id":"W4292230213","doi":"10.32329/uad.992521","title":"Curriculum Evaluation in Higher Education: Examples from Australia, Canada, The United Kingdom, and the United StatesCurriculum Evaluation in Higher Education: Comparative Analysis of Some Practices from Australia, Canada, the United Kingdom, and the United States","year":2021,"lang":"en","type":"article","venue":"DergiPark (Istanbul University)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Kingdom; Curriculum; Political science; Public administration; Library science; Law; Computer science","score_opus":0.1556669228352931,"score_gpt":0.37538849787615597,"score_spread":0.21972157504086287,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4292230213","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9340517,0.023190359,0.0019478236,0.0049570217,0.00011300299,0.00081530627,0.00038525788,0.00007102799,0.03446858],"genre_scores_gemma":[0.9821389,0.007859702,0.0032058258,0.00070263183,0.000017803197,0.00017452035,0.00024890003,0.00003525346,0.00561657],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9829317,0.0074684336,0.0010088667,0.0005710881,0.0054886164,0.0025313983],"domain_scores_gemma":[0.93818444,0.017749107,0.0029368128,0.0016815601,0.030486967,0.008961161],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.018995129,0.0002756686,0.00059122324,0.004602205,0.006253524,0.0036671583,0.0008631706,0.0007666182,0.0016238906],"category_scores_gemma":[0.029652262,0.00034472483,0.00035778712,0.013088986,0.0030221404,0.0013295227,0.004231499,0.0009989071,0.00017225461],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005598945,0.000863088,0.22500883,0.004802844,0.0001273322,0.00082964054,0.13532436,0.0018412595,0.0017375912,0.00980541,0.017513577,0.6015861],"study_design_scores_gemma":[0.00006344173,0.0003469949,0.7993399,0.0025021748,0.000075536685,0.00035441475,0.107789196,0.0007341981,0.002062962,0.0006053791,0.086005665,0.00012006985],"about_ca_topic_score_codex":0.78283954,"about_ca_topic_score_gemma":0.9205248,"teacher_disagreement_score":0.21716046,"about_ca_system_score_codex":0.053237002,"about_ca_system_score_gemma":0.097501665,"threshold_uncertainty_score":0.43687868},"labels":[],"label_agreement":null},{"id":"W4292772413","doi":"10.3102/1443120","title":"Large-Scale Assessment in Mathematics: The Relationship Between Teachers' Views and Classroom Practice","year":2019,"lang":"en","type":"article","venue":"Proceedings of the 2019 AERA Annual Meeting","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Scale (ratio); Mathematics education; Computer science; Mathematics; Geography","score_opus":0.031363479234160864,"score_gpt":0.354898228618803,"score_spread":0.3235347493846421,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4292772413","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98929465,0.00024924235,0.0011444786,0.001399806,0.000018151046,0.000047961123,0.000038674367,0.000009863631,0.007797237],"genre_scores_gemma":[0.99816954,0.0001311012,0.0002390402,0.00011149601,0.0000038459575,0.000027638498,0.000011132129,0.0000066340745,0.0012995887],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.98541266,0.01002577,0.00045985443,0.00069555716,0.0025246919,0.0008814511],"domain_scores_gemma":[0.96731555,0.023401277,0.0029777442,0.0009300093,0.0032952328,0.0020802643],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009133505,0.00023272389,0.00045065163,0.0012902202,0.0047975546,0.003962325,0.0010663834,0.0007767629,0.0020390558],"category_scores_gemma":[0.029869596,0.00039451147,0.0002112032,0.0011194198,0.007884439,0.0019390797,0.003861769,0.0016519703,0.00021086859],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000015945367,0.000020714197,0.010598515,0.000042669202,0.0000028928216,0.00024351153,0.9841366,0.000024828865,0.0005343826,0.00049330015,0.00017402785,0.0037125922],"study_design_scores_gemma":[0.000002978806,0.000028705708,0.010776368,0.00007314527,0.000003103367,0.00013844731,0.9831572,0.00006897789,0.0001778903,0.0001939463,0.0053662024,0.000012944885],"about_ca_topic_score_codex":0.091519676,"about_ca_topic_score_gemma":0.14420103,"teacher_disagreement_score":0.091519676,"about_ca_system_score_codex":0.007448313,"about_ca_system_score_gemma":0.0069893915,"threshold_uncertainty_score":0.18197393},"labels":[],"label_agreement":null},{"id":"W4292841507","doi":"10.3102/1430052","title":"Fairness of Teachers' Grading Practices and Decisions in Canadian and Chinese Secondary Schools","year":2019,"lang":"en","type":"article","venue":"Proceedings of the 2019 AERA Annual Meeting","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Queen's University","funders":"","keywords":"Grading (engineering); Computer science; Mathematics education; Psychology; Engineering","score_opus":0.011611069291201292,"score_gpt":0.31345446260978127,"score_spread":0.30184339331857996,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4292841507","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9856792,0.0002575537,0.00031771837,0.0010169431,0.000045927245,0.00005413338,0.00025125564,0.00002743001,0.012349835],"genre_scores_gemma":[0.9978472,0.0000303994,0.000113781454,0.000040494375,0.000004679008,0.000008143191,0.000055461638,0.0000048922257,0.0018948923],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.97380865,0.0053888503,0.0015641722,0.002356057,0.010844526,0.0060377303],"domain_scores_gemma":[0.9145716,0.025815807,0.008730016,0.004270234,0.036627978,0.009984357],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.022837687,0.00026849846,0.0009427318,0.0040640924,0.010295387,0.005152645,0.0024096807,0.0010209724,0.0028117101],"category_scores_gemma":[0.08692184,0.0003218456,0.00046263135,0.0055947006,0.0044746376,0.00095614727,0.0023513238,0.0013484984,0.0003136984],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0020039782,0.00032419397,0.76516837,0.00014900873,0.00014649,0.00038685693,0.115333155,0.002111387,0.001160401,0.014963394,0.013204119,0.08504862],"study_design_scores_gemma":[0.00005148321,0.000089265115,0.9639131,0.00005922286,0.000050492683,0.00003151349,0.026064223,0.0016252773,0.00071244815,0.0017220854,0.0055893078,0.00009148146],"about_ca_topic_score_codex":0.94372445,"about_ca_topic_score_gemma":0.97002226,"teacher_disagreement_score":0.057564612,"about_ca_system_score_codex":0.057564612,"about_ca_system_score_gemma":0.08977705,"threshold_uncertainty_score":0.4176625},"labels":[],"label_agreement":null},{"id":"W4292847067","doi":"10.3102/1446397","title":"Building Preservice Elementary Teachers' Capacity in Authentic Assessment Through Problem-Based Learning","year":2019,"lang":"en","type":"article","venue":"Proceedings of the 2019 AERA Annual Meeting","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Mathematics education; Computer science; Psychology","score_opus":0.01866985797117298,"score_gpt":0.309482046371426,"score_spread":0.290812188400253,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4292847067","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97105837,0.00016001343,0.015902262,0.0005488426,0.00001083723,0.00027748136,0.000027682967,0.00015439157,0.011860055],"genre_scores_gemma":[0.9861834,0.00010039244,0.012427624,0.0000671841,0.000002754918,0.00014732787,0.000021031803,0.000008838416,0.0010414978],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9939936,0.003563608,0.00033582616,0.0005684949,0.0010612559,0.0004773403],"domain_scores_gemma":[0.9655582,0.018269366,0.0028765725,0.006250631,0.004393756,0.0026515902],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010672783,0.00023264822,0.00031092038,0.0008956118,0.00096071936,0.004074713,0.0010131834,0.0007061202,0.0015857145],"category_scores_gemma":[0.035675425,0.00038053788,0.00025020298,0.00023154751,0.0017458777,0.0025697676,0.0064363484,0.0013412545,0.00062565465],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027909054,0.00473745,0.20215563,0.0007888498,0.000059351292,0.0006436869,0.20344539,0.0031775823,0.034671083,0.010749764,0.0051958333,0.5340963],"study_design_scores_gemma":[0.0004029925,0.006169559,0.3854199,0.0027632196,0.00018661376,0.0035530473,0.25835624,0.019688277,0.091237135,0.04101261,0.19085634,0.00035406585],"about_ca_topic_score_codex":0.0008109203,"about_ca_topic_score_gemma":0.0013944807,"teacher_disagreement_score":0.010672783,"about_ca_system_score_codex":0.00070515886,"about_ca_system_score_gemma":0.0036650489,"threshold_uncertainty_score":0.05644369},"labels":[],"label_agreement":null},{"id":"W4293420146","doi":"10.1111/medu.14932","title":"‘For the most part it works’: Exploring how authors navigate peer review feedback","year":2022,"lang":"en","type":"article","venue":"Medical Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Western University","funders":"","keywords":"Credibility; Context (archaeology); Autonomy; Process (computing); Peer feedback; Peer review; Consistency (knowledge bases); Psychology; Grounded theory; Social psychology; Knowledge management; Public relations; Computer science; Qualitative research; Pedagogy; Sociology; Political science","score_opus":0.10468164831843134,"score_gpt":0.4169217140655558,"score_spread":0.31224006574712443,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4293420146","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":"methods","domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.76931024,0.00893329,0.10790017,0.07062332,0.0015602112,0.0019190887,0.0001246422,0.00094178994,0.0386871],"genre_scores_gemma":[0.95851564,0.0018208354,0.031671748,0.004256211,0.00027165358,0.00062253856,0.000051595915,0.0002467386,0.0025430464],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.45446676,0.48682693,0.013616857,0.0073342077,0.031774495,0.0059808525],"domain_scores_gemma":[0.28650904,0.5710113,0.040042568,0.018086651,0.07173362,0.012616852],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.26938695,0.0010405995,0.001463321,0.0056553856,0.018188963,0.032940485,0.0054102736,0.008135802,0.0017484715],"category_scores_gemma":[0.5759722,0.001249932,0.001280751,0.0037087167,0.025709461,0.026237825,0.014500622,0.0082765315,0.0010665389],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006248764,0.00004899171,0.006219899,0.0005906379,0.00003980765,0.0005330417,0.94964874,0.00018884972,0.000633417,0.004056371,0.0020375357,0.03594029],"study_design_scores_gemma":[0.0000697724,0.0004610498,0.0041590044,0.0020806785,0.000097869284,0.001530266,0.8923058,0.0015080163,0.0011688825,0.020290673,0.07609578,0.00023220612],"about_ca_topic_score_codex":0.0042237327,"about_ca_topic_score_gemma":0.006732137,"teacher_disagreement_score":0.73061305,"about_ca_system_score_codex":0.011020933,"about_ca_system_score_gemma":0.03247892,"threshold_uncertainty_score":0.90097594},"labels":[],"label_agreement":null},{"id":"W4297236988","doi":"10.5430/wjel.v12n8p49","title":"Review of Formative Assessment Practices: Primary Evidence on Relationship with Self-efficacy and Self-esteem","year":2022,"lang":"en","type":"article","venue":"World Journal of English Language","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Formative assessment; Psychology; Self-efficacy; Mathematics education; Variation (astronomy); Self-esteem; Knowledge survey; Social psychology; Summative assessment","score_opus":0.035515425108625806,"score_gpt":0.3701219538905678,"score_spread":0.33460652878194197,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4297236988","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0023125855,0.995538,0.0004560737,0.0005542672,0.00023603321,0.000104914856,0.0001838332,0.000013342854,0.0006010197],"genre_scores_gemma":[0.02299545,0.9743601,0.0013749657,0.00051120576,0.00019110946,0.00019832216,0.00019811782,0.000012544714,0.00015823811],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.97813076,0.0074795955,0.0067429086,0.0012420584,0.006175653,0.00022903609],"domain_scores_gemma":[0.69618696,0.2512272,0.02565607,0.0036520676,0.02227151,0.0010062633],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.022942863,0.0008911994,0.003436402,0.010114062,0.00053360435,0.0029950335,0.0021266341,0.0013923873,0.002206555],"category_scores_gemma":[0.17854814,0.000679634,0.002636931,0.010741875,0.0011005879,0.0022052526,0.0011057957,0.0011095485,0.00043802054],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029447,0.00009484668,0.004920642,0.4745248,0.003999374,0.00017353744,0.0010360812,0.00020880581,0.0005363155,0.00061909057,0.005438549,0.50815344],"study_design_scores_gemma":[0.00016345913,0.0006438391,0.033113003,0.8474733,0.016719995,0.001297188,0.0012492691,0.00017435715,0.001284463,0.0011293312,0.09666827,0.00008345443],"about_ca_topic_score_codex":0.003812505,"about_ca_topic_score_gemma":0.009892584,"teacher_disagreement_score":0.022942863,"about_ca_system_score_codex":0.0019296318,"about_ca_system_score_gemma":0.00804213,"threshold_uncertainty_score":0.12133485},"labels":[],"label_agreement":null},{"id":"W4301180890","doi":"10.21203/rs.3.rs-1942986/v2","title":"Improving the Effectiveness of Teacher Assessment in Higher Education: A Case Study of Professors’ Perceptions in Morocco","year":2022,"lang":"en","type":"preprint","venue":"Research Square","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Montréal; Université du Québec en Outaouais","funders":"","keywords":"Apprehension; Strengths and weaknesses; Perception; Psychology; Higher education; Anxiety; Medical education; Process (computing); Pedagogy; Political science; Medicine; Social psychology","score_opus":0.15942425412388184,"score_gpt":0.5378363459027331,"score_spread":0.37841209177885127,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4301180890","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9987795,0.00006244362,0.00006948268,0.00030435654,0.0000048730935,0.000013517471,0.000003604946,0.0000021397682,0.0007600932],"genre_scores_gemma":[0.99952435,0.000036159134,0.00011093518,0.000036403617,0.0000027166072,0.000004913851,0.0000018111319,0.000001191686,0.0002815758],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99305904,0.00478674,0.0001643328,0.00025486393,0.00058357354,0.0011514726],"domain_scores_gemma":[0.98586977,0.008307509,0.0013230109,0.0003571896,0.0019892761,0.002153302],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008429402,0.00026387355,0.00031943954,0.000790245,0.0055404087,0.0023700385,0.000761039,0.0009387486,0.0016612398],"category_scores_gemma":[0.0151196895,0.00017686584,0.00017589779,0.0007311719,0.0017900271,0.00083662744,0.002042791,0.0010930992,0.00015611612],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00046269633,0.0019667766,0.23715565,0.00033962016,0.000040377454,0.0053137364,0.6748334,0.00075239025,0.0066061933,0.0016282944,0.0013426974,0.069558136],"study_design_scores_gemma":[0.000042402888,0.0014739158,0.33485863,0.00021463375,0.000059368536,0.0007331165,0.6451196,0.0011617151,0.0031879845,0.00023950714,0.012858745,0.000050420946],"about_ca_topic_score_codex":0.043884415,"about_ca_topic_score_gemma":0.085022874,"teacher_disagreement_score":0.043884415,"about_ca_system_score_codex":0.0074965823,"about_ca_system_score_gemma":0.005913129,"threshold_uncertainty_score":0.08725798},"labels":[],"label_agreement":null},{"id":"W4303833150","doi":"10.3390/logistics6040070","title":"Student-Centered Curriculum Design and Evaluation in Logistics Management","year":2022,"lang":"en","type":"article","venue":"Logistics","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Curriculum; Constructive; Plan (archaeology); Logistics management; Conceptual framework; Engineering ethics; Computer science; Mathematics education; Knowledge management; Sociology; Engineering management; Process management; Pedagogy; Engineering; Psychology; Process (computing)","score_opus":0.10667085788631406,"score_gpt":0.40068361902944344,"score_spread":0.29401276114312935,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4303833150","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21326806,0.0035726489,0.7225035,0.011353849,0.000806534,0.0068432586,0.00015593783,0.0006543257,0.040841926],"genre_scores_gemma":[0.61697125,0.0010477172,0.37207037,0.0011015416,0.00010897819,0.0050349403,0.00010442249,0.0001232656,0.0034375004],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.79031765,0.18190248,0.008246115,0.0025988936,0.0152902575,0.0016446415],"domain_scores_gemma":[0.76477796,0.16458035,0.012858378,0.011289821,0.042191986,0.0043014344],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.14525874,0.00048740883,0.00071770995,0.0019211503,0.0013224385,0.00606391,0.0017278049,0.0016096507,0.0029084259],"category_scores_gemma":[0.1772832,0.00031566012,0.00061008683,0.001577052,0.003959839,0.0027323752,0.0030587472,0.0018624698,0.00060391624],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00041559624,0.0021142194,0.02265052,0.003214203,0.00017348495,0.00017751167,0.03271004,0.0071985293,0.0030935726,0.08493524,0.009683701,0.83363336],"study_design_scores_gemma":[0.0016415588,0.015930697,0.05879921,0.01185943,0.0006809067,0.0013279221,0.056537382,0.095515616,0.09522978,0.3203586,0.34170654,0.0004123497],"about_ca_topic_score_codex":0.00057852495,"about_ca_topic_score_gemma":0.0008816763,"teacher_disagreement_score":0.14525874,"about_ca_system_score_codex":0.0047200806,"about_ca_system_score_gemma":0.010042215,"threshold_uncertainty_score":0.7682108},"labels":[],"label_agreement":null},{"id":"W4304693611","doi":"10.1097/acm.0000000000005013","title":"The Case for Feedback-in-Practice as a Topic of Educational Scholarship","year":2022,"lang":"en","type":"article","venue":"Academic Medicine","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Scholarship; Higher education; Sociology; Medical education; Psychology; Pedagogy; Medicine; Political science","score_opus":0.058813945386953254,"score_gpt":0.45603152081014,"score_spread":0.3972175754231867,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4304693611","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.009549476,0.08579164,0.051379748,0.74927694,0.01248138,0.00014552826,0.000047871097,0.00028140142,0.091046],"genre_scores_gemma":[0.71777576,0.0644916,0.057006195,0.11595426,0.025666244,0.0009613949,0.000085327265,0.0008746207,0.017184569],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8573586,0.10601485,0.0047685066,0.008352767,0.01769698,0.005808313],"domain_scores_gemma":[0.7121608,0.23015107,0.0078756185,0.024242291,0.01349226,0.012077792],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.11215393,0.0013231176,0.0024255326,0.008943671,0.015690558,0.04287988,0.007169628,0.03179173,0.0066787973],"category_scores_gemma":[0.1362349,0.001089028,0.002049012,0.006475986,0.16135286,0.07225972,0.033232443,0.039470803,0.0016273871],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000025610214,0.0000516083,0.00032221983,0.00045122256,0.0000090607045,0.00029934736,0.04992591,0.000119853124,0.00007697325,0.9180981,0.006907416,0.023712603],"study_design_scores_gemma":[0.00002765351,0.0000763862,0.00031275465,0.0033926736,0.000011622809,0.00070092274,0.03523542,0.00048770537,0.00016993744,0.7217336,0.23779488,0.00005645783],"about_ca_topic_score_codex":0.004363188,"about_ca_topic_score_gemma":0.00333552,"teacher_disagreement_score":0.11215393,"about_ca_system_score_codex":0.018572913,"about_ca_system_score_gemma":0.028126378,"threshold_uncertainty_score":0.5931338},"labels":[],"label_agreement":null},{"id":"W4308121603","doi":"10.3390/jrfm15110503","title":"Students’ Perception of the Use of a Rubric and Peer Reviews in an Online Learning Environment","year":2022,"lang":"en","type":"article","venue":"Journal of risk and financial management","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":39,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Rubric; Peer assessment; Summative assessment; Grading (engineering); Likert scale; Writing assessment; Peer feedback; Psychology; Computer science; Mathematics education; Medical education; Formative assessment; Engineering; Medicine","score_opus":0.04913201276311174,"score_gpt":0.31686616042821814,"score_spread":0.2677341476651064,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4308121603","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9947465,0.00016915977,0.0013432688,0.00058947614,0.00003593577,0.000091029724,0.000016684184,0.000037332025,0.0029705754],"genre_scores_gemma":[0.9969723,0.00015515745,0.001306877,0.0001530484,0.000013590569,0.00005761531,0.000016584538,0.000011496783,0.0013132169],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9802153,0.009915019,0.0016011907,0.0007874541,0.006211967,0.0012690112],"domain_scores_gemma":[0.9404902,0.027385246,0.009523225,0.0017850904,0.012175211,0.008641063],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012189498,0.00036387492,0.0006665152,0.0011878053,0.001568846,0.004378082,0.0008611238,0.0011601924,0.0025017885],"category_scores_gemma":[0.05850622,0.00029320733,0.0005445228,0.0007526639,0.0012742347,0.0019162137,0.0021231389,0.0015967846,0.00074551126],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00080248987,0.0036557205,0.33597168,0.001506709,0.00017284144,0.002561481,0.37201473,0.0017192098,0.023406781,0.0021246138,0.005503101,0.25056064],"study_design_scores_gemma":[0.00015117742,0.009009233,0.42714623,0.0009195576,0.00016748575,0.0029199729,0.48655015,0.007693155,0.00984218,0.0019891094,0.052960075,0.0006515862],"about_ca_topic_score_codex":0.0016078386,"about_ca_topic_score_gemma":0.001924994,"teacher_disagreement_score":0.012189498,"about_ca_system_score_codex":0.0010496746,"about_ca_system_score_gemma":0.0020314637,"threshold_uncertainty_score":0.06446499},"labels":[],"label_agreement":null},{"id":"W4308198949","doi":"10.1177/00224871221130742","title":"Teachers’ Conceptions of Fairness in Classroom Assessment: An Empirical Study","year":2022,"lang":"en","type":"article","venue":"Journal of Teacher Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":23,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Equity (law); Psychology; Dialectic; Pedagogy; Empirical research; Mathematics education; Social psychology; Epistemology; Political science","score_opus":0.05846958575669899,"score_gpt":0.4690927883659702,"score_spread":0.4106232026092712,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4308198949","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9957968,0.00014096331,0.0014767153,0.00034455617,0.000007493073,0.00004639181,0.0000058297646,0.0000030606159,0.0021781926],"genre_scores_gemma":[0.99900216,0.00009899353,0.00047338958,0.00005687025,0.0000041772337,0.00003472535,0.0000030589345,0.000002775328,0.0003237708],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.96159095,0.025896471,0.002005635,0.0019144837,0.0064173825,0.002175058],"domain_scores_gemma":[0.880478,0.09430186,0.010227358,0.0041884743,0.008172731,0.0026316727],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03814423,0.00029854392,0.0008609453,0.0020009342,0.0077965586,0.006553341,0.0015687571,0.0013625342,0.0014002783],"category_scores_gemma":[0.08227644,0.00095621776,0.00029626937,0.0014907526,0.010799971,0.0053349705,0.0051029813,0.0045558284,0.00018325612],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000054274657,0.00040453384,0.05567725,0.000071901755,0.000007744068,0.00028766823,0.9298527,0.00008518277,0.0006313895,0.0028019839,0.00015705312,0.009968206],"study_design_scores_gemma":[0.000023116587,0.00016512576,0.040246226,0.00020773365,0.000012602729,0.00041435956,0.95005614,0.0005806435,0.0008034102,0.0016549828,0.005802352,0.000033396376],"about_ca_topic_score_codex":0.008927038,"about_ca_topic_score_gemma":0.012659167,"teacher_disagreement_score":0.03814423,"about_ca_system_score_codex":0.0056292103,"about_ca_system_score_gemma":0.0068225106,"threshold_uncertainty_score":0.2017284},"labels":[],"label_agreement":null},{"id":"W4309546005","doi":"10.53967/cje-rce.5515","title":"A Course or a Pathway? Addressing French as a Second Language Teacher Recruitment and Retention in Canadian BEd Programs","year":2022,"lang":"en","type":"article","venue":"Canadian Journal of Education / Revue canadienne de l éducation","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of New Brunswick; University of British Columbia; University of Ottawa","funders":"","keywords":"Practicum; Certification; Graduation (instrument); Teacher education; Professional development; Pedagogy; Medical education; Alternative teacher certification; Psychology; Public relations; Political science; Engineering; Medicine","score_opus":0.11541611075203806,"score_gpt":0.3692933403736302,"score_spread":0.25387722962159215,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4309546005","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95304024,0.0012598421,0.0012796682,0.030353379,0.00015349305,0.0004176954,0.00015716885,0.00006550292,0.013272991],"genre_scores_gemma":[0.9914471,0.0008835161,0.0022302526,0.00217341,0.000021782811,0.00013938667,0.00009408627,0.000017374923,0.002993097],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.9855349,0.0040199496,0.0003574628,0.0006353864,0.0032554546,0.0061967643],"domain_scores_gemma":[0.9666571,0.007277779,0.0026173082,0.0007161804,0.011827452,0.010904151],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01968231,0.00022803461,0.00044009642,0.0024947003,0.01698125,0.0081063425,0.0039725676,0.0018844608,0.0029545606],"category_scores_gemma":[0.042291604,0.0004394358,0.00030786457,0.003625938,0.004747765,0.003022784,0.0056611346,0.0024731972,0.00016681223],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023527733,0.00063294545,0.34047553,0.00086615415,0.000031738065,0.0020591603,0.36581126,0.00042052305,0.0022872481,0.01345674,0.018456528,0.2552669],"study_design_scores_gemma":[0.00002187426,0.00033238792,0.20681372,0.001072946,0.00003363087,0.0004419769,0.7189306,0.0007712311,0.0012690191,0.0012400952,0.06897966,0.00009278664],"about_ca_topic_score_codex":0.9300022,"about_ca_topic_score_gemma":0.97829014,"teacher_disagreement_score":0.92334926,"about_ca_system_score_codex":0.07665074,"about_ca_system_score_gemma":0.25094053,"threshold_uncertainty_score":0.5561426},"labels":[],"label_agreement":null},{"id":"W4310224264","doi":"10.5430/wjel.v12n7p284","title":"Exploring L2 Written Corrective Feedback in the Saudi Context: A Critical Review","year":2022,"lang":"en","type":"review","venue":"World Journal of English Language","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Scope (computer science); Context (archaeology); Corrective feedback; Diversity (politics); Computer science; Function (biology); Psychology; Knowledge management; Mathematics education; Political science","score_opus":0.14835845779168574,"score_gpt":0.4052358743294563,"score_spread":0.2568774165377705,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4310224264","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.002373694,0.99210113,0.00085322367,0.0021102824,0.0007862897,0.00077643903,0.00007819327,0.000010085218,0.00091058016],"genre_scores_gemma":[0.029658895,0.96331656,0.0034372583,0.0016087138,0.00035595847,0.0011336302,0.00009902792,0.000011159111,0.00037867832],"study_design_codex":"systematic_review","study_design_gemma":"not_applicable","domain_scores_codex":[0.9809585,0.008081593,0.005691701,0.0007797616,0.004187103,0.0003013656],"domain_scores_gemma":[0.87320954,0.086169876,0.0104594035,0.0020385014,0.02733409,0.0007885762],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.031154744,0.0010065914,0.0021542616,0.011845221,0.0015528536,0.00338707,0.0018424084,0.0020678304,0.0016979794],"category_scores_gemma":[0.10214811,0.0006665604,0.0020245095,0.008776267,0.0019904901,0.0030395745,0.0015595722,0.001597059,0.0003171627],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026105918,0.00010359093,0.0022307697,0.5461604,0.0013302442,0.0008382376,0.00622512,0.00024651698,0.0010562567,0.0025272614,0.0074654217,0.4315551],"study_design_scores_gemma":[0.00008349202,0.0005110654,0.0067015914,0.79395074,0.0051320074,0.001417822,0.0074682483,0.00023480205,0.0013787665,0.001318238,0.18170206,0.000101171216],"about_ca_topic_score_codex":0.0060538994,"about_ca_topic_score_gemma":0.019390464,"teacher_disagreement_score":0.031154744,"about_ca_system_score_codex":0.004322338,"about_ca_system_score_gemma":0.025840657,"threshold_uncertainty_score":0.16476399},"labels":[],"label_agreement":null},{"id":"W4310243809","doi":"10.5430/wjel.v13n1p121","title":"Investigating Saudi EFL University Teachers' Knowledge in Adopting Learning-Oriented Assessment","year":2022,"lang":"en","type":"article","venue":"World Journal of English Language","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Competence (human resources); English as a foreign language; Mathematics education; Psychology; Foreign language; Medical education; Computer science; Medicine","score_opus":0.01518739486911758,"score_gpt":0.3115365173234899,"score_spread":0.29634912245437234,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4310243809","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9979108,0.00019023684,0.00019884887,0.00024095044,0.00000457521,0.000010888939,0.0000070097467,0.0000021797823,0.0014347066],"genre_scores_gemma":[0.99901533,0.00020768729,0.00023677907,0.00007989385,0.0000021527585,0.0000049134524,0.000008912977,7.221408e-7,0.00044358388],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99778974,0.0006379166,0.00024976386,0.00012690717,0.0009349858,0.00026055434],"domain_scores_gemma":[0.98644036,0.004371044,0.0035482463,0.00059315976,0.0041351514,0.00091205054],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004828445,0.00014554289,0.00021509232,0.0006924051,0.00080248306,0.0016626829,0.00035100282,0.0005495174,0.0011121088],"category_scores_gemma":[0.014819844,0.00018057694,0.00021284248,0.00046756887,0.0007485075,0.0011982333,0.00083396427,0.00056732487,0.00023342835],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010784204,0.00050481106,0.7825307,0.00035856513,0.00002806949,0.00047289766,0.13806589,0.00025387574,0.0051602344,0.00074195414,0.00043971196,0.07133536],"study_design_scores_gemma":[0.000020995181,0.0007695602,0.75842136,0.00051760493,0.0000580573,0.0010104618,0.22174032,0.0013159027,0.003531973,0.00075921684,0.011781246,0.00007329087],"about_ca_topic_score_codex":0.0093892235,"about_ca_topic_score_gemma":0.011648163,"teacher_disagreement_score":0.0093892235,"about_ca_system_score_codex":0.00090993376,"about_ca_system_score_gemma":0.0024481122,"threshold_uncertainty_score":0.025535524},"labels":[],"label_agreement":null},{"id":"W4311636586","doi":"10.3390/higheredu1010002","title":"Improving Student Feedback Literacy in e-Assessments: A Framework for the Higher Education Context","year":2022,"lang":"en","type":"article","venue":"Trends in Higher Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Context (archaeology); Digital literacy; Literacy; Computer science; Process (computing); Formative assessment; Mathematics education; Psychology; Knowledge management; Pedagogy; World Wide Web","score_opus":0.06443909059896195,"score_gpt":0.45411602562832754,"score_spread":0.38967693502936557,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4311636586","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07341651,0.0056974837,0.7069831,0.05670401,0.00051772664,0.0011651862,0.00023880934,0.0007641994,0.15451294],"genre_scores_gemma":[0.7776207,0.0015357562,0.21411727,0.00085302145,0.000105422965,0.0008972556,0.00008975461,0.00006649203,0.0047144024],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98291117,0.0124128135,0.0008554624,0.0011125526,0.0019707682,0.0007373263],"domain_scores_gemma":[0.9839395,0.009512569,0.0011284256,0.0008977493,0.0029473174,0.0015745326],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.016313815,0.0010689858,0.0005401601,0.004914907,0.002994423,0.011286936,0.0022243042,0.0034155503,0.0027516754],"category_scores_gemma":[0.0201255,0.00054978486,0.0009518521,0.002626059,0.016882878,0.010660806,0.0066200853,0.003197078,0.0004860089],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000031416857,0.00036895153,0.0081752855,0.00053152896,0.000023689281,0.0003763584,0.044957053,0.0022375695,0.0008241129,0.8806373,0.0019395229,0.059897326],"study_design_scores_gemma":[0.0000628934,0.00036283614,0.011751516,0.003496648,0.0001008746,0.00086073996,0.070701934,0.029198974,0.0018549656,0.74631745,0.13512056,0.00017068749],"about_ca_topic_score_codex":0.008601679,"about_ca_topic_score_gemma":0.0098445425,"teacher_disagreement_score":0.9836862,"about_ca_system_score_codex":0.007981301,"about_ca_system_score_gemma":0.011147709,"threshold_uncertainty_score":0.08627677},"labels":[],"label_agreement":null},{"id":"W4311788816","doi":"10.3389/fpsyg.2022.1047323","title":"Chinese university students’ conceptions of feedback and the relationships with self-regulated learning, self-efficacy, and English language achievement","year":2022,"lang":"en","type":"article","venue":"Frontiers in Psychology","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":32,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Social Sciences and Humanities Research Council of Canada; Queen's University","keywords":"Formative assessment; Psychology; Mathematics education; Self-efficacy; Self-regulated learning; Context (archaeology); Peer feedback; Test (biology); Curriculum; Language proficiency; English language; Pedagogy; Social psychology","score_opus":0.010369725976700606,"score_gpt":0.30234627433970623,"score_spread":0.29197654836300563,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4311788816","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9996088,0.00003621237,0.000030749485,0.000025773583,0.0000011100011,0.000003621967,0.0000068412814,9.841157e-7,0.00028598972],"genre_scores_gemma":[0.9997645,0.000038784205,0.000028841854,0.000010492373,0.000001121276,0.0000040780483,0.000014822804,3.2679827e-7,0.00013714207],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99926716,0.00016562764,0.000095748925,0.00007913617,0.00025392012,0.0001383265],"domain_scores_gemma":[0.9967114,0.00091666693,0.0010924189,0.00014176825,0.00046395225,0.0006738232],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0018522103,0.00030180984,0.0002606383,0.0013444423,0.0010981681,0.0014295514,0.00029686795,0.00041447632,0.0010272866],"category_scores_gemma":[0.0036260241,0.00021681491,0.00037314158,0.0007673468,0.0011062747,0.0004884355,0.0007439474,0.0005003459,0.000083960724],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000043127282,0.00014897008,0.9761801,0.000024732848,0.000027410806,0.00009617415,0.015296718,0.00013860229,0.0008562472,0.0002690024,0.00008798384,0.0068310103],"study_design_scores_gemma":[0.0000039127463,0.00009425736,0.989023,0.000016031201,0.000015110445,0.00006771263,0.009556797,0.00054577267,0.0002138866,0.0001421285,0.000304973,0.000016447955],"about_ca_topic_score_codex":0.020900862,"about_ca_topic_score_gemma":0.018792232,"teacher_disagreement_score":0.020900862,"about_ca_system_score_codex":0.0010645792,"about_ca_system_score_gemma":0.0012328435,"threshold_uncertainty_score":0.041558444},"labels":[],"label_agreement":null},{"id":"W4312094293","doi":"10.1037/spq0000527","title":"Potential scoring and predictive bias in interim and summative writing assessments.","year":2022,"lang":"en","type":"article","venue":"School Psychology","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"Iowa Department of Education","keywords":"Interim; Summative assessment; Rubric; Psychology; PsycINFO; Test (biology); Scale (ratio); Mathematics education; Medical education; Formative assessment; Medicine; MEDLINE; Political science","score_opus":0.0793813733520772,"score_gpt":0.44927917828844777,"score_spread":0.3698978049363706,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312094293","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7282419,0.004853709,0.21780351,0.0035411424,0.0018267412,0.0067647053,0.003547081,0.00090973766,0.032511447],"genre_scores_gemma":[0.9077219,0.00062600843,0.0786905,0.0014704238,0.00034402616,0.005128435,0.0020083296,0.00026012975,0.003750256],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.67855597,0.19864136,0.0369999,0.02201101,0.060173735,0.0036180965],"domain_scores_gemma":[0.35322058,0.4709547,0.06956897,0.062433712,0.041974887,0.0018471644],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.28525665,0.0013448828,0.0014024763,0.0061393143,0.0018714349,0.0027484375,0.0033727074,0.0015430386,0.0028010162],"category_scores_gemma":[0.55936414,0.000870822,0.0017105085,0.0058621643,0.0043931333,0.0026566503,0.0050880183,0.002702226,0.001076635],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007950877,0.000279327,0.852949,0.0008256211,0.0004874829,0.00031888045,0.012021323,0.0018209617,0.0008738154,0.00934152,0.007030711,0.113256134],"study_design_scores_gemma":[0.0001442823,0.0009452731,0.8812504,0.0030636033,0.00070068653,0.0014937869,0.006731038,0.04214599,0.010246009,0.031548172,0.021509526,0.00022123804],"about_ca_topic_score_codex":0.005420418,"about_ca_topic_score_gemma":0.011083867,"teacher_disagreement_score":0.28525665,"about_ca_system_score_codex":0.0021679313,"about_ca_system_score_gemma":0.0023292922,"threshold_uncertainty_score":0.88140583},"labels":[],"label_agreement":null},{"id":"W4312736783","doi":"10.1007/978-3-031-12680-2_19","title":"Assessment Brokering and Collaboration: Ghostwriter and Student Academic Literacies","year":2022,"lang":"en","type":"book-chapter","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":5,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Cheating; Academic integrity; Literacy; Pedagogy; Sociology; Higher education; Information literacy; Social practice; Mathematics education; Psychology; Political science; Social psychology","score_opus":0.030094312329519538,"score_gpt":0.3854652751015496,"score_spread":0.35537096277203006,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4312736783","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05339534,0.011541803,0.025462996,0.010564033,0.00059254613,0.000034686786,0.000029645591,0.00022121423,0.89815784],"genre_scores_gemma":[0.7387206,0.005128717,0.01137707,0.00088208605,0.00039555563,0.00006796467,0.0000413494,0.00015675325,0.24322993],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.99828416,0.0009199487,0.00006172531,0.000119173055,0.0005214676,0.000093440416],"domain_scores_gemma":[0.9912111,0.007078655,0.00037605426,0.00044436104,0.0004083625,0.00048140908],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029413467,0.0003352862,0.00037323355,0.0011182469,0.0015413867,0.01284802,0.0009378658,0.0014685079,0.00977785],"category_scores_gemma":[0.009217928,0.00020483046,0.00023653691,0.0012480512,0.0051238094,0.0073607685,0.0034964236,0.0021913354,0.0009899404],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000048996404,0.0001000032,0.0017038523,0.00014855142,0.000007761338,0.00027148455,0.048989363,0.0004896618,0.00077483006,0.6668191,0.01897273,0.2616738],"study_design_scores_gemma":[0.000023761844,0.00013455198,0.0045029875,0.00074400625,0.000016365031,0.00092616165,0.031183649,0.0045175585,0.0018358947,0.6941962,0.26187018,0.000048715057],"about_ca_topic_score_codex":0.0013022976,"about_ca_topic_score_gemma":0.0019868757,"teacher_disagreement_score":0.01284802,"about_ca_system_score_codex":0.0017612803,"about_ca_system_score_gemma":0.002199843,"threshold_uncertainty_score":0.032710135},"labels":[],"label_agreement":null},{"id":"W4313145915","doi":"10.7202/1093105ar","title":"Continuous assessment for learning: issues of multiple instances of peer feedback in a university course","year":2021,"lang":"fr","type":"article","venue":"Mesure et évaluation en éducation","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Peer feedback; Notice; Context (archaeology); Perception; Feeling; Peer assessment; Computer science; Mathematics education; Psychology; Course (navigation); Medical education; Social psychology; Engineering; Medicine","score_opus":0.062476903974542336,"score_gpt":0.415684196118278,"score_spread":0.3532072921437357,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313145915","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9398886,0.0010985972,0.044289734,0.002520002,0.0001509718,0.00016154748,0.000017933156,0.00018424739,0.011688369],"genre_scores_gemma":[0.995404,0.0000852523,0.003902934,0.000075680124,0.000044542136,0.000049585775,0.000006093268,0.000014640986,0.00041735108],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.8823871,0.08229282,0.0035191502,0.0046687415,0.025162144,0.0019700227],"domain_scores_gemma":[0.7595336,0.19145335,0.021076357,0.011024862,0.011916581,0.0049951896],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03729528,0.0004519062,0.00073150755,0.0010846665,0.0026470392,0.006279643,0.0015345949,0.0019229706,0.0011368402],"category_scores_gemma":[0.18987787,0.00035517948,0.00046119397,0.00067923253,0.0037257262,0.00421888,0.005463864,0.0024493772,0.00018379386],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009860302,0.0007785374,0.09062853,0.0007282856,0.00020896469,0.0012776399,0.43945172,0.0015044647,0.016425481,0.012412699,0.0012724573,0.4343252],"study_design_scores_gemma":[0.00022621857,0.008282114,0.38939407,0.0024970826,0.00039086115,0.009415685,0.45712522,0.016904343,0.024744108,0.03220085,0.05801721,0.0008021981],"about_ca_topic_score_codex":0.00093556225,"about_ca_topic_score_gemma":0.0015662079,"teacher_disagreement_score":0.03729528,"about_ca_system_score_codex":0.0019639472,"about_ca_system_score_gemma":0.0024981366,"threshold_uncertainty_score":0.19723868},"labels":[],"label_agreement":null},{"id":"W4313330978","doi":"10.18357/otessac.2022.2.1.125","title":"Feedback Generation through Artificial Intelligence","year":2022,"lang":"en","type":"article","venue":"The Open/Technology in Education Society and Scholarship Association Conference","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Process (computing); Dashboard; Artificial intelligence; Learning analytics; Educational data mining; Machine learning; Data science","score_opus":0.11938183437764223,"score_gpt":0.40382248502801654,"score_spread":0.2844406506503743,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313330978","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011028798,0.00086724386,0.9610027,0.0029851652,0.00028913078,0.0006560875,0.00016500984,0.002296513,0.02070936],"genre_scores_gemma":[0.40460685,0.001308656,0.58021533,0.001127506,0.00024297398,0.0010351433,0.00048510407,0.00040888367,0.010569533],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9833838,0.008715379,0.0010000917,0.0018619238,0.004546012,0.00049283355],"domain_scores_gemma":[0.9649079,0.025309235,0.0015488715,0.0033657318,0.0043945163,0.0004737614],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014318357,0.0012791253,0.0007934705,0.002662562,0.0010895837,0.004883906,0.0024127043,0.001900646,0.007692407],"category_scores_gemma":[0.05461508,0.0005164502,0.001072099,0.0014267307,0.0028116275,0.0045033493,0.0040981346,0.0023923933,0.0020905652],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00027932192,0.00041543663,0.0045764297,0.0013632233,0.00017697355,0.00041970075,0.0039998926,0.041685443,0.00957648,0.20368528,0.013191491,0.7206303],"study_design_scores_gemma":[0.00018692367,0.00046235032,0.0021953636,0.0009373685,0.00016547345,0.0005451877,0.0016982781,0.3867603,0.018550891,0.4673418,0.12097341,0.00018273565],"about_ca_topic_score_codex":0.0016171195,"about_ca_topic_score_gemma":0.0011904876,"teacher_disagreement_score":0.014318357,"about_ca_system_score_codex":0.0017352353,"about_ca_system_score_gemma":0.0024800638,"threshold_uncertainty_score":0.07572365},"labels":[],"label_agreement":null},{"id":"W4313343544","doi":"10.18733/cpi29666","title":"All that Glitters is not Gold: Culturally Responsive Online Assessment and Pedagogy in Uncertain Times","year":2022,"lang":"en","type":"article","venue":"Cultural and Pedagogical Inquiry","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of British Columbia; University of Calgary","funders":"","keywords":"Pedagogy; Psychology","score_opus":0.5267311310912989,"score_gpt":0.5478395655922317,"score_spread":0.021108434500932804,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4313343544","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0029520746,0.0050330083,0.0020872594,0.78687924,0.17432085,0.00023765882,0.0001856206,0.0006676739,0.0276367],"genre_scores_gemma":[0.078862526,0.01653761,0.015327442,0.3266396,0.2552783,0.0022585797,0.0009726536,0.003016238,0.30110702],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9791414,0.01033429,0.0013119625,0.00093716587,0.0064239656,0.0018512518],"domain_scores_gemma":[0.86791945,0.057915736,0.0036027988,0.00392269,0.02380369,0.04283563],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.026871325,0.0010388275,0.0013294156,0.0014103255,0.0139752785,0.020607814,0.0030401482,0.013881176,0.05567759],"category_scores_gemma":[0.10261829,0.0007931832,0.00077111425,0.0011462845,0.0072423434,0.016791109,0.01475428,0.018048154,0.015024568],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001803556,0.000047516325,0.00021287522,0.00007403187,0.0000027316285,0.00009335499,0.0020794391,0.0000146861075,0.00008889952,0.0011795624,0.9761796,0.020009369],"study_design_scores_gemma":[0.000016972115,0.00007948062,0.0018770257,0.00064246333,0.0000100500265,0.00017393174,0.021537842,0.00013828854,0.00025056326,0.008227634,0.9669652,0.00008043653],"about_ca_topic_score_codex":0.004818882,"about_ca_topic_score_gemma":0.017750693,"teacher_disagreement_score":0.05567759,"about_ca_system_score_codex":0.0033808884,"about_ca_system_score_gemma":0.013704107,"threshold_uncertainty_score":0.1862601},"labels":[],"label_agreement":null},{"id":"W4317863115","doi":"10.46747/cfp.6901e21","title":"Assessing students and residents","year":2023,"lang":"en","type":"article","venue":"Canadian Family Physician","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Institut du Savoir Montfort","funders":"","keywords":"Process (computing); Computer science; Medical education; Core (optical fiber); Data science; Medicine","score_opus":0.06430008053675226,"score_gpt":0.37810740661134773,"score_spread":0.3138073260745955,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4317863115","genre_codex":"empirical","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8169188,0.0033608482,0.010284675,0.019682333,0.0022017555,0.000958017,0.00089571555,0.00056196,0.1451359],"genre_scores_gemma":[0.945086,0.001868464,0.011030532,0.0046012304,0.00040305915,0.00033349704,0.00057031086,0.00009106692,0.036015794],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9909175,0.0018351222,0.00044888307,0.0004939256,0.005685901,0.00061866926],"domain_scores_gemma":[0.97393936,0.0019845944,0.002101973,0.00071593205,0.017079307,0.0041788495],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0070582386,0.00033691587,0.00044331356,0.0017524543,0.0019430574,0.0022846817,0.0009373709,0.0010008609,0.0066724163],"category_scores_gemma":[0.046255503,0.0001744984,0.00048269003,0.0007500534,0.0011502063,0.0016027519,0.0035927473,0.001674853,0.0020918227],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021899545,0.0006682179,0.38377807,0.0002165054,0.00005955841,0.00029013597,0.027836151,0.00025690283,0.0014974262,0.0032268304,0.09731969,0.48463157],"study_design_scores_gemma":[0.0000542423,0.0013919023,0.6690996,0.0007204386,0.00008255739,0.0022601036,0.045997605,0.0010005906,0.0046597663,0.004990682,0.2695739,0.00016858095],"about_ca_topic_score_codex":0.021765394,"about_ca_topic_score_gemma":0.06373824,"teacher_disagreement_score":0.021765394,"about_ca_system_score_codex":0.0039815684,"about_ca_system_score_gemma":0.007227969,"threshold_uncertainty_score":0.043277383},"labels":[],"label_agreement":null},{"id":"W4319439102","doi":"10.31038/ijnm.2022332","title":"Peer-to-Peer Evaluation: Kritik Pilot at Two Post- secondary Canadian Institutions","year":2022,"lang":"en","type":"article","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Winnipeg; Brandon University","funders":"","keywords":"Peer review; Peer-to-peer; Political science; Psychology; Medical education; Public relations; Computer science; Medicine; World Wide Web; Law","score_opus":0.08764148884602259,"score_gpt":0.40143378418397824,"score_spread":0.31379229533795566,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4319439102","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9675693,0.0001704848,0.0036139472,0.0011779049,0.00014523492,0.014499973,0.00056011445,0.00065703713,0.01160608],"genre_scores_gemma":[0.95531523,0.0002785902,0.021391178,0.00063207507,0.000062073785,0.0061671543,0.00079952314,0.00024140546,0.0151128005],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9794168,0.00699798,0.0011179151,0.0017287475,0.0056423354,0.0050961617],"domain_scores_gemma":[0.91328055,0.010765877,0.0021112391,0.004636152,0.05013366,0.019072466],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03988734,0.0010584767,0.0010425687,0.0016060256,0.009723791,0.0034817941,0.0033126117,0.001549576,0.0033468078],"category_scores_gemma":[0.044632353,0.0008314414,0.000718245,0.0015403903,0.0031102707,0.0016089535,0.004857701,0.0031535907,0.0016127228],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.015092261,0.05283039,0.07379308,0.0025889063,0.00026412762,0.0049116393,0.3045612,0.0050784666,0.04542797,0.0029021432,0.044083316,0.44846645],"study_design_scores_gemma":[0.0064994353,0.054310888,0.44663706,0.0011122944,0.00043114624,0.0008371278,0.20977004,0.011245486,0.060405627,0.0014711391,0.20602025,0.0012594505],"about_ca_topic_score_codex":0.3635264,"about_ca_topic_score_gemma":0.62261593,"teacher_disagreement_score":0.9842023,"about_ca_system_score_codex":0.015797663,"about_ca_system_score_gemma":0.060500387,"threshold_uncertainty_score":0.7228209},"labels":[],"label_agreement":null},{"id":"W4321022335","doi":"10.22329/jtl.v16i3.6976","title":"From Assessment for Learning to Assessment for Expansion: Proposing a New Paradigm of Assessment as a Sociocultural Practice","year":2022,"lang":"en","type":"article","venue":"Journal of Teaching and Learning","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Japan Society for the Promotion of Science","keywords":"Formative assessment; Sociocultural evolution; Situational ethics; Process (computing); Context (archaeology); Psychology; Pedagogy; Engineering ethics; Sociology; Computer science; Social psychology; Engineering","score_opus":0.03207830599429994,"score_gpt":0.4247365324597729,"score_spread":0.39265822646547294,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4321022335","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017075576,0.0069355564,0.8054877,0.061048564,0.001615764,0.0005638213,0.000063150466,0.00037268762,0.10683715],"genre_scores_gemma":[0.5450655,0.0034282606,0.4369879,0.0047322586,0.0010232568,0.001352147,0.000058118218,0.00020719557,0.007145323],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.97455907,0.01766612,0.0013669166,0.0018817812,0.0037603674,0.0007656454],"domain_scores_gemma":[0.9742828,0.015814297,0.0013316834,0.0031969773,0.0039002555,0.0014739898],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.026628373,0.0013208337,0.00140231,0.006445491,0.0038807383,0.017690733,0.0039831647,0.0047712377,0.0025737858],"category_scores_gemma":[0.021794038,0.0006702199,0.0013353518,0.0032756964,0.05725671,0.027189756,0.009762219,0.008821084,0.000715043],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001850551,0.000061053375,0.0009575589,0.00020065517,0.000013052629,0.00013953961,0.021234559,0.000563658,0.0004069763,0.9458551,0.00078693,0.029762477],"study_design_scores_gemma":[0.00002406,0.000097572345,0.0006487434,0.00047924835,0.000015039659,0.00036402332,0.010817562,0.0046266294,0.00039317124,0.93435454,0.04812644,0.0000529294],"about_ca_topic_score_codex":0.0032116186,"about_ca_topic_score_gemma":0.002916202,"teacher_disagreement_score":0.026628373,"about_ca_system_score_codex":0.0077350438,"about_ca_system_score_gemma":0.010899865,"threshold_uncertainty_score":0.14082599},"labels":[],"label_agreement":null},{"id":"W4321099595","doi":"10.5539/elt.v16n3p1","title":"To What Extent are Japanese University Students Successful in Motivating Themselves to Learn English through Project-based Language Education? An Assessment of Students after Two Years of PBL-based English Language Education","year":2023,"lang":"en","type":"article","venue":"English Language Teaching","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology; Mathematics education; Curriculum; Perspective (graphical); Intrinsic motivation; Language proficiency; Goal theory; Self-determination theory; Motivation to learn; Pedagogy; English language; Language acquisition; Social psychology","score_opus":0.015617169646490323,"score_gpt":0.3975462875087326,"score_spread":0.38192911786224226,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4321099595","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99963355,0.000018584155,0.000047587415,0.000009478569,0.0000015142341,0.000009275887,0.0000029151824,0.0000017276002,0.00027528813],"genre_scores_gemma":[0.99905246,0.000054205804,0.00014611414,0.000012857694,0.0000024623755,0.000020889851,0.000017242373,0.0000012967705,0.00069241907],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9994019,0.0001499114,0.00006159496,0.00007316843,0.00017393427,0.0001394487],"domain_scores_gemma":[0.9975292,0.000256645,0.00055343204,0.00010693191,0.00062520197,0.00092855695],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016372857,0.00032290007,0.0003370707,0.0004800489,0.00047415684,0.00097616523,0.0002815408,0.00053130806,0.0010972165],"category_scores_gemma":[0.0040730494,0.00015489667,0.00039212534,0.00019435171,0.00035517476,0.00053605996,0.000741789,0.0004895168,0.0005047883],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00081944733,0.007803209,0.77555215,0.00027772394,0.00011324686,0.0006956341,0.0323348,0.0003127107,0.04313299,0.00019581003,0.00042645234,0.13833575],"study_design_scores_gemma":[0.000031127387,0.004056275,0.97866356,0.000021085541,0.00005487804,0.00020903531,0.011530462,0.0004655634,0.0036504995,0.00006192357,0.0012279884,0.000027612577],"about_ca_topic_score_codex":0.0007852341,"about_ca_topic_score_gemma":0.0010320654,"teacher_disagreement_score":0.0016372857,"about_ca_system_score_codex":0.00017912616,"about_ca_system_score_gemma":0.00043726707,"threshold_uncertainty_score":0.008658886},"labels":[],"label_agreement":null},{"id":"W4321513722","doi":"10.7202/1096356ar","title":"Revue systématique sur les pratiques évaluatives probantes en évaluation formative à l’enseignement primaire et secondaire","year":2022,"lang":"fr","type":"article","venue":"Revue des sciences de l éducation","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université TÉLUQ; Université Laval","funders":"","keywords":"Humanities; Political science; Philosophy","score_opus":0.25248162448681627,"score_gpt":0.42620377040582413,"score_spread":0.17372214591900786,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4321513722","genre_codex":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03471293,0.27625787,0.46820292,0.13191718,0.008990665,0.0056369747,0.0025175367,0.0049116495,0.066852264],"genre_scores_gemma":[0.27076036,0.11244664,0.56161654,0.01638583,0.0051309806,0.01163996,0.002979777,0.0010368811,0.018002998],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.7503517,0.1716632,0.018495986,0.007323318,0.050510652,0.0016551876],"domain_scores_gemma":[0.41038474,0.42189506,0.01811659,0.021585213,0.12436484,0.0036535845],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.22082758,0.0014784096,0.0030429314,0.009701437,0.0024701357,0.017341755,0.0042591346,0.0037568249,0.009479671],"category_scores_gemma":[0.3635543,0.001051695,0.0021689981,0.006648579,0.005092297,0.013740046,0.0069076386,0.005612729,0.004487315],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00067372806,0.00033873296,0.0065870825,0.0095005715,0.00032669868,0.000075236494,0.00574643,0.0008658317,0.0018085107,0.018551096,0.025463317,0.9300628],"study_design_scores_gemma":[0.0010055953,0.0024344472,0.04328314,0.079054125,0.0015402777,0.0014233358,0.013298649,0.014251851,0.01095728,0.09818379,0.7336512,0.0009163054],"about_ca_topic_score_codex":0.011578547,"about_ca_topic_score_gemma":0.010725014,"teacher_disagreement_score":0.22082758,"about_ca_system_score_codex":0.010907486,"about_ca_system_score_gemma":0.027790481,"threshold_uncertainty_score":0.9608583},"labels":[],"label_agreement":null},{"id":"W4321600738","doi":"10.1017/s0261444823000034","title":"The ethical turn in writing assessment: How far have we come, and where do we still need to go?","year":2023,"lang":"en","type":"article","venue":"Language Teaching","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Lethbridge","funders":"","keywords":"Impromptu; Writing assessment; Globe; German; Test (biology); Language assessment; Second language writing; Academic writing; Psychology; Pedagogy; Sociology; Linguistics; Computer science; Second language; Philosophy","score_opus":0.02481394901592722,"score_gpt":0.37919138701233135,"score_spread":0.35437743799640414,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4321600738","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011511666,0.016635379,0.01016338,0.9487431,0.0042012837,0.000041465853,0.00001954137,0.00006172622,0.008622419],"genre_scores_gemma":[0.66035205,0.031614553,0.03433273,0.25523886,0.00780757,0.000425666,0.00006420702,0.00042807925,0.009736314],"study_design_codex":"qualitative","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.89524424,0.07914866,0.0030080597,0.00442478,0.014300463,0.0038738106],"domain_scores_gemma":[0.8254498,0.105844386,0.0083058085,0.0064704395,0.03081468,0.02311489],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.10985927,0.00093227264,0.0018992282,0.002250926,0.020859664,0.034194943,0.0030543385,0.01558045,0.0039214673],"category_scores_gemma":[0.17843556,0.0007222559,0.00080732745,0.0018189248,0.071480095,0.05451066,0.01888861,0.048230827,0.001581183],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000120817334,0.00031762777,0.00581699,0.0011643342,0.000069531045,0.0008502317,0.39130062,0.00032091644,0.0008466932,0.37021118,0.06279908,0.16618201],"study_design_scores_gemma":[0.000037428377,0.00017585115,0.0019575332,0.0037818616,0.000029051562,0.0011729831,0.39670026,0.00060178584,0.0006799581,0.34434938,0.2503029,0.00021094675],"about_ca_topic_score_codex":0.0057246145,"about_ca_topic_score_gemma":0.0069307047,"teacher_disagreement_score":0.10985927,"about_ca_system_score_codex":0.009753267,"about_ca_system_score_gemma":0.022118408,"threshold_uncertainty_score":0.5809983},"labels":[],"label_agreement":null},{"id":"W4322486740","doi":"10.5539/elt.v16n3p23","title":"The Accuracy of Students&amp;#39; Self-Assessment-How Useful Is a Checklist in EAP Writing","year":2023,"lang":"en","type":"article","venue":"English Language Teaching","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Checklist; Psychology; Autonomy; Learner autonomy; Self-assessment; Medical education; Pedagogy; Mathematics education; Language education; Medicine","score_opus":0.02164002909992158,"score_gpt":0.3833339188698593,"score_spread":0.3616938897699377,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4322486740","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9253742,0.0007403331,0.03166493,0.0017529718,0.00034634178,0.0014196818,0.0007297111,0.0007197256,0.037251953],"genre_scores_gemma":[0.9625255,0.00038812822,0.032321375,0.00017047628,0.000034297645,0.00061879854,0.00031463342,0.000073716445,0.0035529851],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.957024,0.021229995,0.0072190706,0.0016183651,0.012248526,0.0006601219],"domain_scores_gemma":[0.78090996,0.11702418,0.022132305,0.013097262,0.06382725,0.0030090997],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.038046643,0.00029747223,0.000538083,0.0028667059,0.00094340293,0.0021862003,0.00081764685,0.00048824813,0.0020693738],"category_scores_gemma":[0.21328607,0.00019699222,0.00044381816,0.0014220272,0.0013040905,0.00220594,0.001524552,0.00080260314,0.0009873337],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003893527,0.00060997636,0.3674302,0.0013606513,0.00014806306,0.00019176796,0.038295884,0.0010315496,0.008777317,0.001882091,0.009686161,0.5701969],"study_design_scores_gemma":[0.00013490132,0.0032678237,0.796821,0.0026597234,0.0002492295,0.001624917,0.06304062,0.018596971,0.033838484,0.0072433767,0.07196863,0.00055434427],"about_ca_topic_score_codex":0.0017090328,"about_ca_topic_score_gemma":0.002784152,"teacher_disagreement_score":0.038046643,"about_ca_system_score_codex":0.00077654974,"about_ca_system_score_gemma":0.0021852811,"threshold_uncertainty_score":0.20121229},"labels":[],"label_agreement":null},{"id":"W4323059193","doi":"10.1007/978-3-031-18950-0_17","title":"Product to Process: The Efficacy of Hybrid Feedback in Academic Writing Classrooms for Fostering Process-Oriented Writing","year":2023,"lang":"en","type":"book-chapter","venue":"New language learning and teaching environments","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Class (philosophy); Process (computing); Writing process; Mathematics education; Product (mathematics); Computer science; Academic writing; Psychology; Peer feedback; Artificial intelligence; Mathematics","score_opus":0.031609611929217,"score_gpt":0.35311848929843126,"score_spread":0.32150887736921424,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4323059193","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.72568125,0.004533991,0.1039197,0.0018016872,0.00090196705,0.0012504201,0.00016834402,0.0014974191,0.16024522],"genre_scores_gemma":[0.8660806,0.0017628968,0.07337331,0.0003627183,0.000108292166,0.00075587176,0.00016161513,0.00039023586,0.057004504],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.996956,0.0014426372,0.00010017086,0.00021020063,0.0012345214,0.000056468918],"domain_scores_gemma":[0.9883017,0.01036787,0.0003493656,0.00025826457,0.0004898668,0.00023295818],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0052374727,0.000447508,0.0003045532,0.00045700892,0.0003712617,0.0021187358,0.0008027132,0.00084027625,0.005929804],"category_scores_gemma":[0.012730112,0.00022355103,0.00025682762,0.0002912051,0.00065200415,0.0018339176,0.0011766881,0.00096595,0.0009464888],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015581752,0.001447899,0.001819528,0.0005607681,0.00003269776,0.00010096354,0.005842288,0.00081929925,0.023692716,0.007575841,0.0045815203,0.95196825],"study_design_scores_gemma":[0.0035318148,0.08024177,0.18182437,0.0042307167,0.0011578972,0.0041614985,0.020788908,0.084878966,0.35609704,0.06753134,0.19514856,0.0004071866],"about_ca_topic_score_codex":0.00039005183,"about_ca_topic_score_gemma":0.0006318893,"teacher_disagreement_score":0.005929804,"about_ca_system_score_codex":0.00038048526,"about_ca_system_score_gemma":0.00085088465,"threshold_uncertainty_score":0.027698755},"labels":[],"label_agreement":null},{"id":"W4327725721","doi":"10.18162/fp.2023.785","title":"Articuler l’évaluation des stagiaires à une approche par compétences : portrait et constats tirés de l’analyse d’outils en formation initiale à l’enseignement au Québec","year":2023,"lang":"fr","type":"article","venue":"Formation et profession","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université de Montréal; Université du Québec en Outaouais","funders":"","keywords":"Valuation (finance); Humanities; Sociology; Philosophy; Economics","score_opus":0.08175911890748164,"score_gpt":0.3961486240250622,"score_spread":0.31438950511758057,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4327725721","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7695714,0.0052231224,0.014592454,0.027301686,0.00041514225,0.0010419153,0.00031496637,0.00015925417,0.18138011],"genre_scores_gemma":[0.9622541,0.0017108547,0.004089407,0.0007229521,0.000030706302,0.00027008474,0.00007665628,0.00004506657,0.030800188],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.97322255,0.012739387,0.0008031038,0.00096336886,0.009880569,0.0023910454],"domain_scores_gemma":[0.94037896,0.02089392,0.0027853285,0.0017848462,0.028874815,0.0052822637],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.030042259,0.0004928913,0.0006147341,0.0043279435,0.0105178645,0.013639895,0.0015705887,0.001675105,0.0059551494],"category_scores_gemma":[0.04680823,0.00038570954,0.00042592743,0.004696825,0.011381785,0.004020874,0.0053216945,0.0037056257,0.00067898433],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015223303,0.00021617515,0.03529074,0.0010806367,0.000054591743,0.00033507354,0.620578,0.0009623498,0.0028378495,0.04638066,0.013231485,0.27888027],"study_design_scores_gemma":[0.00003416178,0.00035578827,0.18176647,0.0029865669,0.00007975195,0.00014098034,0.5696719,0.0018116664,0.0033029886,0.0070672077,0.23258604,0.0001964353],"about_ca_topic_score_codex":0.7296014,"about_ca_topic_score_gemma":0.85861695,"teacher_disagreement_score":0.7296014,"about_ca_system_score_codex":0.08082323,"about_ca_system_score_gemma":0.13526924,"threshold_uncertainty_score":0.5864163},"labels":[],"label_agreement":null},{"id":"W4361026956","doi":"10.1016/j.jslw.2023.100993","title":"Voices from L2 learners across different languages: Development and validation of a student writing assessment literacy scale","year":2023,"lang":"en","type":"article","venue":"Journal of Second Language Writing","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":16,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"National Social Science Fund of China; National Office for Philosophy and Social Sciences","keywords":"Scale (ratio); Context (archaeology); Literacy; Computer science; Reliability (semiconductor); Mathematics education; Construct (python library); Structural equation modeling; Psychology; Pedagogy","score_opus":0.025685623423356133,"score_gpt":0.4048320796905727,"score_spread":0.3791464562672166,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4361026956","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9938566,0.000029654535,0.0022812486,0.00010611922,0.000031157753,0.0007593205,0.0001351695,0.00004629502,0.0027543535],"genre_scores_gemma":[0.9853254,0.0000830525,0.008457793,0.00020150689,0.000020982545,0.002369779,0.0005602867,0.00006127436,0.0029199373],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99120307,0.0033697619,0.0014731919,0.0006982192,0.0027061591,0.0005496501],"domain_scores_gemma":[0.9742802,0.00999107,0.0015799827,0.0014708433,0.010780929,0.0018969921],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014942474,0.00061639765,0.0009378336,0.0019457418,0.001521886,0.0023567427,0.0009129846,0.001263374,0.0020042553],"category_scores_gemma":[0.0360576,0.0005065123,0.00078097376,0.0005809953,0.0011086984,0.0015930239,0.005170051,0.0016838337,0.001190402],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015252952,0.005273834,0.51369876,0.00045397607,0.00017399155,0.001475101,0.19584349,0.00075198436,0.057534337,0.0008135082,0.002677275,0.21977852],"study_design_scores_gemma":[0.0005323416,0.0050956146,0.7874343,0.00037785378,0.00021292841,0.002614394,0.13435405,0.006028495,0.045284666,0.001764918,0.015982704,0.0003177781],"about_ca_topic_score_codex":0.0016503455,"about_ca_topic_score_gemma":0.0028303016,"teacher_disagreement_score":0.014942474,"about_ca_system_score_codex":0.0007897865,"about_ca_system_score_gemma":0.0021045152,"threshold_uncertainty_score":0.079024255},"labels":[],"label_agreement":null},{"id":"W4362575713","doi":"10.22215/etd/2023-15370","title":"The Development of Students' Assessment Literacies as They Transition to University: An Exploratory Case Study","year":2023,"lang":"en","type":"dissertation","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Carleton University","funders":"","keywords":"Context (archaeology); Psychology; Reflexivity; Pedagogy; Mathematics education; Sociology; Social science","score_opus":0.04499213898590357,"score_gpt":0.4135005371911826,"score_spread":0.36850839820527903,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362575713","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99729556,0.00006740024,0.0007682715,0.00042291216,0.000008029738,0.000111986265,0.00002233088,0.000009715835,0.0012937107],"genre_scores_gemma":[0.9963187,0.00016283923,0.00188073,0.00015203841,0.000005966889,0.00012596544,0.000025707131,0.000009187268,0.0013188922],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99186134,0.0044693574,0.00035711649,0.0005929743,0.0011829294,0.0015361807],"domain_scores_gemma":[0.9873563,0.005408769,0.0011805634,0.0007098537,0.0017883783,0.0035561875],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010534617,0.00059479533,0.00086918724,0.0020059042,0.010266475,0.0063332263,0.0026300324,0.002584142,0.0013913043],"category_scores_gemma":[0.016698383,0.00058488845,0.0007352582,0.0018070018,0.0047320956,0.0030632946,0.007404885,0.0042077685,0.00042420288],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014998695,0.0024175153,0.059482377,0.00012602711,0.00001954139,0.008136954,0.8867252,0.00046532415,0.0024174785,0.0024133585,0.00087911234,0.036767174],"study_design_scores_gemma":[0.00003726668,0.001295856,0.029233001,0.0001941045,0.00003053359,0.0029876544,0.9443279,0.0016338219,0.003373885,0.001152512,0.015626065,0.00010738091],"about_ca_topic_score_codex":0.010138266,"about_ca_topic_score_gemma":0.020476859,"teacher_disagreement_score":0.010534617,"about_ca_system_score_codex":0.0065930905,"about_ca_system_score_gemma":0.0057979925,"threshold_uncertainty_score":0.055713058},"labels":[],"label_agreement":null},{"id":"W4362671389","doi":"10.3389/feduc.2023.1154592","title":"Teachers’ test construction competencies in examination-oriented educational system: Exploring teachers’ multiple-choice test construction competence","year":2023,"lang":"en","type":"article","venue":"Frontiers in Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Competence (human resources); Multiple choice; Exploratory factor analysis; Psychology; Test (biology); Mathematics education; Item analysis; Psychometrics; Social psychology; Developmental psychology; Mathematics; Statistics; Significant difference","score_opus":0.032207741940133636,"score_gpt":0.30252988988147195,"score_spread":0.2703221479413383,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4362671389","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99914575,0.000036095043,0.00040913603,0.000047929196,0.000001129371,0.0000082858505,0.000009275218,0.0000019249412,0.0003404692],"genre_scores_gemma":[0.99961156,0.000016414477,0.00028898325,0.00000485843,6.813845e-7,0.00000432166,0.0000064101628,9.2575357e-7,0.00006580754],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9957171,0.0020891675,0.00038724183,0.00026925458,0.0011848537,0.000352391],"domain_scores_gemma":[0.95183074,0.028312862,0.013014685,0.0016541535,0.0033026282,0.0018850631],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008411784,0.00025230338,0.00038466466,0.0014000555,0.0003599852,0.0013588772,0.00037902757,0.00033012094,0.0011269029],"category_scores_gemma":[0.053673245,0.0003038238,0.00025093832,0.00081232906,0.001285802,0.0014508471,0.00136194,0.00074168923,0.00011649334],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000707179,0.000171303,0.9429159,0.000060395076,0.000018744027,0.00023033208,0.03598847,0.00020673336,0.0014784518,0.00025893474,0.00008764258,0.018512268],"study_design_scores_gemma":[0.000006892364,0.00018072104,0.9727365,0.00006165741,0.0000062494337,0.0003891127,0.023271462,0.0012898103,0.000997482,0.00035517174,0.0006881471,0.000016877077],"about_ca_topic_score_codex":0.0046169246,"about_ca_topic_score_gemma":0.006338327,"teacher_disagreement_score":0.008411784,"about_ca_system_score_codex":0.0009007453,"about_ca_system_score_gemma":0.0011797284,"threshold_uncertainty_score":0.044486284},"labels":[],"label_agreement":null},{"id":"W4365144709","doi":"10.1080/0305764x.2023.2196245","title":"Toward a Praxis-Oriented Understanding of Student Self-Assessment in STEAM Education: How Exemplary Educators Leverage Self-Assessment","year":2023,"lang":"en","type":"article","venue":"Cambridge Journal of Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Queen's University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Praxis; Documentation; Mathematics education; Authentic assessment; Self-assessment; Pedagogy; Metacognition; Formative assessment; Psychology; Transformative learning; Grading (engineering); Process (computing); Leverage (statistics); Engineering ethics; Engineering; Curriculum; Computer science; Political science","score_opus":0.050377013661010335,"score_gpt":0.3862939383349915,"score_spread":0.33591692467398115,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4365144709","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.886701,0.0005572784,0.08130724,0.005730627,0.000052498024,0.00014293514,0.000022114584,0.00015613697,0.02533016],"genre_scores_gemma":[0.9849066,0.00020725571,0.01341307,0.00023639116,0.000005402215,0.00004847091,0.000008442958,0.000018979761,0.0011554648],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9852761,0.011684352,0.0004357425,0.0006204257,0.0015460012,0.0004373426],"domain_scores_gemma":[0.968177,0.02390299,0.0021317815,0.00217906,0.0025158944,0.0010932925],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.018510552,0.00032296104,0.00032028698,0.0015580426,0.0020122794,0.005965243,0.0011475891,0.0012539279,0.00093099935],"category_scores_gemma":[0.038919758,0.00031222592,0.00022381636,0.00068085303,0.011119947,0.0050805286,0.005910453,0.002467754,0.00021019191],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000054575085,0.00026371775,0.027244398,0.0003502283,0.000018889661,0.0005582285,0.85599667,0.0007363675,0.004275489,0.036212645,0.00068751513,0.073601216],"study_design_scores_gemma":[0.000041192954,0.00071219483,0.032489624,0.0014845241,0.000041847117,0.0022452339,0.78403074,0.0059799515,0.013170983,0.08625761,0.07339201,0.00015415122],"about_ca_topic_score_codex":0.0011256417,"about_ca_topic_score_gemma":0.0023392309,"teacher_disagreement_score":0.018510552,"about_ca_system_score_codex":0.0016740598,"about_ca_system_score_gemma":0.0027631393,"threshold_uncertainty_score":0.09789431},"labels":[],"label_agreement":null},{"id":"W4366451349","doi":"10.3138/cjpe.0022.003","title":"Teachers’ and Researchers’ Uses of Assessment and Evaluation Can Bring Reading and Writing Together","year":2008,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Viewpoints; Reading (process); Value (mathematics); Writing assessment; Psychology; Mathematics education; Scale (ratio); Pedagogy; Computer science; Linguistics","score_opus":0.3373658739577437,"score_gpt":0.5040456137303412,"score_spread":0.16667973977259748,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366451349","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.33127496,0.0095318165,0.15245257,0.08934485,0.001459023,0.0015232489,0.0001697849,0.0010327938,0.41321096],"genre_scores_gemma":[0.9771022,0.00069847616,0.01627065,0.0013039202,0.0000703228,0.0005508757,0.000019060753,0.000085988664,0.0038984169],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.5192054,0.38558865,0.017938303,0.008649268,0.06389242,0.004726007],"domain_scores_gemma":[0.577205,0.29135117,0.02216805,0.025844954,0.07558904,0.007841782],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.20561418,0.00072669354,0.0009998108,0.0056558414,0.005565307,0.019690156,0.0019326985,0.0031314446,0.003162813],"category_scores_gemma":[0.3280233,0.0007003386,0.0006376144,0.0034859611,0.017644273,0.012849163,0.014992184,0.0052693733,0.00073698105],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025235818,0.00046803692,0.030509178,0.000997372,0.0001847156,0.00034142841,0.48885408,0.0007501765,0.002502023,0.12695208,0.0098946765,0.33829385],"study_design_scores_gemma":[0.00035022185,0.001150986,0.05689279,0.0049594827,0.00034127056,0.0014527289,0.54339814,0.0041411673,0.014631886,0.15039434,0.2215867,0.00070020295],"about_ca_topic_score_codex":0.007410772,"about_ca_topic_score_gemma":0.011185053,"teacher_disagreement_score":0.20561418,"about_ca_system_score_codex":0.010191127,"about_ca_system_score_gemma":0.016420744,"threshold_uncertainty_score":0.97961915},"labels":[],"label_agreement":null},{"id":"W4375945263","doi":"10.1177/02655322231164565","title":"Book review: Learning-Oriented Language Assessment: Putting Theory into Practice","year":2023,"lang":"en","type":"article","venue":"Language Testing","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Psychology; Linguistics; Language assessment; Mathematics education; Philosophy","score_opus":0.019022381633885147,"score_gpt":0.40005753558139345,"score_spread":0.3810351539475083,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4375945263","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00015551728,0.8510592,0.0010249078,0.0672956,0.07443466,0.00012632896,0.00022171886,0.000102347534,0.005579729],"genre_scores_gemma":[0.0029593967,0.7681321,0.0025471991,0.094549134,0.09060175,0.0004261216,0.00053317804,0.00016327458,0.040087845],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9947179,0.0015750612,0.0005590842,0.0004641778,0.0024857074,0.0001980981],"domain_scores_gemma":[0.9607786,0.021161446,0.0024328984,0.0004800741,0.013557679,0.0015892391],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0045517557,0.0011751009,0.004131925,0.005479272,0.00073048007,0.0033206062,0.0029765435,0.0067787697,0.0150992675],"category_scores_gemma":[0.032985445,0.00082830363,0.0013546041,0.0054009156,0.0017339397,0.0025798487,0.0015307604,0.006316013,0.010567267],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003003021,0.000023892017,0.000057545254,0.0028597182,0.00004407664,0.000037998,0.0000129405535,0.00007197631,0.00006313363,0.000330939,0.9384242,0.058043543],"study_design_scores_gemma":[0.00013697085,0.00010838252,0.0011900619,0.01062917,0.00017664224,0.0006301167,0.000051709485,0.00018521021,0.00012020454,0.001238914,0.9854903,0.000042285636],"about_ca_topic_score_codex":0.009466861,"about_ca_topic_score_gemma":0.030305713,"teacher_disagreement_score":0.0150992675,"about_ca_system_score_codex":0.0042643473,"about_ca_system_score_gemma":0.0073432853,"threshold_uncertainty_score":0.050512075},"labels":[],"label_agreement":null},{"id":"W4376626995","doi":"10.58379/rshg8366","title":"DIF investigations across groups of gender and academic background in a large-scale high-stakes language test ","year":2015,"lang":"en","type":"article","venue":"Studies in Language Assessment","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Queen's University","keywords":"Test (biology); Differential item functioning; Psychology; Quality (philosophy); Reliability (semiconductor); Scale (ratio); Gender bias; Social psychology; Applied psychology; Mathematics education; Medical education; Item response theory; Developmental psychology; Psychometrics; Medicine","score_opus":0.11975842518511098,"score_gpt":0.46502313377722004,"score_spread":0.34526470859210906,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4376626995","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9965592,0.000088328045,0.0020132111,0.00009053443,0.000024337005,0.00010035325,0.000057186815,0.0000060166717,0.0010607865],"genre_scores_gemma":[0.99842644,0.00002846117,0.0010995874,0.00005161251,0.000014133468,0.00008854158,0.00008057636,0.0000042118413,0.000206378],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.97159606,0.014780387,0.003445428,0.0019908238,0.0068048094,0.0013825218],"domain_scores_gemma":[0.91588247,0.045783307,0.011258354,0.007485604,0.017835164,0.0017551187],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.040404044,0.00045310234,0.00069807767,0.003450269,0.0012703352,0.0010714261,0.0007638202,0.00049195794,0.0014646762],"category_scores_gemma":[0.108169794,0.00019855378,0.0009474493,0.001651765,0.0016252495,0.0011933197,0.0021456613,0.0005769636,0.00026552432],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00040372353,0.00026182513,0.94342405,0.00008044475,0.00015155991,0.00012015394,0.012631078,0.00013808614,0.0014411221,0.0007012446,0.00027356576,0.04037327],"study_design_scores_gemma":[0.00003085711,0.00073570077,0.98294604,0.00006945791,0.00007142502,0.00025581577,0.010265065,0.0013865526,0.0020003093,0.0010249966,0.0011773878,0.000036373403],"about_ca_topic_score_codex":0.0021361227,"about_ca_topic_score_gemma":0.00292848,"teacher_disagreement_score":0.040404044,"about_ca_system_score_codex":0.0010501702,"about_ca_system_score_gemma":0.001098234,"threshold_uncertainty_score":0.21367955},"labels":[],"label_agreement":null},{"id":"W4378193990","doi":"10.3138/jvme-2023-0011","title":"Student Use and Perceptions of Embedded Formative Assessments in a Basic Science Veterinary Program","year":2023,"lang":"en","type":"article","venue":"Journal of Veterinary Medical Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Formative assessment; Thematic analysis; Curriculum; Preference; Process (computing); Medical education; Psychology; Mathematics education; Perception; Computer science; Qualitative research; Pedagogy; Medicine; Sociology","score_opus":0.12170649137693154,"score_gpt":0.5276690941621207,"score_spread":0.40596260278518914,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4378193990","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9987251,0.000034829,0.0002665983,0.00013204737,0.000009803306,0.000021793478,0.000009552224,0.000009810442,0.0007905889],"genre_scores_gemma":[0.9986119,0.00009038282,0.0004886185,0.00008499519,0.0000060164575,0.000026466985,0.000018949768,0.000004945757,0.00066757534],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9941071,0.0023262806,0.00046162706,0.0003131829,0.0021488762,0.0006429921],"domain_scores_gemma":[0.9746181,0.009990777,0.004495536,0.0005960584,0.0049973726,0.0053022318],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007732,0.00031099038,0.00040011437,0.0010348709,0.0011985998,0.0034031752,0.0005389898,0.0007542371,0.0022407924],"category_scores_gemma":[0.03373324,0.00026768973,0.0004116344,0.00050400174,0.0008594233,0.0010571404,0.0015383001,0.0013871779,0.0004848001],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005345348,0.005444035,0.6543889,0.00042568025,0.00009503031,0.0007644807,0.18427154,0.0008300624,0.009944811,0.0005988638,0.002114479,0.14058761],"study_design_scores_gemma":[0.00006236063,0.009316331,0.6446696,0.00043288883,0.00009010711,0.0012531263,0.31730717,0.003911047,0.00727026,0.0008272871,0.01464154,0.00021829113],"about_ca_topic_score_codex":0.0014958291,"about_ca_topic_score_gemma":0.0019570505,"teacher_disagreement_score":0.007732,"about_ca_system_score_codex":0.00091336796,"about_ca_system_score_gemma":0.0015681299,"threshold_uncertainty_score":0.04089123},"labels":[],"label_agreement":null},{"id":"W4381250449","doi":"10.5206/cjsotlrcacea.2023.1.14439","title":"Assessing the Value of Integrating Writing and Writing Instruction into a Research Methods Course","year":2023,"lang":"en","type":"article","venue":"The Canadian Journal for the Scholarship of Teaching and Learning","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Attendance; Context (archaeology); Mathematics education; Situated; Value (mathematics); Academic writing; Pedagogy; Psychology; Computer science; Political science","score_opus":0.1725336623282052,"score_gpt":0.5409770908104593,"score_spread":0.3684434284822541,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4381250449","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9956072,0.00006877767,0.0006803301,0.00042750564,0.0000117877225,0.0003096674,0.000023782328,0.000036603808,0.0028343683],"genre_scores_gemma":[0.9877294,0.00012293518,0.010699636,0.0001794802,0.000019498384,0.0003009778,0.000053340733,0.0000092531545,0.00088547025],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9639357,0.015285211,0.001966071,0.0017441879,0.014469296,0.0025994843],"domain_scores_gemma":[0.80096835,0.114425726,0.0277597,0.009643074,0.025797566,0.021405594],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.036351208,0.0005866239,0.0006776403,0.0022532812,0.00272009,0.007111392,0.0021744354,0.0013873792,0.0016489915],"category_scores_gemma":[0.16061026,0.00046953993,0.0005752161,0.0020116447,0.0017589295,0.0029951963,0.00397878,0.0020375077,0.00046674797],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0019408222,0.013580597,0.37146842,0.00082698156,0.00022685954,0.0004530031,0.053538248,0.0011188376,0.014012647,0.0008845275,0.001190598,0.54075843],"study_design_scores_gemma":[0.00021689934,0.012321165,0.93246704,0.0004373937,0.0002642207,0.00018497281,0.0348754,0.0023875968,0.009022919,0.0007258815,0.006939369,0.00015704443],"about_ca_topic_score_codex":0.024692232,"about_ca_topic_score_gemma":0.070696905,"teacher_disagreement_score":0.036351208,"about_ca_system_score_codex":0.009459307,"about_ca_system_score_gemma":0.024319869,"threshold_uncertainty_score":0.19224584},"labels":[],"label_agreement":null},{"id":"W4381623794","doi":"10.1007/978-981-287-079-7_135-1","title":"An Equitable Approach to Academic Integrity Through Alternative Assessment","year":2023,"lang":"en","type":"book-chapter","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Athabasca University","funders":"","keywords":"Academic dishonesty; Academic integrity; Disengagement theory; Competition (biology); Cheating; Engineering ethics; Political science; Action (physics); Psychology; Test (biology); Dishonesty; Public relations; Social psychology; Engineering; Medicine","score_opus":0.1827588145916285,"score_gpt":0.45288182951778605,"score_spread":0.27012301492615753,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4381623794","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0030455189,0.0020189981,0.17311439,0.015516874,0.0006550507,0.00008678937,0.000035507215,0.00019479696,0.80533206],"genre_scores_gemma":[0.32523367,0.0035360672,0.20789371,0.0030793853,0.00075847784,0.000384878,0.000099260105,0.00040539933,0.45860904],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9822307,0.007793241,0.0005125996,0.0006369623,0.008354371,0.00047216672],"domain_scores_gemma":[0.9843948,0.0069533414,0.0007039849,0.0027662679,0.0047288467,0.00045274378],"candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.011707142,0.00054942997,0.00055751886,0.0024542955,0.0029215366,0.0090507595,0.002486274,0.0026447163,0.01254937],"category_scores_gemma":[0.026272602,0.0003686891,0.00045345208,0.0017937645,0.00963727,0.009730222,0.0071126306,0.005768776,0.0030539033],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000052713613,0.000019072035,0.00012479682,0.000030878506,0.0000034877673,0.000027108716,0.0011482494,0.00056192855,0.00008970331,0.90316224,0.011306448,0.08352082],"study_design_scores_gemma":[0.0000033662095,0.000019850022,0.00019571494,0.00016234347,0.0000051854618,0.00014026214,0.00076038734,0.0023564184,0.000398438,0.88242245,0.113523774,0.000011752497],"about_ca_topic_score_codex":0.002092246,"about_ca_topic_score_gemma":0.004570075,"teacher_disagreement_score":0.9973553,"about_ca_system_score_codex":0.0032385637,"about_ca_system_score_gemma":0.005586006,"threshold_uncertainty_score":0.061914027},"labels":[],"label_agreement":null},{"id":"W4381740816","doi":"10.1177/02655322231179128","title":"Rethinking student placement to enhance efficiency and student agency","year":2023,"lang":"en","type":"article","venue":"Language Testing","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Université de Montréal; Carleton University; University of Ottawa","funders":"University of Ottawa","keywords":"Agency (philosophy); Context (archaeology); Psychology; Process (computing); Test (biology); Mathematics education; Language proficiency; Pedagogy; Computer science; Sociology","score_opus":0.0478632348052326,"score_gpt":0.4160427232575863,"score_spread":0.3681794884523537,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4381740816","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8548789,0.00019039275,0.108494416,0.003935029,0.0006260409,0.003991201,0.00010342672,0.0023268561,0.025453698],"genre_scores_gemma":[0.807312,0.00022320547,0.18212306,0.0004379776,0.00009896883,0.0018284615,0.00011595993,0.00032970126,0.0075307144],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.93603384,0.04257496,0.003972036,0.0022478437,0.012835615,0.0023356918],"domain_scores_gemma":[0.8475259,0.08954683,0.0076497067,0.021708902,0.025743144,0.007825507],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.060859933,0.0011278093,0.0011995267,0.002030472,0.0022817967,0.009363875,0.0029899322,0.0012839333,0.0042055994],"category_scores_gemma":[0.18690352,0.000583939,0.00085714326,0.0012219523,0.0027535472,0.004686075,0.005997197,0.0030837492,0.002235246],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00041952622,0.0041967407,0.038171753,0.00052994426,0.00005951537,0.00023481432,0.058445252,0.0016487245,0.014439194,0.0040545855,0.0074749943,0.870325],"study_design_scores_gemma":[0.0008399876,0.02330497,0.37568027,0.0024289961,0.00026038443,0.0015605697,0.19154115,0.043473963,0.10691099,0.048011284,0.20459655,0.001390902],"about_ca_topic_score_codex":0.001347309,"about_ca_topic_score_gemma":0.003621288,"teacher_disagreement_score":0.060859933,"about_ca_system_score_codex":0.0028215016,"about_ca_system_score_gemma":0.0056279376,"threshold_uncertainty_score":0.32186192},"labels":[],"label_agreement":null},{"id":"W4381937219","doi":"10.2478/jelpp-2023-0001","title":"Culturally responsive policy development: Co-constructing assessment and reporting practices with First Nation educators in Alberta","year":2023,"lang":"en","type":"article","venue":"Journal of Educational Leadership Policy and Practice","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"St. Mary's University","funders":"","keywords":"Indigenous; Project commissioning; Work (physics); Publishing; Political science; Best practice; Pedagogy; Educational assessment; Sociology; Public relations; Medical education; Engineering; Medicine","score_opus":0.24300334854349917,"score_gpt":0.5005989092489506,"score_spread":0.2575955607054514,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4381937219","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92454994,0.0006496765,0.020586519,0.019204568,0.00016790343,0.0033677767,0.00012621113,0.00036877565,0.030978685],"genre_scores_gemma":[0.9575635,0.00035480715,0.035422552,0.0008916194,0.000019673544,0.00077201624,0.00009219183,0.000056085828,0.0048275497],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9081939,0.06336167,0.0038741948,0.004424332,0.011628095,0.008517874],"domain_scores_gemma":[0.86218727,0.055906918,0.008445294,0.009863554,0.049410254,0.014186664],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.14880542,0.0004939413,0.0005932867,0.004120574,0.021554323,0.010958456,0.0058452734,0.0021841335,0.0018819296],"category_scores_gemma":[0.103519045,0.00076456444,0.0003539604,0.0037152097,0.007961389,0.0033644345,0.009886836,0.0036751095,0.00022264826],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001434103,0.0009943377,0.08866839,0.00030908195,0.000035045272,0.0015330997,0.7000188,0.0032070654,0.0046935803,0.009333373,0.00462421,0.18643948],"study_design_scores_gemma":[0.000042136013,0.00034701763,0.067356154,0.00077134155,0.000040079438,0.00022534787,0.83677137,0.0051879883,0.0050922697,0.004590291,0.079363205,0.00021282426],"about_ca_topic_score_codex":0.72968405,"about_ca_topic_score_gemma":0.8538609,"teacher_disagreement_score":0.27031595,"about_ca_system_score_codex":0.10499766,"about_ca_system_score_gemma":0.27218497,"threshold_uncertainty_score":0.7869677},"labels":[],"label_agreement":null},{"id":"W4382752350","doi":"10.3389/feduc.2023.1192754","title":"Assessment purposes and methods used by EFL teachers in secondary schools in Jordan","year":2023,"lang":"en","type":"article","venue":"Frontiers in Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Descriptive statistics; Medical education; Psychology; Mathematics education; English as a foreign language; Pedagogy; Medicine; Mathematics","score_opus":0.019255209631174445,"score_gpt":0.4148986868049889,"score_spread":0.3956434771738145,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4382752350","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9240908,0.004534507,0.0248952,0.0016929338,0.000088191046,0.0011143945,0.0003133498,0.00033797542,0.04293258],"genre_scores_gemma":[0.93719786,0.00217882,0.051883105,0.00042712496,0.00003084914,0.0006549312,0.00016914231,0.00006597462,0.0073921806],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9818102,0.00972157,0.0020594327,0.0012138492,0.004489112,0.00070581125],"domain_scores_gemma":[0.98264056,0.0051526437,0.0026721866,0.000951543,0.0073921243,0.0011909588],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015302352,0.0005419747,0.00060804345,0.0049003065,0.0025834711,0.0037695928,0.0009595183,0.0006023154,0.0017917755],"category_scores_gemma":[0.015975237,0.0003136236,0.00029946072,0.0028494298,0.0018329622,0.0016150315,0.002767488,0.0007437592,0.0010025573],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026039104,0.000846608,0.20728889,0.0016341627,0.000038865863,0.0008005039,0.20818202,0.00040208836,0.011405792,0.003091825,0.0027014236,0.5633474],"study_design_scores_gemma":[0.000094752184,0.0010242688,0.32480428,0.003058482,0.00005989861,0.00307819,0.4513803,0.0021818602,0.016916871,0.0068498612,0.19028603,0.00026521942],"about_ca_topic_score_codex":0.0032119863,"about_ca_topic_score_gemma":0.008248513,"teacher_disagreement_score":0.015302352,"about_ca_system_score_codex":0.0019800663,"about_ca_system_score_gemma":0.0065268762,"threshold_uncertainty_score":0.08092749},"labels":[],"label_agreement":null},{"id":"W4384788716","doi":"10.1007/978-3-031-33541-9_4","title":"Speaking “CEFR” about Local Tests: What Mapping a Placement Test to the CEFR Can and Can’t Do","year":2023,"lang":"en","type":"book-chapter","venue":"Educational linguistics","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Documentation; Test (biology); Computer science; Language proficiency; Language assessment; Local language; Psychology; Linguistics; Political science; Mathematics education; Natural language processing","score_opus":0.0452173759265551,"score_gpt":0.3451583806976567,"score_spread":0.2999410047711016,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4384788716","genre_codex":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004837934,0.007525376,0.05534619,0.11087967,0.0056309244,0.00010533877,0.00022467018,0.0015021893,0.8139477],"genre_scores_gemma":[0.17883135,0.008507995,0.062981255,0.041608945,0.002511688,0.00033595134,0.00053767924,0.0024222638,0.70226294],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99663275,0.0016811873,0.00011725441,0.00031832018,0.0009887263,0.0002617601],"domain_scores_gemma":[0.9938146,0.0027373512,0.0002230749,0.00047063705,0.0021286698,0.0006256899],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004203166,0.0009838167,0.00057767535,0.0014396954,0.0024702027,0.0077956184,0.0014171252,0.0028596148,0.021685267],"category_scores_gemma":[0.018667772,0.0004013823,0.00053077,0.0014728507,0.006084315,0.013755331,0.0023326678,0.0074403044,0.012698832],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021503569,0.000078756086,0.0012397666,0.00021095063,0.000009405158,0.00012576296,0.007372425,0.0005238327,0.0005199052,0.23671421,0.42557588,0.32760757],"study_design_scores_gemma":[0.000011043408,0.000085415944,0.0023059547,0.0010663526,0.000014740399,0.00049018196,0.01191203,0.0013866222,0.001491902,0.18501979,0.7961446,0.00007133483],"about_ca_topic_score_codex":0.01905216,"about_ca_topic_score_gemma":0.023613477,"teacher_disagreement_score":0.021685267,"about_ca_system_score_codex":0.0035595277,"about_ca_system_score_gemma":0.005282644,"threshold_uncertainty_score":0.072544456},"labels":[],"label_agreement":null},{"id":"W4385240403","doi":"10.5430/wjel.v13n7p243","title":"Peer- and Self-Assessment in Primary School English Language Classrooms","year":2023,"lang":"en","type":"article","venue":"World Journal of English Language","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Universiti Kebangsaan Malaysia","keywords":"Reading (process); English language; Peer assessment; Mathematics education; Peer feedback; Psychology; Self-assessment; Language assessment; Pedagogy; Medical education; Medicine; Linguistics","score_opus":0.009286252171380948,"score_gpt":0.3089423695732991,"score_spread":0.29965611740191817,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385240403","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99653625,0.00020798374,0.00043270754,0.00015821392,0.0000130003355,0.000087261855,0.000010036927,0.000022469527,0.0025321713],"genre_scores_gemma":[0.9973711,0.00016327917,0.0010455402,0.000029669513,0.0000048680877,0.000048452745,0.000010716336,0.0000039315523,0.0013224464],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98708344,0.009049196,0.0005441808,0.0007604887,0.0020308371,0.0005318517],"domain_scores_gemma":[0.98499054,0.006232813,0.0022820248,0.0009720074,0.0030880563,0.002434593],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008359212,0.0002932677,0.00060943654,0.0009238449,0.0014684275,0.0016579799,0.0007922575,0.00043508792,0.001534902],"category_scores_gemma":[0.02010908,0.00030384757,0.00024344097,0.0003389208,0.0009136421,0.0010072336,0.001962487,0.0005547519,0.0003997826],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003611038,0.0030355027,0.3943098,0.0006939328,0.00009004371,0.00086009793,0.2578067,0.00032235193,0.004857248,0.00050819054,0.0020874676,0.33506766],"study_design_scores_gemma":[0.000100417135,0.005006847,0.577833,0.0008729644,0.00012151772,0.0011571855,0.37987533,0.0018427445,0.0058174375,0.001289587,0.025924144,0.00015879111],"about_ca_topic_score_codex":0.0021350638,"about_ca_topic_score_gemma":0.0047680014,"teacher_disagreement_score":0.008359212,"about_ca_system_score_codex":0.00073161704,"about_ca_system_score_gemma":0.0019886268,"threshold_uncertainty_score":0.04420823},"labels":[],"label_agreement":null},{"id":"W4385416815","doi":"10.1080/0969594x.2023.2242004","title":"Educational assessment in Ghana: The influence of historical colonization and political accountability","year":2023,"lang":"en","type":"article","venue":"Assessment in Education Principles Policy and Practice","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Formative assessment; Summative assessment; Accountability; Context (archaeology); Politics; Political science; Educational assessment; Government (linguistics); Pedagogy; Sociology; Public administration; Geography; Law","score_opus":0.05672128565655436,"score_gpt":0.46713834296963386,"score_spread":0.4104170573130795,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385416815","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.76382256,0.02373879,0.002272203,0.09861409,0.00043402394,0.00007995665,0.000107942455,0.000034095872,0.110896304],"genre_scores_gemma":[0.9936592,0.0033063802,0.00035551545,0.0008955793,0.000053992782,0.000010288511,0.000010322761,0.000009955346,0.0016988206],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.9968214,0.0020697175,0.00012626455,0.00022349221,0.00031269854,0.00044647255],"domain_scores_gemma":[0.9899032,0.0057315347,0.0019004018,0.00028884696,0.0011518673,0.0010242257],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005369835,0.00013378053,0.00017037998,0.0013055588,0.003322731,0.003736515,0.00038374055,0.00071763573,0.0026599385],"category_scores_gemma":[0.011900704,0.00022643803,0.00007192354,0.0025529843,0.0105128735,0.0037658755,0.002478466,0.0019907884,0.00020236894],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018497913,0.00015253831,0.09148297,0.0008859916,0.0000140175725,0.007195457,0.46750125,0.0005140936,0.0016820063,0.1900838,0.010982916,0.22931993],"study_design_scores_gemma":[0.000030253928,0.00015603262,0.23545821,0.0031494743,0.000018584486,0.0030300766,0.26520082,0.0006623362,0.0012061028,0.028425762,0.4625871,0.00007531348],"about_ca_topic_score_codex":0.03482587,"about_ca_topic_score_gemma":0.05989663,"teacher_disagreement_score":0.03482587,"about_ca_system_score_codex":0.010398418,"about_ca_system_score_gemma":0.0073672584,"threshold_uncertainty_score":0.07544613},"labels":[],"label_agreement":null},{"id":"W4385721572","doi":"10.1080/20004508.2023.2244136","title":"Conceptions of classroom assessment and approaches to grading: teachers’ and students’ perspectives","year":2023,"lang":"en","type":"article","venue":"Education Inquiry","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":16,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Alberta; Queen's University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Grading (engineering); Psychology; Situational ethics; Mathematics education; Accountability; Pedagogy; Social psychology","score_opus":0.249927262996829,"score_gpt":0.46178672550008454,"score_spread":0.21185946250325555,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385721572","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9443898,0.0023611316,0.0052245627,0.0061687334,0.00006177532,0.000050560524,0.00005787049,0.00002847566,0.041656934],"genre_scores_gemma":[0.9980817,0.0003433922,0.00053412904,0.000077810095,0.0000060283755,0.0000097213515,0.000010874769,0.000005367212,0.0009309351],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9833377,0.0075905244,0.00061148853,0.0007339399,0.0061069923,0.0016194732],"domain_scores_gemma":[0.9819403,0.007813188,0.0023831967,0.0006229106,0.004801791,0.0024386474],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011553341,0.00036940962,0.0003998524,0.0027734952,0.005501403,0.011355717,0.0013781269,0.0010155627,0.0006968596],"category_scores_gemma":[0.018063964,0.00037365613,0.00033364692,0.0021175223,0.015194384,0.003044306,0.003142346,0.0030414737,0.00007957073],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007305524,0.000082026505,0.09979563,0.000103906816,0.000017653372,0.00026928255,0.82985514,0.00044975587,0.0013013431,0.036848325,0.0009466619,0.030257152],"study_design_scores_gemma":[0.000022994469,0.00008489649,0.15567435,0.00026321676,0.000033816093,0.0003647872,0.7909264,0.0012456505,0.00095154723,0.0086854575,0.041617226,0.00012964121],"about_ca_topic_score_codex":0.51476675,"about_ca_topic_score_gemma":0.54427016,"teacher_disagreement_score":0.51476675,"about_ca_system_score_codex":0.027066654,"about_ca_system_score_gemma":0.0253321,"threshold_uncertainty_score":0.97618175},"labels":[],"label_agreement":null},{"id":"W4385727033","doi":"10.1080/13562517.2023.2244439","title":"Applying Sadler’s principles in holistic assessment design: a retrospective account","year":2023,"lang":"en","type":"article","venue":"Teaching in Higher Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Coursework; Epistemology; Engineering ethics; Interpretation (philosophy); Higher education; Work (physics); Psychology; Sociology; Management science; Mathematics education; Pedagogy; Computer science; Engineering; Philosophy; Political science","score_opus":0.18477408254957373,"score_gpt":0.4522338658129323,"score_spread":0.26745978326335856,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385727033","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.042356774,0.00427076,0.87918776,0.014877097,0.0005376917,0.0011963458,0.00013780186,0.0003923241,0.057043422],"genre_scores_gemma":[0.46647453,0.0051140636,0.51281494,0.0022289527,0.0002895037,0.002242295,0.0001456611,0.000290916,0.010399173],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.94187987,0.04219059,0.0037093298,0.0029199228,0.0085852,0.0007150943],"domain_scores_gemma":[0.9191923,0.057908714,0.0038409755,0.0071468237,0.011443611,0.00046756375],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.07009371,0.0010820224,0.0007499265,0.0034196037,0.0026951956,0.007127888,0.0019736465,0.0017087458,0.0016297852],"category_scores_gemma":[0.09658303,0.00090291025,0.00074608123,0.0022312116,0.014871373,0.01018129,0.005912131,0.004143128,0.0006939063],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014300387,0.00014638001,0.007788693,0.0011650207,0.00004791912,0.00043630376,0.12565781,0.00402316,0.0036286653,0.5945591,0.009820548,0.25258347],"study_design_scores_gemma":[0.00008982579,0.00090381457,0.011002009,0.0040388163,0.00013104695,0.002942906,0.040578153,0.019752687,0.010276146,0.47295618,0.4369412,0.00038718],"about_ca_topic_score_codex":0.0018915973,"about_ca_topic_score_gemma":0.0032624775,"teacher_disagreement_score":0.07009371,"about_ca_system_score_codex":0.0040733903,"about_ca_system_score_gemma":0.005006444,"threshold_uncertainty_score":0.3706954},"labels":[],"label_agreement":null},{"id":"W4385780286","doi":"10.1016/j.ijedro.2023.100275","title":"Teachers’ beliefs and attitudes towards students’ self assessment: A latent profile analysis","year":2023,"lang":"en","type":"article","venue":"International Journal of Educational Research Open","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Lifelong learning; Psychology; Context (archaeology); Mathematics education; Self-assessment; Self-efficacy; Pedagogy; Social psychology","score_opus":0.17298423100958948,"score_gpt":0.5825242070376433,"score_spread":0.4095399760280538,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385780286","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99940574,0.0000107988,0.00031684714,0.00003089313,0.0000010114669,0.000021025755,0.000039076192,0.000001600224,0.00017316036],"genre_scores_gemma":[0.99958414,0.000015381982,0.00021435886,0.0000045205393,7.9930106e-7,0.000025995356,0.00006273745,0.0000010119851,0.000091019225],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9984047,0.00064419094,0.00018877958,0.00015226581,0.00038119964,0.0002289035],"domain_scores_gemma":[0.9937542,0.0028051327,0.0016707408,0.0004745907,0.00083381357,0.000461597],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003560551,0.0002752925,0.00042594038,0.0013614115,0.0007370365,0.0016811467,0.0003216944,0.000422056,0.0017884304],"category_scores_gemma":[0.00966661,0.00031405687,0.0006338506,0.0014951947,0.0006794494,0.00088585896,0.0009739872,0.00086322654,0.00032513967],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000053203035,0.00019595193,0.98407817,0.000014335991,0.00002612595,0.000050448063,0.008905577,0.00012898062,0.00026284007,0.00015760322,0.00007794682,0.0060488367],"study_design_scores_gemma":[0.0000125639335,0.00018624768,0.9755105,0.000036705555,0.000027086928,0.00007235424,0.020081207,0.0032278628,0.0002257131,0.00025677678,0.0003500223,0.000012944671],"about_ca_topic_score_codex":0.0071854526,"about_ca_topic_score_gemma":0.008198441,"teacher_disagreement_score":0.0071854526,"about_ca_system_score_codex":0.00077606406,"about_ca_system_score_gemma":0.0011103055,"threshold_uncertainty_score":0.01883024},"labels":[],"label_agreement":null},{"id":"W4385816187","doi":"10.37213/cjal.2023.32829","title":"Teachers’ Perceptions Toward Video as a Tool for Feedback on Students’ Oral Performance","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Applied Linguistics","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"University of Leeds","keywords":"Perception; Quality (philosophy); Psychology; Multimedia; Peer feedback; Process (computing); Educational technology; Mathematics education; Computer science","score_opus":0.04550380798343907,"score_gpt":0.35256506685414957,"score_spread":0.3070612588707105,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4385816187","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9923373,0.00041303042,0.0019852244,0.00062219385,0.00003588636,0.000052447216,0.000024350942,0.00002633703,0.004503293],"genre_scores_gemma":[0.99762255,0.00034305357,0.0008670474,0.000099546305,0.000016246986,0.000035494668,0.000015390086,0.00001183375,0.0009887539],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.98935074,0.0065285526,0.0006037737,0.00038841306,0.0026473706,0.0004811955],"domain_scores_gemma":[0.9575104,0.026832977,0.005707721,0.00074768544,0.007065549,0.0021356752],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008984457,0.00027703395,0.00030121885,0.0009955913,0.0009323779,0.0028095213,0.00037053318,0.0010419248,0.002464072],"category_scores_gemma":[0.04669399,0.0002507054,0.00028592465,0.00038116545,0.001132268,0.0016691341,0.0011454533,0.0009004257,0.00036197098],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011762773,0.00085400377,0.23463833,0.0013124562,0.0000940509,0.0021686943,0.54679894,0.00059508113,0.041647546,0.0013179486,0.002382508,0.16701417],"study_design_scores_gemma":[0.00013186534,0.0047500553,0.2772453,0.0012649305,0.00015068689,0.0030095505,0.66063446,0.0026717128,0.013504147,0.0006641633,0.03567958,0.00029350942],"about_ca_topic_score_codex":0.003537888,"about_ca_topic_score_gemma":0.003449956,"teacher_disagreement_score":0.008984457,"about_ca_system_score_codex":0.0009156176,"about_ca_system_score_gemma":0.0009394197,"threshold_uncertainty_score":0.047514915},"labels":[],"label_agreement":null},{"id":"W4386172632","doi":"10.4018/978-1-6684-8213-1.ch002","title":"Do Our Test Scores Mean What We Think?","year":2023,"lang":"en","type":"book-chapter","venue":"Advances in educational technologies and instructional design book series","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Institute for Christian Studies; University of Toronto; Memorial University of Newfoundland","funders":"","keywords":"Active listening; Construct (python library); Test (biology); Construct validity; Scale (ratio); Language assessment; English language; Psychology; Writing assessment; Cognition; Computer science; Applied psychology; Mathematics education; Psychometrics; Developmental psychology; Communication; Geography; Cartography","score_opus":0.038357665505082114,"score_gpt":0.3299552900022539,"score_spread":0.29159762449717175,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386172632","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12414595,0.033375576,0.054457147,0.16241266,0.013467563,0.00035862724,0.0031662814,0.001918983,0.6066971],"genre_scores_gemma":[0.8345889,0.028785406,0.05083565,0.01930585,0.001886945,0.00071239803,0.0021264988,0.0013798965,0.060378592],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9878836,0.003508619,0.0006424459,0.00075052574,0.0067584338,0.00045636506],"domain_scores_gemma":[0.96555835,0.016962178,0.00234816,0.00147561,0.012333958,0.0013217914],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.014101835,0.0006962446,0.0008081802,0.0023082704,0.0013663521,0.009540361,0.0011659431,0.0009158319,0.007655141],"category_scores_gemma":[0.0865812,0.0002861215,0.00048742018,0.0028842348,0.006713198,0.0076082777,0.0015871669,0.0029856977,0.0055623287],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006907081,0.00010601392,0.06062287,0.0009540461,0.00010437929,0.00008058563,0.035505865,0.00032074886,0.00096707925,0.07309919,0.17115642,0.6570137],"study_design_scores_gemma":[0.000034965673,0.0002903179,0.1548273,0.0051328596,0.00016274613,0.00083717064,0.103480026,0.0013635315,0.0032042826,0.1745163,0.555784,0.00036653725],"about_ca_topic_score_codex":0.018454624,"about_ca_topic_score_gemma":0.028737387,"teacher_disagreement_score":0.98589814,"about_ca_system_score_codex":0.004314577,"about_ca_system_score_gemma":0.005396312,"threshold_uncertainty_score":0.07457852},"labels":[],"label_agreement":null},{"id":"W4386301473","doi":"10.25071/1497-3170.2440","title":"Further Resources on Assignments and Assessing Student Learning","year":2004,"lang":"en","type":"article","venue":"CORE","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Mathematics education; Psychology; Computer science; Medical education; Pedagogy; Medicine","score_opus":0.05337328706321376,"score_gpt":0.39242412687652994,"score_spread":0.3390508398133162,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386301473","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0048437975,0.0076534436,0.04334585,0.008110411,0.006165758,0.0017045242,0.029514942,0.01711141,0.88154984],"genre_scores_gemma":[0.010290847,0.0068011703,0.027265606,0.0031131776,0.0056389784,0.0011989521,0.026589815,0.0069236048,0.9121779],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99797875,0.00052121235,0.000206171,0.00013986435,0.00092377845,0.00023022221],"domain_scores_gemma":[0.9683995,0.014998828,0.0008181892,0.004743422,0.006794308,0.004245742],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0029488842,0.0019320595,0.0029770473,0.013008706,0.0012609463,0.0020329538,0.0034398688,0.0021506525,0.57228225],"category_scores_gemma":[0.026467722,0.0010513103,0.0015322056,0.007746966,0.0005539345,0.0041064178,0.00475769,0.0021222814,0.2998638],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000142537,0.00048580975,0.00030122843,0.00072350097,0.000010570012,0.00012505155,0.00015763917,0.00039425527,0.0022074038,0.0012071138,0.6372377,0.35700724],"study_design_scores_gemma":[0.0000735176,0.0001759998,0.003822593,0.00091663125,0.000040155133,0.0003287661,0.00012683672,0.00045763844,0.002596656,0.0054469556,0.98596466,0.000049552636],"about_ca_topic_score_codex":0.00551566,"about_ca_topic_score_gemma":0.018403253,"teacher_disagreement_score":0.57228225,"about_ca_system_score_codex":0.0011473638,"about_ca_system_score_gemma":0.0037087218,"threshold_uncertainty_score":0.6100874},"labels":[],"label_agreement":null},{"id":"W4386423373","doi":"10.1080/14703297.2023.2254275","title":"The impact of a feedback intervention on university students’ second language writing feedback literacy","year":2023,"lang":"en","type":"article","venue":"Innovations in Education and Teaching International","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Universidade de Macau","keywords":"Peer feedback; Literacy; Affect (linguistics); Language proficiency; Psychology; Mathematics education; Action research; Intervention (counseling); Corrective feedback; Pedagogy","score_opus":0.019851093037725944,"score_gpt":0.4230627981079701,"score_spread":0.4032117050702442,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386423373","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99842405,0.00014264997,0.00044516558,0.000092352406,0.00003892695,0.00023035989,0.000015955702,0.00007670016,0.00053392793],"genre_scores_gemma":[0.99444604,0.00022515193,0.0038245397,0.000081295846,0.000037226622,0.0005110184,0.000033918248,0.000008464995,0.00083226623],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99753594,0.0011966429,0.00024075084,0.00022986763,0.00047930004,0.00031739555],"domain_scores_gemma":[0.9923374,0.0039450377,0.0010902501,0.00025125785,0.0007594417,0.0016166109],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023846296,0.00075819984,0.0009852462,0.0009394783,0.0007494829,0.00058164995,0.0006118495,0.00069712166,0.0027598343],"category_scores_gemma":[0.015008121,0.00027570644,0.000594295,0.00034665043,0.00032994538,0.00047213287,0.00096484035,0.00094081607,0.0002780954],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.012042937,0.06947491,0.034116544,0.0021123588,0.00022491068,0.00058587897,0.01103718,0.00061211624,0.029286437,0.00015473549,0.001337113,0.83901495],"study_design_scores_gemma":[0.010334383,0.24011697,0.67259276,0.0013355917,0.0011455123,0.0008217042,0.012534779,0.0052698413,0.044173576,0.0005658925,0.010825146,0.0002837936],"about_ca_topic_score_codex":0.0011415961,"about_ca_topic_score_gemma":0.0021160448,"teacher_disagreement_score":0.0027598343,"about_ca_system_score_codex":0.0004704009,"about_ca_system_score_gemma":0.001497508,"threshold_uncertainty_score":0.01261127},"labels":[],"label_agreement":null},{"id":"W4386475491","doi":"10.3928/01484834-20230712-12","title":"Optimizing Student Self-Efficacy and Success on the National Registration Examination","year":2023,"lang":"en","type":"article","venue":"Journal of Nursing Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Georgian College","funders":"","keywords":"Medical education; Psychology; Medical physics; Medicine","score_opus":0.09151724207427203,"score_gpt":0.4555501671324382,"score_spread":0.36403292505816615,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386475491","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9971438,0.000018306439,0.00014307417,0.00005938066,0.0000094186025,0.000027849901,0.000018088193,0.00001724648,0.00256283],"genre_scores_gemma":[0.9987326,0.000018971445,0.00031412294,0.000013289661,0.000004929317,0.000022229991,0.00003319915,0.000004710608,0.00085606554],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9974649,0.0010947284,0.00015555332,0.00014931025,0.00073458254,0.0004009652],"domain_scores_gemma":[0.9910886,0.0035931359,0.001464226,0.00044411272,0.0016452189,0.001764734],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0039888797,0.00033613577,0.00055759755,0.0007222173,0.0005991085,0.0011096061,0.00033924502,0.0005311711,0.0022584007],"category_scores_gemma":[0.015758818,0.00014812802,0.0005498703,0.00031350105,0.00031199056,0.0005590328,0.0010483599,0.0008064079,0.00070356263],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002176923,0.013979348,0.79764557,0.000053008003,0.00012261423,0.000063641644,0.0013313217,0.0015356026,0.0032107027,0.00030306925,0.0017787117,0.17779945],"study_design_scores_gemma":[0.00008169869,0.006097803,0.9846102,0.000025706431,0.00007798747,0.000043680135,0.0010262871,0.0031422374,0.0038725173,0.00014564392,0.0008496806,0.000026575533],"about_ca_topic_score_codex":0.0024484594,"about_ca_topic_score_gemma":0.0040000062,"teacher_disagreement_score":0.0039888797,"about_ca_system_score_codex":0.000547592,"about_ca_system_score_gemma":0.0013370666,"threshold_uncertainty_score":0.021095455},"labels":[],"label_agreement":null},{"id":"W4386482646","doi":"10.1111/emip.12572","title":"Digital Module 33: Fairness in Classroom Assessment: Dimensions and Tensions","year":2023,"lang":"en","type":"article","venue":"Educational Measurement Issues and Practice","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Legitimacy; Perception; Psychology; Disengagement theory; Critical reflection; Social psychology; Pedagogy; Political science","score_opus":0.11055476844730784,"score_gpt":0.42774349726989375,"score_spread":0.3171887288225859,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386482646","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.52514666,0.0029755565,0.047154915,0.039892375,0.0027403748,0.0031314332,0.004875981,0.0022830155,0.37179965],"genre_scores_gemma":[0.78727293,0.004544395,0.0323427,0.004432544,0.0013575036,0.002289751,0.0035202652,0.0004672747,0.16377254],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9985655,0.0005285444,0.00012916826,0.000089909576,0.000504419,0.00018257907],"domain_scores_gemma":[0.99504966,0.0019533108,0.0004819242,0.00036156227,0.0012153484,0.0009381611],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029966389,0.0002959309,0.00035538405,0.0009530309,0.000688381,0.0023664245,0.00058048824,0.00084137305,0.03363624],"category_scores_gemma":[0.008356256,0.00016350555,0.00028358932,0.0011993336,0.0007191504,0.0012692689,0.0020103308,0.0013361571,0.0051337117],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022898993,0.0015218077,0.027258843,0.0008043659,0.000019533243,0.00017276529,0.0060416367,0.0015829927,0.0045642545,0.017206961,0.24581572,0.6947821],"study_design_scores_gemma":[0.00005398588,0.00094114087,0.20306507,0.0015929337,0.000028359682,0.00093166815,0.0077161626,0.0044570626,0.008146683,0.024197143,0.74873686,0.00013304694],"about_ca_topic_score_codex":0.0009364573,"about_ca_topic_score_gemma":0.0019601888,"teacher_disagreement_score":0.03363624,"about_ca_system_score_codex":0.0013228455,"about_ca_system_score_gemma":0.0018882873,"threshold_uncertainty_score":0.11252445},"labels":[],"label_agreement":null},{"id":"W4386496830","doi":"10.1080/0969594x.2023.2255936","title":"Classroom assessment fairness inventory: a new instrument to support perceived fairness in classroom assessment","year":2023,"lang":"en","type":"article","venue":"Assessment in Education Principles Policy and Practice","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Queen's University; University of Saskatchewan; University of Alberta","funders":"","keywords":"Psychology; Grading (engineering); Equity (law); Perception; Legitimacy; Diversity (politics); Pedagogy; Medical education; Sociology; Political science","score_opus":0.08886918950009094,"score_gpt":0.4589116453380946,"score_spread":0.37004245583800366,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386496830","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8206001,0.00079088897,0.07308629,0.0015526628,0.00034575426,0.00795811,0.004821991,0.0009084716,0.08993581],"genre_scores_gemma":[0.8504209,0.000755763,0.12849775,0.0003143583,0.00008831438,0.00577275,0.0024200405,0.000113639224,0.011616477],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.9902368,0.0021437192,0.001467936,0.00049545226,0.005106527,0.0005496078],"domain_scores_gemma":[0.9597449,0.01256975,0.0064809034,0.00328822,0.015178542,0.002737746],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012783476,0.0004200992,0.00068040716,0.0033437696,0.0019774523,0.0020984216,0.0011702926,0.0004282756,0.0036697763],"category_scores_gemma":[0.033985958,0.00034266745,0.00088212546,0.0020315216,0.001341013,0.0016968456,0.0027926539,0.0016679665,0.0007078187],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00047681152,0.0018646744,0.45401898,0.0004408814,0.00018481405,0.00017182002,0.016738342,0.0016487817,0.0058285883,0.007685308,0.01632489,0.4946162],"study_design_scores_gemma":[0.00013059264,0.00053515466,0.93632066,0.00034854776,0.00010384048,0.00018172123,0.005942031,0.0049433997,0.0029052643,0.0058765495,0.042483136,0.00022926087],"about_ca_topic_score_codex":0.090728894,"about_ca_topic_score_gemma":0.22003035,"teacher_disagreement_score":0.090728894,"about_ca_system_score_codex":0.006748262,"about_ca_system_score_gemma":0.013734606,"threshold_uncertainty_score":0.18040156},"labels":[],"label_agreement":null},{"id":"W4386646311","doi":"10.24918/cs.2023.35","title":"A Multi-Institutional Alternative Assessment Faculty Learning Community: Supporting Teaching in Higher Education","year":2023,"lang":"en","type":"article","venue":"CourseSource","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"University of Missouri-St. Louis; National Science Foundation","keywords":"Higher education; Mathematics education; Pedagogy; Sociology; Medical education; Political science; Psychology; Medicine","score_opus":0.13876697072006697,"score_gpt":0.47052804912822604,"score_spread":0.33176107840815905,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386646311","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.71497995,0.0010565231,0.12110388,0.040135495,0.001635055,0.0033082631,0.0004391937,0.0037994026,0.11354224],"genre_scores_gemma":[0.9014656,0.0002214459,0.07736735,0.002292236,0.00027590757,0.0010826404,0.00017541618,0.0003178607,0.016801497],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.976518,0.017252294,0.0004607316,0.0011807323,0.002586101,0.0020022031],"domain_scores_gemma":[0.94539523,0.015278324,0.002737819,0.004607075,0.005838525,0.026143068],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.024782673,0.0004087977,0.00025498966,0.002088493,0.014343413,0.008565106,0.0032982624,0.002380325,0.012798591],"category_scores_gemma":[0.04071581,0.00033569286,0.00048229934,0.0015422484,0.0038388225,0.008911882,0.02478387,0.003135684,0.002965034],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022875307,0.0024013126,0.030167898,0.00045159616,0.000032335814,0.0012233048,0.22188607,0.000569924,0.0039548497,0.018215224,0.06367618,0.65719247],"study_design_scores_gemma":[0.00020761327,0.001529738,0.024821084,0.0010049853,0.00004731447,0.0016902107,0.3620283,0.005286124,0.004970493,0.030635841,0.5675242,0.00025405452],"about_ca_topic_score_codex":0.0022929956,"about_ca_topic_score_gemma":0.011478759,"teacher_disagreement_score":0.024782673,"about_ca_system_score_codex":0.0026824167,"about_ca_system_score_gemma":0.017524535,"threshold_uncertainty_score":0.13106489},"labels":[],"label_agreement":null},{"id":"W4387092961","doi":"10.7202/1106315ar","title":"(Un)making the grade: An instructor’s guide to mitigating the negative impacts of grades within a neoliberal university system","year":2023,"lang":"en","type":"article","venue":"McGill Journal of Education / Revue des sciences de l éducation de McGill","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Grading (engineering); Autonomy; Ideology; Mathematics education; Higher education; Pedagogy; Psychology; Sociology; Political science; Politics; Engineering; Law","score_opus":0.24062593713932814,"score_gpt":0.4462539837511797,"score_spread":0.20562804661185155,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387092961","genre_codex":"commentary","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0025870197,0.027564943,0.23411198,0.53416985,0.025134962,0.0024023578,0.0007828041,0.007911091,0.16533491],"genre_scores_gemma":[0.041942917,0.035222284,0.48357993,0.15171781,0.00748235,0.003235024,0.0003603309,0.003379984,0.2730793],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99400985,0.002980673,0.0005479701,0.000355398,0.0018232255,0.00028300987],"domain_scores_gemma":[0.9810353,0.005784841,0.0010736595,0.0014152993,0.008090585,0.0026003027],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013000076,0.0012739142,0.00067391683,0.0041469387,0.0045468216,0.005185195,0.0039015622,0.0073454687,0.014179655],"category_scores_gemma":[0.03623483,0.00076084497,0.00053459837,0.002106898,0.0061132764,0.006804869,0.003931254,0.009053338,0.013305921],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000140495895,0.00010670607,0.0005589807,0.00017602254,0.000006783378,0.00017062546,0.0039895894,0.00032973272,0.0006321996,0.01584701,0.76099575,0.21717253],"study_design_scores_gemma":[0.000010918413,0.000045189365,0.0005781916,0.00050499255,0.0000053002163,0.0001594417,0.0018195161,0.00040623522,0.00024674146,0.00948427,0.9867067,0.000032390137],"about_ca_topic_score_codex":0.033683907,"about_ca_topic_score_gemma":0.11147294,"teacher_disagreement_score":0.033683907,"about_ca_system_score_codex":0.00454158,"about_ca_system_score_gemma":0.0123416325,"threshold_uncertainty_score":0.06875175},"labels":[],"label_agreement":null},{"id":"W4387127679","doi":"10.1007/s11409-023-09359-6","title":"Towards a new theory of student self-assessment: Tracing learners’ cognitive and affective processes","year":2023,"lang":"en","type":"article","venue":"Metacognition and Learning","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":9,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Psychology; Cognition; Metacognition; Session (web analytics); Self-assessment; Qualitative property; Learning analytics; Cognitive psychology; Applied psychology; Mathematics education; Social psychology; Computer science; Data science; World Wide Web","score_opus":0.03971913758098297,"score_gpt":0.3714180673073345,"score_spread":0.3316989297263515,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387127679","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03362753,0.00067406724,0.94797146,0.002257541,0.00008322194,0.00008574831,0.000046065714,0.00022726036,0.015027032],"genre_scores_gemma":[0.73837817,0.0006897264,0.25744697,0.00025890095,0.000062452105,0.00024779182,0.00005318388,0.00009202768,0.0027707047],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9975279,0.0012066979,0.00012291512,0.00048369172,0.00052854983,0.00013024811],"domain_scores_gemma":[0.9872634,0.008432773,0.0008273532,0.0014710592,0.0015684558,0.00043700295],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0040627704,0.0007089116,0.0006354734,0.0023109117,0.00075909024,0.0079915505,0.0020688903,0.001632078,0.0026790407],"category_scores_gemma":[0.017470807,0.00058994966,0.000790876,0.0010810781,0.0067608887,0.011879063,0.0025233738,0.0028540334,0.00056432124],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000054297616,0.00019175053,0.016783996,0.00042923362,0.000118620075,0.00014845762,0.021174159,0.0140044745,0.0054419935,0.79839975,0.0010477154,0.14220554],"study_design_scores_gemma":[0.000016431926,0.00010684981,0.00852443,0.00023521548,0.0000534067,0.00022573344,0.004231963,0.10646151,0.0025989304,0.8686913,0.008794564,0.000059615628],"about_ca_topic_score_codex":0.0025003857,"about_ca_topic_score_gemma":0.0017281059,"teacher_disagreement_score":0.0079915505,"about_ca_system_score_codex":0.001823893,"about_ca_system_score_gemma":0.002459454,"threshold_uncertainty_score":0.021486223},"labels":[],"label_agreement":null},{"id":"W4387429753","doi":"10.1177/02655322231202947","title":"Our validity looks like justice. Does yours?","year":2023,"lang":"en","type":"article","venue":"Language Testing","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":27,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Lethbridge","funders":"","keywords":"Economic Justice; Oppression; Psychology; Licensure; Set (abstract data type); Social psychology; Mathematics education; Pedagogy; Law; Political science; Computer science","score_opus":0.13450710571791363,"score_gpt":0.4132933080995925,"score_spread":0.2787862023816789,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387429753","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.055092845,0.004960268,0.07209195,0.6691323,0.010543173,0.0005949302,0.00052160094,0.00040721486,0.1866557],"genre_scores_gemma":[0.87075263,0.0016521087,0.0331813,0.078876786,0.003154908,0.0006152446,0.0001900357,0.00041892048,0.011157936],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8181638,0.10470825,0.01075343,0.013887708,0.048504703,0.0039820834],"domain_scores_gemma":[0.56779134,0.20396556,0.03484373,0.06526697,0.11840912,0.009723244],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.14140457,0.00080382277,0.0016495985,0.0048978818,0.009235154,0.013172378,0.0020948888,0.004590561,0.004955603],"category_scores_gemma":[0.41526487,0.0006694653,0.0013567093,0.0025301906,0.06089355,0.020363461,0.009169753,0.009881493,0.0018844545],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002285718,0.00032415052,0.04270772,0.0011424083,0.00044750332,0.0002711135,0.058484796,0.00047207205,0.0017390798,0.63451684,0.05859088,0.20107497],"study_design_scores_gemma":[0.000073776784,0.00036838718,0.018010205,0.0026457056,0.00021600362,0.0004913288,0.033465,0.0014202632,0.0021137686,0.7494276,0.19152565,0.0002422938],"about_ca_topic_score_codex":0.009504145,"about_ca_topic_score_gemma":0.007370447,"teacher_disagreement_score":0.85859543,"about_ca_system_score_codex":0.0069159847,"about_ca_system_score_gemma":0.015258612,"threshold_uncertainty_score":0.74782777},"labels":[],"label_agreement":null},{"id":"W4387645971","doi":"10.1007/978-3-319-17461-7_23","title":"Structural Assessment of Knowledge as, of, and for Learning","year":2023,"lang":"en","type":"book-chapter","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Formative assessment; Summative assessment; Computer science; Grading (engineering); Knowledge survey; Knowledge transfer; Knowledge management; Engineering; Mathematics education; Psychology","score_opus":0.07878391421382185,"score_gpt":0.42132641150073846,"score_spread":0.3425424972869166,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387645971","genre_codex":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007851835,0.0038187755,0.11055343,0.0030805597,0.00065368996,0.00019292593,0.00031389837,0.0005992124,0.87293565],"genre_scores_gemma":[0.1898178,0.00599324,0.144139,0.0006672963,0.00033370336,0.00029609908,0.0007270934,0.0003065543,0.6577192],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9989555,0.00019839562,0.000039917475,0.00006585775,0.0007095233,0.000030827927],"domain_scores_gemma":[0.9975897,0.001306484,0.000096951546,0.00014299517,0.0007900962,0.000073827156],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001239956,0.0005191477,0.00035149054,0.0011144663,0.00038574226,0.0025879312,0.0008709573,0.0005445866,0.017818937],"category_scores_gemma":[0.0056049153,0.00020260796,0.00024872948,0.0007849812,0.0012782376,0.002355566,0.000997253,0.0011835718,0.0047433106],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002490133,0.00006481318,0.0013048943,0.00031433546,0.000008046872,0.000046786587,0.0015150674,0.0010783545,0.0018251156,0.23466451,0.072597325,0.68655586],"study_design_scores_gemma":[0.00000793838,0.00016805688,0.009971123,0.0010268728,0.00002805431,0.0006344327,0.003304249,0.011916466,0.0062554753,0.4604691,0.50617826,0.000039913008],"about_ca_topic_score_codex":0.0026814397,"about_ca_topic_score_gemma":0.0080905035,"teacher_disagreement_score":0.017818937,"about_ca_system_score_codex":0.0012257181,"about_ca_system_score_gemma":0.0019666203,"threshold_uncertainty_score":0.059610248},"labels":[],"label_agreement":null},{"id":"W4387821100","doi":"10.1186/s40468-023-00261-1","title":"Instructional practices and students’ reading performance: a comparative study of 10 top performing regions in PISA 2018","year":2023,"lang":"en","type":"article","venue":"Language Testing in Asia","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Enthusiasm; Psychology; Reading (process); Multilevel model; Mathematics education; China; Sample (material); Teacher education; Pedagogy; Geography; Social psychology; Political science; Chemistry","score_opus":0.1189039487434486,"score_gpt":0.4392416959406387,"score_spread":0.3203377471971901,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387821100","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9997054,0.000022014918,0.00001845852,0.0000073644665,6.6826607e-7,0.000003560123,0.000039490285,0.0000012476868,0.00020181373],"genre_scores_gemma":[0.999686,0.00003887251,0.000063112384,0.000008855894,0.0000010842941,0.00001164355,0.000087754495,9.706904e-7,0.000101830294],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9995177,0.00011919225,0.00004263176,0.00010309112,0.00007663698,0.00014071265],"domain_scores_gemma":[0.9989015,0.00025814303,0.00031877228,0.00008730638,0.00019756398,0.00023676948],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006247242,0.00027354844,0.0005287293,0.0018096081,0.0012148421,0.0009505208,0.0003931451,0.0002682922,0.0011128309],"category_scores_gemma":[0.001547433,0.00031068633,0.000357505,0.002376572,0.0005529578,0.00046811387,0.0010720136,0.0004331927,0.0002831244],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007699221,0.00019045689,0.9836248,0.000026976257,0.000038208676,0.0002314762,0.007899558,0.000043916094,0.00082489307,0.000026206822,0.00008379132,0.0069328253],"study_design_scores_gemma":[0.0000017460148,0.00010694511,0.9918276,0.0000066861735,0.000013851708,0.00006716956,0.0076119085,0.000039615723,0.00016666137,0.0000050018793,0.00014967051,0.0000032369276],"about_ca_topic_score_codex":0.02373951,"about_ca_topic_score_gemma":0.04453219,"teacher_disagreement_score":0.02373951,"about_ca_system_score_codex":0.00086365803,"about_ca_system_score_gemma":0.00094765064,"threshold_uncertainty_score":0.047202647},"labels":[],"label_agreement":null},{"id":"W4387886945","doi":"10.7202/1106853ar","title":"La planification flexible des démarches d’évaluation, un levier vers une évaluation pour apprendre ?","year":2023,"lang":"fr","type":"article","venue":"Mesure et évaluation en éducation","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université du Québec à Chicoutimi","funders":"","keywords":"Political science; Humanities; Valuation (finance); Philosophy; Economics","score_opus":0.16570951755185664,"score_gpt":0.42937230069526217,"score_spread":0.2636627831434055,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387886945","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0993365,0.0034876908,0.7804001,0.018561779,0.0005963774,0.002449131,0.0004255574,0.0026025663,0.09214037],"genre_scores_gemma":[0.55269694,0.0013941373,0.4248047,0.0008661379,0.00009428258,0.0015004735,0.00044502673,0.0004230694,0.01777526],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.97219896,0.014940373,0.0017418442,0.0023826745,0.007517042,0.001219086],"domain_scores_gemma":[0.9607359,0.018989997,0.0033071246,0.007471422,0.0073702782,0.0021252672],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.025374034,0.0015001498,0.00077698834,0.0021520846,0.0023944585,0.008398145,0.001822104,0.0022298247,0.009063136],"category_scores_gemma":[0.047319267,0.00077873765,0.0012542008,0.0015852351,0.0051853647,0.011309787,0.00542337,0.0042441376,0.0019405208],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005850405,0.0005086828,0.0072538964,0.001634537,0.00011624256,0.00035745624,0.028479228,0.010921812,0.010572213,0.24197954,0.008184982,0.68940645],"study_design_scores_gemma":[0.0004570638,0.0019738616,0.024836695,0.0045385305,0.00029812774,0.0007590026,0.038324405,0.052690852,0.028692441,0.49476674,0.35213125,0.00053090684],"about_ca_topic_score_codex":0.009504786,"about_ca_topic_score_gemma":0.011607096,"teacher_disagreement_score":0.025374034,"about_ca_system_score_codex":0.005322553,"about_ca_system_score_gemma":0.013063467,"threshold_uncertainty_score":0.13419235},"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,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kellogg's (Canada)","funders":"","keywords":"Formative assessment; Perspective (graphical); Computer science; Mathematics education; Engineering ethics; Psychology; Artificial intelligence; Engineering","score_opus":0.08248159969855182,"score_gpt":0.40453806837561695,"score_spread":0.32205646867706517,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4388945822","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0737337,0.0687464,0.37106606,0.41292718,0.0048009823,0.00054383714,0.00010027963,0.00091681763,0.067164764],"genre_scores_gemma":[0.699131,0.027972698,0.24377574,0.017204598,0.0024603386,0.0009033679,0.00010422257,0.00040933597,0.0080386475],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.87423533,0.098655574,0.005202886,0.0034129773,0.016065935,0.0024271565],"domain_scores_gemma":[0.7288923,0.21840732,0.0067951176,0.011409934,0.027958954,0.00653644],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.14127894,0.000896756,0.0011839545,0.0035651,0.0044391397,0.02446334,0.003992936,0.0062954626,0.0025055418],"category_scores_gemma":[0.14799108,0.00065472093,0.0007612188,0.0030997335,0.02184929,0.023979386,0.011119952,0.00909814,0.000787398],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010582281,0.0004708457,0.009352677,0.0022862186,0.00005453258,0.0008895266,0.12564418,0.0017767643,0.0016594615,0.2651336,0.015006529,0.57761985],"study_design_scores_gemma":[0.000059470578,0.0005248478,0.004454812,0.007292223,0.000052544852,0.003032742,0.14776377,0.0077933553,0.0044733756,0.44606793,0.37822935,0.00025561653],"about_ca_topic_score_codex":0.0029129484,"about_ca_topic_score_gemma":0.0039466512,"teacher_disagreement_score":0.14127894,"about_ca_system_score_codex":0.0069328444,"about_ca_system_score_gemma":0.016428009,"threshold_uncertainty_score":0.74716336},"labels":[],"label_agreement":null},{"id":"W4389063152","doi":"10.1007/978-3-031-42675-9_10","title":"Continuing Professional Development for TESOL Instructors Working in Canadian Settlement Language Training Programmes in Alberta","year":2023,"lang":"en","type":"book-chapter","venue":"Springer texts in education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Reading (process); Professional development; Context (archaeology); Pedagogy; Situated; Continuing professional development; Best practice; Medical education; Construct (python library); Psychology; Political science; Public relations; Medicine; Computer science; Geography","score_opus":0.03501021238634065,"score_gpt":0.3496769211331269,"score_spread":0.3146667087467862,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389063152","genre_codex":"empirical","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7052245,0.012743085,0.00096256466,0.024722442,0.0015153467,0.00042756076,0.0006899145,0.00032366943,0.253391],"genre_scores_gemma":[0.56878495,0.0042920867,0.0024195658,0.0015020777,0.00007033717,0.00014235992,0.00043004882,0.00007221974,0.42228636],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9983382,0.00022759249,0.000036288882,0.00011458889,0.0004896935,0.00079359295],"domain_scores_gemma":[0.99131143,0.00038220003,0.00013581198,0.000061953906,0.0018828213,0.006225823],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020626346,0.00025909944,0.00016624917,0.0014051996,0.009026803,0.0034963957,0.0025815696,0.0011553036,0.017250989],"category_scores_gemma":[0.0029837098,0.00030646476,0.00015283114,0.0016676283,0.0014530884,0.0006993179,0.0020938674,0.0012725566,0.0017033264],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00023397194,0.0009306077,0.07137099,0.00043448235,0.000008773667,0.0026215988,0.17858678,0.0006217096,0.003033092,0.008492823,0.22058235,0.5130828],"study_design_scores_gemma":[0.000045735487,0.00038416992,0.20541659,0.0006732892,0.000010080669,0.00052342284,0.19415934,0.0005542844,0.00071241334,0.00053573534,0.5969301,0.00005487316],"about_ca_topic_score_codex":0.864127,"about_ca_topic_score_gemma":0.9740216,"teacher_disagreement_score":0.864127,"about_ca_system_score_codex":0.037394036,"about_ca_system_score_gemma":0.14524497,"threshold_uncertainty_score":0.27334636},"labels":[],"label_agreement":null},{"id":"W4389071196","doi":"10.55016/ojs/ajer.v69i1.73115","title":"Examining School Principals' Conceptions of Assessment and Grading Practices","year":2023,"lang":"en","type":"article","venue":"Alberta Journal of Educational Research","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Social Sciences and Humanities Research Council of Canada; Queen's University","keywords":"Summative assessment; Accountability; Grading (engineering); Pedagogy; Valuation (finance); Psychology; Mathematics education; Political science; Formative assessment; Engineering","score_opus":0.3830018737737938,"score_gpt":0.5869952308588688,"score_spread":0.20399335708507504,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389071196","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9973488,0.00017553361,0.0005579074,0.0002856442,0.000006629871,0.000019473011,0.000018589837,0.000004353079,0.0015831017],"genre_scores_gemma":[0.99924767,0.00011292051,0.00024497692,0.00002967141,0.0000035507067,0.000012112562,0.000017146638,0.0000014504853,0.00033045068],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.9942855,0.0026934934,0.00050110224,0.00056217826,0.0014085225,0.0005492122],"domain_scores_gemma":[0.9843685,0.0041459817,0.0046189246,0.0007628639,0.0043358062,0.0017679193],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010480083,0.00026420483,0.00031251807,0.002241252,0.0022127335,0.00446677,0.00054198987,0.0005399946,0.0010610173],"category_scores_gemma":[0.013845927,0.0003651708,0.00026567394,0.0018153647,0.0028833766,0.0021513023,0.0018979324,0.0009734789,0.0001556322],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005468636,0.000114852024,0.7419572,0.00011629998,0.000034096334,0.00020387628,0.22817932,0.00020325833,0.0009502622,0.004321596,0.0005706444,0.02329391],"study_design_scores_gemma":[0.000017957744,0.00026209332,0.6680466,0.00017804449,0.000040415096,0.00015952668,0.31791514,0.0013519139,0.0005980605,0.002098066,0.00924867,0.000083476276],"about_ca_topic_score_codex":0.014763995,"about_ca_topic_score_gemma":0.017534913,"teacher_disagreement_score":0.014763995,"about_ca_system_score_codex":0.0036760177,"about_ca_system_score_gemma":0.004543262,"threshold_uncertainty_score":0.05542463},"labels":[],"label_agreement":null},{"id":"W4389150341","doi":"10.1111/medu.15287","title":"Timing's not everything: Immediate and delayed feedback are equally beneficial for performance in formative multiple‐choice testing","year":2023,"lang":"en","type":"article","venue":"Medical Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"The Wilson Centre; University of Toronto","funders":"University of Melbourne","keywords":"Formative assessment; Psychology; Medical education; Medicine; Computer science; Mathematics education","score_opus":0.060264609286590116,"score_gpt":0.3781464413277802,"score_spread":0.3178818320411901,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389150341","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98462623,0.0013366117,0.008594497,0.0008186712,0.0002776046,0.00025667643,0.000103379796,0.00018288987,0.003803495],"genre_scores_gemma":[0.9841733,0.00033898724,0.013996327,0.00022479164,0.00007942775,0.00014077382,0.00007542823,0.00003493127,0.0009360136],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9924644,0.004063604,0.0006828113,0.0004814821,0.002122908,0.00018491292],"domain_scores_gemma":[0.90678996,0.07345378,0.01162674,0.0019522872,0.002617142,0.0035600157],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011316576,0.00041664383,0.00045018256,0.00039749435,0.0002182173,0.0011934368,0.00067245506,0.00086412026,0.0058595026],"category_scores_gemma":[0.088445224,0.0002611637,0.0004223796,0.00030976353,0.00036318184,0.001218003,0.00075120147,0.0006786612,0.0005804089],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.027871193,0.0054539293,0.13026495,0.0018641972,0.00029939922,0.0002262766,0.0014194783,0.0013945795,0.046511598,0.0006195546,0.0018323757,0.78224254],"study_design_scores_gemma":[0.002381277,0.08399832,0.83333564,0.0018216142,0.0010508992,0.002154076,0.001368898,0.009104489,0.05283739,0.0028209891,0.008904574,0.00022187781],"about_ca_topic_score_codex":0.00045628264,"about_ca_topic_score_gemma":0.00077974045,"teacher_disagreement_score":0.011316576,"about_ca_system_score_codex":0.00030972544,"about_ca_system_score_gemma":0.0011172774,"threshold_uncertainty_score":0.059848547},"labels":[],"label_agreement":null},{"id":"W4389312553","doi":"10.5070/w4jwa.6559","title":"Editor’s Introduction: Contract Grading, Portfolios, and Reflection","year":2023,"lang":"en","type":"article","venue":"Journal of writing assessment","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"University of Colorado Colorado Springs; California State University, Fresno; San Francisco State University; University of Toronto Mississauga; Fairleigh Dickinson University; University of Toronto; University of Denver; Appalachian State University; University of South Florida; University of Nevada, Reno; University of Lethbridge; Grand Valley State University; Boise State University; Elon University; University of Central Florida; Wayne State University; University of Miami; York University; Idaho State Board of Education; Montclair State University; Middle Tennessee State University; University of California, Davis; Arizona State University; Florida State University; Santa Clara University","keywords":"Grading (engineering); Watson; Reflection (computer programming); Construct (python library); Mathematics education; Engineering ethics; Sociology; Computer science; Psychology; Engineering; Programming language; Natural language processing; Civil engineering","score_opus":0.02656024756128134,"score_gpt":0.3992466048207308,"score_spread":0.3726863572594495,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389312553","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000054409178,0.0040526236,0.00019700278,0.07264642,0.9221017,0.000011024375,0.00005023367,0.000037772697,0.00084886386],"genre_scores_gemma":[0.0008826093,0.0035325068,0.0003754704,0.07602244,0.91363096,0.000038539813,0.000039316885,0.00004962031,0.0054285377],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9913858,0.001626554,0.0012129081,0.0014500573,0.0039302567,0.00039438583],"domain_scores_gemma":[0.94852024,0.019062657,0.0028240932,0.0013809344,0.024708325,0.003503639],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009325303,0.0029964068,0.0021409234,0.0037812092,0.0039722356,0.010350914,0.003899647,0.013683498,0.010846627],"category_scores_gemma":[0.059256192,0.0010910024,0.0020506128,0.0028397187,0.003701904,0.005906403,0.0021875862,0.016051544,0.005460295],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022074013,0.000016330809,0.000073259085,0.00012789996,0.000010056686,0.000034366276,0.000017158729,0.00002586277,0.00002570373,0.0005610624,0.9926609,0.006425287],"study_design_scores_gemma":[0.00005270511,0.000045379868,0.0010168742,0.0008509829,0.000046317553,0.00023917375,0.00013440431,0.00037951444,0.00016559073,0.0020777597,0.9949522,0.00003922367],"about_ca_topic_score_codex":0.003118785,"about_ca_topic_score_gemma":0.006352286,"teacher_disagreement_score":0.013683498,"about_ca_system_score_codex":0.0033482285,"about_ca_system_score_gemma":0.0046815625,"threshold_uncertainty_score":0.04931754},"labels":[],"label_agreement":null},{"id":"W4389314126","doi":"10.5206/cjsotlrcacea.2023.2.14217","title":"Engagement in Assessment Change and the Role of SoTL","year":2023,"lang":"en","type":"article","venue":"The Canadian Journal for the Scholarship of Teaching and Learning","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Queen's University","funders":"","keywords":"Valuation (finance); Psychology; Pedagogy; Sociology; Business","score_opus":0.0955023403316147,"score_gpt":0.38207473942755693,"score_spread":0.28657239909594223,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389314126","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9179111,0.0005393334,0.010769929,0.011871312,0.00013303114,0.00038025528,0.000055975655,0.00015900606,0.05817998],"genre_scores_gemma":[0.99493426,0.000102111335,0.0019246426,0.0002719525,0.000018456172,0.00013939006,0.000023171626,0.000027843498,0.0025580633],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.89787066,0.07005006,0.002394293,0.0042757317,0.017327229,0.00808206],"domain_scores_gemma":[0.87663096,0.06772532,0.013170271,0.0062204185,0.015923388,0.020329649],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.041758154,0.0004373903,0.000612646,0.003322491,0.009605944,0.015286466,0.0029423372,0.0024839467,0.0045714616],"category_scores_gemma":[0.123646736,0.00051182037,0.00058543944,0.0019778353,0.010819352,0.005733584,0.018011203,0.003962338,0.00057106937],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00024969253,0.0014389479,0.14026685,0.00038720507,0.000072782816,0.0005971752,0.6644102,0.00062150543,0.0020299512,0.025412861,0.0024116982,0.16210115],"study_design_scores_gemma":[0.00011587083,0.0010418355,0.2303683,0.00084496394,0.00006292919,0.00058366824,0.6421285,0.004015571,0.0015391394,0.025089625,0.094017334,0.00019215439],"about_ca_topic_score_codex":0.033536524,"about_ca_topic_score_gemma":0.035650335,"teacher_disagreement_score":0.041758154,"about_ca_system_score_codex":0.016794015,"about_ca_system_score_gemma":0.02601628,"threshold_uncertainty_score":0.22084087},"labels":[],"label_agreement":null},{"id":"W4389317357","doi":"10.1007/978-3-031-39989-3_135","title":"An Equitable Approach to Academic Integrity Through Alternative Assessment","year":2023,"lang":"en","type":"book-chapter","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Athabasca University","funders":"","keywords":"Academic dishonesty; Academic integrity; Disengagement theory; Competition (biology); Cheating; Psychology; Dishonesty; Action (physics); Engineering ethics; Test (biology); Political science; Public relations; Social psychology; Engineering; Medicine","score_opus":0.1827588145916285,"score_gpt":0.45288182951778605,"score_spread":0.27012301492615753,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389317357","genre_codex":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0030455189,0.0020189981,0.17311439,0.015516874,0.0006550507,0.00008678937,0.000035507215,0.00019479696,0.80533206],"genre_scores_gemma":[0.32523367,0.0035360672,0.20789371,0.0030793853,0.00075847784,0.000384878,0.000099260105,0.00040539933,0.45860904],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9822307,0.007793241,0.0005125996,0.0006369623,0.008354371,0.00047216672],"domain_scores_gemma":[0.9843948,0.0069533414,0.0007039849,0.0027662679,0.0047288467,0.00045274378],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.011707142,0.00054942997,0.00055751886,0.0024542955,0.0029215366,0.0090507595,0.002486274,0.0026447163,0.01254937],"category_scores_gemma":[0.026272602,0.0003686891,0.00045345208,0.0017937645,0.00963727,0.009730222,0.0071126306,0.005768776,0.0030539033],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000052713613,0.000019072035,0.00012479682,0.000030878506,0.0000034877673,0.000027108716,0.0011482494,0.00056192855,0.00008970331,0.90316224,0.011306448,0.08352082],"study_design_scores_gemma":[0.0000033662095,0.000019850022,0.00019571494,0.00016234347,0.0000051854618,0.00014026214,0.00076038734,0.0023564184,0.000398438,0.88242245,0.113523774,0.000011752497],"about_ca_topic_score_codex":0.002092246,"about_ca_topic_score_gemma":0.004570075,"teacher_disagreement_score":0.9973553,"about_ca_system_score_codex":0.0032385637,"about_ca_system_score_gemma":0.005586006,"threshold_uncertainty_score":0.061914027},"labels":[],"label_agreement":null},{"id":"W4389437665","doi":"10.1007/s13384-023-00675-z","title":"Mediating teachers’ assessment work","year":2023,"lang":"en","type":"article","venue":"The Australian Educational Researcher","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":7,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Australian Research Council; University of Western Australia; Department of Education and Training, Queensland Government; Australian Catholic University","keywords":"Work (physics); Psychology; Mathematics education; Computer science; Medical education; Medicine; Engineering; Mechanical engineering","score_opus":0.20188555313891177,"score_gpt":0.5174908116563913,"score_spread":0.31560525851747956,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4389437665","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.39280483,0.0013620864,0.05140505,0.02206756,0.0013226767,0.0004630537,0.00014203896,0.0010270553,0.5294056],"genre_scores_gemma":[0.98631305,0.00008967454,0.0026346762,0.0005412164,0.000040534287,0.00014391087,0.000016958744,0.00012752692,0.010092516],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.88774866,0.08215066,0.0031201325,0.007235249,0.013347951,0.0063973446],"domain_scores_gemma":[0.77075016,0.1643888,0.010387309,0.020204324,0.018206814,0.016062643],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0345637,0.00060679304,0.0008769848,0.0029457018,0.009930529,0.017487891,0.0028479819,0.003184846,0.021638246],"category_scores_gemma":[0.16829409,0.0013421145,0.00060765474,0.0015634677,0.016066063,0.008456467,0.019322816,0.0059201093,0.0032563522],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021592106,0.00042419773,0.032019485,0.00027760054,0.000056054043,0.0008572892,0.7288071,0.00029199413,0.004935942,0.16518793,0.0059551634,0.060971394],"study_design_scores_gemma":[0.00026205566,0.00048569,0.083693966,0.001395303,0.00017385806,0.0013910872,0.45651558,0.0023739478,0.008567261,0.1765022,0.26844725,0.00019177744],"about_ca_topic_score_codex":0.014436789,"about_ca_topic_score_gemma":0.01059257,"teacher_disagreement_score":0.0345637,"about_ca_system_score_codex":0.0077325883,"about_ca_system_score_gemma":0.016395617,"threshold_uncertainty_score":0.18279254},"labels":[],"label_agreement":null},{"id":"W4390142211","doi":"10.18733/cpi29712","title":"Designing Culturally Responsive Online Assessments for Equity-Deserving Students","year":2023,"lang":"en","type":"article","venue":"Cultural and Pedagogical Inquiry","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"University of Alberta","keywords":"Equity (law); Key (lock); Alternative assessment; Psychology; Engineering ethics; Knowledge management; Sociology; Engineering; Pedagogy; Computer science; Political science; Computer security","score_opus":0.8118352865393967,"score_gpt":0.6370228546540551,"score_spread":0.17481243188534168,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390142211","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6881279,0.0008633447,0.2506716,0.004744567,0.0004765197,0.003187147,0.000108278444,0.0010210038,0.050799627],"genre_scores_gemma":[0.79729563,0.0006689005,0.19566248,0.000711584,0.00006517907,0.001396088,0.00007185708,0.00007852804,0.004049773],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9883156,0.008147038,0.00060363516,0.00043266037,0.0019810146,0.00052008394],"domain_scores_gemma":[0.97543925,0.014651813,0.0017612062,0.0011902334,0.004291582,0.0026659293],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0149167515,0.00045955094,0.0005177921,0.0008488084,0.001234157,0.0037468763,0.0012737171,0.00091788964,0.0022689882],"category_scores_gemma":[0.054192107,0.00021975904,0.0002843772,0.00045461784,0.0012112585,0.002952738,0.004153894,0.0017895959,0.0007400146],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003006851,0.0030167345,0.05098331,0.0011276939,0.00006105806,0.0007086511,0.08386315,0.0049490742,0.01516265,0.02939355,0.0063294577,0.80410403],"study_design_scores_gemma":[0.00039646495,0.0055218874,0.0800139,0.0037270996,0.00019535201,0.002068366,0.20611301,0.032502834,0.0670205,0.2715488,0.33027303,0.0006187202],"about_ca_topic_score_codex":0.0004751789,"about_ca_topic_score_gemma":0.0011974045,"teacher_disagreement_score":0.0149167515,"about_ca_system_score_codex":0.00084104843,"about_ca_system_score_gemma":0.003384171,"threshold_uncertainty_score":0.07888824},"labels":[],"label_agreement":null},{"id":"W4390142485","doi":"10.18733/cpi29704","title":"CPI Special Issue: \"All That Glitters is Not Gold: Culturally Responsive Online Assessment and Pedagogy in Uncertain Times\"","year":2023,"lang":"en","type":"article","venue":"Cultural and Pedagogical Inquiry","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"University of Alberta","keywords":"Narrative; Pedagogy; Psychology; Art; Literature","score_opus":0.5297709765784591,"score_gpt":0.5571719172056213,"score_spread":0.02740094062716225,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390142485","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0005550318,0.011687784,0.0008981226,0.08467891,0.8431344,0.00022691234,0.000965154,0.0005380543,0.05731574],"genre_scores_gemma":[0.0045427727,0.016532386,0.0011837706,0.032813378,0.69856066,0.00045166528,0.0015306942,0.0010535559,0.2433311],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9972506,0.0004307064,0.00022021629,0.00032667228,0.0014813443,0.00029047765],"domain_scores_gemma":[0.98661256,0.003658585,0.00071502343,0.00043134124,0.005009917,0.0035727622],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0037800167,0.0014252138,0.0015256301,0.0022549091,0.0036016158,0.0097848885,0.0022074769,0.0040391516,0.106774926],"category_scores_gemma":[0.0127730565,0.00061375054,0.0008848782,0.0021903785,0.0015266372,0.0053197946,0.0041998364,0.007455155,0.04923338],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000058726746,0.0000098997625,0.00003232766,0.00004701517,7.7934976e-7,0.000011047112,0.00002992279,0.0000047614376,0.00003697859,0.00012176412,0.9930407,0.006658857],"study_design_scores_gemma":[0.0000056803087,0.000025293833,0.00064266875,0.00022269433,0.000002731799,0.00006571096,0.0001856264,0.0000427897,0.00007077559,0.00031883433,0.9984073,0.0000098270375],"about_ca_topic_score_codex":0.005126498,"about_ca_topic_score_gemma":0.01192016,"teacher_disagreement_score":0.106774926,"about_ca_system_score_codex":0.0030816756,"about_ca_system_score_gemma":0.0066229333,"threshold_uncertainty_score":0.3571977},"labels":[],"label_agreement":null},{"id":"W4390142649","doi":"10.18733/cpi29703","title":"CPI Welcomes the Summer 2023 Special Issue “All That Glitters is Not Gold: Culturally Responsive Online Assessment and Pedagogy in Uncertain Times” with Kim Koh, Jennifer Lock, and Cecille DePass, invited Guest Editors","year":2023,"lang":"en","type":"article","venue":"Cultural and Pedagogical Inquiry","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"University of Alberta","keywords":"Lock (firearm); Pedagogy; Psychology; Sociology; Engineering; Mechanical engineering","score_opus":0.3971217374120482,"score_gpt":0.5071894733987232,"score_spread":0.11006773598667502,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390142649","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00027947655,0.0035075196,0.00077065744,0.15872559,0.8118373,0.00014834106,0.0003230457,0.00042507256,0.023983015],"genre_scores_gemma":[0.004106146,0.00799512,0.0018578143,0.09005609,0.6299938,0.0006099819,0.00082425465,0.0013157798,0.263241],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.994531,0.0008245221,0.0002964576,0.0006279735,0.0030863753,0.00063364074],"domain_scores_gemma":[0.9701666,0.0053776274,0.00120989,0.0006812784,0.011561081,0.011003521],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007636588,0.0017540775,0.0017602971,0.0020339931,0.0050350097,0.012412253,0.0026543671,0.008282596,0.103334196],"category_scores_gemma":[0.02483585,0.00074339466,0.0013561299,0.0015070122,0.0018750179,0.0077109043,0.0072542047,0.017150622,0.06443987],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000007585606,0.000008495095,0.000022337712,0.000029672803,9.265136e-7,0.000022549413,0.00004261103,0.0000040777604,0.000035244317,0.00016436956,0.99513865,0.004523527],"study_design_scores_gemma":[0.0000043595746,0.000013911525,0.00017048682,0.000097974174,0.0000018021033,0.000042317297,0.0002507572,0.000022658312,0.000040379407,0.0002701735,0.9990761,0.000009068775],"about_ca_topic_score_codex":0.003811654,"about_ca_topic_score_gemma":0.009716907,"teacher_disagreement_score":0.103334196,"about_ca_system_score_codex":0.0031309712,"about_ca_system_score_gemma":0.0074375407,"threshold_uncertainty_score":0.34568727},"labels":[],"label_agreement":null},{"id":"W4390224877","doi":"10.59668/279.12260","title":"Ten principles of alternative assessment","year":2023,"lang":"en","type":"book-chapter","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Athabasca University","funders":"","keywords":"Section (typography); Context (archaeology); Engineering ethics; Work (physics); Process (computing); Alternative assessment; Computer science; Mathematics education; Management science; Engineering; Psychology; History; Mechanical engineering","score_opus":0.10060607331262066,"score_gpt":0.3916637760829068,"score_spread":0.29105770277028614,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390224877","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003359611,0.0053662653,0.51265466,0.018538916,0.00078077393,0.00083691877,0.00017971538,0.0004314161,0.45785177],"genre_scores_gemma":[0.13358364,0.0071559455,0.7783902,0.00419145,0.00042788233,0.002920152,0.00021686482,0.000272243,0.07284162],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9669949,0.01675255,0.0018131316,0.0016338475,0.012071837,0.00073382165],"domain_scores_gemma":[0.98182213,0.011128471,0.0006452614,0.0019309985,0.0038959077,0.0005772387],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02429482,0.0014042786,0.0007965186,0.003303876,0.0029160883,0.010679652,0.002844404,0.0037846107,0.0077987723],"category_scores_gemma":[0.022553422,0.00088565936,0.0012523559,0.0021002947,0.024451679,0.009591384,0.0070026782,0.007639303,0.003219932],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000006221531,0.000022332404,0.00014538605,0.00021278548,0.000006772486,0.00002901909,0.002425051,0.00054093456,0.00008843122,0.95396185,0.0040643094,0.038497042],"study_design_scores_gemma":[0.0000101992155,0.000024025016,0.00015171005,0.0005295916,0.0000068801064,0.00014594724,0.0006489771,0.0012003565,0.00024181476,0.85164726,0.14537404,0.00001909989],"about_ca_topic_score_codex":0.0025363115,"about_ca_topic_score_gemma":0.0035454084,"teacher_disagreement_score":0.02429482,"about_ca_system_score_codex":0.007579203,"about_ca_system_score_gemma":0.008175946,"threshold_uncertainty_score":0.12848485},"labels":[],"label_agreement":null},{"id":"W4390275381","doi":"","title":"The Pedagogical Anatomy of Peer-Assessment: Dissecting a peerScholar Assignment","year":2009,"lang":"en","type":"article","venue":"DOAJ (DOAJ: Directory of Open Access Journals)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"The Scarborough Hospital; University of Toronto","funders":"","keywords":"Psychology; Anatomy; Computer science; Medical education; Medicine","score_opus":0.3579369119647551,"score_gpt":0.6569333339152776,"score_spread":0.29899642195052256,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390275381","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.070874065,0.0014982707,0.77992505,0.02195727,0.0024017273,0.0017975655,0.00008144488,0.0013933969,0.12007115],"genre_scores_gemma":[0.4731887,0.0013365045,0.49353862,0.0028367995,0.0010912919,0.0011573815,0.000057432804,0.00041245972,0.026380787],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9592055,0.029152911,0.0008627021,0.0019934527,0.008116882,0.00066857174],"domain_scores_gemma":[0.9509979,0.030565789,0.0027570135,0.005368528,0.007619105,0.0026916964],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.027354483,0.0008792572,0.00068879285,0.0027243232,0.0051785037,0.0075457483,0.002588324,0.0025053094,0.006683202],"category_scores_gemma":[0.09442148,0.00037730666,0.00036824087,0.0011083067,0.016648833,0.008238365,0.008659477,0.004823831,0.0023452512],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019882263,0.0005323343,0.0070391847,0.000986218,0.000041085834,0.00085863087,0.14564164,0.0014272005,0.011732562,0.2473715,0.030920088,0.55325073],"study_design_scores_gemma":[0.00009282183,0.000993227,0.010244153,0.0014358748,0.00003959038,0.0033337586,0.06125805,0.010545046,0.010835302,0.5518105,0.34908554,0.00032616],"about_ca_topic_score_codex":0.0010125566,"about_ca_topic_score_gemma":0.0019707931,"teacher_disagreement_score":0.9726455,"about_ca_system_score_codex":0.0018989198,"about_ca_system_score_gemma":0.0051408815,"threshold_uncertainty_score":0.14466602},"labels":[],"label_agreement":null},{"id":"W4390393512","doi":"10.1016/j.chbah.2023.100040","title":"A review of assessment for learning with artificial intelligence","year":2023,"lang":"en","type":"review","venue":"Computers in Human Behavior Artificial Humans","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":38,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"Simon Fraser University","keywords":"Scopus; Web of science; Artificial intelligence; Field (mathematics); Work (physics); Applications of artificial intelligence; Computer science; Engineering ethics; Engineering; Political science; MEDLINE","score_opus":0.27226750927799603,"score_gpt":0.506271922895003,"score_spread":0.23400441361700697,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390393512","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.000042361753,0.9987828,0.000114136594,0.0003547204,0.000119567696,0.0000096773165,0.000015339281,0.0000028791599,0.00055853697],"genre_scores_gemma":[0.00068017043,0.99843866,0.0003321213,0.00027550294,0.000102023616,0.000018429577,0.000017894665,0.0000017674374,0.00013341293],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99753416,0.0007567955,0.0006669487,0.00022974865,0.0007411742,0.00007106674],"domain_scores_gemma":[0.9896116,0.0079727275,0.0007514848,0.00016240997,0.0013289851,0.00017282451],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0033470353,0.0010540396,0.001994727,0.007898506,0.00062564533,0.0023964357,0.0013361418,0.0020398078,0.0048729773],"category_scores_gemma":[0.0123524,0.00059177744,0.0012685553,0.009434307,0.0012011593,0.0033448425,0.0013863049,0.0021753397,0.0012640487],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000043710937,0.00006045188,0.00029676504,0.13500617,0.00019527285,0.00011317693,0.00038397586,0.0002333422,0.00023962528,0.006790183,0.026777443,0.8298599],"study_design_scores_gemma":[0.000017733084,0.00008289691,0.002199972,0.15690875,0.00042726402,0.0007600681,0.00031395166,0.00008331474,0.00016323736,0.004649233,0.83435625,0.000037463866],"about_ca_topic_score_codex":0.005307772,"about_ca_topic_score_gemma":0.009383969,"teacher_disagreement_score":0.007898506,"about_ca_system_score_codex":0.0024783104,"about_ca_system_score_gemma":0.007263321,"threshold_uncertainty_score":0.01798153},"labels":[],"label_agreement":null},{"id":"W4390474923","doi":"10.1007/978-981-99-6199-3_7","title":"Experiential Assessment Capacity","year":2023,"lang":"en","type":"book-chapter","venue":"Teacher education, learning innovation and accountability","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Experiential learning; Narrative; Experiential education; Embodied cognition; Action (physics); Psychology; Pedagogy; Experiential knowledge; Engineering ethics; Reflective practice; Capacity building; Epistemology; Political science; Engineering; Art; Philosophy","score_opus":0.06506989302560887,"score_gpt":0.3921458850700106,"score_spread":0.32707599204440174,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390474923","genre_codex":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0052317083,0.00028951193,0.015699318,0.00055942417,0.00010882509,0.00008834492,0.00011447443,0.0001841103,0.97772425],"genre_scores_gemma":[0.2576664,0.00075030595,0.010327796,0.0005512107,0.00014344948,0.00032179474,0.00032878906,0.00009125041,0.729819],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99877244,0.00028364972,0.00007721064,0.0002249665,0.00047373679,0.00016804152],"domain_scores_gemma":[0.99682826,0.0011331525,0.00012698199,0.0008549879,0.0006547725,0.00040175428],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0016840117,0.000612439,0.00023445438,0.0010894239,0.0009467514,0.0046377694,0.0017900332,0.00086489535,0.103407055],"category_scores_gemma":[0.006853991,0.0002603574,0.0003435626,0.0007958922,0.0027010785,0.005903713,0.006351368,0.0017894504,0.017565375],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000034342953,0.00011819108,0.0005838199,0.00012395618,0.000004443065,0.000119251956,0.0016567827,0.000730294,0.0014443531,0.7738509,0.019911392,0.20142226],"study_design_scores_gemma":[0.000016034044,0.00008609995,0.0019198696,0.00025743706,0.000005718489,0.0005479774,0.0011892337,0.0016508915,0.0040680347,0.35458875,0.63564354,0.000026394406],"about_ca_topic_score_codex":0.0010502217,"about_ca_topic_score_gemma":0.0011024169,"teacher_disagreement_score":0.103407055,"about_ca_system_score_codex":0.0010943647,"about_ca_system_score_gemma":0.002242438,"threshold_uncertainty_score":0.34593105},"labels":[],"label_agreement":null},{"id":"W4390474934","doi":"10.1007/978-981-99-6199-3_1","title":"Cultivating Teacher Assessment Capacity","year":2023,"lang":"en","type":"book-chapter","venue":"Teacher education, learning innovation and accountability","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Articulation (sociology); Negotiation; Argument (complex analysis); Politics; Pedagogy; Political science; Sociology; Psychology; Engineering ethics; Engineering; Social science; Medicine","score_opus":0.07216905478032726,"score_gpt":0.39311875628174436,"score_spread":0.3209497015014171,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390474934","genre_codex":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.13079034,0.0011070098,0.044268582,0.0034368837,0.00012643547,0.00006137691,0.00005932911,0.00046193227,0.819688],"genre_scores_gemma":[0.86969876,0.00075948826,0.017447464,0.0003913608,0.00003642084,0.000111373396,0.0000517928,0.00009620867,0.111407086],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9995241,0.00019027347,0.000012364615,0.00008593891,0.00013259117,0.000054698503],"domain_scores_gemma":[0.9980427,0.0010839023,0.000111159745,0.00031561064,0.00022894843,0.00021772594],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00095775136,0.00018140617,0.0001167588,0.00039967234,0.00049067073,0.001457417,0.00045979983,0.00041830807,0.007211812],"category_scores_gemma":[0.003688282,0.00016543525,0.00012853094,0.0002810583,0.0018589259,0.0023536505,0.0027191008,0.0013939011,0.0013156947],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000046364064,0.00027785535,0.0046898425,0.0001481956,0.0000074989757,0.00014987386,0.008972609,0.0028090754,0.01496795,0.54723674,0.016857041,0.403837],"study_design_scores_gemma":[0.00003218457,0.00020101292,0.015571538,0.0003893015,0.000018449588,0.00041796378,0.0042013684,0.009572384,0.027251778,0.4475123,0.49479303,0.00003870053],"about_ca_topic_score_codex":0.0009979915,"about_ca_topic_score_gemma":0.0021619094,"teacher_disagreement_score":0.007211812,"about_ca_system_score_codex":0.0008959365,"about_ca_system_score_gemma":0.0014303379,"threshold_uncertainty_score":0.024125874},"labels":[],"label_agreement":null},{"id":"W4390474953","doi":"10.1007/978-981-99-6199-3_6","title":"Ethical Assessment Capacity","year":2023,"lang":"en","type":"book-chapter","venue":"Teacher education, learning innovation and accountability","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Experiential learning; Pedagogy; Engineering ethics; Equity (law); Narrative; Agency (philosophy); Embodied cognition; Capacity building; Psychology; Sociology; Political science; Epistemology; Engineering; Social science","score_opus":0.07947626433589683,"score_gpt":0.4106638558035805,"score_spread":0.3311875914676837,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390474953","genre_codex":"other","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006209717,0.00047885982,0.007012155,0.005758074,0.00037350092,0.00007296787,0.00003431121,0.000043834592,0.9856054],"genre_scores_gemma":[0.1229627,0.00083903945,0.0069612167,0.008099699,0.00058622425,0.0005452608,0.00012145511,0.00015265368,0.8597318],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99012905,0.004253917,0.00043689282,0.0011046065,0.0031963808,0.00087926723],"domain_scores_gemma":[0.9896923,0.004489161,0.00035556767,0.0017175782,0.0031698113,0.000575585],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010100036,0.000690199,0.0005298993,0.0017169219,0.005150817,0.011130365,0.0017362797,0.00430506,0.042666808],"category_scores_gemma":[0.025680473,0.0005214285,0.0004891878,0.00074260234,0.016190913,0.007571266,0.006962094,0.008441582,0.012653261],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000019665792,0.000006836689,0.00003223231,0.000013514187,0.000001083679,0.000017401862,0.00073588133,0.00006458397,0.00003340401,0.9672006,0.023488877,0.008403656],"study_design_scores_gemma":[0.0000043112846,0.000005442215,0.000114806695,0.00015006555,0.0000023160114,0.0000908732,0.00066525483,0.00021725173,0.00023422911,0.59373283,0.40477282,0.000009768923],"about_ca_topic_score_codex":0.0035019775,"about_ca_topic_score_gemma":0.0049133794,"teacher_disagreement_score":0.042666808,"about_ca_system_score_codex":0.0049956124,"about_ca_system_score_gemma":0.008357229,"threshold_uncertainty_score":0.14273477},"labels":[],"label_agreement":null},{"id":"W4390475020","doi":"10.1007/978-981-99-6199-3_3","title":"The Constellation of Assessment Capacity Discourses","year":2023,"lang":"en","type":"book-chapter","venue":"Teacher education, learning innovation and accountability","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Construct (python library); Constellation; Pedagogy; Literacy; Assessment for learning; Educational assessment; Identity (music); Space (punctuation); Work (physics); Engineering ethics; Psychology; Sociology; Political science; Formative assessment; Engineering; Computer science","score_opus":0.05910327133928453,"score_gpt":0.3902570655338809,"score_spread":0.33115379419459634,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4390475020","genre_codex":"other","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.054655932,0.0021631124,0.061493102,0.02654548,0.0003100026,0.000058390804,0.00014370558,0.00034876307,0.85428154],"genre_scores_gemma":[0.97325844,0.00049550115,0.00984935,0.000572134,0.00019263974,0.00014484201,0.00006158234,0.00013538355,0.015290263],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.98408324,0.010073989,0.00046605908,0.0010924708,0.003451162,0.0008330538],"domain_scores_gemma":[0.96926683,0.024573073,0.001044619,0.0023737706,0.0018226351,0.00091908406],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011233295,0.00056994427,0.0006860884,0.004564248,0.0046010693,0.018504646,0.0021964784,0.0035506326,0.006903446],"category_scores_gemma":[0.03522785,0.00059996167,0.0003909721,0.0034441624,0.04212507,0.021961525,0.008591596,0.0060636112,0.0008057419],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000041649346,0.000003962733,0.000085061016,0.000010736852,0.0000013180778,0.00003416013,0.0050249365,0.00012200031,0.00006588532,0.9906193,0.00059154595,0.003436894],"study_design_scores_gemma":[0.0000055632104,0.000005801741,0.00020478833,0.000058275513,0.000002940765,0.00007701617,0.0039398726,0.00069602305,0.00021111379,0.9753136,0.019474145,0.000010858933],"about_ca_topic_score_codex":0.00184541,"about_ca_topic_score_gemma":0.0015542087,"teacher_disagreement_score":0.018504646,"about_ca_system_score_codex":0.004469201,"about_ca_system_score_gemma":0.0028582283,"threshold_uncertainty_score":0.05940807},"labels":[],"label_agreement":null},{"id":"W4391027447","doi":"10.5430/wjel.v14n2p260","title":"Written Corrective Feedback in EFL Context: Contextual and Individual Factors Influencing Students’ Responses","year":2024,"lang":"en","type":"article","venue":"World Journal of English Language","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Qassim University","keywords":"Corrective feedback; Context (archaeology); Psychology; Variation (astronomy); English as a foreign language; Mathematics education; Foreign language","score_opus":0.024428141494156005,"score_gpt":0.3371142447297113,"score_spread":0.3126861032355553,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391027447","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9992021,0.000055747136,0.0002567339,0.00006341242,0.0000046501937,0.000012951088,0.000014051277,0.000009007279,0.00038142293],"genre_scores_gemma":[0.99955624,0.00003672584,0.00019509328,0.000026919188,0.0000028859133,0.0000128038855,0.000012161116,0.000003276515,0.00015390452],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99344134,0.0037,0.0005379052,0.00055454054,0.0013054907,0.0004606246],"domain_scores_gemma":[0.97197604,0.01433236,0.007065336,0.0008754401,0.0038846142,0.00186623],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031688802,0.00029270147,0.00046605236,0.00076586055,0.00070771924,0.0012056534,0.0003878808,0.00051757705,0.0012301918],"category_scores_gemma":[0.02990864,0.00018168539,0.00019721154,0.00047778006,0.0006253858,0.0004417253,0.0008889494,0.00065932644,0.00026674682],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005567346,0.00080899685,0.79789567,0.00031516777,0.00010510197,0.0012856213,0.11612329,0.00049878197,0.01205504,0.00009048725,0.0005065905,0.06975858],"study_design_scores_gemma":[0.00002057699,0.00092689315,0.8929829,0.00010948005,0.000056494653,0.00080697774,0.096758634,0.0010098175,0.004051554,0.0001825918,0.0030044988,0.000089567446],"about_ca_topic_score_codex":0.0018248586,"about_ca_topic_score_gemma":0.003350634,"teacher_disagreement_score":0.0031688802,"about_ca_system_score_codex":0.0005501736,"about_ca_system_score_gemma":0.0007003433,"threshold_uncertainty_score":0},"labels":[],"label_agreement":null},{"id":"W4391144344","doi":"10.1002/berj.3979","title":"How hermeneutics can guide grading in integrated <scp>STEAM</scp> education: An evidence‐informed perspective","year":2024,"lang":"en","type":"article","venue":"British Educational Research Journal","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Queen's University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Summative assessment; Grading (engineering); Formative assessment; Mathematics education; Pedagogy; Psychology; Qualitative research; Engineering; Sociology","score_opus":0.1468865405520672,"score_gpt":0.5037919696087552,"score_spread":0.356905429056688,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391144344","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.14807482,0.028442405,0.5244122,0.123516545,0.0020333577,0.0022438422,0.0003669388,0.0002770322,0.17063276],"genre_scores_gemma":[0.8224576,0.0069108848,0.16237108,0.0035286054,0.00025490078,0.0011293751,0.00011280537,0.0001341397,0.0031005878],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.7668655,0.19467305,0.01123495,0.005060199,0.019911842,0.0022545329],"domain_scores_gemma":[0.5137693,0.41613883,0.020033363,0.025965927,0.022161262,0.0019313368],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.24347435,0.0008726328,0.0011726096,0.010240508,0.0053119813,0.022004602,0.0057732984,0.0053617703,0.0039353753],"category_scores_gemma":[0.26516426,0.0012904474,0.0008449527,0.007860026,0.057338364,0.02247277,0.010495746,0.007915016,0.00074996264],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000097764874,0.00018326456,0.007844418,0.0035997997,0.00007232514,0.0006114409,0.23846227,0.001886366,0.0010539196,0.60004854,0.003466183,0.14267373],"study_design_scores_gemma":[0.00006704002,0.00017767014,0.0062316246,0.018191747,0.00010659593,0.00048816836,0.14383459,0.0034124332,0.0028812801,0.6508168,0.1736276,0.00016450821],"about_ca_topic_score_codex":0.00855785,"about_ca_topic_score_gemma":0.01591804,"teacher_disagreement_score":0.24347435,"about_ca_system_score_codex":0.011385322,"about_ca_system_score_gemma":0.024094291,"threshold_uncertainty_score":0.9329308},"labels":[],"label_agreement":null},{"id":"W4391562794","doi":"10.18260/1-2--41504","title":"Exploring Advantages of the Implementation of a Peer-Assessment Tool in a First-Year Undergraduate Course","year":2024,"lang":"en","type":"article","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Experiential learning; Course (navigation); Passion; Process (computing); Computer science; Mathematics education; Medical education; Multimedia; Engineering ethics; Psychology; Engineering; Medicine","score_opus":0.06224010583132068,"score_gpt":0.4188568108375629,"score_spread":0.3566167050062422,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391562794","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9696469,0.00007336266,0.020155251,0.0004838815,0.00010974069,0.0013485219,0.00008165384,0.0014943782,0.0066064377],"genre_scores_gemma":[0.924978,0.00007786777,0.07012716,0.00013853301,0.000039922284,0.00080276484,0.0001098913,0.0001197997,0.003606095],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9829684,0.009573842,0.0010050122,0.001662441,0.0040064277,0.0007838449],"domain_scores_gemma":[0.94348836,0.029813726,0.0037736057,0.006498382,0.010019081,0.0064068413],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.017808434,0.0008274501,0.00077886047,0.0013926179,0.0016498608,0.0040855776,0.0026776996,0.0012617409,0.0041997726],"category_scores_gemma":[0.061711527,0.0005263481,0.00063547946,0.00062964216,0.0006138132,0.003117106,0.0042090435,0.0014356683,0.0016167292],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0031633866,0.021999827,0.064687826,0.0009758423,0.00013320615,0.0010806305,0.026554182,0.0026343986,0.04615,0.001130809,0.004780383,0.82670957],"study_design_scores_gemma":[0.0038920168,0.11651875,0.45182717,0.0029814504,0.0012903907,0.0042779515,0.054731283,0.109526746,0.13596807,0.005353831,0.11197518,0.0016571387],"about_ca_topic_score_codex":0.0013906606,"about_ca_topic_score_gemma":0.0027331195,"teacher_disagreement_score":0.017808434,"about_ca_system_score_codex":0.0012223638,"about_ca_system_score_gemma":0.0032068396,"threshold_uncertainty_score":0.09418112},"labels":[],"label_agreement":null},{"id":"W4391603175","doi":"10.18260/1-2--42438","title":"Board 128: An Automated Management Process for Digital Correction","year":2024,"lang":"en","type":"article","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Computer science; Upload; Grading (engineering); Python (programming language); Pace; Process (computing); Multimedia; World Wide Web; Operating system; Engineering","score_opus":0.029052146222369585,"score_gpt":0.40511158577998435,"score_spread":0.3760594395576148,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391603175","genre_codex":"software","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.008136499,0.00021593858,0.46887505,0.0003925686,0.00049104687,0.0011357832,0.0019445114,0.50930834,0.009500175],"genre_scores_gemma":[0.21659915,0.00042864116,0.64325255,0.00064975733,0.00043365167,0.0017924206,0.010413254,0.076869264,0.049561262],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.993404,0.0012999908,0.0006814823,0.0015392926,0.0025488378,0.00052639836],"domain_scores_gemma":[0.9827633,0.0047273845,0.0014760135,0.0054710223,0.004175178,0.001387167],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004949031,0.0020798282,0.0010397081,0.004619919,0.0012386552,0.0035886667,0.002640349,0.00096014934,0.067140326],"category_scores_gemma":[0.027079841,0.001122028,0.00094537943,0.0016909931,0.0012705439,0.0035376458,0.0046176068,0.0016664584,0.03599699],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00083802256,0.00028256705,0.004720222,0.0005477995,0.00006789766,0.0008014683,0.0010308025,0.002904206,0.02399816,0.0054227198,0.13617486,0.8232113],"study_design_scores_gemma":[0.0004944317,0.00052043685,0.01100334,0.0004044733,0.00014172672,0.0013967237,0.0007201912,0.16873606,0.2099017,0.01908289,0.58707726,0.00052076054],"about_ca_topic_score_codex":0.0021441325,"about_ca_topic_score_gemma":0.0014230751,"teacher_disagreement_score":0.067140326,"about_ca_system_score_codex":0.001161572,"about_ca_system_score_gemma":0.0027193748,"threshold_uncertainty_score":0.22460675},"labels":[],"label_agreement":null},{"id":"W4391606049","doi":"10.18260/1-2--44480","title":"The Role of Feedback in Enhancing Students’ Learning Experience: An Evaluation of Student Perspectives and Attitudes","year":2024,"lang":"en","type":"article","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Mathematics education; Knowledge management; Human–computer interaction; Psychology; Multimedia; Pedagogy","score_opus":0.03956692107570287,"score_gpt":0.44224854324523777,"score_spread":0.4026816221695349,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391606049","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99898833,0.000032669315,0.0001612335,0.000058191992,0.0000077418135,0.000038086993,0.000021209444,0.0000125372235,0.000680045],"genre_scores_gemma":[0.9987423,0.00006391869,0.00037445436,0.00003866047,0.000010266499,0.00006605595,0.000036017966,0.0000068024133,0.00066144654],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.9936202,0.0025365415,0.000603352,0.00039266812,0.0020816824,0.00076549273],"domain_scores_gemma":[0.9749577,0.009956386,0.003561167,0.0007050556,0.0065876134,0.0042321295],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008834506,0.00045430745,0.0008605468,0.0023704625,0.0011868621,0.0023506428,0.00059013447,0.00088506716,0.002128276],"category_scores_gemma":[0.020998877,0.00029636823,0.0011144042,0.0009661714,0.0008312205,0.001174411,0.002323168,0.0012057361,0.00055408495],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001374112,0.00795123,0.69774055,0.00043115314,0.00021511562,0.0008857705,0.13857886,0.00067782094,0.01098358,0.00026329106,0.0020297563,0.13886876],"study_design_scores_gemma":[0.00012985969,0.016204,0.83377826,0.00021691271,0.00016998904,0.00079402036,0.12898558,0.002749152,0.009524887,0.0002822462,0.0069256583,0.00023937003],"about_ca_topic_score_codex":0.00053485954,"about_ca_topic_score_gemma":0.00067743956,"teacher_disagreement_score":0.008834506,"about_ca_system_score_codex":0.0008628782,"about_ca_system_score_gemma":0.0006469379,"threshold_uncertainty_score":0.046721935},"labels":[],"label_agreement":null},{"id":"W4391731495","doi":"10.1016/j.tate.2024.104518","title":"Evidence of teacher assessment work and its relationship to their assessment identity","year":2024,"lang":"en","type":"article","venue":"Teaching and Teacher Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Australian Research Council; University of Western Australia; Department of Education and Training, Queensland Government; Australian Catholic University","keywords":"Identity (music); Psychology; Work (physics); Pedagogy; Mathematics education; Social psychology; Engineering; Philosophy; Aesthetics","score_opus":0.09114490559044283,"score_gpt":0.4525132888131091,"score_spread":0.3613683832226663,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391731495","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9666512,0.00067203713,0.0035756885,0.0018136647,0.000040810683,0.000035115947,0.000035156223,0.000019955354,0.027156344],"genre_scores_gemma":[0.9988944,0.000117483185,0.00031826604,0.000034310473,0.000005657178,0.000015555466,0.000009248059,0.000006854717,0.00059828744],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.95256203,0.027173221,0.003474049,0.0036206928,0.011320608,0.0018493624],"domain_scores_gemma":[0.731865,0.1974166,0.030255344,0.012233717,0.023654891,0.004574426],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02853047,0.0002125596,0.00054207904,0.0033249094,0.0072892057,0.008305765,0.0015062899,0.0012290517,0.0033413346],"category_scores_gemma":[0.15421836,0.00056881114,0.00023184463,0.0021274255,0.011749013,0.0049697873,0.009168461,0.0028550755,0.00039816054],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009227582,0.00008222788,0.12133297,0.00020062708,0.000022552904,0.0002231901,0.84205014,0.00009879379,0.00068067806,0.0065948702,0.00023864282,0.028382935],"study_design_scores_gemma":[0.000013786903,0.00012795805,0.19400541,0.0004944482,0.000019384292,0.0004981637,0.7788053,0.0007188336,0.0012937154,0.00559262,0.018354107,0.00007628252],"about_ca_topic_score_codex":0.014067753,"about_ca_topic_score_gemma":0.012088005,"teacher_disagreement_score":0.02853047,"about_ca_system_score_codex":0.0042837556,"about_ca_system_score_gemma":0.0053027477,"threshold_uncertainty_score":0.15088534},"labels":[],"label_agreement":null},{"id":"W4391905991","doi":"10.55016/ojs/ajer.v46i3.54818","title":"Changing Assessment Practices in the Classroom: A Study of One Teacher's Challenge","year":2000,"lang":"en","type":"article","venue":"Alberta Journal of Educational Research","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Psychology; Mathematics education; Pedagogy","score_opus":0.24058453480634495,"score_gpt":0.5385362550330982,"score_spread":0.29795172022675326,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391905991","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9848728,0.00031773074,0.0030781294,0.005359592,0.00011617791,0.00015427354,0.000018381174,0.00005573639,0.006027165],"genre_scores_gemma":[0.98897177,0.00053168234,0.0034147727,0.0011903937,0.000051781724,0.00017017836,0.000025641097,0.000072173185,0.005571633],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.97618365,0.01532231,0.0006936944,0.0020653422,0.0028532275,0.0028817072],"domain_scores_gemma":[0.96193254,0.019430356,0.0036419705,0.0018146402,0.0065452643,0.006635245],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013079812,0.0007989491,0.0014951974,0.0020582147,0.024299623,0.011058114,0.005257165,0.0066719516,0.0017218458],"category_scores_gemma":[0.054000728,0.0014124425,0.0007959127,0.0014773732,0.012269692,0.0061497185,0.00656786,0.011475551,0.00078593625],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023047147,0.00037159922,0.0043327403,0.000059391863,0.0000059653867,0.0011986324,0.9851281,0.00006944268,0.000718261,0.00074492133,0.0006816884,0.006666278],"study_design_scores_gemma":[0.000016648673,0.00024766562,0.002912819,0.000080471465,0.000008093813,0.00096733734,0.97830486,0.00025821247,0.00045668383,0.00042061697,0.01629175,0.000034926736],"about_ca_topic_score_codex":0.018526165,"about_ca_topic_score_gemma":0.044482917,"teacher_disagreement_score":0.024299623,"about_ca_system_score_codex":0.0074776253,"about_ca_system_score_gemma":0.009109108,"threshold_uncertainty_score":0.069173455},"labels":[],"label_agreement":null},{"id":"W4392378798","doi":"10.1002/sfr.32356","title":"Expand Your Reach Through Nontraditional Methods","year":2024,"lang":"en","type":"article","venue":"Successful Fundraising","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Psychology; Computer science","score_opus":0.1027487616261196,"score_gpt":0.4767338591528656,"score_spread":0.373985097526746,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392378798","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012081106,0.015340509,0.19868875,0.121023044,0.0065873396,0.001867391,0.0019664494,0.0056761783,0.6367692],"genre_scores_gemma":[0.16558358,0.020338466,0.36401993,0.038080364,0.005128101,0.0050999746,0.0021653776,0.0063007367,0.39328346],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.98017967,0.011261159,0.00067750976,0.0010782864,0.005988321,0.0008151109],"domain_scores_gemma":[0.9227082,0.047666304,0.001740623,0.0120067205,0.010575622,0.005302509],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.040189974,0.0007469374,0.0007206207,0.0042051463,0.0023668895,0.008369892,0.0026679162,0.0019376765,0.19439682],"category_scores_gemma":[0.06863637,0.0005009751,0.0013979845,0.002062184,0.0025020775,0.011465246,0.015008035,0.0029022319,0.052975878],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000120725635,0.00039270334,0.0016989118,0.0012354844,0.000053111708,0.000107012274,0.007024941,0.00016828107,0.00046653533,0.040812075,0.2870855,0.6608347],"study_design_scores_gemma":[0.00008372592,0.00010165591,0.0020003333,0.0017333349,0.000032484582,0.00021475021,0.0036444433,0.00037960673,0.0005498984,0.050726473,0.94050175,0.000031501775],"about_ca_topic_score_codex":0.0021734268,"about_ca_topic_score_gemma":0.0057220045,"teacher_disagreement_score":0.19439682,"about_ca_system_score_codex":0.0016670036,"about_ca_system_score_gemma":0.0055829217,"threshold_uncertainty_score":0.6503222},"labels":[],"label_agreement":null},{"id":"W4392426567","doi":"10.58680/la201424590","title":"Commentaries: Common Core, Rotten Core","year":2014,"lang":"en","type":"article","venue":"Language Arts","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Core (optical fiber); Common core; Psychology; Mathematics education; Pedagogy; Sociology; Computer science","score_opus":0.04165454797447994,"score_gpt":0.36865748933656556,"score_spread":0.32700294136208563,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392426567","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0039877775,0.0010182004,0.0020515774,0.907566,0.057544816,0.0002189259,0.0017583751,0.000406183,0.025448145],"genre_scores_gemma":[0.077845,0.0016016691,0.0013346422,0.8124335,0.038705606,0.001058079,0.00077301194,0.0014461472,0.06480229],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9789312,0.008297422,0.002507305,0.0027152814,0.0052583423,0.0022904598],"domain_scores_gemma":[0.8357034,0.094406895,0.009853594,0.00625914,0.05056063,0.0032163388],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015803559,0.0015424994,0.0010652681,0.0023177136,0.008703836,0.0060731973,0.0034121415,0.014455928,0.041963052],"category_scores_gemma":[0.19882329,0.00069235364,0.0009925162,0.0038211588,0.006395468,0.008229433,0.006652192,0.020254549,0.013101928],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000062187784,0.0000075431913,0.0004007666,0.00025875968,0.0000071077625,0.00028469076,0.010203428,0.000049693845,0.0003959659,0.004390541,0.9813089,0.002630413],"study_design_scores_gemma":[0.000018038523,0.000027396663,0.0021438128,0.00085727865,0.000015933401,0.00020453946,0.024780631,0.00025217445,0.0011429542,0.001961031,0.9685047,0.00009143707],"about_ca_topic_score_codex":0.025290115,"about_ca_topic_score_gemma":0.015683783,"teacher_disagreement_score":0.041963052,"about_ca_system_score_codex":0.009665683,"about_ca_system_score_gemma":0.0057026916,"threshold_uncertainty_score":0.14038038},"labels":[],"label_agreement":null},{"id":"W4392681814","doi":"10.22318/icls2023.105241","title":"Social Context Challenges in Administering Authentic Assessments of Citizenship Competency","year":2023,"lang":"en","type":"article","venue":"Proceedings.","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Vancouver Island University","funders":"","keywords":"Citizenship; Situated; Context (archaeology); Dimension (graph theory); Competency assessment; Vocational education; Pedagogy; Authentic assessment; Medical education; Psychology; Sociology; Computer science; Medicine; Political science; Artificial intelligence; Curriculum; Politics","score_opus":0.18707567280741413,"score_gpt":0.42022678500476013,"score_spread":0.233151112197346,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4392681814","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6527437,0.0028790664,0.25392973,0.021568855,0.0016852726,0.006205382,0.00021748326,0.001219656,0.05955088],"genre_scores_gemma":[0.9063714,0.00066871947,0.084234126,0.002023109,0.00023904309,0.0044268547,0.000055065495,0.00015508558,0.0018265183],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.7606572,0.20043455,0.01077358,0.0064120614,0.018793209,0.0029295082],"domain_scores_gemma":[0.71680063,0.22601175,0.011189605,0.020447116,0.021028284,0.0045226435],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.11976657,0.0006756493,0.0009796536,0.0010295248,0.0051021655,0.00886871,0.0018455328,0.0022973816,0.0036732242],"category_scores_gemma":[0.25924593,0.0011653384,0.0012039038,0.00077249366,0.0037917187,0.0051225135,0.0072912895,0.0027201767,0.0012708168],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015244995,0.0018562556,0.07649337,0.0035198675,0.0004346056,0.0016350307,0.3086307,0.0044966307,0.021995377,0.027271552,0.009096789,0.5430453],"study_design_scores_gemma":[0.0010459638,0.011436154,0.12216904,0.006426794,0.0006711869,0.006670255,0.4272976,0.018100468,0.033894185,0.12521225,0.24612916,0.0009469243],"about_ca_topic_score_codex":0.002526118,"about_ca_topic_score_gemma":0.0044614216,"teacher_disagreement_score":0.11976657,"about_ca_system_score_codex":0.002121407,"about_ca_system_score_gemma":0.007141565,"threshold_uncertainty_score":0.63339376},"labels":[],"label_agreement":null},{"id":"W4393037999","doi":"10.1080/0145935x.2026.2656753","title":"The Strengths/Structured Assessment for Youth (S/SAY): Evaluating Strengths in a Case Study of a Justice-Involved Youth","year":2024,"lang":"en","type":"preprint","venue":"Child & Youth Services","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec en Outaouais","funders":"Social Sciences and Humanities Research Council","keywords":"Strengths and weaknesses; Economic Justice; Psychology; Political science; Applied psychology; Social psychology; Law","score_opus":0.05176695592938487,"score_gpt":0.40860619212623783,"score_spread":0.356839236196853,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393037999","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9923488,0.00008706158,0.0019209617,0.0007255149,0.000029445824,0.0003163268,0.000055719458,0.000016494629,0.0044998094],"genre_scores_gemma":[0.9871739,0.00025418823,0.009901527,0.00009224323,0.000007706332,0.00018479505,0.00004295723,0.000012458039,0.0023303134],"study_design_codex":"qualitative","study_design_gemma":"case_report","domain_scores_codex":[0.99907434,0.0004765957,0.00007357808,0.000058493293,0.00016188761,0.00015512157],"domain_scores_gemma":[0.99835193,0.0005452976,0.00017089894,0.00006686477,0.0003670726,0.00049796345],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0028071657,0.00035687606,0.00028728432,0.0010284196,0.0025634568,0.0007078734,0.0008575656,0.00063790457,0.0012694134],"category_scores_gemma":[0.006603402,0.00024844674,0.00037885582,0.0004933592,0.0014619046,0.0007089887,0.002313827,0.001282598,0.00014282191],"study_design_candidate":"case_report","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0004255321,0.003848405,0.28786427,0.0006314243,0.00006799153,0.10085273,0.37096965,0.0014152529,0.015210652,0.0049421024,0.009117811,0.20465419],"study_design_scores_gemma":[0.00011452958,0.0038778554,0.2548658,0.00080889725,0.0001771779,0.08234459,0.6064284,0.005175787,0.015143356,0.0051527084,0.025706299,0.00020464398],"about_ca_topic_score_codex":0.009712631,"about_ca_topic_score_gemma":0.039914437,"teacher_disagreement_score":0.009712631,"about_ca_system_score_codex":0.0014411034,"about_ca_system_score_gemma":0.0042037885,"threshold_uncertainty_score":0.019312203},"labels":[],"label_agreement":null},{"id":"W4393071056","doi":"10.3389/feduc.2024.1366215","title":"Formative assessment in higher education: an exploratory study within programs for professionals in education","year":2024,"lang":"en","type":"article","venue":"Frontiers in Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":25,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Thomas University","funders":"","keywords":"Formative assessment; Exploratory research; Higher education; Computer science; Engineering management; Medical education; Knowledge management; Mathematics education; Engineering; Psychology; Political science; Sociology; Medicine","score_opus":0.05206261374251999,"score_gpt":0.43691539345796154,"score_spread":0.3848527797154416,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393071056","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9964923,0.00007622873,0.0020834592,0.00012866403,0.000007925123,0.00022800101,0.000010713647,0.000014269373,0.0009584054],"genre_scores_gemma":[0.9934994,0.00015289288,0.0043814345,0.00010438816,0.00001544639,0.00033792178,0.000029094586,0.000013545809,0.0014659845],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.988466,0.0076722275,0.0003583682,0.0006658195,0.00173514,0.0011024793],"domain_scores_gemma":[0.9641609,0.024377977,0.0024538406,0.0017639233,0.0038577537,0.0033856605],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.018768156,0.0006693658,0.00078451383,0.0017025791,0.0045892517,0.00434698,0.0017055772,0.0014975151,0.0010703981],"category_scores_gemma":[0.047279242,0.00058486813,0.0003931344,0.0012244735,0.0027430567,0.0022890696,0.003450061,0.0025533524,0.0003059434],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020681275,0.0051058526,0.065896064,0.00023257128,0.000015357846,0.0009701188,0.85416114,0.00012814578,0.0051231314,0.00061299617,0.00029510978,0.067252666],"study_design_scores_gemma":[0.00007030498,0.006788883,0.16073872,0.00035510646,0.000033227556,0.0021552371,0.80711687,0.0011629343,0.006678941,0.0012196841,0.013588406,0.00009166403],"about_ca_topic_score_codex":0.0016245099,"about_ca_topic_score_gemma":0.0042024734,"teacher_disagreement_score":0.98123187,"about_ca_system_score_codex":0.002028108,"about_ca_system_score_gemma":0.0038410164,"threshold_uncertainty_score":0.099256694},"labels":[],"label_agreement":null},{"id":"W4393370921","doi":"10.37514/per-b.2024.2326.2.14","title":"Chapter 14. Ethical Considerations and Writing Assessment","year":2024,"lang":"en","type":"book-chapter","venue":"The WAC Clearinghouse; University Press of Colorado eBooks","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Lethbridge","funders":"","keywords":"Engineering ethics; Report writing; Psychology; Engineering","score_opus":0.05163489517100832,"score_gpt":0.309715548798189,"score_spread":0.2580806536271807,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393370921","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0019029992,0.01941372,0.014232724,0.08634873,0.010669083,0.0005548627,0.000093140756,0.00014007081,0.8666446],"genre_scores_gemma":[0.049638674,0.01684584,0.0177403,0.04096299,0.004035859,0.0012022576,0.00017284918,0.00024592323,0.8691553],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9891689,0.0057695745,0.00044091512,0.0004971313,0.0036176906,0.0005058126],"domain_scores_gemma":[0.9893244,0.0069412068,0.00033799087,0.0004325695,0.0025685271,0.00039535528],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01003441,0.0005777761,0.00036237357,0.0011612722,0.0053127096,0.007364187,0.0013579386,0.0051204995,0.019528026],"category_scores_gemma":[0.02682319,0.00033778985,0.00042779025,0.00074436126,0.0062288553,0.003967513,0.0028656062,0.007086161,0.006255593],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000008535305,0.000051469662,0.0001942784,0.00018182144,0.000004032438,0.00017174309,0.0064912,0.00014761538,0.00024898304,0.48171234,0.41170692,0.099081054],"study_design_scores_gemma":[0.0000031793772,0.000014125263,0.00020677262,0.0007912961,0.0000025500472,0.00022090173,0.002405947,0.00008641293,0.00026830524,0.08940885,0.90658164,0.000010007947],"about_ca_topic_score_codex":0.002435364,"about_ca_topic_score_gemma":0.0057510915,"teacher_disagreement_score":0.019528026,"about_ca_system_score_codex":0.003289629,"about_ca_system_score_gemma":0.008424342,"threshold_uncertainty_score":0.06532776},"labels":[],"label_agreement":null},{"id":"W4393899036","doi":"10.5430/wjel.v14n4p215","title":"Beyond the Red Pen: Exploring the Impact of Language Peer Assessment Technology on the ESL/EFL Writers’ Performance","year":2024,"lang":"en","type":"article","venue":"World Journal of English Language","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Peer assessment; Linguistics; Mathematics education; Psychology; Philosophy","score_opus":0.026399321928394653,"score_gpt":0.34784514275770956,"score_spread":0.3214458208293149,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4393899036","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9923792,0.00013639891,0.002897356,0.00015749625,0.000027183585,0.000121466546,0.000018525314,0.000057023954,0.0042053107],"genre_scores_gemma":[0.99281996,0.00012533876,0.0049027433,0.00006227215,0.000025430356,0.000102016274,0.000016858396,0.000018992474,0.0019263712],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.990316,0.006399368,0.00035713983,0.0006029367,0.0019965887,0.00032808064],"domain_scores_gemma":[0.95543486,0.03428419,0.003599046,0.0020347654,0.0031470014,0.001500264],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008332319,0.00046740175,0.0005044898,0.00066673855,0.00072350836,0.0025088405,0.0007805378,0.00050055794,0.0026675225],"category_scores_gemma":[0.0452657,0.00018607541,0.00026800024,0.00042231035,0.00084912713,0.0015722549,0.0014151859,0.000700113,0.0006097723],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0025582798,0.007379332,0.08995279,0.0019750423,0.00018063966,0.0014977717,0.14079016,0.0015315249,0.07263853,0.0015985962,0.0017002985,0.67819715],"study_design_scores_gemma":[0.00046254395,0.064714655,0.6177897,0.0013260698,0.0007094048,0.0022936468,0.15062994,0.010764968,0.10252214,0.003498668,0.044906396,0.00038185672],"about_ca_topic_score_codex":0.0004609026,"about_ca_topic_score_gemma":0.00081340264,"teacher_disagreement_score":0.008332319,"about_ca_system_score_codex":0.00041102344,"about_ca_system_score_gemma":0.0010511476,"threshold_uncertainty_score":0.044066012},"labels":[],"label_agreement":null},{"id":"W4395110387","doi":"10.1080/08957347.2024.2345594","title":"A Critical Review of Fairness from Multiple Perspectives: Implications for Classroom Assessment Theory","year":2024,"lang":"en","type":"review","venue":"Applied Measurement in Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Psychology; Item response theory; Critical theory; Mathematics education; Political science; Developmental psychology; Psychometrics","score_opus":0.1496372500266458,"score_gpt":0.4788594395403927,"score_spread":0.3292221895137469,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4395110387","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00020295857,0.9769818,0.002044384,0.01721914,0.0019406407,0.000030208555,0.000018958699,0.0000069170856,0.0015550626],"genre_scores_gemma":[0.008312034,0.9780964,0.004137884,0.0070134564,0.0018832767,0.0001547066,0.000034825105,0.00001404955,0.00035328837],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9656672,0.01989538,0.0052721347,0.001919638,0.006756948,0.00048874447],"domain_scores_gemma":[0.83082056,0.14322294,0.003993862,0.0025653124,0.018379932,0.0010174372],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.049532376,0.0011020788,0.0029860027,0.015195376,0.002311557,0.008651606,0.0029407064,0.004972212,0.0023165266],"category_scores_gemma":[0.13096462,0.00069899735,0.0016113458,0.012391059,0.008770801,0.0137591725,0.004731718,0.008556717,0.0006368609],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007071226,0.000051218147,0.0005069683,0.0774194,0.00040033992,0.00026649435,0.009975262,0.00042225933,0.00035352155,0.15278782,0.05686571,0.7008802],"study_design_scores_gemma":[0.000023299564,0.000066323846,0.0014289656,0.2134713,0.00041629653,0.0005460929,0.0077985027,0.00025766063,0.00035031937,0.11023552,0.6653254,0.00008038062],"about_ca_topic_score_codex":0.004511313,"about_ca_topic_score_gemma":0.0075965817,"teacher_disagreement_score":0.049532376,"about_ca_system_score_codex":0.0071586594,"about_ca_system_score_gemma":0.022191951,"threshold_uncertainty_score":0.26195532},"labels":[],"label_agreement":null},{"id":"W4396538087","doi":"10.18357/otessaj.2024.4.1.57","title":"Technology-Integrated Assessment: A Literature Review","year":2024,"lang":"en","type":"review","venue":"The Open/Technology in Education Society and Scholarship Association Journal","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Queen's University; University of Alberta; University of Victoria","funders":"","keywords":"Computer science","score_opus":0.04140750914591002,"score_gpt":0.45492046864975083,"score_spread":0.4135129595038408,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396538087","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00017918799,0.99863356,0.00012797552,0.0004373295,0.00012776979,0.000018952274,0.0000208125,0.0000041842395,0.00045024403],"genre_scores_gemma":[0.002016677,0.9971631,0.0003096767,0.0002880858,0.00008226999,0.000028034978,0.00003099371,0.0000022291902,0.000078904726],"study_design_codex":"design_other","study_design_gemma":"systematic_review","domain_scores_codex":[0.9954881,0.0012866082,0.0011313318,0.00051943876,0.001400765,0.00017378182],"domain_scores_gemma":[0.9659751,0.02564591,0.002480273,0.00056043017,0.0047511575,0.0005871679],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0069245603,0.0012679036,0.0027814473,0.014958302,0.0012156403,0.0034640145,0.0022203592,0.0028140189,0.004711406],"category_scores_gemma":[0.02944149,0.0010364313,0.0020847565,0.017460128,0.0014016525,0.0050981734,0.0025171272,0.0023660124,0.000987839],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000081269,0.00013281478,0.00086434523,0.23960687,0.0005171026,0.0002915722,0.00088970474,0.00032861487,0.00031773312,0.0039694263,0.01664616,0.7363543],"study_design_scores_gemma":[0.000034423025,0.00017583245,0.0047108014,0.5644534,0.0022723598,0.0017268647,0.0015305727,0.00022047403,0.00034280831,0.0034679035,0.42099226,0.000072243165],"about_ca_topic_score_codex":0.007033522,"about_ca_topic_score_gemma":0.013492836,"teacher_disagreement_score":0.014958302,"about_ca_system_score_codex":0.003131385,"about_ca_system_score_gemma":0.015256908,"threshold_uncertainty_score":0.036620975},"labels":[],"label_agreement":null},{"id":"W4396665291","doi":"10.5206/cjsotlrcacea.2024.1.14923","title":"The Choice is Theirs: Students Achieve Positive Outcomes when Offered Flexibility in Course Assessment Options","year":2024,"lang":"en","type":"article","venue":"The Canadian Journal for the Scholarship of Teaching and Learning","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Windsor","funders":"","keywords":"Flexibility (engineering); Course (navigation); Mathematics education; Psychology; Medical education; Computer science; Medicine; Engineering; Mathematics; Statistics","score_opus":0.06607427284343663,"score_gpt":0.43688141993953306,"score_spread":0.3708071470960964,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396665291","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99287003,0.000040373405,0.000985411,0.0004085627,0.000022034701,0.000030481111,0.000041689367,0.0000446234,0.005556717],"genre_scores_gemma":[0.9957023,0.00005213075,0.0017036194,0.0001208482,0.000009387441,0.00004097725,0.000039912586,0.000009576226,0.0023211786],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9982352,0.00061116106,0.000102525475,0.00018568098,0.0006459741,0.00021938594],"domain_scores_gemma":[0.99180424,0.0020131783,0.0020164372,0.0008530253,0.0007417357,0.0025712978],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003936766,0.00028169496,0.0003825265,0.00042860705,0.0006133184,0.0018328278,0.00032180725,0.00044417498,0.0054214746],"category_scores_gemma":[0.017968656,0.00013115055,0.00033442522,0.00030461387,0.00054119516,0.0010332911,0.001435887,0.0006318354,0.0009980492],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001960807,0.00349471,0.39402947,0.00023935612,0.00018232659,0.0002623886,0.0063697193,0.0013035937,0.023725836,0.0024400777,0.0074548796,0.55853677],"study_design_scores_gemma":[0.00026891025,0.008507277,0.94401807,0.00014663195,0.0001322547,0.00042341286,0.007736946,0.0029580682,0.010675927,0.006562261,0.018446404,0.00012377843],"about_ca_topic_score_codex":0.00090990344,"about_ca_topic_score_gemma":0.0021007783,"teacher_disagreement_score":0.0054214746,"about_ca_system_score_codex":0.00036482612,"about_ca_system_score_gemma":0.00078571116,"threshold_uncertainty_score":0.020819843},"labels":[],"label_agreement":null},{"id":"W4396689913","doi":"10.7202/1111099ar","title":"Analyse des émotions et des compétences émotionnelles d’étudiants universitaires dans le traitement d’un feedback formatif à distance","year":2023,"lang":"fr","type":"article","venue":"Mesure et évaluation en éducation","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Formative assessment; Psychology; Cognitive psychology; Mathematics education; Social psychology; Applied psychology","score_opus":0.07563898955206862,"score_gpt":0.36806984425791356,"score_spread":0.29243085470584496,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396689913","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9922978,0.00043490797,0.0033441933,0.00026060367,0.00009816952,0.00017336024,0.00020697399,0.00004806792,0.00313576],"genre_scores_gemma":[0.9904463,0.00025084958,0.003994034,0.0001113579,0.000039483395,0.00038601313,0.00022892843,0.00002287677,0.0045202607],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9953609,0.0024531751,0.00021807125,0.0003441517,0.0013195205,0.00030414583],"domain_scores_gemma":[0.9814503,0.009301041,0.0016107974,0.0004627175,0.005841799,0.0013333135],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0057103317,0.0005230029,0.0005845705,0.00066293654,0.0005524773,0.0010931669,0.0003693568,0.00063952163,0.004055755],"category_scores_gemma":[0.027852556,0.00014804161,0.00051125034,0.00042409168,0.00042645354,0.00061452,0.0007809901,0.0011383524,0.0009850318],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.009999128,0.005412052,0.23591255,0.0017582789,0.0004303655,0.000572397,0.06703003,0.0017404637,0.087744065,0.00080913305,0.0073275147,0.58126396],"study_design_scores_gemma":[0.00032548708,0.009980562,0.93841016,0.00033239173,0.00018347052,0.000483557,0.016588297,0.0026941558,0.019364567,0.00053613615,0.010916613,0.00018455327],"about_ca_topic_score_codex":0.002631066,"about_ca_topic_score_gemma":0.0024561055,"teacher_disagreement_score":0.0057103317,"about_ca_system_score_codex":0.0009701016,"about_ca_system_score_gemma":0.0007198227,"threshold_uncertainty_score":0.030199468},"labels":[],"label_agreement":null},{"id":"W4396755911","doi":"10.7202/1110995ar","title":"Adapting to the Ethics of Differentiated Learning Assessment: Analysis of Foreign-trained Teachers’ Experiences in Quebec","year":2022,"lang":"en","type":"article","venue":"Mesure et évaluation en éducation","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Engineering ethics; Psychology; Mathematics education; Pedagogy; Sociology; Engineering","score_opus":0.10672369507891309,"score_gpt":0.44606418875250586,"score_spread":0.33934049367359276,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396755911","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9939074,0.00031478138,0.0003708094,0.0009904586,0.000019366862,0.00004829774,0.00004185737,0.0000098764685,0.0042973105],"genre_scores_gemma":[0.9959125,0.00015022562,0.00021714337,0.00020806913,0.0000039576794,0.000016931273,0.000029461971,0.000008718183,0.0034530002],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99252045,0.0033584454,0.00019869543,0.00056845794,0.001596112,0.0017579015],"domain_scores_gemma":[0.98601115,0.0053772847,0.0010740723,0.00042521826,0.004067783,0.0030445356],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0065949336,0.00042946162,0.00055593497,0.0014087933,0.014033734,0.0055406163,0.0018094098,0.0016134812,0.0020449122],"category_scores_gemma":[0.0137300985,0.00043054787,0.00028882336,0.0021515735,0.007821804,0.0017309824,0.00414265,0.0026224137,0.00020703847],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006207108,0.00015961335,0.034911074,0.000082143655,0.000009952439,0.0015025844,0.9435736,0.00015154349,0.0010299179,0.0011544074,0.0013244261,0.016038552],"study_design_scores_gemma":[0.000009514533,0.00009451144,0.056488384,0.00016386992,0.000009364291,0.00032775156,0.92501533,0.00042009348,0.0005101002,0.00013413312,0.016767265,0.000059757534],"about_ca_topic_score_codex":0.9376527,"about_ca_topic_score_gemma":0.9794174,"teacher_disagreement_score":0.062347293,"about_ca_system_score_codex":0.052018188,"about_ca_system_score_gemma":0.04189422,"threshold_uncertainty_score":0.37742013},"labels":[],"label_agreement":null},{"id":"W4396881195","doi":"10.1016/j.tate.2024.104634","title":"Assessment practices of teachers in Myanmar: Are we there yet?","year":2024,"lang":"en","type":"article","venue":"Teaching and Teacher Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Lethbridge","funders":"","keywords":"Mathematics education; Pedagogy; Psychology; Sociology; Political science","score_opus":0.0511862017902367,"score_gpt":0.4463976810256406,"score_spread":0.3952114792354039,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396881195","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9951917,0.0006065939,0.0000984223,0.0021354284,0.000017504934,0.0000104590945,0.00005832669,0.000006820749,0.0018746716],"genre_scores_gemma":[0.998075,0.00047628384,0.00022524332,0.00019262775,0.000004425432,0.000015042788,0.000034525452,0.0000030078086,0.00097379106],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9984895,0.0006236453,0.0001057104,0.000113398164,0.0002153274,0.00045240976],"domain_scores_gemma":[0.996309,0.00082458183,0.0009891831,0.00015435372,0.0009187355,0.0008041994],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013344759,0.00012481726,0.0002263217,0.00053349475,0.0022497762,0.0012426848,0.00088443485,0.00053888606,0.0018569935],"category_scores_gemma":[0.008630794,0.00019970819,0.00012072317,0.00085057906,0.00091719424,0.0011463828,0.0014253644,0.00077030825,0.00023727959],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009868892,0.00023398404,0.6226632,0.0003420872,0.000029302937,0.0007058029,0.28250068,0.00010069778,0.0022206914,0.0010173875,0.0024886425,0.08759884],"study_design_scores_gemma":[0.000004554295,0.00013060066,0.72199833,0.00034893112,0.000014286576,0.00039324182,0.26824796,0.0001563209,0.00035218723,0.00016368592,0.0081624435,0.000027459291],"about_ca_topic_score_codex":0.1140526,"about_ca_topic_score_gemma":0.24500532,"teacher_disagreement_score":0.1140526,"about_ca_system_score_codex":0.00228319,"about_ca_system_score_gemma":0.0047467696,"threshold_uncertainty_score":0.2267775},"labels":[],"label_agreement":null},{"id":"W4396978444","doi":"10.21449/ijate.1376160","title":"The difference between estimated and perceived item difficulty: An empirical study","year":2024,"lang":"en","type":"article","venue":"International Journal of Assessment Tools in Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Psychology; Statistics; Empirical research; Econometrics; Mathematics education; Mathematics","score_opus":0.08975046533286718,"score_gpt":0.5107784354602035,"score_spread":0.42102797012733634,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396978444","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99748516,0.000096576165,0.0014523165,0.00003407165,0.0000053339177,0.000034093748,0.00008361876,0.00000574964,0.0008029802],"genre_scores_gemma":[0.99877506,0.0000426758,0.0009050508,0.000011172618,0.0000041388553,0.00003577165,0.000080862505,0.000004804426,0.00014033524],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9867541,0.006271604,0.0016146905,0.0015110356,0.0034509532,0.00039755265],"domain_scores_gemma":[0.7186046,0.24009314,0.016625967,0.006829373,0.016071811,0.0017750589],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014328685,0.00038766363,0.00045722327,0.0016981143,0.0003756679,0.0014314334,0.00080240815,0.0007078693,0.0026757163],"category_scores_gemma":[0.1241156,0.00035004492,0.00056109705,0.0015775738,0.0012652201,0.0020874557,0.0009099299,0.0012306555,0.00045851414],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015105198,0.00041378004,0.98351246,0.00009524104,0.000118951204,0.00013303531,0.0034224037,0.00035753677,0.00050714536,0.00019085204,0.00014271149,0.010954976],"study_design_scores_gemma":[0.000017595888,0.00058804854,0.9911004,0.000054737353,0.000060167287,0.00033542496,0.0031927056,0.0032590204,0.0007626127,0.00018342507,0.000418335,0.000027542652],"about_ca_topic_score_codex":0.0013614789,"about_ca_topic_score_gemma":0.0016487326,"teacher_disagreement_score":0.014328685,"about_ca_system_score_codex":0.0006575521,"about_ca_system_score_gemma":0.0005531189,"threshold_uncertainty_score":0.075778246},"labels":[],"label_agreement":null},{"id":"W4398216268","doi":"10.1177/14782103241255855","title":"International trends in the implementation of assessment for learning <i>revisited</i> : Implications for policy and practice in a post-COVID world","year":2024,"lang":"en","type":"article","venue":"Policy Futures in Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Manitoba; Queen's University; Brock University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Summative assessment; Globe; Political science; Coronavirus disease 2019 (COVID-19); Pandemic; Public administration; Formative assessment; Economic growth; Sociology; Public relations; Pedagogy; Psychology; Economics","score_opus":0.03391237724382954,"score_gpt":0.5307683282009764,"score_spread":0.49685595095714685,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4398216268","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08488966,0.05706396,0.004668517,0.75870514,0.0028772708,0.000061668514,0.00029415227,0.00010844093,0.0913313],"genre_scores_gemma":[0.8702936,0.05030512,0.0070817005,0.059652608,0.0015043188,0.0001013316,0.00030788622,0.00013664806,0.010616784],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9866371,0.0048811785,0.0014475257,0.0016305699,0.0034247106,0.0019788605],"domain_scores_gemma":[0.9385479,0.028691418,0.00900114,0.002461414,0.015926229,0.005371959],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.024654068,0.00022142082,0.00043572485,0.0024764107,0.0029432506,0.012979284,0.0016084495,0.004473327,0.0041646897],"category_scores_gemma":[0.045273,0.00030893245,0.0003916087,0.0063005183,0.012027126,0.011034096,0.006322232,0.008825246,0.00062326476],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009199764,0.00015810344,0.014086077,0.001140217,0.000016874696,0.00019217763,0.027028095,0.0006112047,0.00078191207,0.64534587,0.02670445,0.28384304],"study_design_scores_gemma":[0.000023644781,0.00021321017,0.0800368,0.0037169175,0.000015224623,0.0005015035,0.06698497,0.00072877714,0.0010896379,0.07155428,0.7750122,0.0001227646],"about_ca_topic_score_codex":0.037146375,"about_ca_topic_score_gemma":0.025127348,"teacher_disagreement_score":0.037146375,"about_ca_system_score_codex":0.016189827,"about_ca_system_score_gemma":0.026546096,"threshold_uncertainty_score":0.13038474},"labels":[],"label_agreement":null},{"id":"W4399561197","doi":"10.61871/mj.v46n4-19","title":"Past, Present, and Future of Language Assessment: An Interview with Dr. Hossein Farhady","year":2023,"lang":"en","type":"article","venue":"Mextesol journal.","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Psychology; Linguistics; Philosophy","score_opus":0.031010176548061298,"score_gpt":0.37809221575371943,"score_spread":0.3470820392056581,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399561197","genre_codex":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.24201924,0.046707466,0.00174103,0.6771957,0.0026155617,0.00012298545,0.00008264054,0.000043514043,0.029471768],"genre_scores_gemma":[0.8631228,0.030583171,0.0024064144,0.08623851,0.00091357523,0.00020440744,0.000067159184,0.00003922355,0.016424775],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.98884726,0.007678525,0.0003359535,0.00047247222,0.0014191049,0.0012466067],"domain_scores_gemma":[0.98649013,0.0066220644,0.0008582662,0.000121245255,0.002609547,0.0032988333],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011540214,0.00029384732,0.0006873089,0.0011133665,0.011986426,0.0055121225,0.0011287287,0.004082215,0.002012536],"category_scores_gemma":[0.014706819,0.00048779507,0.00035616348,0.0016253979,0.0067877937,0.006807809,0.0042594178,0.0104654655,0.0005561501],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000045468583,0.00020683686,0.007839816,0.00029833388,0.000010886877,0.0023405154,0.8527028,0.00015156699,0.00084056775,0.0130936345,0.082148105,0.040321484],"study_design_scores_gemma":[0.00000665719,0.000062739506,0.0058423188,0.00044805228,0.000004206216,0.0016046602,0.81611884,0.00019382476,0.00011367431,0.0009017708,0.1746529,0.00005038704],"about_ca_topic_score_codex":0.020890892,"about_ca_topic_score_gemma":0.020176843,"teacher_disagreement_score":0.020890892,"about_ca_system_score_codex":0.008120882,"about_ca_system_score_gemma":0.012221146,"threshold_uncertainty_score":0.061031222},"labels":[],"label_agreement":null},{"id":"W4399565789","doi":"10.29173/isot1532","title":"Conversations and Reflections on Authentic Assessment","year":2021,"lang":"en","type":"article","venue":"Imagining SoTL","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Psychology; Epistemology; Sociology; Philosophy","score_opus":0.061162770415292445,"score_gpt":0.44456000084983166,"score_spread":0.3833972304345392,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399565789","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.40443465,0.012103338,0.1668263,0.1937079,0.009528827,0.0007364985,0.00025324224,0.0008448274,0.2115644],"genre_scores_gemma":[0.9635229,0.0024560867,0.0105104055,0.008398586,0.00082386174,0.00035553,0.00007905898,0.0004270881,0.013426466],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.8179302,0.1570124,0.0029241648,0.004455658,0.012715598,0.004961969],"domain_scores_gemma":[0.8280985,0.13846427,0.005180575,0.007393543,0.01327287,0.007590243],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.06205434,0.0018552912,0.0012203818,0.0029890323,0.02239833,0.017046493,0.004146307,0.009429985,0.00395229],"category_scores_gemma":[0.18316893,0.0009294009,0.0013412685,0.0023346683,0.041141562,0.021081362,0.028900085,0.029086057,0.0015861848],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000063517924,0.000079388934,0.0004932105,0.00015137596,0.0000131560555,0.0009254932,0.9135041,0.00039671306,0.00087218086,0.06798802,0.004833913,0.01067896],"study_design_scores_gemma":[0.000020061363,0.00011589878,0.0004977429,0.00087839336,0.000013747704,0.0013672054,0.67115605,0.0014561856,0.0020768216,0.045102865,0.27719486,0.00012013699],"about_ca_topic_score_codex":0.0025374566,"about_ca_topic_score_gemma":0.0020078276,"teacher_disagreement_score":0.06205434,"about_ca_system_score_codex":0.009182772,"about_ca_system_score_gemma":0.0046396963,"threshold_uncertainty_score":0.32817864},"labels":[],"label_agreement":null},{"id":"W4399626674","doi":"10.4300/jgme-d-23-00526.1","title":"Exploring the Use of Natural Language Processing to Understand Emotions of Trainees and Faculty Regarding Entrustable Professional Activity Assessments","year":2024,"lang":"en","type":"article","venue":"Journal of Graduate Medical Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Medical education; Psychology; Natural (archaeology); Medicine; Biology","score_opus":0.3044004809950062,"score_gpt":0.47787551308450965,"score_spread":0.17347503208950343,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399626674","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9532927,0.000293876,0.03762402,0.0010305716,0.000033403965,0.0003513376,0.0011373166,0.00018573436,0.0060509844],"genre_scores_gemma":[0.9697826,0.00022569479,0.027776718,0.00034996387,0.00003523457,0.0004282718,0.0007180375,0.000039500686,0.00064393936],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99781597,0.0013867556,0.00017263101,0.00026673052,0.0002535395,0.00010440856],"domain_scores_gemma":[0.96970505,0.024691978,0.003124643,0.00041844594,0.0017880589,0.00027187148],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0034281816,0.00029704487,0.00018376863,0.0017976295,0.00047220042,0.0020930544,0.00034510708,0.0004213706,0.0018810254],"category_scores_gemma":[0.029209651,0.00014107318,0.00038454897,0.00093508244,0.00069387583,0.002319952,0.0008592432,0.0006663339,0.00048868277],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010091393,0.0006811775,0.3462792,0.0019364106,0.00016579218,0.0008591462,0.15686242,0.0030899784,0.046162967,0.0032077846,0.0044725165,0.43527338],"study_design_scores_gemma":[0.000070095775,0.0006925252,0.7992543,0.00072638574,0.00016409987,0.0008178385,0.1054219,0.043610007,0.013607467,0.016599556,0.018847717,0.0001880894],"about_ca_topic_score_codex":0.001423052,"about_ca_topic_score_gemma":0.0018696157,"teacher_disagreement_score":0.0034281816,"about_ca_system_score_codex":0.0008102843,"about_ca_system_score_gemma":0.00055856194,"threshold_uncertainty_score":0.018130124},"labels":[],"label_agreement":null},{"id":"W4399879453","doi":"10.55016/ojs/ajer.v49i4.55029","title":"What Do Teacher Candidates Know About Large-Scale Assessments? What Should They Know?","year":2003,"lang":"en","type":"article","venue":"Alberta Journal of Educational Research","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Lakehead University","funders":"","keywords":"Need to know; Psychology; Scale (ratio); Educational research; Mathematics education; Pedagogy; Computer science; Geography","score_opus":0.0798291492930633,"score_gpt":0.47919424289482,"score_spread":0.3993650936017567,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399879453","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.42197615,0.02980331,0.0034235434,0.5077211,0.0016818767,0.00018216459,0.000911031,0.00019461887,0.0341061],"genre_scores_gemma":[0.9153054,0.033507537,0.0030688255,0.039840586,0.0013180954,0.00021233072,0.00081407494,0.00008019879,0.005853005],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9828303,0.0062572537,0.0016835838,0.00088753586,0.0064104744,0.0019308046],"domain_scores_gemma":[0.8507269,0.047870114,0.024725636,0.0051104883,0.047604404,0.02396239],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.028582811,0.0003036023,0.0011921291,0.0024771695,0.0034110604,0.0062466,0.0012561261,0.0040114075,0.0060911155],"category_scores_gemma":[0.1726308,0.0007679976,0.00060626114,0.0020734486,0.0034101817,0.009659823,0.0019625018,0.00398514,0.0039882325],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025407498,0.0006429772,0.38653532,0.0017424176,0.00011236485,0.0011391604,0.05474221,0.00027477325,0.00074463704,0.0021184753,0.08031068,0.47138292],"study_design_scores_gemma":[0.000070745366,0.0010162608,0.6023209,0.0063663395,0.00016623935,0.003458892,0.20979647,0.0008673266,0.0011322935,0.0055727833,0.16891284,0.00031883345],"about_ca_topic_score_codex":0.039909158,"about_ca_topic_score_gemma":0.060826078,"teacher_disagreement_score":0.039909158,"about_ca_system_score_codex":0.004766225,"about_ca_system_score_gemma":0.0105422195,"threshold_uncertainty_score":0.15116215},"labels":[],"label_agreement":null},{"id":"W4399879966","doi":"10.55016/ojs/ajer.v49i3.54986","title":"Differential Validity and Utility of Successive and Simultaneous Approaches to the Development of Equivalent Achievement Tests in French and English","year":2003,"lang":"en","type":"article","venue":"Alberta Journal of Educational Research","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Differential (mechanical device); Psychology; Multiculturalism; Socioeconomic status; Mathematics education; Multilingualism; Pedagogy; Sociology","score_opus":0.25212667805119937,"score_gpt":0.430524562775349,"score_spread":0.17839788472414964,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4399879966","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95127153,0.00042589378,0.029841816,0.00014859051,0.00008374949,0.00042169457,0.00014570038,0.00013300528,0.017528107],"genre_scores_gemma":[0.96372926,0.00022243854,0.034398198,0.000065638436,0.000033580218,0.00038183478,0.00014396572,0.000032129465,0.0009929618],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9484957,0.030565783,0.0031955875,0.0029908163,0.013752954,0.0009990998],"domain_scores_gemma":[0.81934977,0.13717608,0.010309469,0.013662869,0.017977966,0.0015237881],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.030040778,0.0005610016,0.00040405735,0.003963422,0.00047148368,0.0018625808,0.00094574515,0.00061089674,0.0011436113],"category_scores_gemma":[0.146077,0.00032327586,0.0012302088,0.0015069396,0.001590068,0.0017577225,0.0030695947,0.00093637477,0.0003123191],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0020738218,0.00074150675,0.36805558,0.00040233615,0.00056599866,0.00018580465,0.01562912,0.002535816,0.006658691,0.007822828,0.0005916556,0.5947369],"study_design_scores_gemma":[0.00030467182,0.0067325835,0.91756415,0.00039531494,0.0005481735,0.001039135,0.008698819,0.024507498,0.020431554,0.010621321,0.008931754,0.00022508217],"about_ca_topic_score_codex":0.0036885415,"about_ca_topic_score_gemma":0.009427936,"teacher_disagreement_score":0.030040778,"about_ca_system_score_codex":0.0008538992,"about_ca_system_score_gemma":0.0016911993,"threshold_uncertainty_score":0.15887278},"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,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Grading (engineering); Psychology; Mathematics education; Pedagogy; Engineering","score_opus":0.2729481972337564,"score_gpt":0.5720544857102489,"score_spread":0.29910628847649245,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400440977","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9983188,0.00015625112,0.0003698596,0.00012279177,0.0000059120644,0.000018800401,0.000029296763,0.000011195837,0.0009670118],"genre_scores_gemma":[0.9994659,0.00005096152,0.0002591497,0.00001208426,0.000004310551,0.0000075234657,0.00002509202,0.0000028717582,0.00017221375],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98625004,0.005641961,0.0018330299,0.0012334844,0.004397418,0.000644091],"domain_scores_gemma":[0.89660054,0.062194217,0.02392231,0.0040102107,0.009567021,0.0037057817],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00809396,0.00017698697,0.00030850392,0.0010741987,0.0006850237,0.001302738,0.00047552647,0.00035360997,0.0010539382],"category_scores_gemma":[0.072535686,0.00023034151,0.00020763231,0.0013065564,0.0008566346,0.00071188575,0.0005409879,0.0005050994,0.00026707177],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013878796,0.00017734466,0.9575471,0.00006898767,0.000045634697,0.00016052862,0.007043403,0.00045133394,0.001572106,0.00010691278,0.00034286102,0.03234495],"study_design_scores_gemma":[0.000008521441,0.000121637815,0.995652,0.00001975924,0.000013173932,0.00011882416,0.0023119901,0.00031671848,0.00048691191,0.0000974345,0.0008411086,0.0000118773905],"about_ca_topic_score_codex":0.015233822,"about_ca_topic_score_gemma":0.02152471,"teacher_disagreement_score":0.015233822,"about_ca_system_score_codex":0.0011794644,"about_ca_system_score_gemma":0.001387941,"threshold_uncertainty_score":0.042805433},"labels":[],"label_agreement":null},{"id":"W4400804946","doi":"10.1177/00049441241258496","title":"Creating and enacting culturally responsive assessment for First Nations students in higher education settings","year":2024,"lang":"en","type":"article","venue":"Australian Journal of Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Pedagogy; Higher education; Psychology; Cultural competence; Mathematics education; Sociology; Medical education; Political science; Engineering ethics; Medicine; Engineering","score_opus":0.05268109075650512,"score_gpt":0.4546815064927637,"score_spread":0.40200041573625855,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400804946","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6825844,0.0013427134,0.19325139,0.047834348,0.00095646206,0.0027101347,0.00007629832,0.0013957937,0.06984848],"genre_scores_gemma":[0.7767668,0.0005524632,0.21247004,0.0035849516,0.000047897436,0.0012126307,0.000051635947,0.00016320942,0.005150351],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.8513024,0.12574095,0.0047339736,0.0037456765,0.010498289,0.003978582],"domain_scores_gemma":[0.8739616,0.0585908,0.009968155,0.014581911,0.027878493,0.015019044],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.13852508,0.00089979696,0.0006854097,0.001911653,0.008434074,0.012846532,0.0027236496,0.0028668821,0.0017332194],"category_scores_gemma":[0.15495452,0.000768197,0.0007425924,0.0009287294,0.009767402,0.008357829,0.019693643,0.0062502236,0.001008443],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007748125,0.0007840893,0.03783272,0.00054951414,0.000054018405,0.0007954918,0.73283035,0.0008688092,0.0068493523,0.013377764,0.0049214023,0.20105901],"study_design_scores_gemma":[0.000056761295,0.0009438368,0.031135976,0.0033021763,0.00008145574,0.0015483779,0.7253847,0.004104167,0.012488499,0.04323063,0.17723477,0.0004885956],"about_ca_topic_score_codex":0.0041486425,"about_ca_topic_score_gemma":0.010169739,"teacher_disagreement_score":0.13852508,"about_ca_system_score_codex":0.0051936703,"about_ca_system_score_gemma":0.021993527,"threshold_uncertainty_score":0.7325994},"labels":[],"label_agreement":null},{"id":"W4400898293","doi":"10.55016/ojs/pplt.v3y2019.53345","title":"A Study of Authentic Assessment in an Internship Course","year":2019,"lang":"en","type":"article","venue":"Papers on postsecondary learning and teaching.","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Royal Roads University","funders":"","keywords":"Internship; Authentic learning; Medical education; Pedagogy; Authentic assessment; Psychology; Medicine; Curriculum","score_opus":0.018702050589538707,"score_gpt":0.3694773532151014,"score_spread":0.35077530262556267,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4400898293","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9946932,0.000059703525,0.00095680775,0.00037225138,0.000034681976,0.00008854723,0.000007774619,0.000013429329,0.0037735503],"genre_scores_gemma":[0.9961389,0.0000933106,0.001020716,0.00015494452,0.000015441443,0.00006440583,0.00000997726,0.00000895029,0.00249341],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99105495,0.005540963,0.0002860081,0.00052321906,0.0018767507,0.0007181289],"domain_scores_gemma":[0.96455806,0.017789144,0.0031451597,0.0014691483,0.0058589266,0.0071795443],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.012780492,0.0004990634,0.00073899346,0.0011902048,0.005494502,0.005230181,0.0011835119,0.0011631842,0.0017522058],"category_scores_gemma":[0.05543073,0.00045243185,0.00034853196,0.0008216485,0.0035520312,0.0020195271,0.0030873297,0.0039391266,0.00039314],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014639135,0.0041096606,0.045031797,0.00013029297,0.000012131392,0.0011510456,0.8851482,0.00016028603,0.0040175775,0.0019386188,0.001394896,0.056759074],"study_design_scores_gemma":[0.00007244024,0.0053946213,0.1274535,0.0002467394,0.00002042957,0.0016393823,0.82643104,0.0015718404,0.0036140091,0.0013934774,0.032051492,0.00011111195],"about_ca_topic_score_codex":0.003705341,"about_ca_topic_score_gemma":0.00718942,"teacher_disagreement_score":0.012780492,"about_ca_system_score_codex":0.0025934489,"about_ca_system_score_gemma":0.0034760842,"threshold_uncertainty_score":0.067590475},"labels":[],"label_agreement":null},{"id":"W4401063996","doi":"10.53761/1.20.5.13","title":"Exploring Faculty Mindsets in Equity-Oriented Assessment","year":2023,"lang":"en","type":"article","venue":"Journal of University Teaching and Learning Practice","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University; Athabasca University","funders":"","keywords":"Rigour; Thematic analysis; Equity (law); Medical education; Psychology; Alternative assessment; Higher education; Qualitative property; Pedagogy; Data collection; Public relations; Qualitative research; Sociology; Political science; Social science; Medicine","score_opus":0.1606322251998828,"score_gpt":0.4301161781990955,"score_spread":0.2694839529992127,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401063996","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9735537,0.00028864067,0.008426709,0.0040354365,0.000052507956,0.000071858354,0.0000074103996,0.000027367918,0.013536525],"genre_scores_gemma":[0.99834824,0.00006345173,0.00089956314,0.00020851637,0.0000070456135,0.00001897896,0.0000031183963,0.000005352353,0.00044569565],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9559142,0.033145364,0.0010167441,0.0016666104,0.0059840684,0.002272994],"domain_scores_gemma":[0.9252152,0.058633104,0.0050717914,0.0026715274,0.0037718043,0.0046365233],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.041065156,0.00043237774,0.00048546464,0.002863769,0.007959743,0.0098524615,0.001515106,0.002239734,0.0017498268],"category_scores_gemma":[0.07538257,0.0005219484,0.0005223906,0.001499353,0.020919185,0.008248797,0.016793936,0.004249544,0.00015057817],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000440517,0.00014158669,0.014577796,0.000107432475,0.00001494439,0.00033632223,0.9520443,0.00025651485,0.00186962,0.011698444,0.00028807783,0.018620985],"study_design_scores_gemma":[0.000029342335,0.00027451807,0.020269254,0.00032713346,0.000024113937,0.00060089567,0.91899365,0.0015406522,0.0021491523,0.04098361,0.014728968,0.00007877971],"about_ca_topic_score_codex":0.0025948419,"about_ca_topic_score_gemma":0.0034946848,"teacher_disagreement_score":0.041065156,"about_ca_system_score_codex":0.0067839017,"about_ca_system_score_gemma":0.006951737,"threshold_uncertainty_score":0.2171759},"labels":[],"label_agreement":null},{"id":"W4401116136","doi":"10.1097/nne.0000000000001707","title":"Exam Wrappers in Nursing Education","year":2024,"lang":"en","type":"article","venue":"Nurse Educator","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Cooke Aquaculture (Canada)","funders":"","keywords":"Session (web analytics); Metacognition; Medical education; Psychology; Test (biology); Physical exam; Computer science; Medicine; Internal medicine; Cognition; World Wide Web","score_opus":0.0207929048151693,"score_gpt":0.43070026417597734,"score_spread":0.409907359360808,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401116136","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9736961,0.0049931286,0.008380726,0.0017620942,0.00023975967,0.0004162107,0.00006930854,0.00061135885,0.009831271],"genre_scores_gemma":[0.9786084,0.001717932,0.01649903,0.0004408908,0.00009345909,0.00027052418,0.000072375005,0.00003935944,0.0022579401],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99556327,0.0028134114,0.00026193672,0.00024313669,0.00087074004,0.00024754278],"domain_scores_gemma":[0.9712904,0.01959682,0.0033360112,0.0010691985,0.0014574697,0.0032499556],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0054562204,0.00040827153,0.00033975966,0.00088205107,0.00064612605,0.0012242461,0.00077829737,0.00048284372,0.0037160618],"category_scores_gemma":[0.03983179,0.00019755217,0.00032366475,0.0005190693,0.0003673417,0.0006243242,0.0019831425,0.0007215597,0.0006609487],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00035493023,0.0023086888,0.026147114,0.000486162,0.000040568782,0.00019071822,0.0016735326,0.00043755514,0.0024824354,0.00016363476,0.0024499018,0.9632648],"study_design_scores_gemma":[0.0004803433,0.02894086,0.819856,0.0036805586,0.00053770764,0.004020389,0.009831124,0.005780323,0.034919687,0.0044526565,0.08728459,0.00021582759],"about_ca_topic_score_codex":0.00045511263,"about_ca_topic_score_gemma":0.0013806242,"teacher_disagreement_score":0.0054562204,"about_ca_system_score_codex":0.00072413567,"about_ca_system_score_gemma":0.001760929,"threshold_uncertainty_score":0.028855622},"labels":[],"label_agreement":null},{"id":"W4401119677","doi":"10.1007/s11896-024-09696-5","title":"Investigating a Train-the-Trainer Model of Supervision and Peer Review for Child Interviewers in Canadian Police Services","year":2024,"lang":"en","type":"article","venue":"Journal of Police and Criminal Psychology","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Barrie Urology Group; Hospital for Sick Children","funders":"Australian Research Council; Griffith University; Government of Ontario","keywords":"Interview; Trainer; Psychology; Focus group; Qualitative research; Semi-structured interview; Medical education; Motivational interviewing; Intervention (counseling); Applied psychology; Medicine; Sociology","score_opus":0.08866103449901191,"score_gpt":0.4465185265585714,"score_spread":0.35785749205955947,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401119677","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97424084,0.0003906745,0.0063769934,0.0029345334,0.000050890118,0.002728494,0.000081801314,0.00009712961,0.0130986385],"genre_scores_gemma":[0.98107266,0.00037971226,0.014727144,0.00030830406,0.000019529989,0.001295734,0.00004271535,0.000021189195,0.0021329382],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9476705,0.042172473,0.0007727331,0.0013748395,0.0046236664,0.0033857063],"domain_scores_gemma":[0.9475968,0.025503222,0.004242259,0.0030023898,0.009574787,0.010080545],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.04913884,0.00058985385,0.000524974,0.0017992809,0.010206925,0.0045070513,0.00464696,0.0010483523,0.002526472],"category_scores_gemma":[0.055968396,0.0008034556,0.000402837,0.0010825446,0.005185906,0.0020509388,0.005848289,0.0019094761,0.0003056845],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006952573,0.002918102,0.120260656,0.0011772563,0.0000818483,0.0010810444,0.7367758,0.0012050531,0.003468579,0.0041071973,0.004847736,0.12338138],"study_design_scores_gemma":[0.00055737566,0.004801926,0.26798406,0.0014914887,0.00014374619,0.00077072915,0.6505389,0.0065307063,0.003964301,0.0014576054,0.061476354,0.00028276513],"about_ca_topic_score_codex":0.57990026,"about_ca_topic_score_gemma":0.8279676,"teacher_disagreement_score":0.42009974,"about_ca_system_score_codex":0.051950112,"about_ca_system_score_gemma":0.09367051,"threshold_uncertainty_score":0.84514755},"labels":[],"label_agreement":null},{"id":"W4401163052","doi":"10.1162/qss_a_00319/v1/review1","title":"Review for \"Researcher profile system adoption and use across discipline and rank: A case study at the University of Manitoba\"","year":2023,"lang":"en","type":"peer-review","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Rank (graph theory); Sociology; Library science; Computer science; Mathematics; Combinatorics","score_opus":0.1767180876940532,"score_gpt":0.451189343083615,"score_spread":0.27447125538956185,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401163052","genre_codex":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006372017,0.033330563,0.0050128666,0.7455227,0.10825135,0.0072184517,0.0050528403,0.0014426147,0.087796666],"genre_scores_gemma":[0.054110806,0.074335665,0.025440572,0.48319665,0.035174366,0.015294787,0.007220439,0.0016471833,0.30357957],"study_design_codex":"not_applicable","study_design_gemma":"qualitative","domain_scores_codex":[0.9491847,0.022287551,0.007178753,0.0010435999,0.018545639,0.00175961],"domain_scores_gemma":[0.49003595,0.10297884,0.01543721,0.013689646,0.36731273,0.010545696],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.060632687,0.00054500723,0.0012482278,0.006184497,0.0060662357,0.006427932,0.003806264,0.006425852,0.018635659],"category_scores_gemma":[0.27072573,0.00067457417,0.0013661075,0.004719236,0.003507813,0.0021722647,0.0034236037,0.0035096968,0.011308235],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000325183,0.00002815212,0.00046494682,0.0021119118,0.000031317995,0.00007923185,0.00046190902,0.000015053549,0.00015189081,0.0010368249,0.9583903,0.037195906],"study_design_scores_gemma":[0.00012863387,0.00011553782,0.009391444,0.011489404,0.0001635553,0.000159086,0.0012517434,0.00008451259,0.00036921856,0.0008856476,0.9759203,0.000040933734],"about_ca_topic_score_codex":0.035406813,"about_ca_topic_score_gemma":0.13754894,"teacher_disagreement_score":0.99135536,"about_ca_system_score_codex":0.008644624,"about_ca_system_score_gemma":0.07605695,"threshold_uncertainty_score":0.32066017},"labels":[],"label_agreement":null},{"id":"W4401163090","doi":"10.1162/qss_a_00319/v2/review2","title":"Review for \"Researcher profile system adoption and use across discipline and rank: A case study at the University of Manitoba\"","year":2023,"lang":"en","type":"peer-review","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Rank (graph theory); Geography; Library science; Data science; Sociology; Computer science; Mathematics","score_opus":0.1767180876940532,"score_gpt":0.451189343083615,"score_spread":0.27447125538956185,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401163090","genre_codex":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006372017,0.033330563,0.0050128666,0.7455227,0.10825135,0.0072184517,0.0050528403,0.0014426147,0.087796666],"genre_scores_gemma":[0.054110806,0.074335665,0.025440572,0.48319665,0.035174366,0.015294787,0.007220439,0.0016471833,0.30357957],"study_design_codex":"not_applicable","study_design_gemma":"qualitative","domain_scores_codex":[0.9491847,0.022287551,0.007178753,0.0010435999,0.018545639,0.00175961],"domain_scores_gemma":[0.49003595,0.10297884,0.01543721,0.013689646,0.36731273,0.010545696],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.060632687,0.00054500723,0.0012482278,0.006184497,0.0060662357,0.006427932,0.003806264,0.006425852,0.018635659],"category_scores_gemma":[0.27072573,0.00067457417,0.0013661075,0.004719236,0.003507813,0.0021722647,0.0034236037,0.0035096968,0.011308235],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000325183,0.00002815212,0.00046494682,0.0021119118,0.000031317995,0.00007923185,0.00046190902,0.000015053549,0.00015189081,0.0010368249,0.9583903,0.037195906],"study_design_scores_gemma":[0.00012863387,0.00011553782,0.009391444,0.011489404,0.0001635553,0.000159086,0.0012517434,0.00008451259,0.00036921856,0.0008856476,0.9759203,0.000040933734],"about_ca_topic_score_codex":0.035406813,"about_ca_topic_score_gemma":0.13754894,"teacher_disagreement_score":0.99135536,"about_ca_system_score_codex":0.008644624,"about_ca_system_score_gemma":0.07605695,"threshold_uncertainty_score":0.32066017},"labels":[],"label_agreement":null},{"id":"W4401163117","doi":"10.1162/qss_a_00319/v3/review1","title":"Review for \"Researcher profile system adoption and use across discipline and rank: A case study at the University of Manitoba\"","year":2023,"lang":"en","type":"peer-review","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Rank (graph theory); Sociology; Geography; Library science; Computer science; Mathematics","score_opus":0.1767180876940532,"score_gpt":0.451189343083615,"score_spread":0.27447125538956185,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401163117","genre_codex":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006372017,0.033330563,0.0050128666,0.7455227,0.10825135,0.0072184517,0.0050528403,0.0014426147,0.087796666],"genre_scores_gemma":[0.054110806,0.074335665,0.025440572,0.48319665,0.035174366,0.015294787,0.007220439,0.0016471833,0.30357957],"study_design_codex":"not_applicable","study_design_gemma":"qualitative","domain_scores_codex":[0.9491847,0.022287551,0.007178753,0.0010435999,0.018545639,0.00175961],"domain_scores_gemma":[0.49003595,0.10297884,0.01543721,0.013689646,0.36731273,0.010545696],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.060632687,0.00054500723,0.0012482278,0.006184497,0.0060662357,0.006427932,0.003806264,0.006425852,0.018635659],"category_scores_gemma":[0.27072573,0.00067457417,0.0013661075,0.004719236,0.003507813,0.0021722647,0.0034236037,0.0035096968,0.011308235],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000325183,0.00002815212,0.00046494682,0.0021119118,0.000031317995,0.00007923185,0.00046190902,0.000015053549,0.00015189081,0.0010368249,0.9583903,0.037195906],"study_design_scores_gemma":[0.00012863387,0.00011553782,0.009391444,0.011489404,0.0001635553,0.000159086,0.0012517434,0.00008451259,0.00036921856,0.0008856476,0.9759203,0.000040933734],"about_ca_topic_score_codex":0.035406813,"about_ca_topic_score_gemma":0.13754894,"teacher_disagreement_score":0.99135536,"about_ca_system_score_codex":0.008644624,"about_ca_system_score_gemma":0.07605695,"threshold_uncertainty_score":0.32066017},"labels":[],"label_agreement":null},{"id":"W4401163120","doi":"10.1162/qss_a_00319/v1/review3","title":"Review for \"Researcher profile system adoption and use across discipline and rank: A case study at the University of Manitoba\"","year":2023,"lang":"en","type":"peer-review","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Rank (graph theory); Sociology; Library science; Regional science; Computer science; Mathematics","score_opus":0.1767180876940532,"score_gpt":0.451189343083615,"score_spread":0.27447125538956185,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401163120","genre_codex":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006372017,0.033330563,0.0050128666,0.7455227,0.10825135,0.0072184517,0.0050528403,0.0014426147,0.087796666],"genre_scores_gemma":[0.054110806,0.074335665,0.025440572,0.48319665,0.035174366,0.015294787,0.007220439,0.0016471833,0.30357957],"study_design_codex":"not_applicable","study_design_gemma":"qualitative","domain_scores_codex":[0.9491847,0.022287551,0.007178753,0.0010435999,0.018545639,0.00175961],"domain_scores_gemma":[0.49003595,0.10297884,0.01543721,0.013689646,0.36731273,0.010545696],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.060632687,0.00054500723,0.0012482278,0.006184497,0.0060662357,0.006427932,0.003806264,0.006425852,0.018635659],"category_scores_gemma":[0.27072573,0.00067457417,0.0013661075,0.004719236,0.003507813,0.0021722647,0.0034236037,0.0035096968,0.011308235],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000325183,0.00002815212,0.00046494682,0.0021119118,0.000031317995,0.00007923185,0.00046190902,0.000015053549,0.00015189081,0.0010368249,0.9583903,0.037195906],"study_design_scores_gemma":[0.00012863387,0.00011553782,0.009391444,0.011489404,0.0001635553,0.000159086,0.0012517434,0.00008451259,0.00036921856,0.0008856476,0.9759203,0.000040933734],"about_ca_topic_score_codex":0.035406813,"about_ca_topic_score_gemma":0.13754894,"teacher_disagreement_score":0.99135536,"about_ca_system_score_codex":0.008644624,"about_ca_system_score_gemma":0.07605695,"threshold_uncertainty_score":0.32066017},"labels":[],"label_agreement":null},{"id":"W4401163268","doi":"10.1162/qss_a_00319/v1/review2","title":"Review for \"Researcher profile system adoption and use across discipline and rank: A case study at the University of Manitoba\"","year":2023,"lang":"en","type":"peer-review","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Rank (graph theory); Sociology; Psychology; Library science; Computer science; Mathematics","score_opus":0.1767180876940532,"score_gpt":0.451189343083615,"score_spread":0.27447125538956185,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401163268","genre_codex":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006372017,0.033330563,0.0050128666,0.7455227,0.10825135,0.0072184517,0.0050528403,0.0014426147,0.087796666],"genre_scores_gemma":[0.054110806,0.074335665,0.025440572,0.48319665,0.035174366,0.015294787,0.007220439,0.0016471833,0.30357957],"study_design_codex":"not_applicable","study_design_gemma":"qualitative","domain_scores_codex":[0.9491847,0.022287551,0.007178753,0.0010435999,0.018545639,0.00175961],"domain_scores_gemma":[0.49003595,0.10297884,0.01543721,0.013689646,0.36731273,0.010545696],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.060632687,0.00054500723,0.0012482278,0.006184497,0.0060662357,0.006427932,0.003806264,0.006425852,0.018635659],"category_scores_gemma":[0.27072573,0.00067457417,0.0013661075,0.004719236,0.003507813,0.0021722647,0.0034236037,0.0035096968,0.011308235],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000325183,0.00002815212,0.00046494682,0.0021119118,0.000031317995,0.00007923185,0.00046190902,0.000015053549,0.00015189081,0.0010368249,0.9583903,0.037195906],"study_design_scores_gemma":[0.00012863387,0.00011553782,0.009391444,0.011489404,0.0001635553,0.000159086,0.0012517434,0.00008451259,0.00036921856,0.0008856476,0.9759203,0.000040933734],"about_ca_topic_score_codex":0.035406813,"about_ca_topic_score_gemma":0.13754894,"teacher_disagreement_score":0.99135536,"about_ca_system_score_codex":0.008644624,"about_ca_system_score_gemma":0.07605695,"threshold_uncertainty_score":0.32066017},"labels":[],"label_agreement":null},{"id":"W4401163547","doi":"10.1162/qss_a_00319/v2/review3","title":"Review for \"Researcher profile system adoption and use across discipline and rank: A case study at the University of Manitoba\"","year":2023,"lang":"en","type":"peer-review","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Rank (graph theory); Psychology; Sociology; Mathematics; Combinatorics","score_opus":0.1767180876940532,"score_gpt":0.451189343083615,"score_spread":0.27447125538956185,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401163547","genre_codex":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006372017,0.033330563,0.0050128666,0.7455227,0.10825135,0.0072184517,0.0050528403,0.0014426147,0.087796666],"genre_scores_gemma":[0.054110806,0.074335665,0.025440572,0.48319665,0.035174366,0.015294787,0.007220439,0.0016471833,0.30357957],"study_design_codex":"not_applicable","study_design_gemma":"qualitative","domain_scores_codex":[0.9491847,0.022287551,0.007178753,0.0010435999,0.018545639,0.00175961],"domain_scores_gemma":[0.49003595,0.10297884,0.01543721,0.013689646,0.36731273,0.010545696],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.060632687,0.00054500723,0.0012482278,0.006184497,0.0060662357,0.006427932,0.003806264,0.006425852,0.018635659],"category_scores_gemma":[0.27072573,0.00067457417,0.0013661075,0.004719236,0.003507813,0.0021722647,0.0034236037,0.0035096968,0.011308235],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000325183,0.00002815212,0.00046494682,0.0021119118,0.000031317995,0.00007923185,0.00046190902,0.000015053549,0.00015189081,0.0010368249,0.9583903,0.037195906],"study_design_scores_gemma":[0.00012863387,0.00011553782,0.009391444,0.011489404,0.0001635553,0.000159086,0.0012517434,0.00008451259,0.00036921856,0.0008856476,0.9759203,0.000040933734],"about_ca_topic_score_codex":0.035406813,"about_ca_topic_score_gemma":0.13754894,"teacher_disagreement_score":0.99135536,"about_ca_system_score_codex":0.008644624,"about_ca_system_score_gemma":0.07605695,"threshold_uncertainty_score":0.32066017},"labels":[],"label_agreement":null},{"id":"W4401172997","doi":"10.55016/ojs/ajer.v70i2.79716","title":"Interests, Knowledge and Evaluation: Alternative Approaches to Curriculum Evaluation","year":2024,"lang":"en","type":"article","venue":"Alberta Journal of Educational Research","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Curriculum; Permission; Index (typography); Sociology; Mathematics education; Psychology; Engineering ethics; Pedagogy; Epistemology; Computer science; Philosophy; Engineering","score_opus":0.45716967945896014,"score_gpt":0.5623502702934415,"score_spread":0.10518059083448139,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401172997","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0040446403,0.024711527,0.8938969,0.018748736,0.0021096317,0.0015021479,0.0005270242,0.00043289323,0.05402644],"genre_scores_gemma":[0.15407427,0.009636193,0.8146812,0.0025021068,0.0007878975,0.0056778686,0.0003095076,0.00033256548,0.011998424],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.7978639,0.17343283,0.0061548506,0.0027869993,0.018879019,0.0008823326],"domain_scores_gemma":[0.75683844,0.20331836,0.0067487177,0.011859526,0.019802462,0.001432426],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.1105702,0.0021594472,0.0021279491,0.013124279,0.0018590525,0.011516772,0.003727346,0.0033988277,0.015085631],"category_scores_gemma":[0.222522,0.0012442583,0.0020371985,0.012071002,0.013138386,0.013778773,0.0058583664,0.007829797,0.0021715716],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00026742372,0.00012871987,0.0020488265,0.0025049516,0.00033081727,0.00016156625,0.0074913264,0.0019988657,0.0003189591,0.5829586,0.023429377,0.3783606],"study_design_scores_gemma":[0.00012981272,0.0002264732,0.0028911845,0.0029160536,0.00020249706,0.00047292717,0.005299825,0.014131216,0.0008532285,0.87784284,0.09487104,0.00016302767],"about_ca_topic_score_codex":0.0032407069,"about_ca_topic_score_gemma":0.00743311,"teacher_disagreement_score":0.1105702,"about_ca_system_score_codex":0.006518462,"about_ca_system_score_gemma":0.004465422,"threshold_uncertainty_score":0.5847581},"labels":[],"label_agreement":null},{"id":"W4401285935","doi":"10.18260/1-2--46845","title":"Board 271: Evaluating the Effect of Multi-Attempt Digital Assessments on Student Performance in Foundation Engineering Courses","year":2024,"lang":"en","type":"article","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Innovation Cluster (Canada)","funders":"Directorate for STEM Education; National Science Foundation; National Institutes of Health; Ministry of Education, Science and Technology; University of Cincinnati; American Society for Engineering Education","keywords":"Foundation (evidence); Computer science; Engineering management; Engineering; Political science","score_opus":0.044307724525487306,"score_gpt":0.44155303277887287,"score_spread":0.39724530825338555,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401285935","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9970182,0.000025507488,0.00063354627,0.00007527739,0.000076754775,0.00045489086,0.000080840065,0.000094168914,0.0015407085],"genre_scores_gemma":[0.9897076,0.000100704616,0.003373031,0.00014451472,0.000058863403,0.0015392656,0.00038807854,0.000037985104,0.0046498757],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99651897,0.0013666727,0.00036254534,0.0006590672,0.00077165524,0.00032102497],"domain_scores_gemma":[0.97227806,0.009680348,0.0046705673,0.0016343553,0.0035174403,0.008219179],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005483509,0.0010299319,0.00086231396,0.0006252498,0.0008693289,0.0011754782,0.00076116185,0.00062471075,0.0036107893],"category_scores_gemma":[0.023740724,0.00061331084,0.0008724973,0.000337771,0.0005518574,0.00097222155,0.0013080941,0.0013211526,0.0018970419],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.033011377,0.114133656,0.35228696,0.00058850745,0.00087841525,0.00030321686,0.004577021,0.0067692744,0.03454903,0.00042477666,0.008013113,0.4444646],"study_design_scores_gemma":[0.003568997,0.19776183,0.75488985,0.000098877164,0.00048735298,0.00009818323,0.002112351,0.008991285,0.02153594,0.0003408064,0.009949375,0.00016507485],"about_ca_topic_score_codex":0.0021440305,"about_ca_topic_score_gemma":0.0043654153,"teacher_disagreement_score":0.005483509,"about_ca_system_score_codex":0.00077401195,"about_ca_system_score_gemma":0.0017072245,"threshold_uncertainty_score":0.028999925},"labels":[],"label_agreement":null},{"id":"W4401394229","doi":"10.1111/medu.15487","title":"The pitfalls and perils of anonymous learner feedback","year":2024,"lang":"en","type":"letter","venue":"Medical Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Medical education; Psychology; MEDLINE; Medicine; Computer science; Political science","score_opus":0.014215028337451533,"score_gpt":0.35567680161570403,"score_spread":0.3414617732782525,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401394229","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00062562426,0.00032122876,0.0008522981,0.9928114,0.0025570272,0.00003110107,0.000017100427,0.00008065295,0.0027035926],"genre_scores_gemma":[0.011949174,0.0004244132,0.002115357,0.97546935,0.0056802486,0.00017739092,0.000010789157,0.00008857851,0.004084706],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.80776423,0.10979246,0.012614504,0.0064646704,0.060161196,0.0032030332],"domain_scores_gemma":[0.591013,0.30414343,0.019814512,0.012102899,0.06138554,0.011540704],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.09211002,0.0007404908,0.0007832588,0.0015449498,0.008546537,0.0087029515,0.003918044,0.040092416,0.0037236894],"category_scores_gemma":[0.30904025,0.0011787467,0.0017511493,0.001373276,0.013417299,0.009054943,0.0056612506,0.037039813,0.0047733416],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000095921794,0.000059980892,0.0023493918,0.00019996111,0.0000338799,0.002498513,0.007263249,0.00018067479,0.0007353097,0.014769405,0.92074144,0.051072292],"study_design_scores_gemma":[0.00007989198,0.00019484502,0.003161563,0.001267563,0.00003224669,0.005857494,0.00929759,0.0017883063,0.0009344529,0.02788941,0.9493084,0.00018827339],"about_ca_topic_score_codex":0.008712184,"about_ca_topic_score_gemma":0.01578159,"teacher_disagreement_score":0.09211002,"about_ca_system_score_codex":0.0071877697,"about_ca_system_score_gemma":0.0106997425,"threshold_uncertainty_score":0.48713017},"labels":[],"label_agreement":null},{"id":"W4401488009","doi":"10.37546/jalttlt48.5-1","title":"JALT2024 Plenary Speaker: Toward Justice-Affirming Language Teaching","year":2024,"lang":"en","type":"article","venue":"The Language Teacher","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Plenary session; Linguistics; Economic Justice; Sociology; Psychology; Political science; Computer science; Philosophy; Law; Library science","score_opus":0.03437048302652522,"score_gpt":0.3838888456095768,"score_spread":0.3495183625830516,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401488009","genre_codex":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0038798633,0.008464703,0.0012651427,0.5410343,0.3939189,0.00036897103,0.00060343626,0.00037277423,0.05009194],"genre_scores_gemma":[0.06855395,0.009623149,0.003197192,0.19272004,0.27674884,0.0013274406,0.000725112,0.000785834,0.4463185],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.998041,0.0004990909,0.00012436938,0.00027457395,0.00071579736,0.00034527652],"domain_scores_gemma":[0.99364316,0.00097641256,0.00030215358,0.00011676364,0.0025857938,0.0023756316],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0046500904,0.000752175,0.0006209411,0.0010270008,0.004940015,0.0053901887,0.0014527986,0.008549037,0.047778036],"category_scores_gemma":[0.011055736,0.0002457024,0.00060516055,0.00053596136,0.0015580662,0.0028642223,0.004640368,0.008376563,0.015518554],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000067230685,0.00007599427,0.00030058093,0.00011367918,0.0000033154238,0.00017784255,0.00085305265,0.000024970619,0.0005036124,0.0014833569,0.98178047,0.0146158775],"study_design_scores_gemma":[0.000032561926,0.0001276469,0.0027610632,0.0003899805,0.000011813499,0.00032156383,0.0029690766,0.00019119025,0.00041808048,0.0016289388,0.99111533,0.000032739976],"about_ca_topic_score_codex":0.003638769,"about_ca_topic_score_gemma":0.0060885902,"teacher_disagreement_score":0.047778036,"about_ca_system_score_codex":0.0029169314,"about_ca_system_score_gemma":0.0033209866,"threshold_uncertainty_score":0.15983349},"labels":[],"label_agreement":null},{"id":"W4401490251","doi":"10.1186/s41239-024-00483-0","title":"Rethinking assessment strategies to improve authentic representations of learning: using blogs as a creative assessment alternative to develop professional skills","year":2024,"lang":"en","type":"article","venue":"International Journal of Educational Technology in Higher Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Higher education; Authentic learning; Psychology; Pedagogy; Mathematics education; Sociology; Knowledge management; Computer science; Political science","score_opus":0.03685730727687135,"score_gpt":0.4836799594142759,"score_spread":0.4468226521374045,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401490251","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.79505444,0.00048447566,0.15993531,0.0021964246,0.00047253526,0.001227978,0.00008848966,0.0014575578,0.039082773],"genre_scores_gemma":[0.83749115,0.00033369006,0.15269226,0.00028652998,0.00007793889,0.0005868846,0.00007542585,0.00018412832,0.008271989],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9908179,0.0057832124,0.0004584917,0.00059320615,0.0020377983,0.00030929898],"domain_scores_gemma":[0.9462304,0.03792775,0.0024866625,0.0063300533,0.0052944184,0.0017306219],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011526036,0.0006494054,0.000417802,0.0016740805,0.0009582785,0.0047670053,0.0010931966,0.0008470668,0.0031252792],"category_scores_gemma":[0.04531064,0.00031717448,0.00041457746,0.0006736549,0.0014896812,0.004758489,0.0035424666,0.0014193126,0.0011783122],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003724363,0.002366083,0.018746661,0.00076610985,0.000039599534,0.0003739512,0.04769835,0.0008317789,0.019223768,0.0046301982,0.003782786,0.9011684],"study_design_scores_gemma":[0.00089751644,0.014299647,0.15708,0.0063446583,0.00049329264,0.0049207755,0.18302026,0.042727005,0.11589464,0.078582644,0.39480072,0.0009388219],"about_ca_topic_score_codex":0.0002866537,"about_ca_topic_score_gemma":0.00074267416,"teacher_disagreement_score":0.011526036,"about_ca_system_score_codex":0.00056063297,"about_ca_system_score_gemma":0.0014874019,"threshold_uncertainty_score":0.06095624},"labels":[],"label_agreement":null},{"id":"W4401820437","doi":"10.1177/01614681200310507004","title":"<i>The Assessment Bridge: Positive Ways to Link tests to Learning, Standards, and Curriculum Improvement</i> Pearl G. Solomon. Thousand Oaks: Corwin Press, 2002, ISBN: 0761945946, 160 pp.","year":2003,"lang":"en","type":"article","venue":"Teachers College Record The Voice of Scholarship in Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Learning Partnership","funders":"","keywords":"Pearl; Bridge (graph theory); Link (geometry); Curriculum; Engineering; Psychology; History; Pedagogy; Computer science; Archaeology; Medicine; Internal medicine","score_opus":0.017954572781727678,"score_gpt":0.348182233804585,"score_spread":0.33022766102285733,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401820437","genre_codex":"other","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0021575885,0.15642361,0.17618404,0.23155789,0.033287905,0.00048447994,0.0008924591,0.0065621124,0.39244998],"genre_scores_gemma":[0.05950536,0.19484834,0.2586452,0.05723454,0.016819902,0.0011875788,0.002050798,0.0028624935,0.4068459],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99653447,0.001840769,0.00021061412,0.00015187451,0.0011533165,0.000109022534],"domain_scores_gemma":[0.98908955,0.0075383717,0.00055988965,0.0003940914,0.0018418108,0.00057622825],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0076661035,0.0009057115,0.0004114696,0.0027897113,0.00075620407,0.0044693626,0.0014921657,0.002138126,0.041314516],"category_scores_gemma":[0.022692189,0.0004806203,0.00031969513,0.0023657943,0.0025207587,0.009180182,0.0030723712,0.0033451908,0.01805732],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020978621,0.000022097758,0.00033300483,0.00033400944,0.000011970642,0.000042597225,0.00067000085,0.00006953611,0.00018148203,0.013199005,0.6889334,0.29618195],"study_design_scores_gemma":[0.000012467413,0.000045839715,0.0016552766,0.0010773249,0.000012866386,0.0003328303,0.00092945725,0.00026034244,0.00033175314,0.023201909,0.972122,0.000018035927],"about_ca_topic_score_codex":0.0032870173,"about_ca_topic_score_gemma":0.009950342,"teacher_disagreement_score":0.041314516,"about_ca_system_score_codex":0.000744219,"about_ca_system_score_gemma":0.0018031999,"threshold_uncertainty_score":0.13821083},"labels":[],"label_agreement":null},{"id":"W4401977588","doi":"10.26522/brocked.v33i3.1179","title":"The Role of Students’ Assessment Literacies in Navigating University Assessment, GenAI, and Academic Integrity","year":2024,"lang":"en","type":"article","venue":"Brock Education Journal","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Academic integrity; Psychology; Pedagogy; Surface integrity; Mathematics education; Sociology; Engineering ethics; Social psychology; Engineering","score_opus":0.021832631080602738,"score_gpt":0.4204782449096844,"score_spread":0.39864561382908165,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401977588","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98410416,0.00024806522,0.0014401159,0.0025030368,0.000019042862,0.00002470061,0.000010066245,0.000024201105,0.011626611],"genre_scores_gemma":[0.99913293,0.00005979628,0.00034669798,0.00007052877,0.0000031810048,0.00000731972,0.0000031830136,0.000002707429,0.00037366262],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.9901411,0.0062212697,0.00044916617,0.00035958402,0.0016315302,0.0011972951],"domain_scores_gemma":[0.97301257,0.013864957,0.005320369,0.0013180044,0.0026312906,0.0038529108],"candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.012673741,0.00023102577,0.0002887011,0.0015395179,0.0034082553,0.008915069,0.0008943037,0.0008258589,0.0021159672],"category_scores_gemma":[0.03973703,0.00020010637,0.00029786586,0.0008082631,0.0053952453,0.004156528,0.008548286,0.0021594008,0.00016807817],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014116925,0.0007206931,0.32117954,0.0002299016,0.00005572976,0.0006839992,0.5042141,0.00034485606,0.0017554872,0.011961474,0.0010698236,0.15764311],"study_design_scores_gemma":[0.000019377208,0.00058054394,0.3073188,0.00059547194,0.00005005678,0.0007843128,0.65272295,0.0012270067,0.0024489437,0.011452186,0.022689097,0.0001113481],"about_ca_topic_score_codex":0.0025390887,"about_ca_topic_score_gemma":0.005020347,"teacher_disagreement_score":0.9991741,"about_ca_system_score_codex":0.0021807016,"about_ca_system_score_gemma":0.0043368684,"threshold_uncertainty_score":0.0670259},"labels":[],"label_agreement":null},{"id":"W4401993837","doi":"10.4018/979-8-3693-1499-9.ch010","title":"(Re)Visiting the Efficacy of PBLA for Adult EAL Learners in College-Based Education in Canada","year":2024,"lang":"en","type":"book-chapter","venue":"Advances in higher education and professional development book series","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Seneca Polytechnic; University of Manitoba","funders":"","keywords":"Medical education; Evaluation methods; Medicine; Engineering","score_opus":0.019556463771628847,"score_gpt":0.34717462499875557,"score_spread":0.3276181612271267,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4401993837","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.74985117,0.017354187,0.0016307158,0.0067441203,0.00043239948,0.00025940652,0.00082210056,0.0002794586,0.22262648],"genre_scores_gemma":[0.90081084,0.010445706,0.0036035914,0.0010885402,0.000032942975,0.00007353071,0.0003792218,0.00006631224,0.08349941],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99924755,0.000089945424,0.000021673148,0.00005574616,0.0004907715,0.00009435004],"domain_scores_gemma":[0.998486,0.00032783422,0.000062026134,0.000027022217,0.0008009982,0.00029628145],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013062218,0.00017178075,0.00020360782,0.0005899278,0.002795404,0.0028237393,0.0007204826,0.00032882713,0.005505069],"category_scores_gemma":[0.003439238,0.000100631056,0.00015100738,0.0011799954,0.000926677,0.00071614026,0.0011053086,0.00059745606,0.00052913866],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006460158,0.00022286708,0.037643664,0.0008011329,0.000010925706,0.00038788724,0.08015833,0.0003819324,0.0018778694,0.0063530835,0.077304125,0.7947936],"study_design_scores_gemma":[0.000024039762,0.00038672335,0.28019014,0.0020246175,0.000059790502,0.00089579716,0.18746,0.0013677656,0.004209868,0.0015111015,0.52177376,0.000096392265],"about_ca_topic_score_codex":0.899666,"about_ca_topic_score_gemma":0.9650835,"teacher_disagreement_score":0.10033399,"about_ca_system_score_codex":0.023343218,"about_ca_system_score_gemma":0.045687124,"threshold_uncertainty_score":0.2018497},"labels":[],"label_agreement":null},{"id":"W4402109653","doi":"10.55016/ojs/jet.v44i2.52245","title":"Assessment Reform and the Case for Learning-Focused Accountability","year":2018,"lang":"en","type":"article","venue":"Journal of educational thought.","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Brock University","funders":"","keywords":"Accountability; Political science; Public administration; Psychology; Business; Law","score_opus":0.039596859012279245,"score_gpt":0.42432877390869944,"score_spread":0.3847319148964202,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402109653","genre_codex":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.021699905,0.004003277,0.021840941,0.8639426,0.0011414242,0.00013194345,0.00004358176,0.00014386268,0.08705242],"genre_scores_gemma":[0.9165222,0.0014043383,0.011693364,0.059593294,0.00214828,0.0003689435,0.000031885094,0.0000833348,0.008154405],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.8724683,0.08681682,0.0041643875,0.007965724,0.019672919,0.0089118425],"domain_scores_gemma":[0.80701804,0.1238015,0.015077389,0.016317181,0.02946278,0.008323099],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.098259866,0.0005863858,0.0011573822,0.0027122654,0.007574266,0.015132363,0.0033009192,0.013702908,0.003625096],"category_scores_gemma":[0.19389176,0.0005407067,0.0011601024,0.0025603957,0.05047455,0.020753711,0.010521265,0.020542543,0.00058395125],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016827747,0.00004971401,0.0011860299,0.000067848494,0.000009781486,0.000058811846,0.003438142,0.0005248508,0.00007712453,0.9718544,0.006132963,0.016583433],"study_design_scores_gemma":[0.0000955655,0.00011111174,0.0045403894,0.00052620866,0.00002004203,0.0001171723,0.0030683982,0.0029715498,0.00036096774,0.8704386,0.11767655,0.00007353407],"about_ca_topic_score_codex":0.023632487,"about_ca_topic_score_gemma":0.012861622,"teacher_disagreement_score":0.098259866,"about_ca_system_score_codex":0.021587182,"about_ca_system_score_gemma":0.03240607,"threshold_uncertainty_score":0.51965404},"labels":[],"label_agreement":null},{"id":"W4402109725","doi":"10.55016/ojs/jet.v51i3.68273","title":"Exploring the Intersection Between Culturally Responsive Pedagogy and Academic Integrity Among EAL Students in Canadian Higher Education","year":2019,"lang":"en","type":"article","venue":"Journal of educational thought.","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Academic integrity; Intersection (aeronautics); Pedagogy; Sociology; Culturally sensitive; Psychology; Mathematics education; Social psychology; Geography","score_opus":0.11088557053978763,"score_gpt":0.44686615418647285,"score_spread":0.3359805836466852,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402109725","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9578266,0.000838439,0.0009734832,0.007167006,0.00006292023,0.00010418228,0.000040853658,0.000027620305,0.03295878],"genre_scores_gemma":[0.99716187,0.00036073136,0.0004263484,0.0004660866,0.0000065555278,0.000022653041,0.000011391978,0.000006722864,0.0015377493],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.9874307,0.004214166,0.0004157412,0.0007052962,0.004393907,0.0028401436],"domain_scores_gemma":[0.9687792,0.011467566,0.0038045433,0.0010504941,0.009645825,0.005252388],"candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.015027186,0.00044492655,0.00069589633,0.0042251446,0.028660778,0.009940148,0.002156215,0.0015987471,0.0032208934],"category_scores_gemma":[0.047978114,0.0003150513,0.00040751524,0.0037469903,0.0150983315,0.003698366,0.010580532,0.0046578813,0.00020407156],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002435301,0.00011359107,0.031711962,0.00014266996,0.000009048616,0.00022478017,0.93920815,0.00004400766,0.00064931426,0.004834299,0.00079596817,0.0222418],"study_design_scores_gemma":[0.0000038742223,0.000052165113,0.037917186,0.00026158808,0.000012597739,0.00009459683,0.9454716,0.00008778597,0.0006253247,0.0011226996,0.014312679,0.00003785348],"about_ca_topic_score_codex":0.8226419,"about_ca_topic_score_gemma":0.91503936,"teacher_disagreement_score":0.9984012,"about_ca_system_score_codex":0.068562545,"about_ca_system_score_gemma":0.14463624,"threshold_uncertainty_score":0.4974584},"labels":[],"label_agreement":null},{"id":"W4402441614","doi":"10.1002/berj.4065","title":"From challenge to innovation: A grassroots study of teachers’ classroom assessment innovations","year":2024,"lang":"en","type":"article","venue":"British Educational Research Journal","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Winnipeg; Queen's University","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Grassroots; Sociology; Pedagogy; Mathematics education; Educational research; Psychology; Political science; Public relations","score_opus":0.17608076029473863,"score_gpt":0.5171086715530592,"score_spread":0.34102791125832055,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402441614","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98528045,0.00020580077,0.0011862628,0.0032663275,0.000030467821,0.00010719479,0.000012035459,0.000013958448,0.009897498],"genre_scores_gemma":[0.9985335,0.00008696879,0.00030313636,0.00018432639,0.0000058161977,0.00004067571,0.0000034324632,0.000010445489,0.00083171873],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9621845,0.023784637,0.00076841103,0.0021264192,0.0063447477,0.0047913706],"domain_scores_gemma":[0.9242472,0.059523348,0.004350682,0.002113766,0.00569168,0.0040733735],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.030240769,0.00044632173,0.0009304743,0.0039948993,0.01736135,0.014312611,0.0026633095,0.003163432,0.002071024],"category_scores_gemma":[0.06044329,0.0006651604,0.00036958855,0.002771535,0.03163467,0.008045467,0.011271084,0.0065243877,0.0002801645],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000009806268,0.000046103094,0.0030177135,0.000035856814,0.0000025102263,0.00015938906,0.9899554,0.00003691784,0.00021441947,0.0024761432,0.00017357942,0.0038721368],"study_design_scores_gemma":[0.000004721055,0.000030908228,0.0036370272,0.000049962266,0.0000025306788,0.000033836965,0.9894824,0.00011185889,0.0001199414,0.0012999659,0.005216508,0.00001043391],"about_ca_topic_score_codex":0.04618169,"about_ca_topic_score_gemma":0.06935114,"teacher_disagreement_score":0.04618169,"about_ca_system_score_codex":0.022282269,"about_ca_system_score_gemma":0.019419493,"threshold_uncertainty_score":0.16166997},"labels":[],"label_agreement":null},{"id":"W4402556220","doi":"10.1080/02602938.2024.2400349","title":"Feedback practices in clinical placement: how students come to understand how they are progressing","year":2024,"lang":"en","type":"article","venue":"Assessment & Evaluation in Higher Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Psychology; Mathematics education; Pedagogy; Higher education; Advanced Placement; Medical education; Medicine; Political science","score_opus":0.287976591638158,"score_gpt":0.57342609451059,"score_spread":0.28544950287243204,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402556220","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9596487,0.0021747043,0.014704904,0.009001843,0.0004345617,0.00029640074,0.000051466017,0.0003514588,0.013336005],"genre_scores_gemma":[0.98995435,0.0012068676,0.0051221065,0.0005038444,0.000047074664,0.00009407318,0.000038428,0.00006440587,0.0029688303],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9557458,0.0303743,0.0018010574,0.0016264387,0.008268131,0.0021841368],"domain_scores_gemma":[0.9242875,0.038168676,0.011342959,0.0027480004,0.014376018,0.0090768635],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.029552503,0.00073038886,0.0006721395,0.0021396119,0.004398419,0.010149897,0.0020886122,0.0023848552,0.0027017954],"category_scores_gemma":[0.15905994,0.00062114117,0.00058004167,0.0013419917,0.0042422963,0.005089959,0.0059948973,0.004070992,0.0012926058],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00029544448,0.00096026197,0.08027923,0.0005741373,0.00006276432,0.0011945857,0.62111956,0.0005207294,0.003303882,0.0018245996,0.0071911286,0.28267363],"study_design_scores_gemma":[0.000051913976,0.0024473039,0.10096855,0.0018945658,0.00006859628,0.0020553581,0.8329301,0.0018455837,0.004050803,0.0059813685,0.047360007,0.0003458404],"about_ca_topic_score_codex":0.0028394621,"about_ca_topic_score_gemma":0.003760446,"teacher_disagreement_score":0.029552503,"about_ca_system_score_codex":0.0031846082,"about_ca_system_score_gemma":0.0058654747,"threshold_uncertainty_score":0.15629047},"labels":[],"label_agreement":null},{"id":"W4402569962","doi":"10.1016/j.stueduc.2024.101403","title":"Students’ perceptions of online peer feedback in process-oriented L2 writing: A qualitative inquiry","year":2024,"lang":"en","type":"article","venue":"Studies In Educational Evaluation","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Peer feedback; Perception; Mathematics education; Peer evaluation; Process (computing); Qualitative research; Psychology; Computer science; Pedagogy; Higher education; Sociology; Political science","score_opus":0.23009569155715098,"score_gpt":0.6111867833582557,"score_spread":0.38109109180110473,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402569962","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99555486,0.00012740419,0.0018251367,0.00053504726,0.00001548412,0.00013938153,0.00003334557,0.000013494559,0.0017558186],"genre_scores_gemma":[0.997503,0.00015934547,0.0010452936,0.00015878495,0.000006445446,0.0001971091,0.000018422546,0.00000848891,0.0009032363],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.98728186,0.009311726,0.00051884796,0.0005317061,0.001257487,0.0010985091],"domain_scores_gemma":[0.9780919,0.016617626,0.0013300873,0.00052749045,0.0020649438,0.0013679942],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015004843,0.00042001388,0.00064845855,0.001518649,0.0041360967,0.0043237824,0.0011274694,0.0018408947,0.0015380153],"category_scores_gemma":[0.024770908,0.00045521607,0.00055835006,0.0011898918,0.0050795167,0.003100005,0.0035449688,0.0021692428,0.00028316406],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000047299836,0.0002121761,0.009103642,0.00019004566,0.000008766821,0.0006879005,0.9774415,0.00011543926,0.0019366825,0.00061252294,0.00017636764,0.009467658],"study_design_scores_gemma":[0.000012713867,0.00032145542,0.007881106,0.00018551844,0.000012008743,0.00041090098,0.982278,0.0004324356,0.001694788,0.0005163736,0.0062193633,0.00003531458],"about_ca_topic_score_codex":0.0019630503,"about_ca_topic_score_gemma":0.0021174448,"teacher_disagreement_score":0.015004843,"about_ca_system_score_codex":0.0022368247,"about_ca_system_score_gemma":0.0029214711,"threshold_uncertainty_score":0.07935417},"labels":[],"label_agreement":null},{"id":"W4402676854","doi":"10.7202/1113588ar","title":"Flexible planning of assessment, a lever towards assessment for learning?","year":2022,"lang":"en","type":"article","venue":"Mesure et évaluation en éducation","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Université du Québec à Chicoutimi","funders":"","keywords":"Lever; Assessment for learning; Computer science; Psychology; Engineering; Mathematics education; Formative assessment","score_opus":0.1283791028668994,"score_gpt":0.497807633715495,"score_spread":0.3694285308485956,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402676854","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.030484037,0.0057517155,0.69858605,0.19260097,0.0015511145,0.00054333825,0.00005623379,0.002748632,0.06767793],"genre_scores_gemma":[0.6042424,0.0032213717,0.37962642,0.006033328,0.00044294476,0.00064188003,0.00005626998,0.0003656569,0.0053698285],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.94090223,0.03893123,0.0025730769,0.0032428324,0.012206017,0.002144648],"domain_scores_gemma":[0.90833884,0.05119475,0.009143251,0.018109735,0.00807565,0.0051377015],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.04690174,0.0010176009,0.00068155816,0.0017602954,0.002270375,0.014379713,0.002441551,0.004063855,0.002979908],"category_scores_gemma":[0.09408252,0.0008238963,0.0006911867,0.0019468756,0.016935747,0.027392328,0.009479376,0.009197483,0.0012335523],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001518739,0.00029651125,0.004730651,0.0006935959,0.000081333885,0.00025554933,0.03108259,0.0050098277,0.0023374474,0.4195461,0.009952634,0.52586186],"study_design_scores_gemma":[0.00009202348,0.00044664147,0.0039102184,0.0027719645,0.00004292111,0.0005890466,0.017006693,0.01066998,0.003483724,0.728263,0.23243476,0.0002889773],"about_ca_topic_score_codex":0.004453472,"about_ca_topic_score_gemma":0.0033063942,"teacher_disagreement_score":0.04690174,"about_ca_system_score_codex":0.0048703514,"about_ca_system_score_gemma":0.014797937,"threshold_uncertainty_score":0.24804312},"labels":[],"label_agreement":null},{"id":"W4402746452","doi":"10.18357/otessac.2022.2.1.63","title":"“Students Feel More Dignified\": Alternative Grading and Self-Assessment in Online Courses","year":2023,"lang":"en","type":"article","venue":"The Open/Technology in Education Society and Scholarship Association Conference","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Grading (engineering); Psychology; Mathematics education; Engineering","score_opus":0.05205153241904463,"score_gpt":0.43092948254411895,"score_spread":0.3788779501250743,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402746452","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99777126,0.000026907352,0.00048652088,0.00020641022,0.00001710841,0.000022601027,0.000002610337,0.000009700116,0.0014569642],"genre_scores_gemma":[0.99826366,0.00003240442,0.0009193071,0.000105012645,0.000009646401,0.000017480139,0.0000067244537,0.000003095003,0.0006426262],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.9902834,0.0062863478,0.00039118849,0.00037549023,0.002309832,0.00035365496],"domain_scores_gemma":[0.98100305,0.00893114,0.0041910205,0.0016080223,0.002344575,0.0019221269],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008413272,0.000295701,0.00030745246,0.0006668612,0.0011836698,0.002286852,0.00055357296,0.0005656284,0.0012662925],"category_scores_gemma":[0.040649194,0.00016660939,0.0003094477,0.00034979993,0.0017971265,0.0013661602,0.002300989,0.0013275493,0.00024124177],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00049877324,0.0024671603,0.4560114,0.00025298676,0.00008430878,0.0005052823,0.14471424,0.00038451984,0.009591821,0.0019210443,0.0025011774,0.3810672],"study_design_scores_gemma":[0.00010072607,0.0039157965,0.7428033,0.0003141469,0.00008227312,0.0010790302,0.22347479,0.003023849,0.0061863377,0.004189244,0.0146395555,0.00019103571],"about_ca_topic_score_codex":0.00085599977,"about_ca_topic_score_gemma":0.0027824938,"teacher_disagreement_score":0.008413272,"about_ca_system_score_codex":0.0006963046,"about_ca_system_score_gemma":0.0010316378,"threshold_uncertainty_score":0.044494152},"labels":[],"label_agreement":null},{"id":"W4402798678","doi":"10.1080/02602938.2024.2402956","title":"Connecting students’ descriptions of classroom assessment in higher education with wellness","year":2024,"lang":"en","type":"article","venue":"Assessment & Evaluation in Higher Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":6,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Psychology; Higher education; Pedagogy; Mathematics education; Medical education; Medicine","score_opus":0.1083461691642832,"score_gpt":0.47227263569398775,"score_spread":0.36392646652970456,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402798678","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9915901,0.00025895095,0.0036247096,0.0008343827,0.000029597291,0.000045290617,0.000041195908,0.000020787906,0.0035550895],"genre_scores_gemma":[0.99772316,0.00015426739,0.0010253676,0.00011306221,0.0000065095205,0.00004954806,0.000025008765,0.000010544845,0.00089249184],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99277323,0.004847777,0.00043960425,0.00026267726,0.0011974707,0.00047921075],"domain_scores_gemma":[0.97687745,0.016323522,0.002382764,0.0006404587,0.002105485,0.0016703876],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007166652,0.00040682647,0.00044096867,0.001295019,0.0016658328,0.0039891093,0.0006762594,0.0009276275,0.0021918078],"category_scores_gemma":[0.02204512,0.00027080093,0.00037248267,0.0008941095,0.0038987468,0.0025659206,0.0034537844,0.0020923205,0.0002371794],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00008591649,0.00020008058,0.03843201,0.00030858384,0.000015925603,0.00047523735,0.9269399,0.00038833715,0.0036159586,0.0045467224,0.0008220851,0.024169235],"study_design_scores_gemma":[0.000016232489,0.00030611348,0.050486,0.0004917963,0.000022381508,0.0009332252,0.91348493,0.0012832228,0.0031758477,0.003923354,0.025741298,0.00013552338],"about_ca_topic_score_codex":0.0015089004,"about_ca_topic_score_gemma":0.0026521224,"teacher_disagreement_score":0.007166652,"about_ca_system_score_codex":0.0020780128,"about_ca_system_score_gemma":0.0017574958,"threshold_uncertainty_score":0.037901342},"labels":[],"label_agreement":null},{"id":"W4403600135","doi":"10.1007/s44217-024-00258-9","title":"Improving teaching effectiveness: feedback preferences by teachers on a faculty facing dashboard","year":2024,"lang":"en","type":"article","venue":"Discover Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Health Sciences Centre; University of Toronto; Sunnybrook Health Science Centre","funders":"","keywords":"Dashboard; Mathematics education; Medical education; Computer science; Psychology; Data science; Medicine","score_opus":0.023699125449706617,"score_gpt":0.38396114107304335,"score_spread":0.36026201562333676,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403600135","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97848415,0.00018794337,0.012732808,0.0022142134,0.00012975385,0.00052831584,0.00022347836,0.00041933137,0.0050800806],"genre_scores_gemma":[0.98080313,0.00023918842,0.016352804,0.00046059335,0.00005364883,0.0005382045,0.00012084578,0.00008537607,0.0013462147],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.95897907,0.027126122,0.0042161304,0.0011896027,0.0066233594,0.0018657855],"domain_scores_gemma":[0.90199107,0.066097304,0.0092616705,0.003012447,0.015749788,0.0038877367],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.033394564,0.00046858887,0.0006179013,0.0018576611,0.0010472733,0.002615665,0.00063823507,0.00087618956,0.0032915948],"category_scores_gemma":[0.1331898,0.00032190455,0.00064849743,0.0010633635,0.00069043325,0.0018139724,0.002097475,0.0011153107,0.00080236373],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0016882973,0.0010324824,0.28105268,0.0010694532,0.00013453336,0.00088664796,0.118141256,0.0015270652,0.023003828,0.0005675364,0.00904927,0.561847],"study_design_scores_gemma":[0.00041873378,0.010367043,0.47587228,0.0018334999,0.0002545981,0.0040963013,0.37503353,0.017920246,0.054297734,0.0033221187,0.055759605,0.0008242453],"about_ca_topic_score_codex":0.0010057607,"about_ca_topic_score_gemma":0.0011757257,"teacher_disagreement_score":0.033394564,"about_ca_system_score_codex":0.0013484496,"about_ca_system_score_gemma":0.0017941036,"threshold_uncertainty_score":0.1766094},"labels":[],"label_agreement":null},{"id":"W4403674160","doi":"10.20360/langandlit29724","title":"“What’s the Use?”: Undoing, Decolonizing, Liberating, and Righting Literacies Assessment in Turbulent Times","year":2024,"lang":"en","type":"article","venue":"Language and Literacy","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"University of Manitoba","funders":"","keywords":"Undoing; Literacy; Sociology; Psychology; Pedagogy; Psychoanalysis","score_opus":0.019767530958709707,"score_gpt":0.3585840405335926,"score_spread":0.3388165095748829,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403674160","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6379654,0.0024272068,0.10021632,0.058984354,0.0006877545,0.00030326808,0.00004794919,0.0004846719,0.19888318],"genre_scores_gemma":[0.98653084,0.00031157897,0.008801544,0.00093720446,0.0000344525,0.00008620722,0.000008480659,0.00008183565,0.0032078493],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.956201,0.034025285,0.0013897013,0.001505118,0.0047151847,0.002163603],"domain_scores_gemma":[0.96161455,0.023604749,0.0035918944,0.0047030426,0.0043332446,0.002152499],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.032285336,0.00059418817,0.0004880383,0.0020481036,0.00748499,0.016708095,0.0014607336,0.0025707628,0.002239993],"category_scores_gemma":[0.061810948,0.00048586944,0.00051117485,0.0014518318,0.052808583,0.019883905,0.013427111,0.0056216894,0.0004937478],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010217255,0.00013413407,0.009847124,0.0001941133,0.000015778567,0.0003762358,0.73186904,0.00021980319,0.0021687672,0.172853,0.0018820306,0.08033783],"study_design_scores_gemma":[0.00004324244,0.00029867675,0.008323364,0.0011494465,0.000037657715,0.0009390174,0.6378022,0.0018502494,0.007511394,0.20450695,0.13735218,0.00018558453],"about_ca_topic_score_codex":0.0029871531,"about_ca_topic_score_gemma":0.002272922,"teacher_disagreement_score":0.032285336,"about_ca_system_score_codex":0.003697029,"about_ca_system_score_gemma":0.0070613506,"threshold_uncertainty_score":0.17074323},"labels":[],"label_agreement":null},{"id":"W4403899111","doi":"10.5539/jel.v14n2p74","title":"Scoring Difficulty in Summary Writing Assessment: Toward the Reconstruction of Analytic Rubric","year":2024,"lang":"en","type":"article","venue":"Journal of Education and Learning","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Japan Society for the Promotion of Science","keywords":"Rubric; Psychology; Mathematics education; Evaluation methods","score_opus":0.030654970869895302,"score_gpt":0.38441113039933944,"score_spread":0.3537561595294441,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403899111","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21115185,0.0015785991,0.7719566,0.0016505253,0.0003346275,0.0022480495,0.00017443587,0.0011028483,0.0098023955],"genre_scores_gemma":[0.42124814,0.0008936102,0.57383835,0.00022184441,0.00014063282,0.0017901706,0.00028575433,0.0003204626,0.0012610771],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.8711856,0.08198194,0.01634669,0.0045789536,0.024685936,0.0012207555],"domain_scores_gemma":[0.7079954,0.1411939,0.037073385,0.019476056,0.091968074,0.0022931392],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.11338461,0.001593447,0.0012997029,0.008802667,0.0018014018,0.006253823,0.0029917776,0.0008257087,0.0009229388],"category_scores_gemma":[0.34961462,0.0010279048,0.001141171,0.0043818103,0.003441991,0.005978318,0.005503104,0.0025837645,0.00062854105],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006132458,0.000489711,0.09018537,0.0018450726,0.00023908244,0.0003607158,0.060560685,0.003723181,0.02329304,0.019849045,0.00567398,0.79316676],"study_design_scores_gemma":[0.00044868683,0.005196593,0.31033236,0.0069814785,0.0010080037,0.005490926,0.13936478,0.25407404,0.07083536,0.09168607,0.112855114,0.0017265407],"about_ca_topic_score_codex":0.0024960393,"about_ca_topic_score_gemma":0.003591433,"teacher_disagreement_score":0.8866154,"about_ca_system_score_codex":0.002293074,"about_ca_system_score_gemma":0.004705263,"threshold_uncertainty_score":0.5996423},"labels":[],"label_agreement":null},{"id":"W4403985536","doi":"10.1080/08841233.2024.2408317","title":"Peer Feedback for Teaching Communication Skills: Students’ Experiences in a BSW Interviewing Skills Course","year":2024,"lang":"en","type":"article","venue":"Journal of Teaching in Social Work","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Social work; Interview; Medical education; Psychology; Communication skills; Course (navigation); Pedagogy; Medicine; Sociology","score_opus":0.03471179257880846,"score_gpt":0.4289714118564918,"score_spread":0.3942596192776833,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4403985536","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.987751,0.00018232675,0.007322711,0.0011876461,0.00010833504,0.00039896354,0.00003241394,0.00016449323,0.0028521328],"genre_scores_gemma":[0.99007976,0.00017714933,0.006401842,0.00030038255,0.00010673282,0.00035105785,0.000036030968,0.00007928881,0.0024678677],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9693667,0.02448454,0.0006664262,0.0009421308,0.0020305351,0.0025096226],"domain_scores_gemma":[0.9496176,0.032507762,0.003536495,0.0023039938,0.004815145,0.007219023],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.021203835,0.001240643,0.00084279565,0.0011237101,0.008923642,0.003275946,0.0024490056,0.0025636214,0.002259688],"category_scores_gemma":[0.06739049,0.00086315535,0.0006555961,0.00069692166,0.0036438447,0.0021239421,0.0056113587,0.0039178017,0.0007722538],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003753592,0.0019677612,0.012095944,0.0003331704,0.000030477031,0.0035822608,0.8809157,0.0004610056,0.014357366,0.00042048076,0.0020011407,0.08345934],"study_design_scores_gemma":[0.00014605914,0.010202671,0.032234915,0.00039141395,0.00008035686,0.007878474,0.87429774,0.0036098121,0.018023243,0.0009453997,0.051908884,0.00028097202],"about_ca_topic_score_codex":0.0017947134,"about_ca_topic_score_gemma":0.0042541954,"teacher_disagreement_score":0.021203835,"about_ca_system_score_codex":0.0018942398,"about_ca_system_score_gemma":0.0023499967,"threshold_uncertainty_score":0.11213791},"labels":[],"label_agreement":null},{"id":"W4404136350","doi":"10.1080/10511253.2024.2422314","title":"Teacher Reflections on Assessing Indigenous Cultural Competency in a Criminal Justice Subject Through Interactive Oral Assessment","year":2024,"lang":"en","type":"article","venue":"Journal of Criminal Justice Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Charles Sturt University","keywords":"Indigenous; Subject (documents); Criminal justice; Criminology; Psychology; Political science; Sociology; Computer science; Library science","score_opus":0.11624800203147558,"score_gpt":0.512853261473025,"score_spread":0.39660525944154945,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404136350","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9448546,0.0002810897,0.0137828775,0.0070978394,0.00035199165,0.0007545874,0.000068323105,0.00023375651,0.032574967],"genre_scores_gemma":[0.93146026,0.00067734695,0.020794407,0.0012813143,0.00007834335,0.00046434175,0.000056345358,0.00014374767,0.04504381],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99008954,0.0067177247,0.0004580081,0.00057237525,0.0013599837,0.00080219004],"domain_scores_gemma":[0.9747693,0.017228464,0.0008395193,0.0010700346,0.004154058,0.0019385609],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010172361,0.0005621227,0.00062059204,0.0007892904,0.004607586,0.0030615693,0.0010709,0.0017637626,0.004669052],"category_scores_gemma":[0.035393666,0.0005562418,0.000497774,0.000458172,0.0032337753,0.0019015191,0.0050324663,0.00449601,0.0014794278],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021467624,0.0020093555,0.010282926,0.000483192,0.000015216661,0.0026124949,0.8644588,0.00065854826,0.011444733,0.0015911986,0.007339851,0.09888911],"study_design_scores_gemma":[0.0001103866,0.0037138388,0.018679332,0.0010480148,0.0000829759,0.003742329,0.77176946,0.0025765677,0.021338712,0.0029993732,0.17372058,0.00021840357],"about_ca_topic_score_codex":0.0065792636,"about_ca_topic_score_gemma":0.018712636,"teacher_disagreement_score":0.010172361,"about_ca_system_score_codex":0.0024114652,"about_ca_system_score_gemma":0.0039847693,"threshold_uncertainty_score":0.053797245},"labels":[],"label_agreement":null},{"id":"W4404173077","doi":"10.61669/001c.122484","title":"The Intersection of Student Assessment and Faculty Learning","year":2024,"lang":"en","type":"article","venue":"Intersection A Journal at the Intersection of Assessment and Learning","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Thompson Rivers University","funders":"","keywords":"Intersection (aeronautics); Mathematics education; Psychology; Medical education; Pedagogy; Engineering; Medicine; Transport engineering","score_opus":0.03403379402823651,"score_gpt":0.4174538805122966,"score_spread":0.38342008648406006,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404173077","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.55470765,0.008752925,0.101672105,0.055461884,0.0005965246,0.00017104225,0.00009009238,0.0005640674,0.2779837],"genre_scores_gemma":[0.99095976,0.0005570335,0.0060482114,0.0005282112,0.000070552655,0.0000619818,0.000008888645,0.000028732493,0.001736693],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.919419,0.06309393,0.0018546229,0.0027270033,0.010475404,0.002430017],"domain_scores_gemma":[0.92446035,0.05543713,0.0052317353,0.003958587,0.005571379,0.0053407587],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.024957886,0.00042710712,0.0007561089,0.00291788,0.004005921,0.020261608,0.001499842,0.002080136,0.0034568731],"category_scores_gemma":[0.057657626,0.0003356887,0.00045955027,0.001993682,0.016132213,0.009206968,0.016412813,0.0038859788,0.00039423403],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018074902,0.0006822282,0.07591594,0.00082411687,0.00013216947,0.00034577367,0.15766944,0.0012974722,0.0019569919,0.28097463,0.0037934887,0.47622693],"study_design_scores_gemma":[0.000051081082,0.001193742,0.07978513,0.001514055,0.00009258308,0.0010924711,0.17854953,0.005660495,0.0058964756,0.5979781,0.12796217,0.00022421588],"about_ca_topic_score_codex":0.002258796,"about_ca_topic_score_gemma":0.002878556,"teacher_disagreement_score":0.024957886,"about_ca_system_score_codex":0.004458428,"about_ca_system_score_gemma":0.01102414,"threshold_uncertainty_score":0.13199145},"labels":[],"label_agreement":null},{"id":"W4404293607","doi":"10.36834/cmej.72320","title":"User experience of the Written Exam Question Quality tool to inform the writing of new written-exam questions","year":2024,"lang":"en","type":"article","venue":"Canadian Medical Education Journal","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Task (project management); Perception; Quality (philosophy); Computer science; Test (biology); Psychology; Medical education; Medicine","score_opus":0.03389104683518359,"score_gpt":0.41162157544418665,"score_spread":0.3777305286090031,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404293607","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9868204,0.00016861723,0.008657854,0.00046088174,0.00002564468,0.00026470202,0.00013072633,0.00041886794,0.003052268],"genre_scores_gemma":[0.97979283,0.00012743029,0.017937822,0.00025868684,0.000018180916,0.00018268818,0.000132068,0.0000696219,0.0014806446],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.98931736,0.007509888,0.0006089594,0.00038374736,0.00153778,0.0006423612],"domain_scores_gemma":[0.9116214,0.06709557,0.0041161054,0.0029549503,0.010572979,0.0036389898],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.017247375,0.00057620683,0.00036712026,0.0012094214,0.0011880293,0.0018968829,0.0007400457,0.00084292144,0.0030978716],"category_scores_gemma":[0.072301716,0.00029481936,0.0004635259,0.00076386245,0.0009662091,0.0013241426,0.0016613812,0.00062766136,0.00050528074],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013939849,0.0013904545,0.1897189,0.0012735808,0.000090515394,0.0022455782,0.4405807,0.0010903982,0.041582476,0.00071359397,0.00682658,0.31309325],"study_design_scores_gemma":[0.00043504033,0.009949629,0.4883216,0.001720809,0.0003595323,0.0053207916,0.3348487,0.015106534,0.03595036,0.0012826289,0.10587829,0.00082615693],"about_ca_topic_score_codex":0.010622145,"about_ca_topic_score_gemma":0.016474463,"teacher_disagreement_score":0.017247375,"about_ca_system_score_codex":0.0016050731,"about_ca_system_score_gemma":0.0022637716,"threshold_uncertainty_score":0.09121394},"labels":[],"label_agreement":null},{"id":"W4404331919","doi":"10.1111/jcal.13087","title":"The impact of frequency and stakes of formative assessment on student achievement in higher education: A learning analytics study","year":2024,"lang":"en","type":"article","venue":"Journal of Computer Assisted Learning","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":14,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Concordia University of Edmonton; University of Alberta","funders":"","keywords":"Formative assessment; Learning analytics; Mathematics education; Academic achievement; Analytics; Educational technology; Student achievement; Higher education; Educational research; Psychology; Computer science; Data science; Political science","score_opus":0.051717165546726666,"score_gpt":0.4235158600968853,"score_spread":0.3717986945501586,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404331919","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9993917,0.00002652051,0.00018873495,0.000021876138,0.0000033900637,0.000016407643,0.00003068475,0.0000073390715,0.00031334942],"genre_scores_gemma":[0.99952877,0.000013531018,0.0002646395,0.000008314068,0.0000054203956,0.000019187635,0.00004132558,0.0000033590331,0.00011546733],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98968595,0.004235327,0.0008843829,0.0012463364,0.0033129493,0.0006350419],"domain_scores_gemma":[0.7668922,0.18534742,0.023325147,0.0071125063,0.008483996,0.00883868],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013470096,0.00046940992,0.0006535517,0.0018970501,0.0008209962,0.0033235778,0.0010847191,0.0007370678,0.001728574],"category_scores_gemma":[0.08636252,0.00024269658,0.000891365,0.0015492057,0.00094701786,0.0020090854,0.0015595796,0.0015289562,0.00031578777],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00100695,0.0026887183,0.9604195,0.000092607195,0.00023314642,0.0000704014,0.0019260314,0.0011092249,0.00079077843,0.00012141891,0.00018587822,0.031355314],"study_design_scores_gemma":[0.00002879907,0.0017009183,0.9922174,0.000038336464,0.0001005567,0.000035225443,0.001455551,0.0032315643,0.0007447359,0.00016253788,0.00025065476,0.000033642275],"about_ca_topic_score_codex":0.005305575,"about_ca_topic_score_gemma":0.0055166227,"teacher_disagreement_score":0.013470096,"about_ca_system_score_codex":0.0014388039,"about_ca_system_score_gemma":0.0013488978,"threshold_uncertainty_score":0.071237564},"labels":[],"label_agreement":null},{"id":"W4404840547","doi":"10.32920/27931464.v1","title":"The Impact of Electronic Data to Capture Qualitative Comments in a Competency-Based Assessment System","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Data science; Computer science","score_opus":0.0878788296559014,"score_gpt":0.5045773296626463,"score_spread":0.41669850000674497,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404840547","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9424502,0.00044937193,0.035985667,0.00090398785,0.00021055462,0.008609533,0.0025770436,0.00037815384,0.008435533],"genre_scores_gemma":[0.8812472,0.00032983904,0.10528115,0.00042424208,0.00015107283,0.009111314,0.0017090256,0.000108960085,0.0016372212],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.82581854,0.11796968,0.022422675,0.0064782337,0.025512328,0.0017985682],"domain_scores_gemma":[0.26153463,0.62876815,0.030847888,0.022174047,0.054223955,0.0024513737],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.11990981,0.000657964,0.0007120479,0.006689688,0.0012157278,0.004938243,0.0012790394,0.0007837516,0.0029508716],"category_scores_gemma":[0.40954298,0.00076194206,0.00082770525,0.0046199015,0.0011927282,0.0038034823,0.0042069834,0.00096868584,0.00087049016],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0052675707,0.0020342642,0.333809,0.0032549638,0.0002655797,0.0005097941,0.05261596,0.0029702487,0.012686963,0.0017692536,0.0038452721,0.5809711],"study_design_scores_gemma":[0.00082040136,0.01224633,0.82915473,0.0046005556,0.00066335144,0.00069142954,0.05191567,0.03633589,0.033018228,0.0023547881,0.027720291,0.00047832736],"about_ca_topic_score_codex":0.0035295463,"about_ca_topic_score_gemma":0.0055614477,"teacher_disagreement_score":0.11990981,"about_ca_system_score_codex":0.0027988076,"about_ca_system_score_gemma":0.00531613,"threshold_uncertainty_score":0.6341512},"labels":[],"label_agreement":null},{"id":"W4404840942","doi":"10.32920/27931464","title":"The Impact of Electronic Data to Capture Qualitative Comments in a Competency-Based Assessment System","year":2024,"lang":"en","type":"preprint","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Electronic data capture; Automatic identification and data capture; Qualitative property; Computer science; Data science; Psychology; Data collection; Sociology; Social science; Machine learning","score_opus":0.0878788296559014,"score_gpt":0.5045773296626463,"score_spread":0.41669850000674497,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404840942","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9424502,0.00044937193,0.035985667,0.00090398785,0.00021055462,0.008609533,0.0025770436,0.00037815384,0.008435533],"genre_scores_gemma":[0.8812472,0.00032983904,0.10528115,0.00042424208,0.00015107283,0.009111314,0.0017090256,0.000108960085,0.0016372212],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.82581854,0.11796968,0.022422675,0.0064782337,0.025512328,0.0017985682],"domain_scores_gemma":[0.26153463,0.62876815,0.030847888,0.022174047,0.054223955,0.0024513737],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.11990981,0.000657964,0.0007120479,0.006689688,0.0012157278,0.004938243,0.0012790394,0.0007837516,0.0029508716],"category_scores_gemma":[0.40954298,0.00076194206,0.00082770525,0.0046199015,0.0011927282,0.0038034823,0.0042069834,0.00096868584,0.00087049016],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0052675707,0.0020342642,0.333809,0.0032549638,0.0002655797,0.0005097941,0.05261596,0.0029702487,0.012686963,0.0017692536,0.0038452721,0.5809711],"study_design_scores_gemma":[0.00082040136,0.01224633,0.82915473,0.0046005556,0.00066335144,0.00069142954,0.05191567,0.03633589,0.033018228,0.0023547881,0.027720291,0.00047832736],"about_ca_topic_score_codex":0.0035295463,"about_ca_topic_score_gemma":0.0055614477,"teacher_disagreement_score":0.11990981,"about_ca_system_score_codex":0.0027988076,"about_ca_system_score_gemma":0.00531613,"threshold_uncertainty_score":0.6341512},"labels":[],"label_agreement":null},{"id":"W4404910374","doi":"10.1145/3649409.3691071","title":"Developing a Playbook of Equitable Grading Practices","year":2024,"lang":"en","type":"article","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia; The Scarborough Hospital; University of Toronto","funders":"Universitas Brawijaya","keywords":"Grading (engineering); Computer science; Business; Engineering","score_opus":0.13536100550904578,"score_gpt":0.4583071248508491,"score_spread":0.32294611934180334,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404910374","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.023506358,0.012827759,0.82287747,0.028320827,0.0060885814,0.018555725,0.007915686,0.008855168,0.071052395],"genre_scores_gemma":[0.024572147,0.010286106,0.9335039,0.0015476871,0.00041254712,0.0066663246,0.0033075642,0.0006856864,0.019018045],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.98051995,0.010004974,0.0035045901,0.0010419547,0.004568568,0.00035999445],"domain_scores_gemma":[0.89051086,0.0728006,0.005900754,0.010679623,0.0179558,0.0021523514],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.046468824,0.0024332416,0.0018201821,0.014221311,0.0018626542,0.0044751707,0.0043849526,0.0016270719,0.010897845],"category_scores_gemma":[0.05544023,0.0015156311,0.0011842387,0.007510866,0.0018502048,0.00911878,0.0040636733,0.004002773,0.004241152],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000112584385,0.0005382966,0.0011035918,0.006944611,0.00010077726,0.00030494414,0.015993945,0.0019262056,0.0056373905,0.016097862,0.11915568,0.83208406],"study_design_scores_gemma":[0.00012319534,0.0009089349,0.0037509713,0.012572169,0.00014767278,0.001068811,0.011186835,0.0029718718,0.0064070933,0.021835933,0.9388123,0.00021419955],"about_ca_topic_score_codex":0.0031556182,"about_ca_topic_score_gemma":0.0114678135,"teacher_disagreement_score":0.046468824,"about_ca_system_score_codex":0.0027766728,"about_ca_system_score_gemma":0.013543955,"threshold_uncertainty_score":0.24575359},"labels":[],"label_agreement":null},{"id":"W4404940578","doi":"10.1080/14703297.2024.2436046","title":"Investigating how students’ perceptions of peer comments and edits affect academic writing performance","year":2024,"lang":"en","type":"article","venue":"Innovations in Education and Teaching International","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Affect (linguistics); Perception; Psychology; Academic achievement; Higher education; Mathematics education; Peer influence; Pedagogy; Social psychology; Communication","score_opus":0.03747358532231683,"score_gpt":0.43688187095494374,"score_spread":0.3994082856326269,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404940578","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9989507,0.000030051997,0.00011715794,0.00004079653,0.0000045528122,0.0000073995975,0.000012253243,0.0000041427384,0.00083285384],"genre_scores_gemma":[0.9993051,0.00003815423,0.000121865414,0.000015429485,0.0000047621957,0.000009740204,0.00002123852,0.0000021118578,0.00048167785],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99725586,0.00091986824,0.00030136807,0.00023432638,0.0010383148,0.0002502605],"domain_scores_gemma":[0.96600914,0.01510441,0.00968658,0.00091548817,0.0049861837,0.0032982223],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0032042935,0.00029263005,0.0003276152,0.00066421716,0.0005470849,0.002009882,0.00028197735,0.00041330053,0.0021896064],"category_scores_gemma":[0.028524946,0.00012193018,0.00036920348,0.0004778295,0.00052002334,0.0008860371,0.0008658131,0.000770382,0.00050068245],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00035608638,0.0014558976,0.901478,0.00019133819,0.00013214244,0.0002519073,0.032397326,0.00029162457,0.0070301266,0.00018908917,0.00053643674,0.055690024],"study_design_scores_gemma":[0.00001639947,0.0009647628,0.968019,0.000046502515,0.00006860708,0.00011485481,0.02586334,0.0008120368,0.002643252,0.00018400628,0.0012271954,0.000040006937],"about_ca_topic_score_codex":0.0009642535,"about_ca_topic_score_gemma":0.0017329413,"teacher_disagreement_score":0.0032042935,"about_ca_system_score_codex":0.00034622094,"about_ca_system_score_gemma":0.0006231394,"threshold_uncertainty_score":0.016946137},"labels":[],"label_agreement":null},{"id":"W4404993933","doi":"10.21428/cb6ab371.584102f8","title":"Teacher Reflections on Assessing Indigenous Cultural Competency in a Criminal Justice Subject Through Interactive Oral Assessment","year":2024,"lang":"en","type":"preprint","venue":"CrimRxiv","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Indigenous; Subject (documents); Criminal justice; Economic Justice; Criminology; Psychology; Sociology; Pedagogy; Political science; Law; Library science; Computer science","score_opus":0.1738148616393724,"score_gpt":0.5105462522940751,"score_spread":0.3367313906547027,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404993933","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9288953,0.00028775676,0.020355014,0.0069383685,0.00037300677,0.0007476766,0.00008459227,0.00028818243,0.04203],"genre_scores_gemma":[0.9077028,0.00064350927,0.02495294,0.0010624824,0.00008765764,0.0004319102,0.00007308621,0.00020650223,0.0648391],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99175346,0.0055715735,0.00034606873,0.0005707897,0.0011077125,0.0006504954],"domain_scores_gemma":[0.9798321,0.014102148,0.00058621645,0.0009552798,0.0030009244,0.0015232962],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009024449,0.00057258666,0.00053435756,0.00070155837,0.0041639027,0.0031897284,0.0009856067,0.0016709111,0.005072193],"category_scores_gemma":[0.029388562,0.0005106277,0.00044764043,0.0004143256,0.0032767819,0.0017845172,0.004615356,0.004172255,0.0016573865],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022478649,0.0017785495,0.009285192,0.0004120593,0.000015855929,0.002780821,0.8548192,0.0009012214,0.015528704,0.0021692277,0.008180871,0.10390352],"study_design_scores_gemma":[0.00011053207,0.0031227206,0.018608257,0.00088725245,0.00008021228,0.003958444,0.69674766,0.003286247,0.028629554,0.0037058813,0.24063917,0.00022401976],"about_ca_topic_score_codex":0.007147738,"about_ca_topic_score_gemma":0.019141156,"teacher_disagreement_score":0.009024449,"about_ca_system_score_codex":0.0025403788,"about_ca_system_score_gemma":0.0031492126,"threshold_uncertainty_score":0.047726452},"labels":[],"label_agreement":null},{"id":"W4405015817","doi":"10.1007/s40670-024-02197-4","title":"The Predictive Power of Short Answer Questions in Undergraduate Medical Education Progress Difficulty","year":2024,"lang":"en","type":"article","venue":"Medical Science Educator","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"","keywords":"Formative assessment; Logistic regression; Odds; Medical education; Predictive power; Referral; Psychology; Medicine; Mathematics education; Family medicine; Internal medicine","score_opus":0.01476621263406066,"score_gpt":0.40068161397087415,"score_spread":0.3859154013368135,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405015817","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99782735,0.0001380258,0.000314901,0.00015461283,0.000039572442,0.000024595824,0.0001731717,0.000020718655,0.0013069941],"genre_scores_gemma":[0.9990293,0.000058063106,0.0001849754,0.00003123306,0.000026117337,0.000024469095,0.00019614249,0.000009310549,0.00044049227],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99408454,0.002708897,0.0007617139,0.00054046395,0.0016066163,0.00029779828],"domain_scores_gemma":[0.67806876,0.27605575,0.021222433,0.005465254,0.010239127,0.008948624],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00909804,0.0006951324,0.0006624553,0.0032474,0.000482349,0.0015744069,0.0011219911,0.0019794889,0.003877788],"category_scores_gemma":[0.14190196,0.00033180648,0.0009771432,0.0010432985,0.00074720336,0.0021677187,0.0018563167,0.0019605723,0.0010082681],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00030671104,0.00028703682,0.9939255,0.00001581466,0.00005564919,0.000028316388,0.00026511424,0.00020155215,0.00014421271,0.000030938452,0.00013530294,0.0046038544],"study_design_scores_gemma":[0.000025263036,0.0006097544,0.9952991,0.000028531787,0.000051065792,0.00008398908,0.00043301628,0.0028009594,0.00027292146,0.00016274364,0.00021925716,0.000013306033],"about_ca_topic_score_codex":0.0024491234,"about_ca_topic_score_gemma":0.0021092822,"teacher_disagreement_score":0.00909804,"about_ca_system_score_codex":0.0004478522,"about_ca_system_score_gemma":0.0007335362,"threshold_uncertainty_score":0.04811561},"labels":[],"label_agreement":null},{"id":"W4405343076","doi":"10.1177/17577438241265462","title":"Re-imagining teacher assessment: How teachers are encouraged (or not) to pursue ongoing professional learning in New Brunswick","year":2024,"lang":"en","type":"article","venue":"Power and Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Pedagogy; Professional development; Sociology; Professional learning community; Mathematics education; Teacher education; Faculty development; Psychology","score_opus":0.028399564590299294,"score_gpt":0.4001026426598453,"score_spread":0.371703078069546,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405343076","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8795118,0.0041659526,0.0032379068,0.024291448,0.00015278789,0.0004510498,0.00008225397,0.00012663928,0.08798019],"genre_scores_gemma":[0.9821644,0.001922107,0.0023326476,0.0005440658,0.00000602954,0.000095212505,0.000033937766,0.00003302739,0.012868548],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9852691,0.007720712,0.0008305968,0.0009751782,0.0029834362,0.0022208898],"domain_scores_gemma":[0.9829627,0.007463141,0.0012900963,0.0007502443,0.004561102,0.0029727363],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0130500905,0.00041829655,0.0005096593,0.0019073071,0.015737694,0.0111831175,0.0031315607,0.001403737,0.0015858322],"category_scores_gemma":[0.023394264,0.0006308645,0.00021087803,0.0028995231,0.010999784,0.0038608506,0.0076614683,0.003152251,0.00023134582],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005995237,0.00010033939,0.018682698,0.0002197805,0.0000123125365,0.0015671222,0.88505155,0.00039709551,0.0015412704,0.006228513,0.0031680434,0.08297134],"study_design_scores_gemma":[0.000016007514,0.0000615848,0.029497325,0.00061656727,0.000019784065,0.00030949377,0.89508855,0.00049730146,0.0011219971,0.0018730626,0.07080403,0.00009426226],"about_ca_topic_score_codex":0.9438556,"about_ca_topic_score_gemma":0.98207355,"teacher_disagreement_score":0.87667346,"about_ca_system_score_codex":0.12332657,"about_ca_system_score_gemma":0.16713929,"threshold_uncertainty_score":0.8948011},"labels":[],"label_agreement":null},{"id":"W4405795202","doi":"10.56380/mjer.si.2024.04","title":"Educational Development through the Lens of Curriculum: A Holistic and Systemic Approach","year":2024,"lang":"en","type":"article","venue":"БОЛОВСРОЛЫН СУДАЛГААНЫ МОНГОЛЫН СЭТГҮҮЛ","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Curriculum; Transformative learning; Engineering ethics; Curriculum theory; Pedagogy; Holistic education; Presentation (obstetrics); Sociology; Curriculum development; Philosophy of education; Emergent curriculum; Personal development; Curriculum mapping; Political science; Higher education; Engineering; Medicine","score_opus":0.061610088329893564,"score_gpt":0.36920759791918895,"score_spread":0.3075975095892954,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405795202","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06474699,0.03433568,0.2195971,0.16021107,0.0019374449,0.00029673622,0.00023183193,0.00027756707,0.5183656],"genre_scores_gemma":[0.9008073,0.014808684,0.057981092,0.0045745256,0.00068108283,0.000373306,0.000099753255,0.00013997153,0.020534351],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9945503,0.004201465,0.00011485551,0.00025314777,0.0005501331,0.0003301351],"domain_scores_gemma":[0.9968817,0.0021187186,0.00019607693,0.00020854254,0.0003212947,0.00027361547],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0059134313,0.00079331925,0.00042867425,0.004536269,0.005317552,0.015877703,0.0011589162,0.0024636996,0.002323052],"category_scores_gemma":[0.0037395768,0.00036473904,0.00044140394,0.002478559,0.037962217,0.01117067,0.0067656776,0.0057771155,0.0003246286],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000004337093,0.000014246491,0.0002837232,0.000118376345,0.0000051090733,0.00013126367,0.029799363,0.0004717464,0.00019748864,0.9534104,0.0022006873,0.0133632915],"study_design_scores_gemma":[0.000009602505,0.000039577168,0.0006901323,0.00080100296,0.000012451168,0.00027276127,0.04294918,0.0014254426,0.00046709477,0.6618524,0.29145974,0.000020593292],"about_ca_topic_score_codex":0.0046767015,"about_ca_topic_score_gemma":0.0058146073,"teacher_disagreement_score":0.015877703,"about_ca_system_score_codex":0.009560731,"about_ca_system_score_gemma":0.010400434,"threshold_uncertainty_score":0.0693683},"labels":[],"label_agreement":null},{"id":"W4405940634","doi":"10.18554/rt.v17i3.7450","title":"CONCEPTIONS OF ASSESSMENT IN HIGHER EDUCATION","year":2024,"lang":"en","type":"article","venue":"Revista Triângulo","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Fundação para a Ciência e a Tecnologia; Universidade do Minho; International Council for Canadian Studies","keywords":"Mathematics education; Psychology; Pedagogy; Medical education; Medicine","score_opus":0.06498206847688327,"score_gpt":0.43897680006160134,"score_spread":0.3739947315847181,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4405940634","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6781832,0.007901182,0.05316276,0.020629335,0.0002686221,0.0003321608,0.00010099753,0.0001406676,0.2392811],"genre_scores_gemma":[0.99468464,0.00045782546,0.0027664388,0.00017126068,0.000017508632,0.000043529828,0.000009794841,0.000007207655,0.0018418027],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.97546273,0.01687494,0.0011484954,0.0012017421,0.004200933,0.0011111872],"domain_scores_gemma":[0.97613996,0.015034751,0.0036824043,0.0014765369,0.002301563,0.0013647838],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01543942,0.0003993922,0.00026770352,0.004515413,0.0028303945,0.010108388,0.00080928614,0.001054253,0.001232797],"category_scores_gemma":[0.02749258,0.00030364544,0.00025254887,0.0027944816,0.02068996,0.005023647,0.0037661814,0.0017773913,0.00017524173],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00007804943,0.00017765771,0.09626632,0.00033162627,0.00003476076,0.00037427156,0.28779113,0.0019221908,0.0009719998,0.4789978,0.00216539,0.13088872],"study_design_scores_gemma":[0.00005285095,0.00040643895,0.18549195,0.0018929524,0.000040562245,0.0013807113,0.2970673,0.0043509225,0.0014771819,0.28628942,0.22134109,0.00020865105],"about_ca_topic_score_codex":0.012716408,"about_ca_topic_score_gemma":0.010867664,"teacher_disagreement_score":0.01579593,"about_ca_system_score_codex":0.01579593,"about_ca_system_score_gemma":0.007923452,"threshold_uncertainty_score":0.11460805},"labels":[],"label_agreement":null},{"id":"W4406043859","doi":"10.1080/15427587.2024.2448815","title":"The impact of TOEFL iBT preparation on Chinese test-takers’ perceptions of integrated speaking and writing design","year":2025,"lang":"en","type":"article","venue":"Critical Inquiry in Language Studies","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Test (biology); Test of English as a Foreign Language; Psychology; Perception; Context (archaeology); Construct validity; Language assessment; Test design; Applied psychology; Social psychology; Medical education; Mathematics education; Developmental psychology; Psychometrics; Test method; Medicine","score_opus":0.07430071452784202,"score_gpt":0.5133190650981386,"score_spread":0.4390183505702966,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406043859","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9986149,0.000034690544,0.0003759087,0.00010026379,0.000006044875,0.000054427284,0.000008065981,0.00001017746,0.0007956141],"genre_scores_gemma":[0.9987589,0.000046190526,0.0006860471,0.000072991905,0.0000066839634,0.00006587041,0.000016975617,0.0000056368467,0.0003406657],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.98721457,0.006867002,0.00091763615,0.00058946,0.0031749606,0.001236464],"domain_scores_gemma":[0.9533818,0.024804933,0.009803039,0.0031582473,0.005065951,0.003786107],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.019371953,0.0005874946,0.00046447702,0.0012718467,0.0019297907,0.0030978967,0.00070240296,0.0005856817,0.00212305],"category_scores_gemma":[0.059033506,0.00028917685,0.0005919235,0.00071142655,0.0025332444,0.0011476886,0.002690534,0.0012577723,0.0002495069],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00086509803,0.0012256117,0.3781837,0.00051427516,0.000092662216,0.0012533809,0.47641063,0.00046918646,0.022743927,0.0006002795,0.00080721214,0.11683401],"study_design_scores_gemma":[0.00008229495,0.0046945154,0.63051724,0.00027640775,0.00010074386,0.0007088767,0.34689528,0.0016130335,0.008507777,0.0006619964,0.005732791,0.0002090635],"about_ca_topic_score_codex":0.004850521,"about_ca_topic_score_gemma":0.0054395567,"teacher_disagreement_score":0.019371953,"about_ca_system_score_codex":0.0023132786,"about_ca_system_score_gemma":0.002796663,"threshold_uncertainty_score":0.102449894},"labels":[],"label_agreement":null},{"id":"W4406293560","doi":"10.21432/cjlt28759","title":"Technological Tool for Formative Assessment in Higher Education: ZipGrade","year":2025,"lang":"en","type":"article","venue":"Canadian Journal of Learning and Technology","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Formative assessment; Higher education; Mathematics education; Technological literacy; Technology integration; Pedagogy; Qualitative research; Psychology; Teaching method; Computer science; Sociology; Political science; Social science","score_opus":0.020358299633339568,"score_gpt":0.35352175307328504,"score_spread":0.33316345343994547,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406293560","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8846488,0.0006421563,0.08397841,0.00089660456,0.00030672134,0.0037925052,0.0028516082,0.0033896382,0.019493682],"genre_scores_gemma":[0.85658246,0.0005786909,0.13158573,0.00030300004,0.00009975656,0.0039291168,0.0010664614,0.00015251078,0.00570231],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99020773,0.0060628275,0.000858622,0.0006061177,0.0019324542,0.00033220364],"domain_scores_gemma":[0.9581765,0.025765091,0.0047074235,0.0040069097,0.005985391,0.0013586617],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0111933425,0.00067354826,0.00067321456,0.0032941801,0.0006875923,0.0023354115,0.0011911131,0.0004289007,0.0051097325],"category_scores_gemma":[0.056873553,0.00029833935,0.0004977692,0.0018546035,0.00059607165,0.0020167918,0.002756512,0.00089968514,0.0019983887],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011837484,0.0018942312,0.10917035,0.0011702151,0.00004320039,0.000343974,0.013333048,0.0008001877,0.011150111,0.0013951357,0.0060815015,0.8534344],"study_design_scores_gemma":[0.00053922646,0.02283433,0.6170506,0.0040913024,0.00037022922,0.004727865,0.05142078,0.014644928,0.06007888,0.006389637,0.21704979,0.0008024167],"about_ca_topic_score_codex":0.00061303703,"about_ca_topic_score_gemma":0.0019661204,"teacher_disagreement_score":0.0111933425,"about_ca_system_score_codex":0.0008290297,"about_ca_system_score_gemma":0.0017452628,"threshold_uncertainty_score":0.05919683},"labels":[],"label_agreement":null},{"id":"W4406716639","doi":"10.1007/978-3-031-47411-8_44-1","title":"Teaching Within Social Justice and Diversity Frameworks: A (White) Teacher’s Approach","year":2024,"lang":"en","type":"book-chapter","venue":"Springer international handbooks of education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brandon University","funders":"","keywords":"Diversity (politics); Social justice; White (mutation); Economic Justice; Sociology; Pedagogy; Social psychology; Psychology; Criminology; Political science; Anthropology; Law; Biology","score_opus":0.03701825137104098,"score_gpt":0.34711474001636106,"score_spread":0.3100964886453201,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4406716639","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011867386,0.014188325,0.06273642,0.2143575,0.004462535,0.00022801518,0.00004487771,0.00020249018,0.6919124],"genre_scores_gemma":[0.39065227,0.011189073,0.044352993,0.02832001,0.0016474085,0.0006057339,0.000044990004,0.00044339013,0.5227441],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9966175,0.002012226,0.00008705742,0.00031509862,0.0006739879,0.000294153],"domain_scores_gemma":[0.99652964,0.00203072,0.00012962904,0.0001957594,0.000605811,0.00050844083],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0055138087,0.00053152617,0.00046392306,0.0016659366,0.0071160085,0.009371814,0.0014170631,0.004157408,0.0059845494],"category_scores_gemma":[0.005160837,0.0003720568,0.0003812552,0.0011730404,0.017881032,0.009042266,0.0063670115,0.007340064,0.0011488512],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013744146,0.000094666444,0.00032145684,0.00014269091,0.0000052213086,0.00013896951,0.031977378,0.00026230412,0.0002443899,0.8316305,0.061648063,0.073520534],"study_design_scores_gemma":[0.0000122137435,0.00003763261,0.00077359093,0.00051709835,0.000007675063,0.00023916394,0.024223506,0.00063394173,0.00050401787,0.38055614,0.59247565,0.000019409015],"about_ca_topic_score_codex":0.014250901,"about_ca_topic_score_gemma":0.03232941,"teacher_disagreement_score":0.014250901,"about_ca_system_score_codex":0.00616012,"about_ca_system_score_gemma":0.010209122,"threshold_uncertainty_score":0.04469502},"labels":[],"label_agreement":null},{"id":"W4407090464","doi":"10.1007/s42330-024-00341-1","title":"Communities of Practice for Canadian University Mathematics Instructors","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Science Mathematics and Technology Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Science education; Mathematics education; Sociology; Pedagogy; Psychology","score_opus":0.02116335119734801,"score_gpt":0.3197334815633598,"score_spread":0.29857013036601177,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407090464","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.77815557,0.0025633143,0.010453456,0.08577639,0.0015311658,0.0026283807,0.00033566853,0.0009209236,0.11763521],"genre_scores_gemma":[0.9713931,0.00042590575,0.009821426,0.0015583591,0.00005591321,0.0005354868,0.0000904535,0.000072559254,0.016046813],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.97036856,0.0146152275,0.0008221535,0.0019045694,0.0067203147,0.0055691693],"domain_scores_gemma":[0.811261,0.023203343,0.005948889,0.0041023283,0.044252384,0.11123209],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.026839692,0.00047619143,0.00057467417,0.004490516,0.033831183,0.01171267,0.004630516,0.004406656,0.014751495],"category_scores_gemma":[0.07206343,0.00068668695,0.00062711694,0.0028682756,0.005939259,0.0049571055,0.017143905,0.0034173278,0.001150168],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00041149586,0.002632273,0.09121226,0.0004991176,0.000051893756,0.0014976192,0.43964705,0.00045768707,0.001340393,0.018180866,0.07192983,0.37213957],"study_design_scores_gemma":[0.00026349482,0.0009342741,0.058785502,0.0016236914,0.000044284876,0.00045647295,0.6661746,0.0014021484,0.0006292802,0.011266794,0.25818598,0.00023354936],"about_ca_topic_score_codex":0.55324537,"about_ca_topic_score_gemma":0.8138796,"teacher_disagreement_score":0.55324537,"about_ca_system_score_codex":0.04979386,"about_ca_system_score_gemma":0.26829502,"threshold_uncertainty_score":0.89877135},"labels":[],"label_agreement":null},{"id":"W4407944763","doi":"10.18552/joaw.v15is1.1036","title":"Being and Becoming: Addressing Equity, Diversity and Inclusion Issues in Learning Academic Writing through an Academic Integrity Socialisation Process","year":2025,"lang":"en","type":"article","venue":"Journal of Academic Writing","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"The Scarborough Hospital; University of Toronto","funders":"","keywords":"Equity (law); Inclusion (mineral); Academic integrity; Diversity (politics); Process (computing); Sociology; Psychology; Pedagogy; Engineering ethics; Political science; Social science; Social psychology; Anthropology; Computer science; Engineering","score_opus":0.12376111737684485,"score_gpt":0.4784814084030815,"score_spread":0.35472029102623664,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407944763","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9319262,0.00032210036,0.008095512,0.011083579,0.00015926924,0.00031099087,0.000009074484,0.00007426165,0.048019044],"genre_scores_gemma":[0.9937359,0.00015597782,0.0028447597,0.00039795777,0.000023252875,0.0000788944,0.0000043933906,0.00001308532,0.0027458225],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9507013,0.040513918,0.0008296406,0.0010513837,0.004859519,0.0020442829],"domain_scores_gemma":[0.9630745,0.021964272,0.0038460512,0.0020573908,0.0029470143,0.0061108475],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03220444,0.0005160145,0.00052356406,0.0014447351,0.012044113,0.010808803,0.0015003791,0.0018242603,0.0024337752],"category_scores_gemma":[0.058280364,0.00029844404,0.00051204115,0.0006664466,0.016469534,0.006692005,0.017531686,0.0040517356,0.00036307727],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000034776764,0.00034630892,0.006273842,0.00010512055,0.000007735318,0.0002417557,0.9235616,0.000083094565,0.0012299264,0.00785117,0.0007653896,0.059499353],"study_design_scores_gemma":[0.0000263444,0.00041132013,0.012547924,0.00029933607,0.000020111764,0.00045126,0.93616086,0.000366194,0.0017355342,0.0105869835,0.037345544,0.000048489066],"about_ca_topic_score_codex":0.0030577949,"about_ca_topic_score_gemma":0.0054880176,"teacher_disagreement_score":0.03220444,"about_ca_system_score_codex":0.0032506415,"about_ca_system_score_gemma":0.014137479,"threshold_uncertainty_score":0.17031538},"labels":[],"label_agreement":null},{"id":"W4408054097","doi":"10.1080/02602938.2025.2468848","title":"Enhancing the structure of feedback forms increases trustworthiness and usefulness of peer feedback","year":2025,"lang":"en","type":"article","venue":"Assessment & Evaluation in Higher Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Peer feedback; Trustworthiness; Psychology; Peer evaluation; Peer review; Higher education; Negative feedback; Social psychology; Mathematics education; Political science; Engineering","score_opus":0.039775825084288216,"score_gpt":0.4023611073920225,"score_spread":0.3625852823077343,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408054097","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9248818,0.000551374,0.057425953,0.00088286534,0.00015018324,0.0036049618,0.000102204736,0.001038636,0.011361905],"genre_scores_gemma":[0.89114094,0.00039409634,0.10549953,0.00018129133,0.00012918946,0.0013074485,0.000072722585,0.00013023711,0.0011444995],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9261714,0.04651383,0.0062383865,0.002983245,0.016967898,0.001125259],"domain_scores_gemma":[0.5634441,0.3327027,0.032814685,0.030554429,0.03578961,0.0046945675],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.040740207,0.0008198669,0.0009751558,0.0018757408,0.0011472228,0.002984375,0.00094146753,0.0010267098,0.0029141104],"category_scores_gemma":[0.29577383,0.00060863723,0.0008304684,0.0008412204,0.0011380402,0.0030321535,0.0025680999,0.00123618,0.00075804384],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0028572092,0.0043283557,0.095026314,0.0030141529,0.00028586035,0.00033019666,0.031683646,0.0025193128,0.05305385,0.001516421,0.0023781143,0.80300653],"study_design_scores_gemma":[0.002833156,0.04728124,0.7076008,0.0066678645,0.0018349083,0.0025173342,0.023906635,0.033377722,0.1091016,0.01259832,0.051330347,0.0009500515],"about_ca_topic_score_codex":0.00071849866,"about_ca_topic_score_gemma":0.0010823507,"teacher_disagreement_score":0.9592598,"about_ca_system_score_codex":0.0010709265,"about_ca_system_score_gemma":0.002729222,"threshold_uncertainty_score":0.21545738},"labels":[],"label_agreement":null},{"id":"W4408090665","doi":"10.1007/s10459-025-10419-6","title":"Correction to: Can all roads lead to competency? School levels effects in licensing examinations scores","year":2025,"lang":"en","type":"erratum","venue":"Advances in Health Sciences Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ottawa Hospital; McMaster University; Laurentian University; Thunder Bay Regional Health Sciences Centre; Medical Council of Canada; NOSM University; London Health Sciences Centre; Queen's University; University of Toronto; Western University; The Wilson Centre; Bruyère; University of Ottawa","funders":"","keywords":"Medical education; Psychology; Lead (geology); Mathematics education; Medicine","score_opus":0.02945443184243357,"score_gpt":0.4407449427705345,"score_spread":0.4112905109281009,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408090665","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00030307745,0.00037371303,0.00036304924,0.10277205,0.8879072,0.000027195838,0.0040555145,0.00034453397,0.0038535872],"genre_scores_gemma":[0.02626674,0.0034938655,0.005291542,0.20015056,0.28524312,0.00049577275,0.00801683,0.002938134,0.46810332],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99398744,0.0007298502,0.0012080799,0.0007844679,0.0026087882,0.00068149815],"domain_scores_gemma":[0.9319246,0.01919913,0.0032973283,0.0042516934,0.038313113,0.003014137],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005047624,0.0017762419,0.0021937902,0.003557384,0.0044775615,0.0048246616,0.0038252845,0.009541863,0.09728884],"category_scores_gemma":[0.1126014,0.0013272522,0.0015522646,0.0032206743,0.0023476623,0.002267843,0.0023468516,0.01351837,0.04858701],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000019291158,0.0000043020386,0.00013117625,0.000034253517,0.000004271899,0.00009137077,0.000020855035,0.000019851299,0.00000834914,0.00026564216,0.9974921,0.0019086432],"study_design_scores_gemma":[0.00010833525,0.000027361679,0.00452679,0.0007183971,0.00006114203,0.00054090685,0.00038661534,0.00053726515,0.00033698266,0.002356786,0.9903137,0.00008570923],"about_ca_topic_score_codex":0.10896283,"about_ca_topic_score_gemma":0.09879928,"teacher_disagreement_score":0.10896283,"about_ca_system_score_codex":0.0061759185,"about_ca_system_score_gemma":0.011537472,"threshold_uncertainty_score":0.3254636},"labels":[],"label_agreement":null},{"id":"W4408156977","doi":"10.1080/02188791.2025.2465296","title":"Advancing e-assessment for learning in the primary EFL writing classroom: the role of collaborative teacher professional learning","year":2025,"lang":"en","type":"article","venue":"Asia Pacific Journal of Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"Hubei Provincial Department of Education","keywords":"Psychology; Mathematics education; Professional learning community; Professional development; Pedagogy; Collaborative learning; Assessment for learning; Formative assessment","score_opus":0.009083673617588496,"score_gpt":0.369719841353591,"score_spread":0.3606361677360025,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408156977","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.81501436,0.0026389405,0.044541787,0.010789115,0.00024436033,0.00090975047,0.000034449695,0.00032068463,0.12550652],"genre_scores_gemma":[0.97802657,0.0006100503,0.018046668,0.00021582787,0.000024494046,0.0001030935,0.00000922294,0.000013972347,0.002950023],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9817576,0.012903481,0.0006850592,0.0011626391,0.0023386038,0.001152764],"domain_scores_gemma":[0.9656101,0.02100619,0.0024797614,0.0028745853,0.0028176738,0.0052117133],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.017271275,0.0003401129,0.00042478376,0.0009590331,0.003740721,0.007473412,0.0014035733,0.0014086216,0.0023977822],"category_scores_gemma":[0.03012773,0.0002604684,0.00031271004,0.0009195134,0.004007664,0.0049274154,0.009014212,0.0019021191,0.00055898534],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013742139,0.002023028,0.044230293,0.0009816274,0.000027420658,0.0010506342,0.21843392,0.0004836587,0.0039587705,0.012196314,0.002256399,0.71422046],"study_design_scores_gemma":[0.00033925395,0.0034891553,0.15527324,0.004524827,0.00015107532,0.0038644073,0.5524913,0.008936988,0.01700098,0.04738085,0.2062996,0.00024829074],"about_ca_topic_score_codex":0.0027125026,"about_ca_topic_score_gemma":0.0041234554,"teacher_disagreement_score":0.017271275,"about_ca_system_score_codex":0.0020756994,"about_ca_system_score_gemma":0.013744628,"threshold_uncertainty_score":0.09134036},"labels":[],"label_agreement":null},{"id":"W4408329028","doi":"10.18060/28006","title":"Assessment in Higher Education and Student Affairs Graduate Education","year":2024,"lang":"en","type":"article","venue":"Journal of Student Affairs Inquiry Improvement and Impact","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Student affairs; Higher education; Graduate education; Pedagogy; Political science; Graduate students; Medical education; Mathematics education; Sociology; Psychology; Medicine; Law","score_opus":0.07429800249368668,"score_gpt":0.44500567858384954,"score_spread":0.37070767609016286,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408329028","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8939157,0.0032291047,0.011335171,0.0065912637,0.000436093,0.00046945552,0.00011323583,0.0002540096,0.083655946],"genre_scores_gemma":[0.9860823,0.0007044796,0.0070922496,0.00055892207,0.00005940547,0.000101169746,0.00006237591,0.000023338403,0.0053158933],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9823941,0.010212923,0.00075972726,0.0009346534,0.00456141,0.0011371601],"domain_scores_gemma":[0.961811,0.015957149,0.0032592611,0.0018202917,0.00922936,0.007922917],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.025632048,0.00027600944,0.0003828282,0.0017700815,0.0031423087,0.0055621285,0.000863009,0.00094287156,0.0045620864],"category_scores_gemma":[0.06856861,0.00017212555,0.00021843151,0.001884252,0.0030432455,0.0023876068,0.0072457655,0.0018183205,0.00075839134],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014577188,0.0011264549,0.15302345,0.00041288344,0.000018214472,0.00016090006,0.03880727,0.0007923156,0.0015979118,0.01455633,0.010853321,0.77850515],"study_design_scores_gemma":[0.000052534324,0.0041735885,0.62323624,0.0018379217,0.000027012373,0.0010816827,0.11115814,0.00260522,0.0075071957,0.052149605,0.19600895,0.00016192053],"about_ca_topic_score_codex":0.0027255737,"about_ca_topic_score_gemma":0.0059537357,"teacher_disagreement_score":0.025632048,"about_ca_system_score_codex":0.0038752176,"about_ca_system_score_gemma":0.010400307,"threshold_uncertainty_score":0.13555688},"labels":[],"label_agreement":null},{"id":"W4408534011","doi":"10.5430/wjel.v15n4p327","title":"Comparative Analysis of Feedback Practices and Perspectives in Online Academic Writing Assessments at Two Regional Tertiary Institutions","year":2025,"lang":"en","type":"article","venue":"World Journal of English Language","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Computer science; Academic writing; Tertiary level; Tertiary care; Mathematics education; Political science; Psychology; Medicine","score_opus":0.08060432853243352,"score_gpt":0.4593552918058232,"score_spread":0.37875096327338964,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408534011","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9970891,0.00016119408,0.0006300636,0.00024288474,0.00001069889,0.000026976619,0.000023090677,0.00001305395,0.0018030084],"genre_scores_gemma":[0.99846053,0.00013218068,0.0006017175,0.00007427694,0.000007868485,0.000024768413,0.000014866824,0.0000073071315,0.0006765963],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.97929937,0.012838678,0.0014073151,0.0007580215,0.004167328,0.0015292893],"domain_scores_gemma":[0.92976296,0.04057254,0.009583517,0.0020861567,0.012341355,0.005653497],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01727721,0.00025030607,0.00047696213,0.0036414168,0.0030064145,0.0038996872,0.000753871,0.0007265187,0.0019543134],"category_scores_gemma":[0.064552344,0.00020209514,0.00027420855,0.0030214523,0.0021031338,0.0022383013,0.0036849456,0.00090511056,0.00036536687],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00037732132,0.0005957893,0.17152666,0.00041147444,0.000036166355,0.0008815651,0.6740701,0.00019528612,0.0054263324,0.0011922679,0.0008162188,0.14447072],"study_design_scores_gemma":[0.000015416636,0.0007575077,0.22135869,0.00029178048,0.000027502423,0.0005094831,0.76251876,0.00047551404,0.003917701,0.00042082675,0.009639019,0.000067708716],"about_ca_topic_score_codex":0.0019543178,"about_ca_topic_score_gemma":0.0045968625,"teacher_disagreement_score":0.01727721,"about_ca_system_score_codex":0.0026728588,"about_ca_system_score_gemma":0.0037587387,"threshold_uncertainty_score":0.091371715},"labels":[],"label_agreement":null},{"id":"W4408596861","doi":"10.5539/jel.v14n4p241","title":"Errors in Chinese Post Graduate Students’ Writing in an International Program at a Thai Public University","year":2025,"lang":"en","type":"article","venue":"Journal of Education and Learning","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Psychology; Graduate students; Mathematics education; Public university; Statistical analysis; Medical education; Pedagogy; Political science; Statistics; Medicine; Mathematics","score_opus":0.03677948400717187,"score_gpt":0.4250899526048032,"score_spread":0.38831046859763135,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408596861","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9994436,0.00005247845,0.00012108083,0.00004519742,0.000007679558,0.000011226349,0.000012132095,0.0000066059015,0.00030017822],"genre_scores_gemma":[0.9986187,0.00011435108,0.00045524232,0.00004061359,0.000008606261,0.000018015024,0.000042397594,0.000008227657,0.000693881],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99389726,0.0017232957,0.0010991093,0.00044762643,0.0024085592,0.00042409083],"domain_scores_gemma":[0.9528646,0.023718592,0.010917604,0.0017316515,0.00906875,0.0016988532],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004165728,0.0005303073,0.00041499818,0.002549332,0.0018122491,0.0013385013,0.0005374275,0.0007228622,0.0009220879],"category_scores_gemma":[0.039856005,0.00024041971,0.00023850803,0.0019567655,0.0012292273,0.0008711104,0.001576952,0.0007569909,0.0002453634],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00045944523,0.00065374264,0.5592998,0.0004593977,0.0000769021,0.005796514,0.29968205,0.00028269587,0.011114706,0.00019851545,0.001341911,0.12063433],"study_design_scores_gemma":[0.000034443114,0.001508582,0.77607226,0.0002723925,0.00010502759,0.007514453,0.19436331,0.001830115,0.011918648,0.00041186422,0.0058482285,0.000120585144],"about_ca_topic_score_codex":0.0028408559,"about_ca_topic_score_gemma":0.0047655827,"teacher_disagreement_score":0.004165728,"about_ca_system_score_codex":0.00083151,"about_ca_system_score_gemma":0.001665465,"threshold_uncertainty_score":0.022030711},"labels":[],"label_agreement":null},{"id":"W4408741152","doi":"10.1080/13562517.2025.2468598","title":"The multiplicity of authenticity in higher education assessment","year":2025,"lang":"en","type":"article","venue":"Teaching in Higher Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Higher education; Mathematics education; Multiplicity (mathematics); Pedagogy; Psychology; Sociology; Mathematics; Political science","score_opus":0.047747205810736326,"score_gpt":0.4288700821852897,"score_spread":0.3811228763745534,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408741152","genre_codex":"editorial","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.012440164,0.057887573,0.0408806,0.35638773,0.40141973,0.00008259951,0.000044022454,0.0003606928,0.1304968],"genre_scores_gemma":[0.32816482,0.044048563,0.0142819695,0.043159116,0.5005165,0.0001258951,0.0000691574,0.00080755906,0.06882642],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9782573,0.011542428,0.0016466768,0.0012857574,0.0065188543,0.0007490082],"domain_scores_gemma":[0.93026036,0.05824188,0.0015494995,0.0027438595,0.005506146,0.001698164],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014310545,0.0004798801,0.0008607092,0.0014683715,0.004061563,0.0155499475,0.0015385441,0.004715667,0.0042106784],"category_scores_gemma":[0.037670277,0.0003026489,0.0005747333,0.0009479884,0.015090605,0.010840147,0.0052752877,0.011342647,0.0008319645],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00004875649,0.00006554074,0.0010124097,0.0008856003,0.00003085882,0.0005147029,0.037546154,0.0003087556,0.0007528151,0.45950502,0.28581497,0.21351448],"study_design_scores_gemma":[0.000004281348,0.000057839006,0.0004550555,0.000756552,0.00000780298,0.0005138446,0.005879115,0.00046079687,0.00042088504,0.067357585,0.9240507,0.00003546843],"about_ca_topic_score_codex":0.00070826744,"about_ca_topic_score_gemma":0.0017080551,"teacher_disagreement_score":0.0155499475,"about_ca_system_score_codex":0.0024601384,"about_ca_system_score_gemma":0.0037182467,"threshold_uncertainty_score":0.07568228},"labels":[],"label_agreement":null},{"id":"W4408961082","doi":"10.1080/00131911.2025.2475829","title":"An interdisciplinary review of learning through failure in higher education","year":2025,"lang":"en","type":"article","venue":"Educational Review","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Higher education; Mathematics education; Engineering ethics; Pedagogy; Psychology; Sociology; Engineering; Economic growth; Economics","score_opus":0.04710432301078445,"score_gpt":0.48620981867136687,"score_spread":0.43910549566058243,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408961082","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00017777241,0.9977533,0.00014355044,0.00096238544,0.00033231202,0.000010635536,0.00001459832,0.0000028894326,0.00060252607],"genre_scores_gemma":[0.001810552,0.99726784,0.00018743816,0.00044356915,0.00015164663,0.000013930568,0.000015517377,0.0000016379075,0.000107901935],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9962232,0.0015977098,0.0008109581,0.00032953598,0.0009172636,0.00012118455],"domain_scores_gemma":[0.9729707,0.021619454,0.0013641969,0.00032559008,0.003355148,0.00036486378],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006748495,0.00083300524,0.0016451323,0.006907913,0.0006198921,0.002603303,0.0012845051,0.0017241259,0.0029497491],"category_scores_gemma":[0.023212478,0.00042963788,0.0009605633,0.008610764,0.001483245,0.0029871373,0.00149629,0.0020848429,0.0005923812],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006564594,0.00005663844,0.0005866519,0.17121576,0.00042149707,0.00016452753,0.0015316017,0.000342194,0.00041896946,0.005519569,0.03281139,0.7868654],"study_design_scores_gemma":[0.00001633385,0.0002053055,0.003406415,0.24284232,0.00085351086,0.0007335917,0.0016048439,0.0000817273,0.00030871373,0.0033108715,0.74658525,0.000051134473],"about_ca_topic_score_codex":0.0036434499,"about_ca_topic_score_gemma":0.008910087,"teacher_disagreement_score":0.006907913,"about_ca_system_score_codex":0.002221995,"about_ca_system_score_gemma":0.009115308,"threshold_uncertainty_score":0.03568989},"labels":[],"label_agreement":null},{"id":"W4408998993","doi":"10.3390/educsci15040438","title":"Formative Assessment in Upper Secondary Schools: Ideas, Concepts, and Strategies","year":2025,"lang":"en","type":"article","venue":"Education Sciences","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Thomas University","funders":"","keywords":"Formative assessment; Mathematics education; Computer science; Pedagogy; Psychology","score_opus":0.02534208960626211,"score_gpt":0.4571228579096512,"score_spread":0.4317807683033891,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4408998993","genre_codex":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.32543632,0.092274666,0.33585873,0.097558066,0.0011831694,0.0029635017,0.00015648287,0.00088962767,0.14367951],"genre_scores_gemma":[0.8881639,0.015498887,0.08747254,0.0019969044,0.00023715962,0.0013715476,0.000055353365,0.000051485444,0.0051521696],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9742774,0.018853424,0.0014742459,0.0010854134,0.0034301477,0.0008794159],"domain_scores_gemma":[0.95928055,0.029560762,0.0030084583,0.0015054684,0.004803323,0.001841388],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.042007327,0.0010000445,0.0007945221,0.00762337,0.0029871955,0.011518064,0.0023899067,0.002208225,0.0010318299],"category_scores_gemma":[0.036350932,0.00047492713,0.0005282374,0.0046161558,0.015086105,0.007537036,0.005015157,0.0029271673,0.00024320293],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009441699,0.00060200784,0.03878978,0.0019084117,0.00004602223,0.00051426335,0.22701326,0.0012164223,0.0012137691,0.20141333,0.003696837,0.52349144],"study_design_scores_gemma":[0.00009751006,0.0008203957,0.06715518,0.013254626,0.00009485356,0.002687196,0.25982913,0.010268171,0.004657951,0.44158322,0.19924594,0.00030577494],"about_ca_topic_score_codex":0.009765723,"about_ca_topic_score_gemma":0.0065355273,"teacher_disagreement_score":0.042007327,"about_ca_system_score_codex":0.009989274,"about_ca_system_score_gemma":0.0134328855,"threshold_uncertainty_score":0.22215861},"labels":[],"label_agreement":null},{"id":"W4409046326","doi":"10.1016/b978-0-323-95504-1.00418-x","title":"Learning-Oriented Assessment (LOA)","year":2025,"lang":"en","type":"book-chapter","venue":"Elsevier eBooks","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University; McGill University","funders":"","keywords":"Loa loa; Computer science; Psychology; Biology; Zoology","score_opus":0.01721180118315386,"score_gpt":0.3258029582369012,"score_spread":0.30859115705374734,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409046326","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0023403636,0.010318855,0.10684665,0.0010114354,0.0013319852,0.0001304179,0.00031778638,0.0038512896,0.8738511],"genre_scores_gemma":[0.012793172,0.0065533435,0.045281842,0.0005163883,0.0002727879,0.00017437774,0.000408239,0.000565121,0.93343484],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.99952674,0.00006424861,0.00002566032,0.000059503047,0.00030254445,0.000021406535],"domain_scores_gemma":[0.99937135,0.0002763339,0.000026744392,0.00006568854,0.00019566495,0.0000642874],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0005524107,0.0007706228,0.00045448076,0.0011537304,0.00043930218,0.0033317457,0.000887328,0.00091547816,0.08511533],"category_scores_gemma":[0.0017397942,0.00030156795,0.00033026419,0.0013717584,0.0004111416,0.001968467,0.0015767472,0.0014749103,0.05667433],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000012393041,0.00006467113,0.000091885,0.00017246521,0.000002983876,0.00003281952,0.00018251814,0.00038339128,0.001575467,0.017532848,0.08897926,0.8909692],"study_design_scores_gemma":[0.000008089369,0.00006420187,0.0011023397,0.00050998095,0.000008280903,0.00040235344,0.00017608357,0.002067005,0.001402887,0.031128047,0.9631137,0.00001691574],"about_ca_topic_score_codex":0.0013578985,"about_ca_topic_score_gemma":0.0023100555,"teacher_disagreement_score":0.08511533,"about_ca_system_score_codex":0.0005768915,"about_ca_system_score_gemma":0.0008476651,"threshold_uncertainty_score":0.28473914},"labels":[],"label_agreement":null},{"id":"W4409147234","doi":"10.1080/10400419.2025.2485887","title":"Supporting Creative Thinking Using Online Peer Assessment: Student Perceptions and Team Processes in Higher Education","year":2025,"lang":"en","type":"article","venue":"Creativity Research Journal","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"The Scarborough Hospital; University of Toronto; Queen's University","funders":"","keywords":"Creativity; Psychology; Perception; Peer assessment; Higher education; Peer evaluation; Creative thinking; Pedagogy; Mathematics education; Applied psychology; Social psychology","score_opus":0.16585881592418503,"score_gpt":0.570853872350848,"score_spread":0.4049950564266629,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409147234","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9990759,0.00003177617,0.0002398645,0.00006411517,0.0000047259446,0.0000123658265,0.0000035254836,0.0000047967706,0.0005628761],"genre_scores_gemma":[0.99942774,0.000038277256,0.00029481793,0.000020311709,0.000005808906,0.000013469966,0.000006757897,0.0000023835473,0.00019038853],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.99189574,0.004174698,0.000522132,0.00037834063,0.0023855015,0.0006435659],"domain_scores_gemma":[0.96370625,0.016980844,0.008321737,0.0010950688,0.005008138,0.004887972],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0092467675,0.00031656332,0.00044140161,0.0014707478,0.0013194958,0.0030018804,0.00053142686,0.0005604375,0.0018478701],"category_scores_gemma":[0.037626073,0.00022020267,0.0004439608,0.0007757151,0.0009061171,0.0014022152,0.001828936,0.0011695359,0.00027918912],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025775915,0.0027000743,0.8004785,0.00018887596,0.00010266354,0.00027579878,0.09364938,0.00047774025,0.0032431574,0.0003061116,0.0005830734,0.09773682],"study_design_scores_gemma":[0.000048505823,0.0026975542,0.7989088,0.00018824062,0.000073875555,0.00042876284,0.18770212,0.0027684108,0.002935413,0.00096249447,0.0031851758,0.000100597594],"about_ca_topic_score_codex":0.001114999,"about_ca_topic_score_gemma":0.0015462906,"teacher_disagreement_score":0.0092467675,"about_ca_system_score_codex":0.0005761206,"about_ca_system_score_gemma":0.001291989,"threshold_uncertainty_score":0.048902154},"labels":[],"label_agreement":null},{"id":"W4409225263","doi":"10.1111/medu.15706","title":"Untangling feedback: Mapping the patterns behind the practice","year":2025,"lang":"en","type":"article","venue":"Medical Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"Canadian Institutes of Health Research; Royal College of Physicians and Surgeons of Canada","keywords":"Coaching; Divergence (linguistics); Computer science; Audit; Diversity (politics); Perspective (graphical); Convergence (economics); Psychology; Data science; Cognitive psychology; Artificial intelligence","score_opus":0.022511260621877003,"score_gpt":0.3949465201244899,"score_spread":0.37243525950261286,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409225263","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.42621365,0.0008421314,0.52457434,0.0041045006,0.000091023765,0.00068596425,0.00029935397,0.0005453682,0.042643696],"genre_scores_gemma":[0.9031647,0.00030287282,0.09433542,0.00011108604,0.000007411131,0.00029926831,0.00012379079,0.00007713485,0.0015782262],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.98389786,0.009279255,0.0009749082,0.0020316632,0.0032869563,0.0005293128],"domain_scores_gemma":[0.96962434,0.020902751,0.0023733648,0.0039200913,0.0027606287,0.00041888223],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013142907,0.0005746013,0.00058794685,0.0045613935,0.001865561,0.006921731,0.001388842,0.0013803106,0.0022280377],"category_scores_gemma":[0.048976373,0.00055865163,0.0007491115,0.003241066,0.00895231,0.011122626,0.0041659693,0.0015189231,0.000371466],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002482768,0.00009531524,0.05401291,0.0010290915,0.0001109974,0.00058198813,0.40817085,0.004111515,0.005520012,0.17524514,0.0014944234,0.34937957],"study_design_scores_gemma":[0.00007509304,0.00057834294,0.061874937,0.0016978726,0.00014009533,0.0013345572,0.33848554,0.056562707,0.0059153787,0.47412932,0.05897616,0.00023006319],"about_ca_topic_score_codex":0.007580265,"about_ca_topic_score_gemma":0.00708642,"teacher_disagreement_score":0.013142907,"about_ca_system_score_codex":0.004200506,"about_ca_system_score_gemma":0.004092475,"threshold_uncertainty_score":0.06950718},"labels":[],"label_agreement":null},{"id":"W4409835544","doi":"10.59944/postaxial.v3i1.416","title":"Rethinking Assessment and Evaluation: Towards a Holistic Approach to Measuring Student Success","year":2025,"lang":"en","type":"article","venue":"International Journal of Post Axial Futuristic Teaching and Learning","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Holistic education; Engineering ethics; Psychology; Mathematics education; Pedagogy; Management science; Sociology; Medical education; Engineering; Medicine","score_opus":0.05991971905779656,"score_gpt":0.43043897238728857,"score_spread":0.370519253329492,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409835544","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.41233164,0.008932434,0.51406074,0.0052184705,0.0010543179,0.004671928,0.0006380062,0.0014866313,0.05160586],"genre_scores_gemma":[0.8049369,0.0019790323,0.18684909,0.000440342,0.00015138346,0.0026762495,0.00029107332,0.00018064433,0.0024952549],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8418427,0.08440674,0.015009441,0.0036934682,0.05358035,0.0014672462],"domain_scores_gemma":[0.7847601,0.111848846,0.027006773,0.014168022,0.057963338,0.0042528827],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.13367897,0.0013104385,0.0022965206,0.012506914,0.001837715,0.012180161,0.0028140214,0.0013521172,0.0011780356],"category_scores_gemma":[0.17996377,0.0005095959,0.00096928875,0.0058678556,0.004912853,0.009268193,0.006278863,0.002347842,0.0006090643],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00040376815,0.0005505919,0.14736308,0.001605346,0.00041161108,0.00015469892,0.022180296,0.0019838188,0.003911758,0.012421911,0.003692391,0.8053208],"study_design_scores_gemma":[0.00021247544,0.009089941,0.56672233,0.016254496,0.0011195549,0.0022057404,0.088296324,0.05812372,0.025637072,0.12993358,0.10089383,0.0015109113],"about_ca_topic_score_codex":0.0021321764,"about_ca_topic_score_gemma":0.0037523466,"teacher_disagreement_score":0.13367897,"about_ca_system_score_codex":0.0029871531,"about_ca_system_score_gemma":0.006049993,"threshold_uncertainty_score":0.70697045},"labels":[],"label_agreement":null},{"id":"W4409835840","doi":"10.59944/postaxial.v3i2.442","title":"Culturally Responsive Assessment and Evaluation Practices in Multilingual Classrooms","year":2025,"lang":"en","type":"article","venue":"International Journal of Post Axial Futuristic Teaching and Learning","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Linguistics; Psychology; Computer science; Mathematics education; Natural language processing","score_opus":0.03007877792885581,"score_gpt":0.4561858292430154,"score_spread":0.42610705131415955,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409835840","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.80411917,0.002583933,0.12980756,0.0086754095,0.0004553218,0.0020766703,0.00004932847,0.0010471733,0.051185478],"genre_scores_gemma":[0.9331504,0.00061817345,0.061098658,0.00062005315,0.00003884892,0.00058206037,0.000022026199,0.00011653492,0.0037532146],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.83399934,0.13481838,0.00668674,0.005996085,0.015773894,0.002725636],"domain_scores_gemma":[0.90452856,0.04769015,0.009351192,0.010659911,0.021879895,0.0058903093],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.07993362,0.00078509265,0.0006811747,0.0029228786,0.0060822074,0.0076777637,0.00295537,0.001612807,0.0011370303],"category_scores_gemma":[0.12785023,0.0006257981,0.000558,0.0011769426,0.0062434003,0.004944677,0.012527513,0.0028938376,0.0005228302],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002644881,0.0014314895,0.022548929,0.000740126,0.00010009584,0.0017092155,0.53718764,0.0025234518,0.012083958,0.009292663,0.0028553605,0.40926266],"study_design_scores_gemma":[0.0002924704,0.0022225683,0.039797712,0.005047574,0.0001694098,0.0042377254,0.59945375,0.008957053,0.034247838,0.044863235,0.25970492,0.0010057746],"about_ca_topic_score_codex":0.0028654851,"about_ca_topic_score_gemma":0.006241673,"teacher_disagreement_score":0.07993362,"about_ca_system_score_codex":0.0057265805,"about_ca_system_score_gemma":0.01252175,"threshold_uncertainty_score":0.42273444},"labels":[],"label_agreement":null},{"id":"W4409954575","doi":"10.1002/berj.4181","title":"Preservice teachers' assessment decisions: Exploring the role of fairness conceptions","year":2025,"lang":"en","type":"article","venue":"British Educational Research Journal","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Winnipeg","funders":"","keywords":"Psychology; Mathematics education; Pedagogy; Educational research; Sociology","score_opus":0.16526556795964736,"score_gpt":0.5029873425817295,"score_spread":0.33772177462208214,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4409954575","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99511397,0.00012232874,0.0014253797,0.00042973584,0.0000067226088,0.000017634018,0.000005298931,0.000004259963,0.002874691],"genre_scores_gemma":[0.9996131,0.000020348632,0.0002281393,0.000019197123,0.0000014539163,0.000004929167,0.0000017175753,8.933193e-7,0.000110207075],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.97212607,0.019079326,0.0012172214,0.0011858214,0.0049475594,0.0014439423],"domain_scores_gemma":[0.87377155,0.08689788,0.020448154,0.0051759593,0.009662272,0.004044185],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.032758873,0.00021504618,0.0004633088,0.0016482861,0.0027326415,0.00655895,0.0009630508,0.00076148944,0.0012881175],"category_scores_gemma":[0.09671562,0.00037064267,0.00029165632,0.0006633695,0.0064802887,0.0026429044,0.0037975535,0.0023451361,0.00010506016],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00021653334,0.00037566095,0.36005884,0.00011949625,0.00004101546,0.0002596691,0.58712405,0.0005625067,0.0017121694,0.009713496,0.0003914742,0.039425064],"study_design_scores_gemma":[0.000038020302,0.00043247768,0.32182574,0.0004848902,0.000048188245,0.00039430603,0.646978,0.0038492752,0.0024633987,0.015975034,0.0073930337,0.0001176085],"about_ca_topic_score_codex":0.008445439,"about_ca_topic_score_gemma":0.011263233,"teacher_disagreement_score":0.032758873,"about_ca_system_score_codex":0.0038544661,"about_ca_system_score_gemma":0.004377573,"threshold_uncertainty_score":0.17324758},"labels":[],"label_agreement":null},{"id":"W4410015948","doi":"10.1080/15434303.2025.2497818","title":"On the Interplay Between Conceptions of Assessment and Assessment Agency: Perspectives of Iranian EFL Preservice Teachers","year":2025,"lang":"en","type":"article","venue":"Language Assessment Quarterly","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Mathematics education; Pedagogy; Agency (philosophy); Psychology; Alternative assessment; Semi-structured interview; Qualitative research; Sociology; Social science","score_opus":0.017476476578897192,"score_gpt":0.4119940254646767,"score_spread":0.39451754888577956,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410015948","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9864352,0.00075177074,0.0015077693,0.002659538,0.000014563854,0.000015027121,0.0000073560636,0.0000054992747,0.008603334],"genre_scores_gemma":[0.9994466,0.00013455217,0.00018432399,0.000056882473,0.0000026811463,0.0000033146628,0.000002025581,9.5177023e-7,0.00016860744],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99212545,0.005459922,0.00024433678,0.00031403336,0.0011596536,0.0006966524],"domain_scores_gemma":[0.9842217,0.009286229,0.002746321,0.00043297262,0.0019214363,0.0013913497],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011378084,0.00030593402,0.0003282383,0.0016409938,0.0048369924,0.006694677,0.00077496516,0.0008716239,0.0006438482],"category_scores_gemma":[0.0132535,0.00036694252,0.00026809276,0.0009923446,0.014130337,0.002955193,0.0023682364,0.003114628,0.000068881396],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003718337,0.00010535364,0.0614876,0.00005197553,0.000011883828,0.00045875311,0.9081308,0.00024399676,0.0007051123,0.01719747,0.0003450235,0.011224681],"study_design_scores_gemma":[0.0000110157425,0.00008079194,0.038181707,0.000099386496,0.000013453051,0.0004755961,0.94642556,0.00070744083,0.00034560644,0.0063584126,0.0072631347,0.00003785331],"about_ca_topic_score_codex":0.02382147,"about_ca_topic_score_gemma":0.02462208,"teacher_disagreement_score":0.02382147,"about_ca_system_score_codex":0.006337504,"about_ca_system_score_gemma":0.0065972367,"threshold_uncertainty_score":0.06017375},"labels":[],"label_agreement":null},{"id":"W4410019844","doi":"10.36834/cmej.81477","title":"Embracing the next frontier in assessment","year":2025,"lang":"en","type":"editorial","venue":"Canadian Medical Education Journal","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Université de Sherbrooke","funders":"","keywords":"Frontier; Computer science; Data science; Computational biology; Biology; Geography; Archaeology","score_opus":0.014186935595631762,"score_gpt":0.3787503147277961,"score_spread":0.3645633791321643,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410019844","genre_codex":"editorial","genre_gemma":"editorial","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"editorial","genre_consensus":"editorial","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00004790343,0.035233796,0.0003351192,0.20746313,0.7549851,0.0000099419885,0.000014335783,0.000034069843,0.0018764631],"genre_scores_gemma":[0.0014555921,0.02247862,0.000278862,0.060717944,0.9118381,0.000016903054,0.000009103482,0.000031958436,0.0031729732],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.97906154,0.005602366,0.0018329123,0.001499047,0.011169966,0.00083432114],"domain_scores_gemma":[0.8930484,0.066230625,0.0018936191,0.0018948384,0.028846364,0.008086274],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.020243045,0.0019432545,0.0024279023,0.004444521,0.0049329996,0.013459389,0.0032326302,0.018975133,0.0039020143],"category_scores_gemma":[0.0840837,0.00068274944,0.0015917495,0.0020395836,0.01107882,0.008714061,0.0036318467,0.037618592,0.0020353952],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001757738,0.000009316518,0.000049819606,0.00037645406,0.00001553536,0.00008469324,0.00019651095,0.00003534973,0.0000339194,0.004551497,0.9773547,0.01727462],"study_design_scores_gemma":[0.00001754713,0.000011463646,0.00022464225,0.0012908815,0.00001746704,0.00017463086,0.0001797061,0.0001165621,0.00003965996,0.0055441894,0.9923596,0.000023684483],"about_ca_topic_score_codex":0.016734429,"about_ca_topic_score_gemma":0.047958463,"teacher_disagreement_score":0.9895819,"about_ca_system_score_codex":0.010418123,"about_ca_system_score_gemma":0.01632892,"threshold_uncertainty_score":0.10705674},"labels":[],"label_agreement":null},{"id":"W4410358712","doi":"10.1080/29984475.2025.2501997","title":"Protocol for a Systematic Review of the Impact of Test Preparation Practices on L2 Test Performance and Language Proficiency","year":2025,"lang":"en","type":"review","venue":"Research Synthesis in Applied Linguistics","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université de Sherbrooke; Western University","funders":"","keywords":"Protocol (science); Test (biology); Computer science; Test preparation; Medicine; Engineering; Biology; Manufacturing engineering","score_opus":0.16362987987667385,"score_gpt":0.5843519821444451,"score_spread":0.4207221022677712,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410358712","genre_codex":"protocol","genre_gemma":"protocol","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"protocol","genre_consensus":"protocol","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00040494336,0.0036268525,0.00212315,0.0007536329,0.00045242862,0.982301,0.0094468575,0.00015804461,0.0007331147],"genre_scores_gemma":[0.00039907114,0.0011588783,0.0031616776,0.00030969863,0.000032575572,0.9938539,0.00069136295,0.000012112362,0.00038083232],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.9536134,0.017038876,0.0163952,0.0046771923,0.0061109173,0.002164351],"domain_scores_gemma":[0.92136186,0.032221455,0.017172966,0.008096447,0.018539235,0.0026080362],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.09061655,0.0054719704,0.017603036,0.019178146,0.0053664944,0.008061595,0.004894222,0.008256883,0.10155063],"category_scores_gemma":[0.12579934,0.0059429426,0.016790772,0.015404035,0.0055688503,0.009730819,0.006079882,0.008136522,0.01485805],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0027357906,0.00017229676,0.000584916,0.9252732,0.0023828845,0.00046457635,0.0019547786,0.00059333834,0.00096263323,0.006487171,0.030890064,0.027498445],"study_design_scores_gemma":[0.018650794,0.0010148402,0.004425565,0.74882215,0.010809183,0.00059156,0.002485159,0.00081343297,0.0016195927,0.01178848,0.19852963,0.00044973154],"about_ca_topic_score_codex":0.009015319,"about_ca_topic_score_gemma":0.020089967,"teacher_disagreement_score":0.10155063,"about_ca_system_score_codex":0.018005658,"about_ca_system_score_gemma":0.079171345,"threshold_uncertainty_score":0.47923183},"labels":[],"label_agreement":null},{"id":"W4410373832","doi":"10.53761/7jj6at39","title":"Online Student Peer-Assessment in Higher Education: A Systematic Review of the Literature","year":2025,"lang":"en","type":"review","venue":"Journal of University Teaching and Learning Practice","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Ontario Tech University","funders":"","keywords":"Peer evaluation; Higher education; Psychology; Multimethodology; Mathematics education; Pedagogy; Medical education; Medicine; Political science","score_opus":0.03655516409390172,"score_gpt":0.4290288710822172,"score_spread":0.3924737069883155,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410373832","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0007272417,0.99798214,0.0002533748,0.00025949054,0.00015069422,0.00030221173,0.00008902091,0.0000074525415,0.00022833687],"genre_scores_gemma":[0.01003676,0.98770195,0.0010646355,0.0003109191,0.00008118192,0.00059301057,0.00010061802,0.0000052664436,0.00010578077],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.98333514,0.0069409763,0.004888447,0.0010028202,0.003460341,0.00037229832],"domain_scores_gemma":[0.93312263,0.050130412,0.0067162556,0.0010520138,0.008138606,0.0008400497],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.020715835,0.0013496219,0.0049292864,0.015097269,0.0010809622,0.0027779366,0.0019456928,0.002085739,0.0027041733],"category_scores_gemma":[0.06895015,0.00095835933,0.0035564357,0.01628483,0.0012689215,0.003910737,0.0023341863,0.0014599361,0.00035318243],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010927787,0.000046668058,0.0006616354,0.8346216,0.0016297502,0.00011496607,0.0006114446,0.000105145635,0.00020405206,0.00039926657,0.0023260212,0.15917026],"study_design_scores_gemma":[0.00006622842,0.00019296259,0.0025873282,0.9499325,0.009016752,0.00037880283,0.00081246014,0.000085609725,0.00023727471,0.00037052596,0.036284193,0.000035324418],"about_ca_topic_score_codex":0.00743444,"about_ca_topic_score_gemma":0.025422197,"teacher_disagreement_score":0.97928417,"about_ca_system_score_codex":0.004223514,"about_ca_system_score_gemma":0.024826577,"threshold_uncertainty_score":0.10955709},"labels":[],"label_agreement":null},{"id":"W4410839902","doi":"10.1038/s41598-025-03753-7","title":"A phenomenographic study on Chinese EFL teachers’ cognitions of positive and negative educational, social, and psychological consequences of high-stake tests","year":2025,"lang":"en","type":"article","venue":"Scientific Reports","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Phenomenography; Psychology; Cognition; Social psychology; Developmental psychology; Clinical psychology; Mathematics education; Psychiatry","score_opus":0.05859291485390382,"score_gpt":0.4162507589408014,"score_spread":0.35765784408689755,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410839902","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9960204,0.0003763229,0.00076955726,0.00046764003,0.000022664362,0.00009766679,0.000060920105,0.000008061399,0.0021769328],"genre_scores_gemma":[0.9966286,0.00067593803,0.0005674649,0.00023531423,0.000016929655,0.00015165727,0.00006308175,0.000010932233,0.0016501222],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9976878,0.0011852892,0.00014599263,0.00022779916,0.00032219113,0.0004308825],"domain_scores_gemma":[0.9930902,0.004826597,0.00073950924,0.00028464192,0.0005694092,0.0004896003],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004088625,0.00072419154,0.00071790384,0.0019047845,0.008780225,0.0024436784,0.0007932278,0.0009685419,0.0019560596],"category_scores_gemma":[0.008070294,0.0004997563,0.00038590922,0.0022856232,0.006195908,0.0025834267,0.0026084983,0.0014401829,0.00025160145],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000020609246,0.000033051947,0.0059642405,0.00009801134,0.0000021845117,0.0008683895,0.9889875,0.000026189664,0.0007931673,0.00028983582,0.00023300979,0.002683748],"study_design_scores_gemma":[0.000002778847,0.000047876383,0.005883922,0.00007386422,0.000004376283,0.00026494308,0.9896011,0.00004729695,0.00023938557,0.00010250318,0.0037180283,0.000013907732],"about_ca_topic_score_codex":0.023907777,"about_ca_topic_score_gemma":0.038586237,"teacher_disagreement_score":0.023907777,"about_ca_system_score_codex":0.0058004195,"about_ca_system_score_gemma":0.0047998982,"threshold_uncertainty_score":0.047537267},"labels":[],"label_agreement":null},{"id":"W4410870169","doi":"10.1007/978-3-031-76485-1_44","title":"Teaching Within Social Justice and Diversity Frameworks: A (White) Teacher’s Approach","year":2025,"lang":"en","type":"book-chapter","venue":"Springer international handbooks of education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brandon University","funders":"","keywords":"Social justice; Diversity (politics); White (mutation); Sociology; Pedagogy; Economic Justice; Political science; Criminology; Anthropology; Biology; Law","score_opus":0.03255359092607509,"score_gpt":0.3448269454730962,"score_spread":0.31227335454702115,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410870169","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0115397535,0.014313077,0.063372724,0.21007629,0.004470925,0.00022678015,0.00004473494,0.00020292899,0.6957528],"genre_scores_gemma":[0.38518032,0.011518441,0.045271914,0.027976763,0.0016559416,0.00059848814,0.000045395846,0.00043995306,0.52731276],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9966767,0.0019722644,0.000085970685,0.00030979788,0.0006683286,0.00028691106],"domain_scores_gemma":[0.9965102,0.002043363,0.00012893387,0.00019526988,0.00061030564,0.0005118845],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0055205696,0.0005295345,0.00046262675,0.001666695,0.006966345,0.009295506,0.001402976,0.0040570265,0.006089522],"category_scores_gemma":[0.005132414,0.00036615017,0.0003780251,0.0011625328,0.017550629,0.008890385,0.006332776,0.0072392304,0.0011496065],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000013476318,0.000093418836,0.0003159945,0.00014378974,0.0000051160528,0.00013855346,0.03130763,0.00026368734,0.00024263514,0.8305114,0.061782826,0.075181454],"study_design_scores_gemma":[0.000011821837,0.00003709825,0.000758145,0.0005287461,0.000007432851,0.00023903292,0.023790844,0.0006337986,0.0004940437,0.3770481,0.59643173,0.000019201787],"about_ca_topic_score_codex":0.013879453,"about_ca_topic_score_gemma":0.03186338,"teacher_disagreement_score":0.013879453,"about_ca_system_score_codex":0.0061138645,"about_ca_system_score_gemma":0.010076522,"threshold_uncertainty_score":0.044359446},"labels":[],"label_agreement":null},{"id":"W4410967522","doi":"10.21083/ajote.v14i1.8038","title":"Teachers’ conceptualization of validity and reliability in classroom assessment in Ghana","year":2025,"lang":"en","type":"article","venue":"African Journal of Teacher Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Conceptualization; Psychology; Reliability (semiconductor); Validity; Test validity; Mathematics education; Construct validity; Psychometrics; Computer science; Developmental psychology; Artificial intelligence; Physics","score_opus":0.030491168946546555,"score_gpt":0.389104163268703,"score_spread":0.35861299432215643,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4410967522","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.87776244,0.011128118,0.043190606,0.017906047,0.00026920968,0.00063419255,0.00007999292,0.000113514965,0.04891581],"genre_scores_gemma":[0.9926742,0.00091665785,0.0056975666,0.00023950529,0.000020199192,0.00010349776,0.000013250618,0.000010869724,0.00032422622],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.95746297,0.028021855,0.003188429,0.0017186797,0.008163619,0.0014444253],"domain_scores_gemma":[0.9003653,0.06714836,0.011529586,0.0036365308,0.0155998655,0.0017203921],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.048953462,0.0002911396,0.000548645,0.0035442712,0.0017367913,0.0042091296,0.0009297388,0.0010249644,0.0007446599],"category_scores_gemma":[0.08597456,0.0006409663,0.00042470422,0.0022912626,0.012181681,0.003940901,0.0029898114,0.0016972619,0.00011879295],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00017536452,0.00025627445,0.32572192,0.0015496549,0.000121595585,0.0018337488,0.3984338,0.0023007253,0.004287696,0.08679127,0.0038195653,0.1747083],"study_design_scores_gemma":[0.00009894087,0.0006787198,0.48676848,0.0070904843,0.00014317279,0.0031461809,0.3316994,0.008939307,0.0031820452,0.08503645,0.07293285,0.00028400842],"about_ca_topic_score_codex":0.01267599,"about_ca_topic_score_gemma":0.008978497,"teacher_disagreement_score":0.048953462,"about_ca_system_score_codex":0.00615342,"about_ca_system_score_gemma":0.007480078,"threshold_uncertainty_score":0.25889373},"labels":[],"label_agreement":null},{"id":"W4411069075","doi":"10.1080/07294360.2025.2505136","title":"From emotion to action: investigating the role of affective rhetorical moves in peer feedback implementation in university classrooms","year":2025,"lang":"en","type":"article","venue":"Higher Education Research & Development","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"Nanyang Technological University","keywords":"Peer feedback; Rhetorical question; Action (physics); Psychology; Higher education; Peer evaluation; Social psychology; Mathematics education; Political science; Linguistics","score_opus":0.06444782108709217,"score_gpt":0.4504747937903455,"score_spread":0.3860269727032533,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411069075","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9975305,0.000061988765,0.00074093376,0.00010116305,0.000005318647,0.000025892074,0.0000041912967,0.000007770296,0.0015221905],"genre_scores_gemma":[0.9985819,0.00006430907,0.0008449533,0.000034597648,0.0000032259734,0.000026157575,0.0000055720157,0.000004720676,0.00043460986],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9923234,0.0051818364,0.00024131201,0.00043587043,0.0013977274,0.00041979877],"domain_scores_gemma":[0.98282963,0.011406524,0.002887979,0.00036080647,0.0014732688,0.0010418261],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0053020683,0.00035163987,0.00043240184,0.0010412,0.0011452017,0.0034980958,0.00068796263,0.00082412985,0.0010781073],"category_scores_gemma":[0.024494985,0.00029583354,0.00021188556,0.00037967018,0.0021576448,0.0012338214,0.0017702854,0.0012912485,0.00020633098],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00052984257,0.0016135547,0.18931761,0.0006288317,0.00007869167,0.00088812946,0.65028745,0.00057664927,0.03750631,0.0025837603,0.0004690813,0.11552008],"study_design_scores_gemma":[0.000051010502,0.0019317869,0.5047174,0.00036013615,0.00010416538,0.0006123996,0.46703207,0.00402113,0.012292896,0.002858344,0.005888573,0.00013011189],"about_ca_topic_score_codex":0.0010170082,"about_ca_topic_score_gemma":0.0018833249,"teacher_disagreement_score":0.0053020683,"about_ca_system_score_codex":0.0011285751,"about_ca_system_score_gemma":0.0014675179,"threshold_uncertainty_score":0.02804035},"labels":[],"label_agreement":null},{"id":"W4411166761","doi":"10.31542/869t8m43","title":"Greater Realism in Authentic Assessments Promotes Student Motivation and Engagement","year":2025,"lang":"en","type":"article","venue":"Pedagogical Inquiry and Practice","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"MacEwan University","funders":"","keywords":"Realism; Student engagement; Psychology; Mathematics education; Epistemology; Philosophy","score_opus":0.39954958497718773,"score_gpt":0.5491930691161431,"score_spread":0.14964348413895534,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411166761","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9888502,0.00003526065,0.00522851,0.00019340756,0.000011350305,0.00013333997,0.000014927621,0.000071575414,0.0054615135],"genre_scores_gemma":[0.99220616,0.00004493119,0.006343142,0.000046350604,0.000010878907,0.0001286249,0.000029583614,0.000017072034,0.0011731905],"study_design_codex":"observational","study_design_gemma":"not_applicable","domain_scores_codex":[0.99327976,0.0036052768,0.00030246942,0.00049959286,0.0019868452,0.00032605548],"domain_scores_gemma":[0.9821712,0.008100787,0.003647738,0.0013522625,0.0020999261,0.0026281942],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0054572243,0.00033615404,0.0004312708,0.00059679843,0.00069929386,0.0029429651,0.0004286628,0.0007066931,0.0034192607],"category_scores_gemma":[0.028901793,0.00028530596,0.00047577088,0.00026440897,0.0007280639,0.0007624221,0.002941642,0.0010444989,0.00054664834],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010816649,0.012171454,0.5100401,0.0008769963,0.00024638357,0.00064737606,0.05331949,0.0031357529,0.10928884,0.0042892043,0.0033014303,0.3016014],"study_design_scores_gemma":[0.00018873207,0.008956603,0.9105528,0.00030990588,0.0001233653,0.0010110692,0.013486118,0.006955767,0.02525872,0.0077000917,0.025246205,0.00021054785],"about_ca_topic_score_codex":0.00019926671,"about_ca_topic_score_gemma":0.0004274383,"teacher_disagreement_score":0.0054572243,"about_ca_system_score_codex":0.0004668,"about_ca_system_score_gemma":0.00076149526,"threshold_uncertainty_score":0.028860867},"labels":[],"label_agreement":null},{"id":"W4411260555","doi":"10.1016/j.ijedudev.2025.103336","title":"Understanding the diverse ways teachers approach classroom assessment in an examination-oriented educational system","year":2025,"lang":"en","type":"article","venue":"International Journal of Educational Development","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University; Queen's University; York University","funders":"","keywords":"Mathematics education; Psychology; Pedagogy; Computer science; Sociology","score_opus":0.08503189697839836,"score_gpt":0.38751702237792957,"score_spread":0.3024851253995312,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411260555","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9908698,0.00038298094,0.002896414,0.0012424147,0.0000133047415,0.000023719353,0.000010955126,0.000010192338,0.004550024],"genre_scores_gemma":[0.99780756,0.0002721167,0.0013660943,0.00013173507,0.0000032326552,0.000015145783,0.000007845189,0.0000048354013,0.00039143136],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9854328,0.009797049,0.00076293526,0.0007852071,0.0020994742,0.0011225294],"domain_scores_gemma":[0.98458797,0.007904043,0.0031889435,0.0007646468,0.0022487855,0.0013056294],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010497751,0.00019079134,0.00026507102,0.0017203587,0.0027632785,0.0065209293,0.0006790348,0.00061556516,0.0005581524],"category_scores_gemma":[0.027675033,0.0003435436,0.00018226978,0.0012317002,0.00405858,0.00463882,0.0041394033,0.0011894249,0.00012556971],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000052391493,0.000076384036,0.24474388,0.00009963078,0.000021588381,0.00030605117,0.7062713,0.00017970454,0.0023770705,0.003481888,0.00037512908,0.04201503],"study_design_scores_gemma":[0.000015020274,0.00011681864,0.19479132,0.00033169874,0.000021034626,0.0005464098,0.78412044,0.0006607241,0.0010774197,0.0033228335,0.014954313,0.000042025364],"about_ca_topic_score_codex":0.014495839,"about_ca_topic_score_gemma":0.03569554,"teacher_disagreement_score":0.014495839,"about_ca_system_score_codex":0.003822925,"about_ca_system_score_gemma":0.0056432732,"threshold_uncertainty_score":0.05551809},"labels":[],"label_agreement":null},{"id":"W4411307838","doi":"10.1080/20004508.2025.2519831","title":"Do students perceive assessment differently? Exploring the diverse ways students conceive assessment and its impact on their assessment experiences and engagement","year":2025,"lang":"en","type":"article","venue":"Education Inquiry","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Psychology; Pedagogy; Mathematics education","score_opus":0.1503994172707718,"score_gpt":0.4960694933686223,"score_spread":0.3456700760978505,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411307838","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9975829,0.000110621964,0.00040184893,0.00047522323,0.0000074177574,0.000006524608,0.000007929796,0.000004405257,0.0014031887],"genre_scores_gemma":[0.9994816,0.00007760694,0.0001318401,0.00007135238,0.0000019247657,0.0000045064658,0.0000063886487,0.0000016645691,0.000223142],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99454063,0.0031373703,0.00027031108,0.0002705752,0.0012725249,0.00050867005],"domain_scores_gemma":[0.98686093,0.006536613,0.0028279806,0.0004934125,0.0014288214,0.0018522539],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0061178934,0.0002533406,0.00052571634,0.0009482454,0.0014087785,0.006434388,0.000508813,0.0007545944,0.0013142187],"category_scores_gemma":[0.023214608,0.00030522756,0.0004113133,0.0008150794,0.0033034037,0.002677925,0.0027900776,0.0018813012,0.00022314429],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000090791866,0.0002036804,0.44120878,0.000087251006,0.00003754301,0.00033359346,0.5265291,0.00013287427,0.0020772645,0.0016252141,0.00042637723,0.027247583],"study_design_scores_gemma":[0.0000129171185,0.0002913033,0.23439576,0.00013590923,0.00003049115,0.00040270874,0.7555664,0.000478604,0.000802059,0.0019676515,0.0058442573,0.00007194443],"about_ca_topic_score_codex":0.004499984,"about_ca_topic_score_gemma":0.0076916097,"teacher_disagreement_score":0.006434388,"about_ca_system_score_codex":0.0013786952,"about_ca_system_score_gemma":0.0015868201,"threshold_uncertainty_score":0.03235489},"labels":[],"label_agreement":null},{"id":"W4411445047","doi":"10.7202/1118375ar","title":"Analysis of the Emotions and Emotional Skills of University Students in Processing Distance Formative Feedback","year":2023,"lang":"en","type":"article","venue":"Mesure et évaluation en éducation","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Formative assessment; Psychology; Affect (linguistics); Social psychology; Applied psychology; Mathematics education; Communication","score_opus":0.03795279578834834,"score_gpt":0.3911984893591588,"score_spread":0.3532456935708105,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411445047","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99938154,0.00002074141,0.00016630681,0.0000164826,0.0000020305088,0.000005494202,0.000006469444,0.0000023787707,0.00039844972],"genre_scores_gemma":[0.99937975,0.00003072541,0.00014148725,0.000014037085,0.0000028079419,0.000009256523,0.00001362761,0.0000012639667,0.00040700383],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9989593,0.0003857504,0.00005614838,0.000065110406,0.00035956406,0.00017426809],"domain_scores_gemma":[0.9963354,0.0014641499,0.00073568005,0.00013484452,0.000809685,0.00052021886],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013336106,0.00027456958,0.00036758743,0.0005166417,0.00029667324,0.0010224759,0.00015343726,0.0003385791,0.0014964397],"category_scores_gemma":[0.0075333784,0.00008720845,0.0002765291,0.00026941646,0.000346703,0.0002081316,0.0004571745,0.0005976631,0.00036021814],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011912092,0.0028804,0.73673517,0.000226878,0.00013945033,0.000635644,0.03732288,0.0006195358,0.08255685,0.00026682712,0.00056941685,0.13685581],"study_design_scores_gemma":[0.000015897607,0.0012984223,0.9731207,0.000026283062,0.000037274698,0.0003475665,0.014265746,0.0008006469,0.008856599,0.00012420467,0.0010806688,0.000026015927],"about_ca_topic_score_codex":0.00047367412,"about_ca_topic_score_gemma":0.00049357885,"teacher_disagreement_score":0.0014964397,"about_ca_system_score_codex":0.00025620885,"about_ca_system_score_gemma":0.00023472545,"threshold_uncertainty_score":0.0070528984},"labels":[],"label_agreement":null},{"id":"W4411475719","doi":"10.25071/1916-4467.40814","title":"A Call for Change in Summative Assessment: Ideas Generated by Students During the COVID-19 Pandemic","year":2025,"lang":"en","type":"article","venue":"Journal of the Canadian Association for Curriculum Studies","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Acadia University; St. Francis Xavier University","funders":"","keywords":"Summative assessment; Agency (philosophy); Coronavirus disease 2019 (COVID-19); Curriculum; Pandemic; Medical education; Psychology; Formative assessment; Mathematics education; Pedagogy; Sociology; Medicine; Social science; Internal medicine","score_opus":0.061140568603317354,"score_gpt":0.4328354853042999,"score_spread":0.37169491670098254,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411475719","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.08274977,0.0032084496,0.0034021654,0.89869916,0.0042556725,0.00013294228,0.00003834365,0.000095872056,0.0074176085],"genre_scores_gemma":[0.86272055,0.0038264042,0.009680904,0.115746215,0.0017790751,0.0002701786,0.00004656691,0.00020456406,0.005725551],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.86407727,0.09464521,0.004019332,0.0046250075,0.019749219,0.012883972],"domain_scores_gemma":[0.8502833,0.07568799,0.0055443733,0.004754411,0.034358677,0.029371245],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.15122882,0.0009968783,0.001200113,0.002034847,0.029394051,0.030378785,0.0064872303,0.021093702,0.0018513446],"category_scores_gemma":[0.1653146,0.0013254579,0.0014357475,0.0014450771,0.039948814,0.014269922,0.016400808,0.043332003,0.00051942345],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000092071496,0.0001565172,0.005254172,0.00022866936,0.000032844353,0.0012580637,0.907541,0.0002591213,0.0007262262,0.010436755,0.03574591,0.03826872],"study_design_scores_gemma":[0.00002736017,0.00017365253,0.002864673,0.00084292097,0.000021751359,0.00068590126,0.81847084,0.00049681903,0.0006532219,0.00892305,0.1666627,0.00017715202],"about_ca_topic_score_codex":0.05237898,"about_ca_topic_score_gemma":0.09205571,"teacher_disagreement_score":0.94762105,"about_ca_system_score_codex":0.038032196,"about_ca_system_score_gemma":0.05400975,"threshold_uncertainty_score":0.79978395},"labels":[],"label_agreement":null},{"id":"W4411475738","doi":"10.25071/1916-4467.40823","title":"High-Stakes Tests and Applied Learners: The (Dis)connections Between Curriculum Expectations and Exam Notions of “Literacy”","year":2025,"lang":"en","type":"article","venue":"Journal of the Canadian Association for Curriculum Studies","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":true,"ca_institutions":"Queen's University","funders":"","keywords":"Curriculum; Literacy; Test (biology); Mathematics education; Pedagogy; Psychology; Thematic analysis; Sociology; Qualitative research","score_opus":0.023528646522270817,"score_gpt":0.3394058327517759,"score_spread":0.31587718622950506,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411475738","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9856852,0.00032508056,0.00033601743,0.0036576532,0.000014691419,0.000009416489,0.00004128657,0.000006547715,0.009924078],"genre_scores_gemma":[0.9994123,0.00007351457,0.000047710644,0.00013192731,0.0000026322286,0.0000036133727,0.000014992503,0.0000020754164,0.00031127364],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.99104404,0.0025745737,0.00049788255,0.00036525857,0.0046247425,0.00089346],"domain_scores_gemma":[0.96715194,0.015366324,0.0072653973,0.00073990104,0.0054349243,0.0040413975],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0076674414,0.00012674199,0.00021574569,0.0010350286,0.0016074292,0.0037086462,0.0006733291,0.000700621,0.0017916688],"category_scores_gemma":[0.052818947,0.00017025931,0.00016004907,0.0010687822,0.0049993424,0.002193952,0.0025264123,0.0016583352,0.0001902237],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006948177,0.000113477436,0.8061965,0.00013094473,0.00002093979,0.0004935107,0.15281494,0.000092721864,0.00058911304,0.0040553566,0.0013845148,0.034038424],"study_design_scores_gemma":[0.0000033810554,0.00008037507,0.8689923,0.00018199308,0.000007972172,0.00022899981,0.12318861,0.00018116673,0.00035978452,0.0019158383,0.0048319674,0.000027494092],"about_ca_topic_score_codex":0.22919716,"about_ca_topic_score_gemma":0.24950008,"teacher_disagreement_score":0.77080286,"about_ca_system_score_codex":0.0069457847,"about_ca_system_score_gemma":0.009995868,"threshold_uncertainty_score":0.45572615},"labels":[],"label_agreement":null},{"id":"W4411565602","doi":"10.1007/s11409-025-09430-4","title":"How do students self-assess? examining the metacognitive processes of student self-assessment","year":2025,"lang":"en","type":"article","venue":"Metacognition and Learning","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Metacognition; Psychology; Self-assessment; Self-concept; Developmental psychology; Self-control; Self-regulated learning; Self evaluation; Academic achievement; Cognition; Social psychology; Applied psychology","score_opus":0.04062015942691434,"score_gpt":0.37832243636529805,"score_spread":0.3377022769383837,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411565602","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9956625,0.0002148259,0.0014770696,0.00015219553,0.000010439572,0.000025580577,0.000021242668,0.000029832432,0.0024062365],"genre_scores_gemma":[0.99813616,0.00014413432,0.0011982127,0.00002700832,0.0000033123758,0.000022251508,0.000021011165,0.0000056764866,0.000442108],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.9954196,0.0022456204,0.00028965413,0.00043455043,0.001419832,0.00019074461],"domain_scores_gemma":[0.92877054,0.0451152,0.013097593,0.004060885,0.0068943915,0.0020613652],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0073559973,0.00033959062,0.0004523072,0.0010949653,0.00038490345,0.0040633357,0.0006162631,0.00074887497,0.0007351016],"category_scores_gemma":[0.08705341,0.0002920573,0.00034060612,0.00064006436,0.0006059567,0.0023549485,0.0013119553,0.0012015881,0.00033205934],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00041999717,0.0017569079,0.74072325,0.00018306727,0.00027561586,0.00006530826,0.017212624,0.0014056655,0.0051535,0.001118602,0.0006839918,0.23100148],"study_design_scores_gemma":[0.000063358566,0.0015322776,0.95739794,0.00021603168,0.00021294424,0.0002899031,0.010349929,0.011161877,0.011591819,0.0041661593,0.002887188,0.00013059023],"about_ca_topic_score_codex":0.0015018558,"about_ca_topic_score_gemma":0.0024431974,"teacher_disagreement_score":0.0073559973,"about_ca_system_score_codex":0.0005292406,"about_ca_system_score_gemma":0.0014239745,"threshold_uncertainty_score":0.0389027},"labels":[],"label_agreement":null},{"id":"W4411702131","doi":"10.1080/02602938.2025.2524095","title":"The role of digital technology in authentic assessment: perspectives of university educators","year":2025,"lang":"en","type":"article","venue":"Assessment & Evaluation in Higher Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Northern British Columbia","funders":"","keywords":"Higher education; Pedagogy; Technology integration; Psychology; Technological literacy; Mathematics education; Educational technology; Sociology; Engineering ethics; Medical education; Engineering; Political science; Medicine","score_opus":0.020031202184941713,"score_gpt":0.4013315858594782,"score_spread":0.3813003836745365,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411702131","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.91127145,0.0077444133,0.010075312,0.02673563,0.00034734773,0.0001074624,0.000026651498,0.00004379497,0.043647867],"genre_scores_gemma":[0.9932853,0.0018263726,0.0012280397,0.0012827864,0.000049316997,0.000030046274,0.000004838353,0.000010965965,0.0022824171],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9656659,0.027714988,0.0008829993,0.000875936,0.0023070746,0.0025532115],"domain_scores_gemma":[0.95299566,0.03411937,0.0023284995,0.0009658586,0.003804883,0.005785703],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02645272,0.00048334477,0.0006675501,0.0021964011,0.011489417,0.020198837,0.0011659025,0.0039478983,0.0012600998],"category_scores_gemma":[0.03372413,0.0005143689,0.0004286808,0.0014719934,0.016056042,0.008846351,0.012285396,0.005918291,0.00028776567],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00002576454,0.000080686266,0.007813605,0.00014876637,0.000005121592,0.0010608933,0.96298635,0.0000827109,0.000498443,0.009657978,0.00067217747,0.016967518],"study_design_scores_gemma":[0.000005892037,0.00009293945,0.0017845465,0.0004196021,0.000008653542,0.0009929278,0.9475718,0.00020816209,0.00055349193,0.0024496738,0.045884654,0.000027603324],"about_ca_topic_score_codex":0.00377152,"about_ca_topic_score_gemma":0.00476285,"teacher_disagreement_score":0.02645272,"about_ca_system_score_codex":0.0048051123,"about_ca_system_score_gemma":0.0064921035,"threshold_uncertainty_score":0.13989705},"labels":[],"label_agreement":null},{"id":"W4412395771","doi":"10.1007/978-981-96-5658-5_6","title":"Formative Assessment in DGBL: A Qualitative Analysis of Players’ Perceptions of Game-Based Feedback in Complex Scenarios","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in educational technology","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Chicoutimi","funders":"","keywords":"Formative assessment; Qualitative analysis; Perception; Psychology; Game based learning; Computer science; Qualitative research; Mathematics education; Sociology; Neuroscience","score_opus":0.036582402176650375,"score_gpt":0.4207477439321418,"score_spread":0.38416534175549144,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412395771","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9384657,0.00019910124,0.037994366,0.0005104502,0.000047455545,0.0015084061,0.00072742446,0.00015569261,0.020391481],"genre_scores_gemma":[0.9662743,0.0001678197,0.023511166,0.00023190722,0.0000103394505,0.0020149075,0.00037758297,0.000093166505,0.007318775],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9900889,0.0073688584,0.00032806673,0.0005308731,0.0012331064,0.0004501772],"domain_scores_gemma":[0.9602965,0.03280542,0.00138052,0.000903992,0.0036061807,0.0010073493],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011719925,0.0006027464,0.00040089744,0.0018079387,0.0017026959,0.0032993914,0.0013482376,0.0008208057,0.0038187618],"category_scores_gemma":[0.035013337,0.00033414032,0.00028362987,0.0014610828,0.0023421706,0.0023989982,0.0028460233,0.0014625333,0.00073070073],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003442498,0.00078808353,0.023660466,0.00092706253,0.000019252326,0.0005048604,0.84492654,0.0007697898,0.018495787,0.004142849,0.0018793492,0.103541635],"study_design_scores_gemma":[0.00009695901,0.0016446075,0.09734249,0.001800782,0.000057100624,0.0013372835,0.79445076,0.0059506767,0.02395561,0.0077505023,0.06539278,0.00022049686],"about_ca_topic_score_codex":0.0025036465,"about_ca_topic_score_gemma":0.004420017,"teacher_disagreement_score":0.011719925,"about_ca_system_score_codex":0.002777378,"about_ca_system_score_gemma":0.0022775496,"threshold_uncertainty_score":0.06198162},"labels":[],"label_agreement":null},{"id":"W4412676320","doi":"10.1177/02655322251359320","title":"Book review: Innovation in Learning-Oriented Language Assessment ChongS.ReindersH. (Eds.), Innovation in Learning-Oriented Language Assessment. Palgrave MacMillan, 2023. 333 pp. ISBN 978-3-031-18949-4 (hbk) US$169.99 ISBN 978-3-031-18952-4 (sbk) US$169.99 ISBN 978-3-031-18950-0 (ebk) US$129.99","year":2025,"lang":"en","type":"article","venue":"Language Testing","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Psychology; Linguistics; Sociology; Philosophy","score_opus":0.01741045735498279,"score_gpt":0.3375408814479155,"score_spread":0.3201304240929327,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4412676320","genre_codex":"review","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00006622175,0.9838356,0.0002952583,0.0036199428,0.0075360187,0.000031980144,0.00019731474,0.00005194247,0.0043657036],"genre_scores_gemma":[0.00064457924,0.97168916,0.0006175718,0.0019090376,0.0055541038,0.000091289825,0.0005186516,0.000034751934,0.018940846],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982389,0.00032029327,0.00023347029,0.00019186783,0.0009092348,0.00010611957],"domain_scores_gemma":[0.9929946,0.0032817854,0.0007981328,0.00012895395,0.002269938,0.0005265838],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00172693,0.0017989974,0.003506903,0.005709479,0.00048559517,0.0034287795,0.0022676026,0.0024246085,0.04336648],"category_scores_gemma":[0.008051196,0.0007211311,0.0012721367,0.00860929,0.0007939931,0.0030540193,0.0012655889,0.0031800687,0.031967796],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003516505,0.000023187751,0.0000764033,0.006506568,0.000043154538,0.000047672234,0.00004563451,0.00011384949,0.00012922793,0.0006548604,0.74475175,0.24757248],"study_design_scores_gemma":[0.000020032348,0.000038843056,0.0006147796,0.0060786386,0.000058008383,0.000539795,0.000045551365,0.00005722386,0.000068397,0.0007622139,0.9916985,0.000018099652],"about_ca_topic_score_codex":0.0059187147,"about_ca_topic_score_gemma":0.013530799,"teacher_disagreement_score":0.04336648,"about_ca_system_score_codex":0.0018297344,"about_ca_system_score_gemma":0.00431752,"threshold_uncertainty_score":0.14507538},"labels":[],"label_agreement":null},{"id":"W4413200584","doi":"10.3102/ip.25.2185450","title":"Student-Generated Questions and Goal Orientation in Literacy Assessment","year":2025,"lang":"en","type":"article","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Goal orientation; Orientation (vector space); Computer science; Literacy; Psychology; Human–computer interaction; Pedagogy; Social psychology","score_opus":0.01566195994059493,"score_gpt":0.4307261578120048,"score_spread":0.41506419787140986,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413200584","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9551914,0.00018377407,0.025258793,0.00037926552,0.000052263193,0.00030538466,0.0001848246,0.00025115826,0.018193264],"genre_scores_gemma":[0.98627275,0.0000578011,0.011517551,0.00005723916,0.000009287923,0.00018669458,0.00013786543,0.000043283922,0.0017173854],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9858797,0.0103673125,0.0006327151,0.0004872152,0.0023108153,0.0003222488],"domain_scores_gemma":[0.8891512,0.093185104,0.0047547733,0.0020454961,0.008228646,0.0026348608],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01075876,0.00036397937,0.00039610252,0.0015062467,0.00032957536,0.002375122,0.00049121195,0.0008696943,0.0031615202],"category_scores_gemma":[0.10387661,0.00022576738,0.0003720151,0.0006525254,0.00052448513,0.0018679661,0.0017000191,0.0011105404,0.0005933232],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0031022432,0.00424565,0.45316926,0.00044853197,0.00016312998,0.0003074503,0.015677352,0.0063927053,0.0062735863,0.010102057,0.0041573304,0.49596083],"study_design_scores_gemma":[0.00057089154,0.005137772,0.8680995,0.00063219806,0.00031785233,0.00061476766,0.011258977,0.057983864,0.016658194,0.026343675,0.012152809,0.00022946506],"about_ca_topic_score_codex":0.0020765776,"about_ca_topic_score_gemma":0.0031059536,"teacher_disagreement_score":0.01075876,"about_ca_system_score_codex":0.00091862807,"about_ca_system_score_gemma":0.0011722059,"threshold_uncertainty_score":0.056898415},"labels":[],"label_agreement":null},{"id":"W4413228388","doi":"10.5430/wjel.v15n8p162","title":"Functions and Focus of Supervisory Feedback on Undergraduate Students’ Theses Writing","year":2025,"lang":"en","type":"article","venue":"World Journal of English Language","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Supervisor; Directive; Focus (optics); Computer science; Process (computing); Peer feedback; Academic writing; Writing process; Focus group; Mathematics education; Psychology; Pedagogy; Management; Sociology","score_opus":0.02137497802591898,"score_gpt":0.3232372813041563,"score_spread":0.3018623032782373,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413228388","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9934855,0.0003279263,0.0024952327,0.0001358015,0.000018055065,0.00004938413,0.00002758083,0.00007761623,0.0033828628],"genre_scores_gemma":[0.9976908,0.00017746771,0.0015058969,0.00002961292,0.000012796235,0.00004051708,0.000030739342,0.000013068295,0.00049907016],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9896611,0.00603272,0.00067079725,0.00048621313,0.0028446768,0.0003044692],"domain_scores_gemma":[0.9014192,0.064466596,0.0135338,0.0030454537,0.014886911,0.0026479478],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008811134,0.00037968415,0.00042043132,0.0017878396,0.0008415446,0.0016094361,0.0005395437,0.00044499585,0.0012669837],"category_scores_gemma":[0.06906984,0.00023706793,0.00030158347,0.00068405725,0.0008972688,0.00074884784,0.0012182014,0.0005086176,0.00036607025],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000888649,0.00054439495,0.3052671,0.0007207155,0.00008862112,0.000617959,0.1719236,0.00053602486,0.025062243,0.00041103648,0.0011373259,0.49280235],"study_design_scores_gemma":[0.00005720278,0.0016165144,0.9083054,0.0004918929,0.000082133854,0.0009676386,0.06913237,0.0018899976,0.010026547,0.0006270475,0.0066882605,0.000115061484],"about_ca_topic_score_codex":0.00074475957,"about_ca_topic_score_gemma":0.0010725949,"teacher_disagreement_score":0.008811134,"about_ca_system_score_codex":0.0006054083,"about_ca_system_score_gemma":0.0012568933,"threshold_uncertainty_score":0.046598256},"labels":[],"label_agreement":null},{"id":"W4413563369","doi":"10.64628/aam.53avwyrpv","title":"STEM learning should engage students’ minds, hands and hearts","year":2020,"lang":"en","type":"preprint","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Brock University","funders":"","keywords":"Psychology; Mathematics education","score_opus":0.14451897737884709,"score_gpt":0.40942119993424797,"score_spread":0.26490222255540086,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413563369","genre_codex":"empirical","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.40488225,0.0008066204,0.26983437,0.026465533,0.0012077179,0.001072333,0.0002717434,0.0019987118,0.29346076],"genre_scores_gemma":[0.8765518,0.00039720087,0.10185961,0.0016927918,0.00021089034,0.00037888688,0.00016332533,0.00015369794,0.018591793],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9957956,0.0019210052,0.00012692717,0.0002923073,0.0014884631,0.00037569244],"domain_scores_gemma":[0.98489016,0.005613688,0.0009932818,0.0011580435,0.0039407434,0.0034039826],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007555389,0.0006639573,0.00039249277,0.0006830563,0.0009361605,0.0042112605,0.00053650414,0.0015639054,0.0079594],"category_scores_gemma":[0.03047747,0.00017626934,0.0002760968,0.00041050324,0.0010352678,0.0032985215,0.0030477508,0.001348158,0.0030351891],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003960168,0.0024701532,0.03534485,0.0006165715,0.00006501436,0.00017084545,0.009952582,0.002427089,0.03011342,0.042692725,0.021925949,0.85382473],"study_design_scores_gemma":[0.00028168573,0.002549305,0.13681565,0.0013645414,0.00013010645,0.000592834,0.023220798,0.019048557,0.062246837,0.497602,0.25593373,0.00021406746],"about_ca_topic_score_codex":0.0006865001,"about_ca_topic_score_gemma":0.0016847621,"teacher_disagreement_score":0.0079594,"about_ca_system_score_codex":0.00075297133,"about_ca_system_score_gemma":0.0030528752,"threshold_uncertainty_score":0.039957225},"labels":[],"label_agreement":null},{"id":"W4413589329","doi":"10.64628/aam.vjwdv7phn","title":"Why Ontario’s ‘Right to Read Inquiry’ needs to broaden its recommendations","year":2022,"lang":"en","type":"preprint","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Toronto; University of Windsor","funders":"","keywords":"Political science; Psychology; Sociology","score_opus":0.09904579181292285,"score_gpt":0.40561022692810267,"score_spread":0.30656443511517983,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413589329","genre_codex":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0014031545,0.00071792904,0.00066277635,0.9672372,0.0045945663,0.00004421101,0.00025694314,0.00012143814,0.024961838],"genre_scores_gemma":[0.064906165,0.0017012511,0.008239118,0.7628866,0.004746597,0.00025553556,0.00048143536,0.0005681379,0.15621513],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.92397773,0.011256013,0.0048309765,0.0051574884,0.04084508,0.013932858],"domain_scores_gemma":[0.7374115,0.06522959,0.004665584,0.011679138,0.12771726,0.05329685],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03552384,0.00067790033,0.0016436715,0.003647782,0.025005244,0.023657445,0.0063339793,0.042275235,0.027288537],"category_scores_gemma":[0.15001883,0.0014229261,0.0018462568,0.004287367,0.022433162,0.012569528,0.0105252275,0.03352559,0.006856598],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":true,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000050271625,0.000048114525,0.0019248932,0.00017215233,0.000026670301,0.00011048926,0.0031800594,0.00015483318,0.00023123865,0.046450913,0.932553,0.015097383],"study_design_scores_gemma":[0.000053313477,0.000018918463,0.0044307415,0.00041527173,0.000041092888,0.000037423102,0.0029723863,0.00021602998,0.00028623635,0.0135242855,0.97786474,0.0001395356],"about_ca_topic_score_codex":0.9554918,"about_ca_topic_score_gemma":0.9720578,"teacher_disagreement_score":0.9190992,"about_ca_system_score_codex":0.08090082,"about_ca_system_score_gemma":0.33999294,"threshold_uncertainty_score":0.58697927},"labels":[],"label_agreement":null},{"id":"W4413846339","doi":"10.1080/09575146.2025.2552415","title":"Challenges, struggles and needs in assessment: voices of early childhood teachers","year":2025,"lang":"en","type":"article","venue":"Early Years Journal of International Research and Development","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Education and Early Childhood Development","funders":"","keywords":"Early childhood; Psychology; Pedagogy; Sociology; Political science; Developmental psychology","score_opus":0.06789655495680331,"score_gpt":0.4245258210491768,"score_spread":0.3566292660923735,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413846339","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9789914,0.0024200948,0.0030217364,0.008605958,0.00011123414,0.00004506098,0.00002470636,0.000033236753,0.006746615],"genre_scores_gemma":[0.9955983,0.0010933938,0.0008678864,0.00040638942,0.000015241571,0.000041942258,0.000009148707,0.000019229226,0.0019484714],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.98277426,0.0105923815,0.00091461674,0.0009331684,0.002410593,0.0023750416],"domain_scores_gemma":[0.9736472,0.017895713,0.0023916608,0.00080663344,0.0025754364,0.0026833243],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.016169295,0.0005423899,0.0012852185,0.0015061378,0.011994968,0.012877009,0.0016909369,0.0036466157,0.001107378],"category_scores_gemma":[0.036699813,0.0010853006,0.000421372,0.0016455834,0.015831158,0.0076403324,0.010471956,0.006841555,0.00032098393],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011975469,0.000015003523,0.002619921,0.00005077001,0.0000019937218,0.0008900503,0.9911596,0.000024297284,0.0003553224,0.0008185316,0.00018780543,0.0038647503],"study_design_scores_gemma":[0.0000015281346,0.000015572381,0.0009953743,0.00007576837,0.0000024254084,0.00078795425,0.99221754,0.000035204997,0.00014820049,0.00047929777,0.005228586,0.0000126184295],"about_ca_topic_score_codex":0.011437198,"about_ca_topic_score_gemma":0.017571343,"teacher_disagreement_score":0.016169295,"about_ca_system_score_codex":0.005136939,"about_ca_system_score_gemma":0.00760903,"threshold_uncertainty_score":0.0855124},"labels":[],"label_agreement":null},{"id":"W4413927455","doi":"10.7870/cjcmh-2025-006","title":"Asynchronous Innovation to Support Well-being Through Mindfulness and Feedback Literacy in Higher Education","year":2025,"lang":"en","type":"article","venue":"Canadian Journal of Community Mental Health","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Western University","funders":"","keywords":"Mindfulness; Asynchronous communication; Literacy; Psychology; Computer science; Psychotherapist; Pedagogy","score_opus":0.042513688755462554,"score_gpt":0.40101260230982544,"score_spread":0.35849891355436286,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413927455","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.61203605,0.0022776606,0.22322264,0.01841437,0.0064761923,0.0036813624,0.0009981003,0.012197239,0.12069637],"genre_scores_gemma":[0.7926616,0.0010928024,0.15319794,0.0030348143,0.0017597482,0.0018483291,0.0005162462,0.00040242195,0.04548609],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.99764866,0.0011610128,0.00008021592,0.0001941341,0.0006882711,0.0002278467],"domain_scores_gemma":[0.9923908,0.0045583798,0.0003611041,0.000593795,0.0006086276,0.0014873529],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0036067446,0.0002827276,0.00016293561,0.000517707,0.0006343053,0.0010555062,0.000984998,0.0007375263,0.010959179],"category_scores_gemma":[0.012142981,0.00011662037,0.0003669051,0.00026159032,0.00040671322,0.00097589986,0.00224077,0.0011518926,0.0020819274],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00043134514,0.0044628982,0.0037649279,0.00045854528,0.000026468007,0.00013303527,0.002509429,0.0004371228,0.006532669,0.0018040305,0.034662753,0.9447768],"study_design_scores_gemma":[0.0034484137,0.020810915,0.14342213,0.0037356769,0.00044242982,0.0022208816,0.006848284,0.026797686,0.05319059,0.03198277,0.7066448,0.00045539357],"about_ca_topic_score_codex":0.00047115932,"about_ca_topic_score_gemma":0.0012769866,"teacher_disagreement_score":0.9995288,"about_ca_system_score_codex":0.00040042875,"about_ca_system_score_gemma":0.0013223629,"threshold_uncertainty_score":0.0366621},"labels":[],"label_agreement":null},{"id":"W4413982879","doi":"10.3390/higheredu4030048","title":"Learning with Peers in Higher Education: Exploring Strengths and Weaknesses of Formative Assessment","year":2025,"lang":"en","type":"article","venue":"Trends in Higher Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Thomas University","funders":"Università degli Studi di Genova","keywords":"Formative assessment; Strengths and weaknesses; Peer assessment; Psychology; Assessment for learning; Mathematics education; Higher education; Pedagogy; Peer evaluation; Political science; Social psychology","score_opus":0.05943047214718355,"score_gpt":0.4132873053782435,"score_spread":0.35385683323105993,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4413982879","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9591927,0.0033045972,0.022217516,0.0023754057,0.00017114253,0.00066720776,0.0000657116,0.00008656084,0.011919144],"genre_scores_gemma":[0.9831685,0.0010409274,0.01445447,0.00016967548,0.000063865766,0.0003255798,0.000036192272,0.00001847942,0.000722307],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.8924839,0.07482471,0.0046326225,0.0029833228,0.023943884,0.0011314851],"domain_scores_gemma":[0.7861522,0.16784215,0.012101897,0.007738636,0.02392577,0.0022393828],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.12588486,0.00059999776,0.00078324316,0.0041398653,0.0013897695,0.005924188,0.0022768485,0.00092199165,0.00080927147],"category_scores_gemma":[0.23143771,0.00032751026,0.0006108918,0.0025418326,0.0019338239,0.007520412,0.0037181124,0.0011381741,0.00018473524],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003359775,0.0007674169,0.17007469,0.0011157854,0.00027052584,0.000073430194,0.06315586,0.00065800274,0.0010673881,0.0031327973,0.00049016246,0.75885797],"study_design_scores_gemma":[0.00022308099,0.008130636,0.7298808,0.0071235183,0.0008314658,0.0009567434,0.17316274,0.021509737,0.011812691,0.019537408,0.026403701,0.00042743026],"about_ca_topic_score_codex":0.0035566303,"about_ca_topic_score_gemma":0.00785625,"teacher_disagreement_score":0.12588486,"about_ca_system_score_codex":0.0026963572,"about_ca_system_score_gemma":0.0042522987,"threshold_uncertainty_score":0.66575074},"labels":[],"label_agreement":null},{"id":"W4414298304","doi":"10.1002/tesq.70032","title":"Automated Diagnostic Feedback vs. Self‐Assessment: Rethinking Feedback Mechanisms on Academic Writing Development","year":2025,"lang":"en","type":"article","venue":"TESOL Quarterly","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"University of Toronto; Educational Testing Service","keywords":"Academic writing; Peer feedback; Vocabulary; Task (project management); Graduate students; Second language writing; Higher education; Corrective feedback","score_opus":0.018631390327964244,"score_gpt":0.3371814660702979,"score_spread":0.3185500757423337,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414298304","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9861683,0.00016661397,0.011675497,0.00013773835,0.000036361744,0.000233142,0.00002869278,0.00015409687,0.0013995558],"genre_scores_gemma":[0.9904489,0.00006543863,0.008925374,0.000042708376,0.000014364093,0.00015120712,0.000013941913,0.000015305975,0.00032269486],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9858714,0.01002828,0.0006368253,0.0008087624,0.0024332134,0.00022151534],"domain_scores_gemma":[0.8471927,0.1343994,0.0060310652,0.005506377,0.00544411,0.001426316],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015404282,0.00046326683,0.00056019024,0.000764747,0.00032414123,0.0013742999,0.0006315509,0.0005399146,0.0017683787],"category_scores_gemma":[0.098714165,0.0002511116,0.0002997429,0.0003345732,0.0008033744,0.0012422611,0.001250248,0.0005831009,0.00025614072],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0070356023,0.0041613765,0.08256211,0.0007779103,0.00013951346,0.00009613204,0.01165263,0.0038697328,0.030919475,0.0011661006,0.00056206237,0.8570572],"study_design_scores_gemma":[0.0025316812,0.05909616,0.6774127,0.0016825019,0.0010190486,0.0005700593,0.0093712155,0.10637119,0.12128912,0.0077847936,0.01238925,0.00048226118],"about_ca_topic_score_codex":0.00061461015,"about_ca_topic_score_gemma":0.0006192308,"teacher_disagreement_score":0.015404282,"about_ca_system_score_codex":0.0005135346,"about_ca_system_score_gemma":0.0008667244,"threshold_uncertainty_score":0.081466615},"labels":[],"label_agreement":null},{"id":"W4414502288","doi":"10.37213/cjal.2025.34455","title":"Written corrective feedback at university","year":2025,"lang":"en","type":"article","venue":"Canadian Journal of Applied Linguistics","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"Agència de Gestió d'Ajuts Universitaris i de Recerca; Generalitat de Catalunya","keywords":"Corrective feedback; Spelling; Peer feedback; Metalinguistics; Higher education; Written language; Primary education; Error detection and correction","score_opus":0.012468651667480731,"score_gpt":0.26810295954232505,"score_spread":0.2556343078748443,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414502288","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98135597,0.0007119037,0.0047383592,0.0008692941,0.00026078502,0.000121040226,0.00021152999,0.0007650788,0.010965966],"genre_scores_gemma":[0.986989,0.00024518976,0.0036916833,0.00019478596,0.000054515538,0.00005488456,0.00013263844,0.0001335397,0.008503748],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.986206,0.0062864413,0.0008766646,0.001096653,0.0049838214,0.00055039144],"domain_scores_gemma":[0.90397257,0.042116452,0.011286204,0.009385656,0.027862526,0.005376545],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005624267,0.0005892363,0.0007582324,0.0019896983,0.001225564,0.0020377657,0.0009295935,0.0009210417,0.006843551],"category_scores_gemma":[0.10818164,0.00023909661,0.0003203065,0.0012148323,0.00080518046,0.0010400302,0.0018461384,0.001159709,0.0019509195],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0015531874,0.00093277445,0.08410014,0.0009619664,0.00008659977,0.00281949,0.12727955,0.0010947796,0.049180932,0.00077474985,0.010098628,0.72111726],"study_design_scores_gemma":[0.00034433123,0.008650231,0.5353447,0.0019354158,0.0002665095,0.010231533,0.132143,0.0065676114,0.11027786,0.0037436413,0.18993364,0.0005613754],"about_ca_topic_score_codex":0.00093023636,"about_ca_topic_score_gemma":0.001088889,"teacher_disagreement_score":0.006843551,"about_ca_system_score_codex":0.0013378055,"about_ca_system_score_gemma":0.0015640788,"threshold_uncertainty_score":0.029744327},"labels":[],"label_agreement":null},{"id":"W4414502711","doi":"10.37213/cjal.2025.34396","title":"A comparison of EFL students and instructors’ written feedback preferences and reported practices at a Moroccan university","year":2025,"lang":"en","type":"article","venue":"Canadian Journal of Applied Linguistics","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Textuality; Perception; Applied linguistics; Study abroad; Higher education; Written language","score_opus":0.05836475130016532,"score_gpt":0.37724672825808925,"score_spread":0.3188819769579239,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414502711","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9994412,0.000055126093,0.0000639533,0.000055619417,0.0000022451873,0.0000035179883,0.00001048066,0.0000036912882,0.00036408473],"genre_scores_gemma":[0.9993838,0.000052380015,0.00012107833,0.00003917313,0.0000026676878,0.0000062693684,0.00001406861,0.0000018257173,0.000378809],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99764234,0.0008597683,0.00027382554,0.00021482035,0.0007137593,0.000295438],"domain_scores_gemma":[0.9876201,0.0036764517,0.0034385268,0.00037559273,0.003244103,0.0016452329],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.003297374,0.00019613662,0.00030680682,0.0013144217,0.0009421486,0.0014971215,0.00032731364,0.00030550122,0.001428171],"category_scores_gemma":[0.014266249,0.00012235797,0.00011524021,0.0007325466,0.00053138606,0.00044145508,0.0007754678,0.00029875178,0.00030887325],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001835227,0.00041923436,0.78961134,0.00018389657,0.000027140894,0.0005679207,0.1187258,0.000100191006,0.008968859,0.00010249949,0.000493902,0.080615744],"study_design_scores_gemma":[0.000009117355,0.0004727677,0.884513,0.00011507104,0.000015791404,0.00044145243,0.10880629,0.00034164175,0.0018937573,0.00007661576,0.003277144,0.00003737121],"about_ca_topic_score_codex":0.006595796,"about_ca_topic_score_gemma":0.01300723,"teacher_disagreement_score":0.006595796,"about_ca_system_score_codex":0.0010341879,"about_ca_system_score_gemma":0.0011736897,"threshold_uncertainty_score":0.017438412},"labels":[],"label_agreement":null},{"id":"W4414503355","doi":"10.37213/cjal.2025.34475","title":"Collaboration in the revision of a piece of writing","year":2025,"lang":"en","type":"article","venue":"Canadian Journal of Applied Linguistics","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Context (archaeology); Process (computing); Natural (archaeology); Corrective feedback; Natural language; Phase (matter); Composition (language); Test (biology); Language acquisition","score_opus":0.016253375693617608,"score_gpt":0.34328282681194133,"score_spread":0.3270294511183237,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4414503355","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8955243,0.0011864938,0.045938507,0.0011887909,0.00022117433,0.00044684537,0.00006688011,0.0005071893,0.05491984],"genre_scores_gemma":[0.98290735,0.00020994637,0.0121317115,0.00009425367,0.00007728837,0.00012773907,0.000055988978,0.000095029165,0.0043006325],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.9345115,0.047587022,0.0022027448,0.00475588,0.008807197,0.002135675],"domain_scores_gemma":[0.9024421,0.067659274,0.010916087,0.01040223,0.005668173,0.0029121337],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015298113,0.0008006602,0.00071570766,0.0027338488,0.005386271,0.0071966248,0.0025175787,0.0027818414,0.0028535204],"category_scores_gemma":[0.088757455,0.0006131992,0.0006712279,0.0017525736,0.006860301,0.0049839225,0.009737304,0.0021027506,0.0013034156],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00053900806,0.0004235038,0.028842537,0.00068055955,0.00010100588,0.005054382,0.6997508,0.0013503981,0.017882163,0.010900226,0.00209489,0.23238058],"study_design_scores_gemma":[0.00031556806,0.0030562594,0.10645781,0.0016544661,0.00034467503,0.016229024,0.5405627,0.012497157,0.025480092,0.057356767,0.23544641,0.0005991322],"about_ca_topic_score_codex":0.00078607973,"about_ca_topic_score_gemma":0.0011076523,"teacher_disagreement_score":0.015298113,"about_ca_system_score_codex":0.0014154299,"about_ca_system_score_gemma":0.0025281312,"threshold_uncertainty_score":0.08090514},"labels":[],"label_agreement":null},{"id":"W4415150289","doi":"10.1002/berj.70056","title":"Self‐ and peer‐assessment in upper secondary schools. A quasi‐experimental study to investigate the educational effectiveness of formative assessment","year":2025,"lang":"en","type":"article","venue":"British Educational Research Journal","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Thomas University","funders":"","keywords":"Formative assessment; Summative assessment; Metacognition; Knowledge survey; Test (biology); Educational research","score_opus":0.04421725327059,"score_gpt":0.4866450570754541,"score_spread":0.4424278038048641,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415150289","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9993906,0.0000216766,0.00008005033,0.0000156554,0.000010047684,0.00023840113,0.000010815827,0.0000066014327,0.00022612841],"genre_scores_gemma":[0.99773777,0.000041366606,0.00074667716,0.000035594567,0.000015502143,0.0006251923,0.000031382664,0.0000037624138,0.00076275435],"study_design_codex":"nonrandomized_trial","study_design_gemma":"nonrandomized_trial","domain_scores_codex":[0.99370617,0.0030181562,0.00040952102,0.0008675449,0.0010627497,0.00093593],"domain_scores_gemma":[0.9867491,0.0049559753,0.0020900085,0.0015947722,0.001312148,0.00329795],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01219724,0.00079105305,0.0013335763,0.0010904205,0.0021776936,0.001371008,0.00093567144,0.0008501537,0.003089583],"category_scores_gemma":[0.015718464,0.00087097095,0.00069363916,0.0004481099,0.0017592409,0.0007595066,0.0010925287,0.0015043332,0.0008950948],"study_design_candidate":"nonrandomized_trial","study_design_consensus":"nonrandomized_trial","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.015908763,0.55177283,0.2126621,0.00074997015,0.0002735056,0.00048733334,0.07370545,0.00068138243,0.019886857,0.00072367856,0.0013407541,0.121807486],"study_design_scores_gemma":[0.006964603,0.28736272,0.6646575,0.0002562156,0.00020270952,0.00029495524,0.018126551,0.002051676,0.010250477,0.00070449384,0.008955243,0.00017289179],"about_ca_topic_score_codex":0.0032373678,"about_ca_topic_score_gemma":0.0034482926,"teacher_disagreement_score":0.01219724,"about_ca_system_score_codex":0.0012605884,"about_ca_system_score_gemma":0.0031272157,"threshold_uncertainty_score":0.064505935},"labels":[],"label_agreement":null},{"id":"W4415225444","doi":"10.15173/ijsap.v9i2.5886","title":"Assessment Met-befores","year":2025,"lang":"en","type":"article","venue":"International Journal for Students as Partners","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"St. Francis Xavier University","funders":"","keywords":"Formative assessment; Thematic analysis; Educational assessment; Self-assessment; Perception; Peer assessment; Assessment for learning; Alternative assessment","score_opus":0.04477588560886075,"score_gpt":0.6110586355681135,"score_spread":0.5662827499592528,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415225444","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.78295976,0.00095281407,0.055145595,0.006414531,0.0012526267,0.0028919657,0.0014084949,0.0017983221,0.14717588],"genre_scores_gemma":[0.95027226,0.00032184098,0.021671163,0.00063761603,0.000075353295,0.0009597824,0.00058918295,0.00012228855,0.02535059],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9853698,0.0070643704,0.0013371109,0.0012103211,0.003785783,0.0012326192],"domain_scores_gemma":[0.95389813,0.013387794,0.005350873,0.0063315043,0.013596649,0.0074350075],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0093148425,0.00037062733,0.00048822857,0.0009931088,0.0029375374,0.0028286388,0.0013999902,0.00081468996,0.012246592],"category_scores_gemma":[0.049616873,0.0004221735,0.00060717366,0.0007065544,0.0011347926,0.0024502873,0.0066780187,0.00241194,0.0028667154],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007530192,0.0016859449,0.087623954,0.0013814968,0.00006399152,0.0018935108,0.15533692,0.00064481207,0.010531751,0.020384427,0.035901867,0.6837983],"study_design_scores_gemma":[0.00006683531,0.0027520154,0.11725278,0.001353046,0.00005729668,0.0052218027,0.15561537,0.0021027555,0.0134283155,0.015917119,0.685974,0.00025864804],"about_ca_topic_score_codex":0.0014925473,"about_ca_topic_score_gemma":0.0048421617,"teacher_disagreement_score":0.012246592,"about_ca_system_score_codex":0.0020231688,"about_ca_system_score_gemma":0.0042421874,"threshold_uncertainty_score":0.049262226},"labels":[],"label_agreement":null},{"id":"W4415642192","doi":"10.65214/2164-7992.1633","title":"A Situated Lens to Designing Assessments of Citizenship Competency","year":2024,"lang":"en","type":"article","venue":"Democracy & Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary; Vancouver Island University","funders":"","keywords":"Operationalization; Situated; Citizenship; Democracy; Active listening; Situated learning; Value (mathematics); Capability approach; Citizenship education","score_opus":0.049335920173832315,"score_gpt":0.4051396013983132,"score_spread":0.35580368122448086,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415642192","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.06309008,0.0012731906,0.83735204,0.00644593,0.00028033694,0.0022092604,0.00028097074,0.0003973751,0.08867074],"genre_scores_gemma":[0.43172002,0.0005390024,0.5611219,0.0006253739,0.000027981418,0.0021981976,0.00008762889,0.00008022719,0.003599657],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.96902084,0.026498009,0.00095910364,0.0011760489,0.0019248656,0.0004210615],"domain_scores_gemma":[0.9625405,0.030860294,0.0013353892,0.0028134233,0.0015879001,0.0008624178],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01858365,0.0013434713,0.000758755,0.005976604,0.003305007,0.008485355,0.002212325,0.002282547,0.0065971743],"category_scores_gemma":[0.028750746,0.00076924457,0.000913902,0.0024225148,0.018079478,0.007840636,0.006456912,0.003739557,0.0005222736],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00016273,0.00055765326,0.008314543,0.002170669,0.00009210217,0.0006777814,0.17255706,0.0049527152,0.0068871467,0.6647678,0.0026874596,0.13617238],"study_design_scores_gemma":[0.00021231781,0.0008942827,0.0058429847,0.002639624,0.000103616345,0.00088044547,0.16790587,0.008977178,0.0083385855,0.64966935,0.15439974,0.00013606701],"about_ca_topic_score_codex":0.0028800182,"about_ca_topic_score_gemma":0.007398758,"teacher_disagreement_score":0.01858365,"about_ca_system_score_codex":0.004830483,"about_ca_system_score_gemma":0.005003806,"threshold_uncertainty_score":0.09828097},"labels":[],"label_agreement":null},{"id":"W4415830486","doi":"10.1016/j.bushor.2025.10.007","title":"Lost in the stars: Making sense of information compression in ratings","year":2025,"lang":"en","type":"article","venue":"Business Horizons","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Leverage (statistics); Quality (philosophy); Phenomenon; Information system; Boundary (topology); Convergence (economics)","score_opus":0.01987467738093282,"score_gpt":0.3395603708934862,"score_spread":0.3196856935125534,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415830486","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.66354364,0.0011834465,0.26400965,0.018427663,0.00023872912,0.00030446076,0.00020003466,0.0005923613,0.051500004],"genre_scores_gemma":[0.9743032,0.00013529115,0.024303593,0.00044387873,0.00006052159,0.000059299673,0.00004177481,0.00004895096,0.0006034643],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9565402,0.031890616,0.0016118248,0.002904036,0.0060834913,0.0009698453],"domain_scores_gemma":[0.8129888,0.13346113,0.025897097,0.014119551,0.010859649,0.0026738474],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.035641015,0.0005695327,0.0006418493,0.0027774968,0.0021036472,0.010386152,0.0015245099,0.0018850816,0.0025347858],"category_scores_gemma":[0.21954994,0.0006415707,0.0004321058,0.0018471006,0.011925541,0.014363287,0.0068985634,0.0030045314,0.0003118853],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0013020256,0.00024182572,0.13387437,0.0005977127,0.00020484919,0.0008420424,0.19491868,0.008136769,0.009112036,0.23191397,0.005259734,0.41359597],"study_design_scores_gemma":[0.00013390758,0.00084899075,0.08914662,0.0009460313,0.00016593433,0.0011016508,0.07475294,0.0918348,0.011406174,0.69660354,0.03262034,0.00043901117],"about_ca_topic_score_codex":0.0018086099,"about_ca_topic_score_gemma":0.0017210117,"teacher_disagreement_score":0.035641015,"about_ca_system_score_codex":0.002421644,"about_ca_system_score_gemma":0.0018346075,"threshold_uncertainty_score":0.18848997},"labels":[],"label_agreement":null},{"id":"W4415962483","doi":"10.1128/jmbe.00205-25","title":"Question format is the best predictor of item discrimination: a multivariable analysis","year":2025,"lang":"en","type":"article","venue":"Journal of Microbiology and Biology Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Trent University","funders":"","keywords":"Recall; Logistic regression; Item bank; Odds; Multivariable calculus; Correlation; Exploratory analysis; Relation (database); Odds ratio","score_opus":0.019586373810779545,"score_gpt":0.37255539891190975,"score_spread":0.3529690251011302,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4415962483","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99621874,0.00032070122,0.0019147755,0.00026802823,0.000055926994,0.00003446377,0.00070833083,0.00005306319,0.00042604245],"genre_scores_gemma":[0.9981969,0.00006565353,0.000543157,0.000046156652,0.000044664645,0.000043306685,0.00051682844,0.000030041581,0.00051331235],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9954364,0.0021983443,0.00027516636,0.00094784074,0.0005476359,0.00059456506],"domain_scores_gemma":[0.98037386,0.0126488935,0.0023189934,0.0018411789,0.0014589481,0.0013579822],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0077454597,0.0010607167,0.0011696495,0.0014251847,0.0006790128,0.0018786873,0.0015122915,0.0012779027,0.006149106],"category_scores_gemma":[0.021403339,0.0006425747,0.0038724227,0.0016314426,0.00047305346,0.0013510308,0.0013921121,0.0027346055,0.00095461844],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0007019911,0.0001468372,0.9940698,0.000021774093,0.0007044644,0.000091294234,0.000089464775,0.00035748474,0.00028354998,0.000062272105,0.00054543844,0.0029256225],"study_design_scores_gemma":[0.00009159737,0.0011531409,0.9711311,0.00004676828,0.0014381199,0.00044808985,0.00049887644,0.023147129,0.00054798485,0.00049008464,0.0009620405,0.000045191595],"about_ca_topic_score_codex":0.004692957,"about_ca_topic_score_gemma":0.0020925764,"teacher_disagreement_score":0.0077454597,"about_ca_system_score_codex":0.00042535653,"about_ca_system_score_gemma":0.001303495,"threshold_uncertainty_score":0.040962398},"labels":[],"label_agreement":null},{"id":"W4416175796","doi":"10.1016/j.ijme.2025.101307","title":"Innovative assessment and grading practices in higher education: a critical exploration for management educators","year":2025,"lang":"en","type":"article","venue":"The International Journal of Management Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"HEC Montréal","funders":"","keywords":"Grading (engineering); Higher education; Mainstream; Relevance (law); Continuous assessment; Management development; Best practice","score_opus":0.09367867799178597,"score_gpt":0.5023638013586159,"score_spread":0.40868512336682994,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416175796","genre_codex":"commentary","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.059351336,0.36145186,0.03547806,0.5170756,0.006568109,0.00082795776,0.000051984982,0.00012021838,0.019074935],"genre_scores_gemma":[0.70115185,0.17312984,0.080734156,0.038130585,0.0028013203,0.00073207734,0.00003409026,0.00008304891,0.003203119],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.91218567,0.066854954,0.006119763,0.0021442578,0.011631346,0.001063995],"domain_scores_gemma":[0.6228652,0.3230774,0.009400211,0.006080333,0.036874197,0.0017026406],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.1493745,0.00055293355,0.0009478705,0.009175533,0.00517298,0.016283082,0.002369935,0.004367038,0.0007941615],"category_scores_gemma":[0.1981754,0.0004433678,0.0006947695,0.006457469,0.020820105,0.023792142,0.00485946,0.007116124,0.00016333227],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00006840785,0.00016678186,0.008060126,0.0090852445,0.00008411637,0.00069729734,0.20250851,0.00045336524,0.00089197134,0.14411697,0.017297773,0.61656946],"study_design_scores_gemma":[0.000054872686,0.0003695458,0.007824117,0.050848693,0.00014533113,0.0012608279,0.3358256,0.0012251906,0.0021261098,0.13257912,0.46749315,0.00024755535],"about_ca_topic_score_codex":0.003822279,"about_ca_topic_score_gemma":0.0092875175,"teacher_disagreement_score":0.1493745,"about_ca_system_score_codex":0.0109480675,"about_ca_system_score_gemma":0.025403194,"threshold_uncertainty_score":0.7899773},"labels":[],"label_agreement":null},{"id":"W4416263112","doi":"10.55016/ojs/cpai.v8i4.81748","title":"Neutralizing the Threat of Technology","year":2025,"lang":"","type":"article","venue":"Canadian Perspectives on Academic Integrity","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Conestoga College","funders":"","keywords":"Value (mathematics); Foundation (evidence); Point (geometry); Filter (signal processing); Cognition","score_opus":0.028981222021889567,"score_gpt":0.36279158077491913,"score_spread":0.33381035875302956,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416263112","genre_codex":"other","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19777009,0.0028644558,0.12558617,0.1699294,0.001268367,0.0004437999,0.000075050455,0.0011241568,0.50093853],"genre_scores_gemma":[0.95771974,0.0009221861,0.019796351,0.0055275974,0.00012477137,0.00010620195,0.000023341356,0.00013205141,0.015647754],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9223859,0.036300268,0.0017231432,0.002777859,0.030815227,0.005997661],"domain_scores_gemma":[0.9217393,0.03733584,0.0059126527,0.0110499775,0.017264044,0.006698294],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03812935,0.0010515897,0.0007438726,0.0032233342,0.0127873635,0.023088446,0.0027059126,0.005339575,0.0051696263],"category_scores_gemma":[0.09827361,0.0004397094,0.0006588958,0.0014218071,0.035531975,0.014345779,0.016571833,0.010184803,0.0010641275],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015315757,0.00015403675,0.009764969,0.00031907175,0.00003627567,0.0003942555,0.1293079,0.0014351857,0.0033065353,0.6482931,0.012511145,0.19432439],"study_design_scores_gemma":[0.00006370686,0.0006997621,0.009144042,0.0016863879,0.00009315455,0.0009205442,0.13704877,0.0066695744,0.011094,0.3902604,0.44203854,0.00028104038],"about_ca_topic_score_codex":0.060317885,"about_ca_topic_score_gemma":0.047290258,"teacher_disagreement_score":0.060317885,"about_ca_system_score_codex":0.014404084,"about_ca_system_score_gemma":0.041168243,"threshold_uncertainty_score":0.20164967},"labels":[],"label_agreement":null},{"id":"W4416328737","doi":"10.7592/tertium.2025.10.1.322","title":"Beyond the Bubble","year":2025,"lang":"pl","type":"article","venue":"Półrocznik Językoznawczy Tertium","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Summative assessment; Construct (python library); Excellence; Test (biology); Foreign language; Language assessment; Government (linguistics)","score_opus":0.01482895853523709,"score_gpt":0.3296920592079808,"score_spread":0.3148631006727437,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416328737","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005108268,0.020156147,0.0050401506,0.114506856,0.011346046,0.000056762285,0.00066986855,0.00055847486,0.8425574],"genre_scores_gemma":[0.1924171,0.013681659,0.0034967507,0.036834173,0.006226761,0.00014006144,0.00088399014,0.0015060133,0.74481344],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.9976587,0.0007147733,0.000071252674,0.0005337467,0.00051419577,0.000507306],"domain_scores_gemma":[0.9973328,0.00082194025,0.00018587688,0.0006582314,0.0005732038,0.00042808452],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020598588,0.0007580142,0.0006742503,0.0017587753,0.008434788,0.013344377,0.001361523,0.0042324434,0.12302049],"category_scores_gemma":[0.013054593,0.00035459097,0.000429223,0.001993016,0.009259124,0.019576335,0.0084574185,0.0056389775,0.036072344],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000037947146,0.000010666829,0.00039785303,0.00008784606,0.000007157247,0.00018340429,0.0050058123,0.00006867868,0.00014265966,0.6688455,0.2655834,0.059629075],"study_design_scores_gemma":[0.000001982421,0.0000037100772,0.0001086214,0.00007296851,0.0000013086668,0.00005504848,0.0009266821,0.00002790605,0.000025639894,0.019250745,0.97952133,0.0000040214627],"about_ca_topic_score_codex":0.016033337,"about_ca_topic_score_gemma":0.013473834,"teacher_disagreement_score":0.12302049,"about_ca_system_score_codex":0.0061501875,"about_ca_system_score_gemma":0.0038975596,"threshold_uncertainty_score":0.41154456},"labels":[],"label_agreement":null},{"id":"W4416363396","doi":"10.1080/0047231x.2025.2576707","title":"Can a Small Change in Exam Question Format Help Students? Sadly, Not","year":2025,"lang":"en","type":"article","venue":"Journal of College Science Teaching","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of New Brunswick","funders":"","keywords":"Field (mathematics); Set (abstract data type); Feature (linguistics); Frequently asked questions","score_opus":0.04610037157081655,"score_gpt":0.4123545222884498,"score_spread":0.3662541507176333,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416363396","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6932543,0.0031473348,0.042883817,0.2111061,0.006899626,0.0018190276,0.00048373936,0.0064227404,0.033983253],"genre_scores_gemma":[0.86260706,0.00119156,0.094509535,0.026029626,0.0014487192,0.0011248981,0.00035037316,0.00032847747,0.012409699],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.995297,0.0025242104,0.0004415274,0.00045761061,0.0010648968,0.0002148599],"domain_scores_gemma":[0.95862716,0.025469627,0.003882771,0.0035109455,0.0043320763,0.0041774567],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0084065,0.0006000298,0.0006210477,0.00048759536,0.0005433943,0.0012220925,0.00148481,0.0030399864,0.010275123],"category_scores_gemma":[0.08638623,0.0002883823,0.0005529691,0.000313025,0.00055262825,0.0026855054,0.0009820557,0.0018655778,0.0052296873],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0020300013,0.0064365854,0.02214999,0.0005911155,0.0001157216,0.00024302123,0.0027184158,0.0005428433,0.011864576,0.0007077905,0.056679703,0.89592016],"study_design_scores_gemma":[0.004577816,0.035708893,0.45096776,0.0030661076,0.0011507574,0.004810347,0.019475682,0.01732171,0.04504417,0.023271421,0.39321914,0.00138613],"about_ca_topic_score_codex":0.0008917272,"about_ca_topic_score_gemma":0.0021506483,"teacher_disagreement_score":0.010275123,"about_ca_system_score_codex":0.00049226964,"about_ca_system_score_gemma":0.0008568509,"threshold_uncertainty_score":0.04445839},"labels":[],"label_agreement":null},{"id":"W4416466302","doi":"10.5430/wje.v15n4p1","title":"Exploring Students' Perspective on University Exit Exam","year":2025,"lang":"","type":"article","venue":"World Journal of Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"","funders":"","keywords":"Grading (engineering); Higher education; Anxiety; Relevance (law); Preference; Perspective (graphical); Likert scale; Test anxiety; Perception","score_opus":0.08070052760520088,"score_gpt":0.3979036730819686,"score_spread":0.31720314547676776,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416466302","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9945814,0.00014613934,0.0003936925,0.0010329927,0.000035188386,0.000011563356,0.000027940458,0.000010099936,0.003760933],"genre_scores_gemma":[0.9976203,0.00020335443,0.00020088966,0.00028184516,0.000021553413,0.000009577284,0.000032979315,0.000005960753,0.00162347],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.99460053,0.0026796483,0.00024656113,0.00018382428,0.0014302159,0.0008590921],"domain_scores_gemma":[0.98659897,0.0041027623,0.0025053388,0.00026955022,0.0031221546,0.0034012801],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0054361084,0.00031781467,0.00042766405,0.0012187725,0.001717428,0.004011575,0.0004382507,0.0010624926,0.003176914],"category_scores_gemma":[0.016689258,0.00017515988,0.00045649018,0.0005657961,0.0012700877,0.0013107775,0.002178727,0.0018992652,0.00075179944],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000415405,0.0008914085,0.54144454,0.00025047932,0.00006884222,0.0032829416,0.34563234,0.000512831,0.012264399,0.0028225943,0.005145503,0.08726876],"study_design_scores_gemma":[0.000016767011,0.0016793961,0.3102391,0.00036023083,0.000036912075,0.0016478878,0.6498395,0.0010206423,0.0032863112,0.00083138206,0.030899128,0.0001427654],"about_ca_topic_score_codex":0.001260577,"about_ca_topic_score_gemma":0.0021664177,"teacher_disagreement_score":0.0054361084,"about_ca_system_score_codex":0.000998517,"about_ca_system_score_gemma":0.0010602959,"threshold_uncertainty_score":0.028749228},"labels":[],"label_agreement":null},{"id":"W4416564265","doi":"10.1007/s12564-025-10099-2","title":"The impact of online feedback on student learning outcomes: a meta-analysis study","year":2025,"lang":"en","type":"article","venue":"Asia Pacific Education Review","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Trois-Rivières","funders":"","keywords":"Peer feedback; Cognition; Set (abstract data type); Outcome (game theory); TUTOR; Inclusion (mineral); Online learning; Feedback regulation; Significant difference; Higher education","score_opus":0.08081612670346547,"score_gpt":0.4959486766171236,"score_spread":0.4151325499136581,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416564265","genre_codex":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.05448638,0.9420962,0.0011168894,0.00043751803,0.0005228302,0.00037987475,0.0003956376,0.00003641051,0.0005283377],"genre_scores_gemma":[0.74383837,0.25033292,0.002401651,0.0012079421,0.00044186076,0.00074218964,0.00046038517,0.000043163764,0.0005315488],"study_design_codex":"meta_analysis","study_design_gemma":"meta_analysis","domain_scores_codex":[0.97753716,0.012761474,0.004980491,0.0016942215,0.0025701083,0.00045655356],"domain_scores_gemma":[0.92650676,0.056723908,0.0092150755,0.0021625278,0.004549928,0.0008418334],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.031057045,0.002239233,0.010476533,0.0036171367,0.0006512611,0.0035920935,0.0014679004,0.00206861,0.0018392394],"category_scores_gemma":[0.08405225,0.0010517141,0.026324391,0.004333104,0.0010101305,0.00178287,0.0017848553,0.0024319296,0.00022732497],"study_design_candidate":"meta_analysis","study_design_consensus":"meta_analysis","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00949862,0.00017995575,0.012837637,0.11409963,0.8393387,0.00009609968,0.0002880275,0.00030422493,0.0003247267,0.00009863649,0.00049852266,0.022435218],"study_design_scores_gemma":[0.0017486021,0.00096695026,0.008695999,0.008912774,0.9781261,0.00006975167,0.00010745173,0.00013459998,0.00020825432,0.00012794863,0.0008735502,0.000028090992],"about_ca_topic_score_codex":0.0052460954,"about_ca_topic_score_gemma":0.010029309,"teacher_disagreement_score":0.031057045,"about_ca_system_score_codex":0.0020253207,"about_ca_system_score_gemma":0.002810486,"threshold_uncertainty_score":0.16424733},"labels":[],"label_agreement":null},{"id":"W4416724673","doi":"10.3126/erj.v2i01.86476","title":"From Standardized Tests to Meaningful Experiences: The Future of Student Assessment","year":2025,"lang":"","type":"article","venue":"Education Review Journal","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Experiential learning; Standardized test; Dominance (genetics); Educational assessment; Rote learning; Sample (material)","score_opus":0.024654410534224732,"score_gpt":0.45762656978673516,"score_spread":0.4329721592525104,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416724673","genre_codex":"review","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.030325592,0.76617277,0.028726928,0.11222101,0.0036229887,0.0003161353,0.00014348114,0.00025264404,0.058218483],"genre_scores_gemma":[0.5083944,0.41997263,0.045226965,0.018534992,0.0019891418,0.0010839918,0.00016098461,0.00013807193,0.0044987476],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.91978294,0.06276229,0.004246687,0.0014968853,0.01091524,0.0007959354],"domain_scores_gemma":[0.8477538,0.12007419,0.005965207,0.004496417,0.018306548,0.003403824],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.07494669,0.00051847915,0.0016205397,0.0039071036,0.001365056,0.0134422425,0.0022477221,0.0030813124,0.0029367746],"category_scores_gemma":[0.17239821,0.00036871404,0.00060407806,0.003411657,0.010709191,0.014482195,0.008384754,0.003750623,0.0006110068],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000073678966,0.00008404136,0.0023105582,0.00862756,0.000083174025,0.00008281374,0.023409944,0.00021759002,0.0002662978,0.05783846,0.009403986,0.89760184],"study_design_scores_gemma":[0.00008643362,0.0008302935,0.0075947503,0.06419157,0.00014645477,0.00079224736,0.06794675,0.0005068498,0.00086405233,0.13977316,0.71708846,0.00017894385],"about_ca_topic_score_codex":0.00332287,"about_ca_topic_score_gemma":0.004265702,"teacher_disagreement_score":0.07494669,"about_ca_system_score_codex":0.004569197,"about_ca_system_score_gemma":0.01437045,"threshold_uncertainty_score":0.3963607},"labels":[],"label_agreement":null},{"id":"W4416760191","doi":"10.47116/apjcri.2025.11.20","title":"A Global Bibliometric Analysis of Assessment Literacy in Preservice Teacher Education (2000–2024)","year":2025,"lang":"","type":"article","venue":"Asia-pacific Journal of Convergent Research Interchange","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Teacher education; Literacy; Higher education; Student teacher","score_opus":0.07266060113008153,"score_gpt":0.48620090350209716,"score_spread":0.4135403023720156,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416760191","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.6136481,0.10595367,0.0062768646,0.0045788703,0.0008524544,0.0010328183,0.20482467,0.0011261399,0.061706394],"genre_scores_gemma":[0.83368796,0.04494644,0.011825748,0.00040261506,0.00071048876,0.0013575268,0.10233866,0.0002064157,0.00452414],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9893121,0.0014893931,0.002396298,0.0010524127,0.0051866774,0.0005631202],"domain_scores_gemma":[0.9622427,0.013577018,0.0093433205,0.0019716814,0.011724963,0.001140198],"candidate_categories":["bibliometrics"],"consensus_categories":[],"category_scores_codex":[0.009088059,0.00081126427,0.0015438426,0.19524348,0.0011963437,0.0056019556,0.0008169505,0.00071344373,0.0032897806],"category_scores_gemma":[0.03345035,0.00033541152,0.0020052951,0.22263314,0.00093861535,0.004325739,0.0032502597,0.0008005293,0.0011116962],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00034884407,0.0001403684,0.54771477,0.023176003,0.002255444,0.0007660914,0.0062415,0.002016289,0.0023468006,0.009715903,0.045786392,0.35949162],"study_design_scores_gemma":[0.000029187717,0.00018437498,0.8656891,0.0028820366,0.0011294154,0.001029786,0.005657227,0.001405113,0.0013198777,0.0017927119,0.11878846,0.000092712915],"about_ca_topic_score_codex":0.009007536,"about_ca_topic_score_gemma":0.009630045,"teacher_disagreement_score":0.8047565,"about_ca_system_score_codex":0.0025277475,"about_ca_system_score_gemma":0.0055880304,"threshold_uncertainty_score":0.0480628},"labels":[],"label_agreement":null},{"id":"W4416789755","doi":"10.3389/feduc.2025.1695771","title":"Training in-service subject teachers to implement formative assessment through action research","year":2025,"lang":"en","type":"article","venue":"Frontiers in Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"St. Thomas University","funders":"","keywords":"Formative assessment; Action research; Professional development; Action (physics); Subject (documents); Faculty development; Training (meteorology)","score_opus":0.13557708049205017,"score_gpt":0.5319322045050002,"score_spread":0.39635512401295003,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416789755","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.60023546,0.0014787406,0.31986958,0.0056611313,0.00045097704,0.011339395,0.00020386427,0.0022184209,0.058542497],"genre_scores_gemma":[0.47363055,0.001744921,0.49920535,0.0010881856,0.000109040506,0.0063886815,0.00032667635,0.00012309884,0.017383527],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.99420506,0.0032819246,0.00033553998,0.0007264839,0.0010126991,0.00043831122],"domain_scores_gemma":[0.9746719,0.013171427,0.0020909612,0.0034987587,0.0037131368,0.0028539142],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01567023,0.00061743625,0.0005261701,0.001182322,0.0012889525,0.002161897,0.0015034548,0.0009547786,0.0055847643],"category_scores_gemma":[0.017151264,0.0005223045,0.00052139617,0.00078888284,0.0016712267,0.0014829448,0.0024416556,0.002035708,0.0023131764],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022910451,0.012011048,0.025928289,0.0021880276,0.00004018887,0.00056536624,0.08001153,0.0010959588,0.037578143,0.003536727,0.009213742,0.82760185],"study_design_scores_gemma":[0.0016224138,0.014206134,0.28125134,0.004613222,0.00022865683,0.00519418,0.110736035,0.011452612,0.07594975,0.0271666,0.46726212,0.0003169383],"about_ca_topic_score_codex":0.0020026376,"about_ca_topic_score_gemma":0.0054989406,"teacher_disagreement_score":0.01567023,"about_ca_system_score_codex":0.0016570117,"about_ca_system_score_gemma":0.0113723995,"threshold_uncertainty_score":0.08287305},"labels":[],"label_agreement":null},{"id":"W4416872428","doi":"10.47772/ijriss.2025.903sedu0705","title":"Global Trends in School-Based Assessment: Implications for Effective Implementation in Sri Lanka","year":2025,"lang":"","type":"article","venue":"International Journal of Research and Innovation in Social Science","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Formative assessment; Nexus (standard); Moderation; Workload; Quality (philosophy); Reliability (semiconductor); Foundation (evidence); Empirical evidence","score_opus":0.07689676829601365,"score_gpt":0.5939911336009404,"score_spread":0.5170943653049267,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416872428","genre_codex":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.02280245,0.9196446,0.0032688053,0.04114866,0.0009315806,0.0008071212,0.0014095715,0.000102919585,0.009884352],"genre_scores_gemma":[0.29221836,0.67105526,0.023434464,0.008946652,0.00023895591,0.002289971,0.0012709585,0.00007719887,0.00046815685],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9142868,0.04968688,0.019968372,0.0038488263,0.009814137,0.0023950178],"domain_scores_gemma":[0.82900983,0.11405309,0.01655793,0.006348768,0.03170627,0.0023241206],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.10728884,0.00075866247,0.0026336685,0.006709381,0.0009878306,0.008653005,0.002743486,0.0014695934,0.003046873],"category_scores_gemma":[0.17529847,0.0008932447,0.0026164288,0.01386252,0.0030714893,0.007398951,0.0057801423,0.003917867,0.00033907237],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00020835323,0.000112923204,0.0291847,0.15748018,0.002051281,0.00019001793,0.009069015,0.0008724756,0.00032391647,0.011394083,0.0071152155,0.7819979],"study_design_scores_gemma":[0.0003225068,0.0010689297,0.16260509,0.59808385,0.007191537,0.00058223674,0.03229865,0.00070264156,0.0008660882,0.010832547,0.18520834,0.00023759315],"about_ca_topic_score_codex":0.043309405,"about_ca_topic_score_gemma":0.06870868,"teacher_disagreement_score":0.10728884,"about_ca_system_score_codex":0.010801505,"about_ca_system_score_gemma":0.060762815,"threshold_uncertainty_score":0.5674044},"labels":[],"label_agreement":null},{"id":"W4416894890","doi":"10.1080/0969594x.2025.2591284","title":"An implementation of argument-based validation for assessing college major preferences with a hybrid of Likert-rating and forced-choice formats","year":2025,"lang":"en","type":"article","venue":"Assessment in Education Principles Policy and Practice","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Data collection; Measure (data warehouse); Key (lock); Quality (philosophy)","score_opus":0.04844669177838798,"score_gpt":0.4835110550125784,"score_spread":0.4350643632341904,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416894890","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.21599603,0.00012250993,0.7313499,0.0013783247,0.0007145423,0.026451118,0.0012544052,0.0015255238,0.021207625],"genre_scores_gemma":[0.23601893,0.00007108289,0.71895576,0.00060981396,0.00007989855,0.041035693,0.0007042863,0.0002880181,0.0022365637],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.72703624,0.21878016,0.017902903,0.007827743,0.02615341,0.0022996147],"domain_scores_gemma":[0.40942302,0.4311151,0.018199928,0.060468394,0.079038076,0.0017555339],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.22691339,0.0016696452,0.0014944646,0.0046746642,0.0027724642,0.0036013266,0.0023836894,0.0021085467,0.004780988],"category_scores_gemma":[0.39466777,0.0013499625,0.0023270715,0.003256688,0.0031252836,0.004003254,0.0049858997,0.0039498163,0.0019102168],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.004052783,0.007814126,0.139231,0.001901658,0.00061423896,0.00040253816,0.04054982,0.005708607,0.030399706,0.04781372,0.016594965,0.70491695],"study_design_scores_gemma":[0.0043577827,0.017031813,0.25684407,0.004184096,0.00074815156,0.0023050483,0.029330783,0.24406256,0.16880952,0.11953221,0.15073615,0.0020577596],"about_ca_topic_score_codex":0.0008998437,"about_ca_topic_score_gemma":0.0022168874,"teacher_disagreement_score":0.22691339,"about_ca_system_score_codex":0.0028008313,"about_ca_system_score_gemma":0.00545352,"threshold_uncertainty_score":0.9533534},"labels":[],"label_agreement":null},{"id":"W4416920459","doi":"10.1108/book-978-1-64113-529-020251067","title":"Assessment For Learning In Saskatchewan Mathematics Classes","year":2019,"lang":"en","type":"book-chapter","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Class (philosophy); Work (physics); Process (computing); Data collection","score_opus":0.04024173403330422,"score_gpt":0.3559005485326526,"score_spread":0.3156588144993484,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416920459","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04188708,0.025968052,0.023090424,0.012774724,0.0019013173,0.00045711803,0.0011668132,0.0014313691,0.89132303],"genre_scores_gemma":[0.13441603,0.013921071,0.0274694,0.0009952514,0.000093759285,0.00030276433,0.0010104742,0.0002325527,0.8215588],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9993248,0.00015267948,0.000041226423,0.00005915943,0.0003438779,0.00007827677],"domain_scores_gemma":[0.9989066,0.00025534572,0.000035730467,0.000057192818,0.00060984964,0.0001353406],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0013718794,0.000690657,0.00043987983,0.0014804024,0.0015230291,0.003792697,0.001125379,0.00074737926,0.013975837],"category_scores_gemma":[0.003271062,0.00035657425,0.0002878118,0.0021416396,0.00056544464,0.001226996,0.0016453235,0.0015210008,0.004180963],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000049147646,0.000095219606,0.0027483176,0.00018416285,0.0000075413427,0.000098694174,0.0014993617,0.0009552034,0.0010937058,0.017694762,0.17168303,0.8038908],"study_design_scores_gemma":[0.000027444867,0.00015160926,0.04348196,0.0015798095,0.00003651303,0.00039938465,0.006220644,0.0042389096,0.0031700316,0.028205657,0.91241825,0.00006985165],"about_ca_topic_score_codex":0.29494947,"about_ca_topic_score_gemma":0.6770591,"teacher_disagreement_score":0.7050505,"about_ca_system_score_codex":0.012455265,"about_ca_system_score_gemma":0.018966286,"threshold_uncertainty_score":0.58646536},"labels":[],"label_agreement":null},{"id":"W4416934519","doi":"10.1016/j.tate.2025.105343","title":"“How should I assess their writing? It’s a headache for me.”: Understanding teacher assessment literacy in the collaborative writing context","year":2025,"lang":"en","type":"article","venue":"Teaching and Teacher Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"National Social Science Fund of China","keywords":"Literacy; Context (archaeology); Writing assessment; Collaborative learning; Collaborative writing; Mainland China; Teacher education","score_opus":0.10887334018280642,"score_gpt":0.4503753852886655,"score_spread":0.3415020451058591,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416934519","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.40483132,0.006378484,0.06152032,0.3580045,0.003109442,0.00024440902,0.00028442245,0.0009921006,0.16463497],"genre_scores_gemma":[0.9526908,0.0022196914,0.0129852155,0.014926691,0.00042445768,0.00012732347,0.00007791192,0.00012409418,0.01642388],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99016154,0.0070388177,0.0004266031,0.00037947207,0.0016652183,0.00032833556],"domain_scores_gemma":[0.97658336,0.015918273,0.0020808408,0.00059490575,0.003596591,0.0012260041],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0075600706,0.0002669613,0.00030918643,0.0009898037,0.0025486785,0.0044128904,0.0006697107,0.0019979437,0.003570136],"category_scores_gemma":[0.06827187,0.00021092751,0.00021430316,0.0005623654,0.004992265,0.0059642456,0.0031691093,0.0050838245,0.0010256403],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00011680373,0.00023154935,0.0273106,0.0005642485,0.000037590475,0.0013235911,0.64319766,0.00022192916,0.003537401,0.020429512,0.08288654,0.22014256],"study_design_scores_gemma":[0.00005160295,0.0003472036,0.040615972,0.0020692672,0.000044866443,0.009960575,0.5947922,0.002301949,0.0044857375,0.045260943,0.29986846,0.00020115753],"about_ca_topic_score_codex":0.0057052122,"about_ca_topic_score_gemma":0.006983628,"teacher_disagreement_score":0.0075600706,"about_ca_system_score_codex":0.0012316868,"about_ca_system_score_gemma":0.0031616285,"threshold_uncertainty_score":0.03998196},"labels":[],"label_agreement":null},{"id":"W4417318533","doi":"10.65431/jrell.v1i2.22","title":"The influence of peer assessment on students’ writing scores in descriptive text","year":2025,"lang":"","type":"article","venue":"Journal of Research in English Language Teaching and Linguistics","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"CLARITY; Peer assessment; Peer feedback; Descriptive statistics; Peer tutor; Context (archaeology); Writing assessment; Thematic analysis; Metacognition; Perception","score_opus":0.041063488038485814,"score_gpt":0.4627083866701615,"score_spread":0.4216448986316757,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417318533","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9959241,0.00021647105,0.0010507604,0.000114836286,0.000031575644,0.00005928089,0.000012220953,0.000040141724,0.0025506036],"genre_scores_gemma":[0.99885595,0.000076832184,0.0005865609,0.0000109610755,0.00001142769,0.00003686252,0.000010611324,0.000008581133,0.00040223397],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98240787,0.009924341,0.0011414995,0.0010695757,0.004968582,0.00048814525],"domain_scores_gemma":[0.86218,0.08974299,0.015346788,0.0049176384,0.021219678,0.0065928614],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0073651248,0.0004288688,0.00056175975,0.001052752,0.00089872,0.0020719,0.00058871007,0.00035449973,0.0009955467],"category_scores_gemma":[0.117729865,0.00015672631,0.00042876296,0.00043050517,0.0008200505,0.0007862737,0.0016374493,0.00074140204,0.00036455394],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0012851077,0.0021696496,0.5141449,0.00039188133,0.0003676958,0.0010022303,0.045642264,0.0010861799,0.022603255,0.00035790904,0.0013362783,0.4096127],"study_design_scores_gemma":[0.000060015132,0.0036852271,0.9491488,0.00021044411,0.00026288486,0.0007959673,0.02296136,0.0034394267,0.014775265,0.00067806884,0.003817529,0.0001651401],"about_ca_topic_score_codex":0.0013222377,"about_ca_topic_score_gemma":0.0017262332,"teacher_disagreement_score":0.0073651248,"about_ca_system_score_codex":0.0004155821,"about_ca_system_score_gemma":0.0010957828,"threshold_uncertainty_score":0.03895098},"labels":[],"label_agreement":null},{"id":"W4417351506","doi":"10.1093/conphys/coaf085","title":"Tips and tricks for writing constructive peer reviews","year":2025,"lang":"en","type":"article","venue":"Conservation Physiology","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University; Fisheries and Oceans Canada; University of New Brunswick","funders":"","keywords":"Constructive; Peer review; Peer evaluation","score_opus":0.05521597252947013,"score_gpt":0.40198410600867734,"score_spread":0.3467681334792072,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417351506","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0064834794,0.012414841,0.4357538,0.16329312,0.18599868,0.017106151,0.02360557,0.08489369,0.07045071],"genre_scores_gemma":[0.03938817,0.0069569196,0.7131652,0.02712531,0.0555274,0.03300662,0.006068057,0.019439943,0.099322304],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.850636,0.08902844,0.01569242,0.0060253744,0.03671582,0.001901968],"domain_scores_gemma":[0.34525418,0.32995775,0.032866783,0.05160583,0.22796142,0.0123539865],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.08403287,0.003405466,0.0034342716,0.009965677,0.0024299624,0.0072666253,0.0027485213,0.0043627173,0.24436612],"category_scores_gemma":[0.5343183,0.0023199928,0.0029193328,0.006909418,0.0036264034,0.005650692,0.005451746,0.006872641,0.15671292],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022268675,0.00006344713,0.00034024747,0.0020817139,0.00007349104,0.0002466601,0.0009972397,0.00027297082,0.0012963912,0.0018339047,0.86613363,0.12643777],"study_design_scores_gemma":[0.0004885317,0.00019316835,0.0029295303,0.0038534952,0.0001048932,0.0008460453,0.0011029629,0.0026843096,0.0018582802,0.019925198,0.96574765,0.00026601722],"about_ca_topic_score_codex":0.0012477766,"about_ca_topic_score_gemma":0.0046282923,"teacher_disagreement_score":0.9159671,"about_ca_system_score_codex":0.0019189899,"about_ca_system_score_gemma":0.010329566,"threshold_uncertainty_score":0.8174861},"labels":[],"label_agreement":null},{"id":"W4417409629","doi":"10.13140/rg.2.2.31942.42560","title":"Pupils' self-evaluation biases influence teachers' judgments about their competence","year":2019,"lang":"en","type":"article","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Competence (human resources); Perception; Affect (linguistics); Cognitive bias","score_opus":0.043450442722163106,"score_gpt":0.3578247868108449,"score_spread":0.3143743440886818,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417409629","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99352735,0.00016653593,0.0010275213,0.00022631245,0.000022797121,0.000016774951,0.000026840726,0.000022177512,0.004963765],"genre_scores_gemma":[0.998995,0.00005714826,0.00040571654,0.000035577887,0.000008359273,0.000012693928,0.000020285168,0.000018509794,0.00044671635],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98781013,0.0054931426,0.0009574936,0.000871484,0.004369365,0.0004984676],"domain_scores_gemma":[0.8495363,0.11294574,0.017450795,0.0038913686,0.01274012,0.003435659],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015061603,0.00029472326,0.0006075679,0.0012596066,0.0007160651,0.0028689164,0.0003898316,0.00080946385,0.0027256722],"category_scores_gemma":[0.12603712,0.00034663227,0.00042975217,0.00049899134,0.0010057157,0.0013668226,0.0017046909,0.0010497221,0.00056607986],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0021517933,0.00033910284,0.89283025,0.00028998265,0.0003094755,0.00014800474,0.022749767,0.0007779545,0.012967183,0.0012240338,0.0013426193,0.06486987],"study_design_scores_gemma":[0.00010561954,0.00062293164,0.97648597,0.00016538471,0.00018761127,0.00015870393,0.007296452,0.002389745,0.008888698,0.0017609302,0.0018681276,0.00006987459],"about_ca_topic_score_codex":0.0031183492,"about_ca_topic_score_gemma":0.0036907957,"teacher_disagreement_score":0.015061603,"about_ca_system_score_codex":0.0010202563,"about_ca_system_score_gemma":0.0010750045,"threshold_uncertainty_score":0.079654336},"labels":[],"label_agreement":null},{"id":"W4417427785","doi":"10.1111/tct.70259","title":"Feeling Feedback: The Role of Emotions in Feedback","year":2025,"lang":"en","type":"article","venue":"The Clinical Teacher","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Feeling; Pride; Sadness; Situated; Negative feedback; Peer feedback; Control (management); Anger","score_opus":0.06854066440182474,"score_gpt":0.4319387592460753,"score_spread":0.36339809484425056,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4417427785","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.29962966,0.07766515,0.10857868,0.22026652,0.010863704,0.0006116415,0.00066353014,0.0013039719,0.2804172],"genre_scores_gemma":[0.95549667,0.009169569,0.012385644,0.013004794,0.0013411079,0.0003047205,0.000089177986,0.00039872847,0.0078095654],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.9675885,0.023196349,0.0007801942,0.0015037797,0.0056575458,0.0012735986],"domain_scores_gemma":[0.9112936,0.06326905,0.008511652,0.0025916316,0.0098148575,0.004519252],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.017088665,0.0006352436,0.00058504037,0.0016196435,0.0034888394,0.012506107,0.0011735997,0.0032623766,0.0066284793],"category_scores_gemma":[0.08706692,0.00047669286,0.00082447036,0.001224537,0.011626438,0.010355991,0.0062580174,0.006179964,0.0013359841],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0006716541,0.00021091447,0.018334169,0.0033643455,0.00020510038,0.0015142147,0.6007665,0.00061666616,0.006763271,0.07661294,0.04733114,0.24360916],"study_design_scores_gemma":[0.00023422869,0.0011842254,0.08553969,0.009658723,0.00035751835,0.0056633633,0.33225995,0.0035692914,0.00479079,0.17827713,0.37756446,0.0009006479],"about_ca_topic_score_codex":0.0016337321,"about_ca_topic_score_gemma":0.0013077192,"teacher_disagreement_score":0.017088665,"about_ca_system_score_codex":0.0029922556,"about_ca_system_score_gemma":0.0026372557,"threshold_uncertainty_score":0.09037459},"labels":[],"label_agreement":null},{"id":"W568408786","doi":"10.1057/9780230621565_12","title":"The Uses of Error: Toward a Realist Methodology of Student Evaluation","year":2009,"lang":"en","type":"book-chapter","venue":"Palgrave Macmillan US eBooks","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Grading (engineering); Wonder; Documentation; Mathematics education; Class (philosophy); Perception; Set (abstract data type); Quarter (Canadian coin); Psychology; Field (mathematics); Epistemology; Pedagogy; Computer science; Social psychology; Mathematics; Engineering; Philosophy","score_opus":0.21058115007426195,"score_gpt":0.4256058278644708,"score_spread":0.21502467779020887,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W568408786","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004614712,0.0036818509,0.91036445,0.026136445,0.0009394881,0.0005601736,0.00010400286,0.0008084444,0.0527904],"genre_scores_gemma":[0.12721382,0.0025220178,0.84621406,0.002612855,0.00093226606,0.0022895283,0.00011898539,0.0008312961,0.017265093],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.7911892,0.1735122,0.0045272233,0.0051273573,0.024698429,0.00094557565],"domain_scores_gemma":[0.6809792,0.24947564,0.009478599,0.027658502,0.0303664,0.0020416752],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.17411877,0.0016491596,0.0020825178,0.007606002,0.0025088463,0.021858336,0.00948402,0.0036396093,0.0057121324],"category_scores_gemma":[0.22512196,0.001123428,0.001197067,0.0043699127,0.034469463,0.022688504,0.008700829,0.00847373,0.0018329978],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000602769,0.00008449301,0.0023093058,0.0009590895,0.0000828075,0.000077607125,0.015878592,0.002675589,0.0003378132,0.7349827,0.016877344,0.22567433],"study_design_scores_gemma":[0.00004801038,0.00015847378,0.001591949,0.0016471784,0.000045110482,0.00019137166,0.007086511,0.013334826,0.0013942309,0.8695466,0.1048527,0.00010308251],"about_ca_topic_score_codex":0.0015340617,"about_ca_topic_score_gemma":0.0027853623,"teacher_disagreement_score":0.17411877,"about_ca_system_score_codex":0.0076441914,"about_ca_system_score_gemma":0.0075111464,"threshold_uncertainty_score":0.9208391},"labels":[],"label_agreement":null},{"id":"W6886083659","doi":"10.14288/1.0406080","title":"English for academic purposes in Canada : practitioners’ assessment practices and construction of assessment literacy","year":2021,"lang":"en","type":"article","venue":"cIRcle (University of British Columbia)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Competence (human resources); Literacy; English for academic purposes; Assessment for learning; Higher education; Population; Mainland; Grounded theory; Needs assessment","score_opus":0.01624634877687258,"score_gpt":0.2852179691138342,"score_spread":0.2689716203369616,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6886083659","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9890075,0.0006427114,0.0003052318,0.001956633,0.000015527568,0.00006029052,0.00006974493,0.000019374933,0.007923071],"genre_scores_gemma":[0.9966143,0.00053271925,0.00051559706,0.00018563672,0.0000026086486,0.000015984602,0.000031358864,0.000007770907,0.0020940471],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9938206,0.001464101,0.00029633517,0.0005203523,0.0026895474,0.0012091489],"domain_scores_gemma":[0.9727792,0.006757936,0.0023416737,0.0004917729,0.011608128,0.006021241],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005936385,0.0002539084,0.00038632314,0.001904701,0.009781677,0.0044606295,0.0011694289,0.0006686456,0.0015389586],"category_scores_gemma":[0.024434242,0.0003800227,0.00017514001,0.003302377,0.0038148835,0.0012601538,0.004412863,0.0015990516,0.00016795787],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000080303915,0.00012418372,0.18843779,0.00023317157,0.000010899227,0.00079366495,0.7032318,0.00013599209,0.0012878369,0.0013112687,0.0022787554,0.10207438],"study_design_scores_gemma":[0.000013326451,0.000106007305,0.28945398,0.00040360854,0.000016838148,0.0002856238,0.68328303,0.00057923805,0.0005525634,0.00043139115,0.024803981,0.00007044948],"about_ca_topic_score_codex":0.97771764,"about_ca_topic_score_gemma":0.99085,"teacher_disagreement_score":0.055194635,"about_ca_system_score_codex":0.055194635,"about_ca_system_score_gemma":0.15765497,"threshold_uncertainty_score":0.40046698},"labels":[],"label_agreement":null},{"id":"W6887713702","doi":"10.17608/k6.auckland.5547727.v1","title":"Appendix B 2013 Safeya Janahi MA.pdf","year":2017,"lang":"en","type":"article","venue":"Figshare","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Citation; Quarter (Canadian coin); Glossary; Appendix","score_opus":0.06679611374813141,"score_gpt":0.3683753477491411,"score_spread":0.3015792340010097,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6887713702","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0010726288,0.0007419453,0.003479451,0.0031430186,0.002924467,0.00089022814,0.30026484,0.008819452,0.67866397],"genre_scores_gemma":[0.009695928,0.001778426,0.006853607,0.0014446662,0.0007441172,0.0019864475,0.12349106,0.005526264,0.8484794],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99944717,0.00009488174,0.00005518281,0.000054725548,0.00028845257,0.0000595678],"domain_scores_gemma":[0.99247426,0.0027352683,0.00032731646,0.0005175368,0.0034969505,0.0004485983],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0009801866,0.0006622965,0.00068119966,0.0032064756,0.0010484833,0.0032493656,0.0011927315,0.0009452097,0.87241954],"category_scores_gemma":[0.014373874,0.0005433024,0.00040042648,0.004761123,0.00034693908,0.0024494438,0.001357804,0.0010293116,0.626675],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000029564218,0.000010825694,0.00007498378,0.00013436795,0.0000012035812,0.000016938779,0.000032085598,0.000043013675,0.000025718906,0.0004533392,0.97388625,0.025291737],"study_design_scores_gemma":[0.000020717142,0.000011628879,0.001382669,0.00019385292,0.000001618366,0.00004639957,0.000082341685,0.00006073001,0.00008601761,0.0006038489,0.99749845,0.000011760672],"about_ca_topic_score_codex":0.012141541,"about_ca_topic_score_gemma":0.010340603,"teacher_disagreement_score":0.12758046,"about_ca_system_score_codex":0.0016039097,"about_ca_system_score_gemma":0.0018273123,"threshold_uncertainty_score":0.18197805},"labels":[],"label_agreement":null},{"id":"W6902225316","doi":"10.6084/m9.figshare.22615813","title":"Additional file 1 of Introducing ACTFAiREST2 to implement online assessments amid COVID–19: a case study from a low resource setting","year":2023,"lang":"en","type":"article","venue":"Open MIND","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Resource (disambiguation); Key (lock); Government (linguistics); Data collection","score_opus":0.09351254665865326,"score_gpt":0.46311784848391685,"score_spread":0.3696053018252636,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6902225316","genre_codex":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005356548,0.00008038297,0.005445555,0.0037778327,0.00028985142,0.0045614727,0.9383645,0.0041132225,0.038010627],"genre_scores_gemma":[0.14184083,0.000588064,0.06610613,0.006561714,0.00049850426,0.07415006,0.5257591,0.0056014736,0.17889413],"study_design_codex":"not_applicable","study_design_gemma":"case_report","domain_scores_codex":[0.99797183,0.0009421365,0.00030145215,0.00017399175,0.00043568184,0.00017494596],"domain_scores_gemma":[0.90460485,0.078384005,0.002669106,0.0027878154,0.008371346,0.0031829681],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0055674906,0.00048735444,0.00051829434,0.0020175022,0.0015589611,0.0016730728,0.0017101038,0.0010217401,0.8338825],"category_scores_gemma":[0.07008568,0.0003323206,0.00038692594,0.002074712,0.00034870298,0.0017895576,0.0014751189,0.0011164503,0.12584938],"study_design_candidate":"case_report","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00022222946,0.00025514647,0.0017778194,0.0011613072,0.00000812966,0.00011910046,0.00064139656,0.00024218831,0.00004961902,0.000728599,0.96304464,0.031749725],"study_design_scores_gemma":[0.0028051988,0.00056166266,0.023990719,0.0035217777,0.000058052858,0.0004924386,0.0049456987,0.0017485124,0.00082773104,0.008454599,0.9524407,0.0001530163],"about_ca_topic_score_codex":0.009652619,"about_ca_topic_score_gemma":0.020078551,"teacher_disagreement_score":0.8338825,"about_ca_system_score_codex":0.0019605407,"about_ca_system_score_gemma":0.0055865888,"threshold_uncertainty_score":0.23694646},"labels":[],"label_agreement":null},{"id":"W6902235466","doi":"10.6084/m9.figshare.26720376.v1","title":"Additional file 3 of Protocol for a scoping review study on learning plan use in undergraduate medical education","year":2024,"lang":"en","type":"article","venue":"Figshare","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; Ottawa Hospital","funders":"","keywords":"Protocol (science); Plan (archaeology); Data collection; Protocol analysis; MEDLINE; Data extraction","score_opus":0.1710229444398138,"score_gpt":0.48094805455268513,"score_spread":0.3099251101128713,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6902235466","genre_codex":"dataset","genre_gemma":"protocol","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"protocol","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008793099,0.0002760559,0.003030278,0.0011038793,0.00040644043,0.06986662,0.91712755,0.001051031,0.0062587494],"genre_scores_gemma":[0.0072284583,0.00056345906,0.021374933,0.0015787613,0.0002544917,0.84698856,0.10117229,0.0007166787,0.02012235],"study_design_codex":"not_applicable","study_design_gemma":"systematic_review","domain_scores_codex":[0.9927291,0.0025552127,0.0028028004,0.0006196552,0.0009475798,0.00034555348],"domain_scores_gemma":[0.79247844,0.16809334,0.010779514,0.006093394,0.021055827,0.0014995146],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.019865273,0.0015697409,0.0027706348,0.00710815,0.0019706,0.0029046834,0.0018515614,0.002053508,0.8114924],"category_scores_gemma":[0.15171814,0.0017559129,0.002057728,0.008631311,0.0008242308,0.0030998427,0.0021103413,0.0018608351,0.0843861],"study_design_candidate":"systematic_review","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002034279,0.00020217724,0.0008491913,0.067915946,0.00017038171,0.00011363244,0.0008697098,0.00038964328,0.00024721219,0.0026596515,0.8920544,0.032493792],"study_design_scores_gemma":[0.02875829,0.00082520145,0.012809464,0.067196265,0.0007984965,0.00040457613,0.0024351908,0.0015114438,0.0016682919,0.0258737,0.8573095,0.0004096318],"about_ca_topic_score_codex":0.004027077,"about_ca_topic_score_gemma":0.00862988,"teacher_disagreement_score":0.8114924,"about_ca_system_score_codex":0.003901781,"about_ca_system_score_gemma":0.011417543,"threshold_uncertainty_score":0.26888323},"labels":[],"label_agreement":null},{"id":"W6922134379","doi":"10.11575/ajer.v50i3.55088","title":"Teachers' Attitudes Toward Government-Mandated Provincial Testing in Manitoba","year":2009,"lang":"en","type":"article","venue":"University of Calgary","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Negativity effect; Rural area; Test (biology); Measure (data warehouse); Data collection","score_opus":0.028802977772965133,"score_gpt":0.26591936553619494,"score_spread":0.2371163877632298,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6922134379","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9980742,0.000040592142,0.000029873023,0.00036635803,0.0000038545195,0.000008221501,0.000019664978,0.0000043501173,0.001453032],"genre_scores_gemma":[0.99826545,0.00011008147,0.00008111273,0.00011942043,0.0000018366825,0.000008490232,0.0000241559,0.0000029342746,0.0013864783],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.9984977,0.00037536133,0.00008526913,0.00010359824,0.00048640658,0.00045172696],"domain_scores_gemma":[0.9940691,0.0009122646,0.0010130205,0.00018038481,0.0023992213,0.0014260124],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0021420105,0.00015610988,0.00019623298,0.00067734945,0.004059995,0.0015089745,0.0005449254,0.00031781496,0.001655211],"category_scores_gemma":[0.0055250553,0.0003423008,0.00020314107,0.0010396017,0.0016378554,0.0002475657,0.001064311,0.0009946537,0.00021844191],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000111139816,0.0001385806,0.9253831,0.000039095088,0.000019918327,0.0003757209,0.05514895,0.0002064778,0.0031738237,0.0004146962,0.0008507293,0.014137709],"study_design_scores_gemma":[0.0000096861995,0.0001431804,0.9501549,0.000049995677,0.000013715037,0.00009036916,0.045267742,0.00033541495,0.000594313,0.00004690737,0.003272435,0.000021344817],"about_ca_topic_score_codex":0.91273195,"about_ca_topic_score_gemma":0.9654038,"teacher_disagreement_score":0.087268054,"about_ca_system_score_codex":0.015873918,"about_ca_system_score_gemma":0.017617283,"threshold_uncertainty_score":0.17556393},"labels":[],"label_agreement":null},{"id":"W6924725559","doi":"10.15468/dl.t73qgv","title":"Occurrence Download","year":2022,"lang":"en","type":"dataset","venue":"Global Biodiversity Information Facility","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Download; Matching (statistics); Alien; Range (aeronautics); State (computer science); Identification (biology)","score_opus":0.024638893759826846,"score_gpt":0.28368674675292505,"score_spread":0.2590478529930982,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6924725559","genre_codex":"dataset","genre_gemma":"dataset","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"dataset","genre_consensus":"dataset","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.00005609824,0.000027137765,0.000050415932,0.000044125587,0.000014568681,0.0000072617113,0.99865085,0.0004819787,0.0006676934],"genre_scores_gemma":[0.0001730781,0.000029822373,0.00021119346,0.000047951115,0.00000392944,0.000052464235,0.9988527,0.00015346376,0.00047532195],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9989164,0.00016118238,0.00013634021,0.0003757727,0.00024274786,0.00016754722],"domain_scores_gemma":[0.99734384,0.0007915963,0.00022561171,0.0007090253,0.0006208454,0.00030904886],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0010996677,0.0019876126,0.0014923931,0.00462497,0.0010397033,0.0025564958,0.0027630567,0.0021408796,0.14000458],"category_scores_gemma":[0.0063390657,0.0008816448,0.0012361447,0.008594383,0.00046410222,0.0022138255,0.0025305708,0.0021224378,0.2134218],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000026276706,0.000013383213,0.000397024,0.0004708699,0.000012776051,0.000013850958,0.000022261758,0.00012031505,0.000104238454,0.00031540904,0.997195,0.0013086445],"study_design_scores_gemma":[0.000086676184,0.000010422355,0.002100321,0.00018746854,0.000014302491,0.000038839255,0.00008434556,0.00020676681,0.00021383847,0.0008018561,0.9962365,0.00001868926],"about_ca_topic_score_codex":0.019320156,"about_ca_topic_score_gemma":0.03433597,"teacher_disagreement_score":0.8599954,"about_ca_system_score_codex":0.0015764365,"about_ca_system_score_gemma":0.0023327942,"threshold_uncertainty_score":0.46836197},"labels":[],"label_agreement":null},{"id":"W6931027851","doi":"10.5281/zenodo.14233711","title":"Strategies of the Principal in Establishing Partnerships with Stakeholders at SMK Negeri 1 Simpang Kanan in 2023","year":2024,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Christian Studies","funders":"","keywords":"Internship; Principal (computer security); Work (physics); Qualitative research; Data collection","score_opus":0.13942321416138787,"score_gpt":0.32131755364104747,"score_spread":0.1818943394796596,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6931027851","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9632541,0.00059856666,0.0018391651,0.003411713,0.000083541985,0.0004503072,0.000051437368,0.00006423481,0.030246777],"genre_scores_gemma":[0.97164816,0.00041421488,0.0014789146,0.00036795443,0.000008542184,0.00017264305,0.000052847387,0.000018748582,0.025837993],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9969727,0.0016576087,0.00008159447,0.00015499808,0.00036777355,0.00076533935],"domain_scores_gemma":[0.99775225,0.00031242156,0.00026397198,0.000062361076,0.00040134892,0.0012077355],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0036436196,0.00044689266,0.00030281744,0.00074017054,0.010232681,0.0028101625,0.0010743211,0.0013190988,0.0110215675],"category_scores_gemma":[0.0021097702,0.00049538084,0.00023167316,0.0010268742,0.001822006,0.0018995238,0.005324669,0.0013408962,0.0016001253],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005677375,0.0011565168,0.08991656,0.001219372,0.0000493285,0.029458655,0.70444727,0.001008265,0.017492995,0.02039448,0.02189586,0.11239296],"study_design_scores_gemma":[0.000016043752,0.00025871833,0.029343663,0.00020470089,0.000013584521,0.0017168006,0.8521868,0.0005938403,0.0013341582,0.00093476474,0.11335559,0.00004135791],"about_ca_topic_score_codex":0.007966972,"about_ca_topic_score_gemma":0.02002006,"teacher_disagreement_score":0.0110215675,"about_ca_system_score_codex":0.005490449,"about_ca_system_score_gemma":0.011482877,"threshold_uncertainty_score":0.039836228},"labels":[],"label_agreement":null},{"id":"W6939359645","doi":"10.6084/m9.figshare.22615813.v1","title":"Additional file 1 of Introducing ACTFAiREST2 to implement online assessments amid COVID–19: a case study from a low resource setting","year":2023,"lang":"en","type":"article","venue":"Figshare","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Saskatchewan","funders":"","keywords":"Resource (disambiguation); Key (lock); Government (linguistics); Data collection","score_opus":0.09088905368708154,"score_gpt":0.42840310566075385,"score_spread":0.3375140519736723,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6939359645","genre_codex":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0047982433,0.00007608355,0.0048587616,0.0039674556,0.0003267568,0.0036214015,0.9310332,0.0048649744,0.0464532],"genre_scores_gemma":[0.15345527,0.00057437015,0.06623163,0.0071763247,0.00053589366,0.053743657,0.49462205,0.007594582,0.2160663],"study_design_codex":"not_applicable","study_design_gemma":"qualitative","domain_scores_codex":[0.99784744,0.0010365006,0.00028191254,0.00017214441,0.0004740127,0.00018798669],"domain_scores_gemma":[0.89968413,0.08242414,0.002520815,0.002855929,0.009349168,0.0031658774],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0051846267,0.00053007714,0.00050605583,0.0021142643,0.00153844,0.0018156593,0.0017875028,0.0010772209,0.870754],"category_scores_gemma":[0.07113286,0.0003374567,0.0004598548,0.0023202444,0.00036847757,0.0019109542,0.0014988775,0.0011107763,0.1670363],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00015468644,0.00015550929,0.0014495447,0.0008530792,0.000006917362,0.00008232959,0.00046639863,0.00023023167,0.00003177741,0.00061397895,0.97128785,0.024667704],"study_design_scores_gemma":[0.0019892447,0.00043000822,0.019048765,0.0027582143,0.00004942645,0.00038096873,0.0035329491,0.001532372,0.0005978414,0.0075864745,0.9619539,0.00013988363],"about_ca_topic_score_codex":0.009888236,"about_ca_topic_score_gemma":0.019394044,"teacher_disagreement_score":0.870754,"about_ca_system_score_codex":0.0019263971,"about_ca_system_score_gemma":0.0050444426,"threshold_uncertainty_score":0.18435365},"labels":[],"label_agreement":null},{"id":"W6939399316","doi":"10.6084/m9.figshare.26758069.v1","title":"Additional file 1 of Rethinking assessment strategies to improve authentic representations of learning: using blogs as a creative assessment alternative to develop professional skills","year":2024,"lang":"en","type":"article","venue":"Figshare","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Online assessment; Creativity; Qualitative research; The Internet","score_opus":0.05138699011387045,"score_gpt":0.4314784504174476,"score_spread":0.38009146030357716,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6939399316","genre_codex":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0009037797,0.000025763798,0.0011686713,0.0005795846,0.00013495082,0.00093346444,0.9884304,0.00168532,0.0061381133],"genre_scores_gemma":[0.051860474,0.00035942873,0.036870327,0.002296061,0.00051128963,0.0374518,0.7542869,0.008281273,0.108082466],"study_design_codex":"not_applicable","study_design_gemma":"qualitative","domain_scores_codex":[0.9979388,0.0007039931,0.00031415836,0.00023755361,0.0006044529,0.00020096454],"domain_scores_gemma":[0.80009675,0.17270687,0.003592971,0.0055619576,0.016161278,0.0018801787],"candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0055120336,0.0010307339,0.0010407572,0.0028887899,0.0014374137,0.002314517,0.0017763536,0.0013457257,0.9192751],"category_scores_gemma":[0.11631181,0.00056778087,0.00094960793,0.003281668,0.00040342502,0.0028241326,0.0018061469,0.001355359,0.2124514],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00047386618,0.00015221084,0.00096074335,0.0018893033,0.000016831575,0.000028279856,0.00026304013,0.00017625156,0.000058357753,0.00045775415,0.9738792,0.021644168],"study_design_scores_gemma":[0.008570545,0.0007629237,0.03291827,0.004838114,0.00018802086,0.0002228918,0.0021508408,0.0017786006,0.001539937,0.012728596,0.9340049,0.00029640744],"about_ca_topic_score_codex":0.0052136276,"about_ca_topic_score_gemma":0.012677697,"teacher_disagreement_score":0.99448794,"about_ca_system_score_codex":0.0013749746,"about_ca_system_score_gemma":0.0024727536,"threshold_uncertainty_score":0.11514425},"labels":[],"label_agreement":null},{"id":"W6966793858","doi":"10.48550/arxiv.astro-ph/0301378","title":"The initial Helium content of Galactic Globular Cluster stars from the R-parameter: comparison with the CMB constraint","year":2003,"lang":"en","type":"preprint","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Globular cluster; Cosmic microwave background; Metallicity; Stars; Big Bang nucleosynthesis; Nucleosynthesis; Helium; Equation of state; Constraint (computer-aided design)","score_opus":0.08819173292958332,"score_gpt":0.35891130730223664,"score_spread":0.2707195743726533,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6966793858","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99253803,0.0005060584,0.0025815452,0.000039946,0.0000042000793,0.0000035138319,0.0008616548,0.000052761166,0.0034123762],"genre_scores_gemma":[0.9973041,0.00012031456,0.0011141481,0.000009669349,0.0000034530826,0.0000028299482,0.0011741994,0.000016323758,0.0002549723],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9998435,0.000018897512,0.0000070111164,0.0000776694,0.000029199004,0.00002367279],"domain_scores_gemma":[0.99934345,0.0002743118,0.000082101724,0.00010469432,0.00012852444,0.00006695556],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0004544517,0.00029435597,0.00017260762,0.0009356162,0.000270588,0.00065501087,0.0004075774,0.00039565796,0.0012078581],"category_scores_gemma":[0.0011598024,0.000097258315,0.00023551185,0.00070252316,0.0002582624,0.00037881843,0.0005499825,0.00026980205,0.00053663226],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0009809926,0.00006972601,0.84762865,0.00017355755,0.00013515876,0.00035574174,0.00053050416,0.030155433,0.06636573,0.0057319812,0.0012971561,0.046575323],"study_design_scores_gemma":[0.000025718111,0.00006919503,0.9415634,0.000018885794,0.000037394908,0.00017751081,0.00014921946,0.027177857,0.025956644,0.0014238124,0.003365728,0.000034713245],"about_ca_topic_score_codex":0.008461187,"about_ca_topic_score_gemma":0.007212475,"teacher_disagreement_score":0.008461187,"about_ca_system_score_codex":0.0006716086,"about_ca_system_score_gemma":0.00027503542,"threshold_uncertainty_score":0.016823828},"labels":[],"label_agreement":null},{"id":"W6967454824","doi":"10.5281/zenodo.11196292","title":"HOLISTIC APPROACHES TO ASSESSMENT: BRIDGING GAPS IN TEACHING AND LEARNING","year":2024,"lang":"en","type":"article","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Bell (Canada)","funders":"","keywords":"Bridging (networking); Variety (cybernetics); Process (computing); Quality (philosophy); Promotion (chess); Holistic education; Cognition","score_opus":0.1268015008519633,"score_gpt":0.34620474149193614,"score_spread":0.21940324063997285,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6967454824","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.031149976,0.04310532,0.7934963,0.022534994,0.0018194765,0.00088090095,0.000090449146,0.000665502,0.10625709],"genre_scores_gemma":[0.43176585,0.022536341,0.5297587,0.0027090472,0.00064787036,0.0018705897,0.00014252638,0.00024543292,0.0103235915],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.95385855,0.029292282,0.0023066497,0.0022896673,0.011412941,0.00083986827],"domain_scores_gemma":[0.9652358,0.024389217,0.0017451518,0.0036132983,0.0038479574,0.0011684527],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.034430802,0.0012305628,0.0019362883,0.005829005,0.0027097873,0.016636355,0.0031550692,0.0029602114,0.004369747],"category_scores_gemma":[0.0452831,0.00071888044,0.00059187337,0.004361173,0.022166908,0.021555081,0.017095642,0.0045238663,0.00075798784],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000091378715,0.00013379577,0.001920378,0.0022031202,0.00008045446,0.00020824623,0.041800715,0.0019643798,0.0011628409,0.44285554,0.0043444918,0.5032346],"study_design_scores_gemma":[0.000030405916,0.00019483583,0.0021833472,0.0027649638,0.00004481634,0.0006659468,0.019935455,0.004590327,0.0007555945,0.87133247,0.09740257,0.000099178054],"about_ca_topic_score_codex":0.0016454057,"about_ca_topic_score_gemma":0.0023742702,"teacher_disagreement_score":0.034430802,"about_ca_system_score_codex":0.005863448,"about_ca_system_score_gemma":0.012215586,"threshold_uncertainty_score":0.18208969},"labels":[],"label_agreement":null},{"id":"W6976950042","doi":"10.6084/m9.figshare.26758069","title":"Additional file 1 of Rethinking assessment strategies to improve authentic representations of learning: using blogs as a creative assessment alternative to develop professional skills","year":2024,"lang":"en","type":"article","venue":"Figshare","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Online assessment; Creativity; Qualitative research; The Internet","score_opus":0.05138699011387045,"score_gpt":0.4314784504174476,"score_spread":0.38009146030357716,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6976950042","genre_codex":"dataset","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0009037797,0.000025763798,0.0011686713,0.0005795846,0.00013495082,0.00093346444,0.9884304,0.00168532,0.0061381133],"genre_scores_gemma":[0.051860474,0.00035942873,0.036870327,0.002296061,0.00051128963,0.0374518,0.7542869,0.008281273,0.108082466],"study_design_codex":"not_applicable","study_design_gemma":"qualitative","domain_scores_codex":[0.9979388,0.0007039931,0.00031415836,0.00023755361,0.0006044529,0.00020096454],"domain_scores_gemma":[0.80009675,0.17270687,0.003592971,0.0055619576,0.016161278,0.0018801787],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0055120336,0.0010307339,0.0010407572,0.0028887899,0.0014374137,0.002314517,0.0017763536,0.0013457257,0.9192751],"category_scores_gemma":[0.11631181,0.00056778087,0.00094960793,0.003281668,0.00040342502,0.0028241326,0.0018061469,0.001355359,0.2124514],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00047386618,0.00015221084,0.00096074335,0.0018893033,0.000016831575,0.000028279856,0.00026304013,0.00017625156,0.000058357753,0.00045775415,0.9738792,0.021644168],"study_design_scores_gemma":[0.008570545,0.0007629237,0.03291827,0.004838114,0.00018802086,0.0002228918,0.0021508408,0.0017786006,0.001539937,0.012728596,0.9340049,0.00029640744],"about_ca_topic_score_codex":0.0052136276,"about_ca_topic_score_gemma":0.012677697,"teacher_disagreement_score":0.9192751,"about_ca_system_score_codex":0.0013749746,"about_ca_system_score_gemma":0.0024727536,"threshold_uncertainty_score":0.11514425},"labels":[],"label_agreement":null},{"id":"W6977076320","doi":"10.6084/m9.figshare.26720376","title":"Additional file 3 of Protocol for a scoping review study on learning plan use in undergraduate medical education","year":2024,"lang":"en","type":"article","venue":"Figshare","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Ottawa; Ottawa Hospital","funders":"","keywords":"Protocol (science); Plan (archaeology); Data collection; Protocol analysis; MEDLINE; Data extraction","score_opus":0.1710229444398138,"score_gpt":0.48094805455268513,"score_spread":0.3099251101128713,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6977076320","genre_codex":"dataset","genre_gemma":"protocol","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"protocol","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008793099,0.0002760559,0.003030278,0.0011038793,0.00040644043,0.06986662,0.91712755,0.001051031,0.0062587494],"genre_scores_gemma":[0.0072284583,0.00056345906,0.021374933,0.0015787613,0.0002544917,0.84698856,0.10117229,0.0007166787,0.02012235],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9927291,0.0025552127,0.0028028004,0.0006196552,0.0009475798,0.00034555348],"domain_scores_gemma":[0.79247844,0.16809334,0.010779514,0.006093394,0.021055827,0.0014995146],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.019865273,0.0015697409,0.0027706348,0.00710815,0.0019706,0.0029046834,0.0018515614,0.002053508,0.8114924],"category_scores_gemma":[0.15171814,0.0017559129,0.002057728,0.008631311,0.0008242308,0.0030998427,0.0021103413,0.0018608351,0.0843861],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002034279,0.00020217724,0.0008491913,0.067915946,0.00017038171,0.00011363244,0.0008697098,0.00038964328,0.00024721219,0.0026596515,0.8920544,0.032493792],"study_design_scores_gemma":[0.02875829,0.00082520145,0.012809464,0.067196265,0.0007984965,0.00040457613,0.0024351908,0.0015114438,0.0016682919,0.0258737,0.8573095,0.0004096318],"about_ca_topic_score_codex":0.004027077,"about_ca_topic_score_gemma":0.00862988,"teacher_disagreement_score":0.8114924,"about_ca_system_score_codex":0.003901781,"about_ca_system_score_gemma":0.011417543,"threshold_uncertainty_score":0.26888323},"labels":[],"label_agreement":null},{"id":"W6977109243","doi":"10.6084/m9.figshare.26586285.v1","title":"Additional file 1 of Breastfeeding support provided by lactation consultants in high-income countries for improved breastfeeding rates, self-efficacy, and infant growth: a systematic review and meta-analysis protocol","year":2024,"lang":"en","type":"article","venue":"Figshare","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"SickKids Foundation; Hospital for Sick Children; Toronto Western Hospital; University of Toronto","funders":"","keywords":"Breastfeeding; Protocol (science); MEDLINE; Breast feeding; Lactation","score_opus":0.029451509741930854,"score_gpt":0.33811026254807486,"score_spread":0.308658752806144,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6977109243","genre_codex":"dataset","genre_gemma":"protocol","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"protocol","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0006939667,0.00061392225,0.0009627288,0.0004843906,0.00012400263,0.014588873,0.98071164,0.00037714542,0.0014433538],"genre_scores_gemma":[0.017932199,0.002344937,0.024754548,0.0022646987,0.00026689662,0.61283195,0.32130703,0.0007535879,0.017544193],"study_design_codex":"not_applicable","study_design_gemma":"meta_analysis","domain_scores_codex":[0.99700385,0.00086158654,0.0011024952,0.00041861009,0.0003832812,0.00023019504],"domain_scores_gemma":[0.95112526,0.037799146,0.004827419,0.0014393433,0.004225814,0.00058311166],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.008407836,0.0018322207,0.0036735088,0.005266375,0.0011467678,0.0021853237,0.0020755206,0.0016477134,0.75422204],"category_scores_gemma":[0.07210816,0.0015947259,0.005002111,0.0078003365,0.0006235039,0.003111343,0.0015958925,0.00166558,0.028572625],"study_design_candidate":"meta_analysis","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0036274085,0.00021835479,0.0017767057,0.42736492,0.0018561865,0.00011671956,0.0003405856,0.0007691166,0.0002981417,0.002628775,0.54227495,0.018728156],"study_design_scores_gemma":[0.14836054,0.0020238415,0.046086174,0.21331467,0.0139625715,0.0008064974,0.0013320902,0.004094853,0.0018443717,0.023869032,0.54355896,0.000746528],"about_ca_topic_score_codex":0.0069085276,"about_ca_topic_score_gemma":0.018566322,"teacher_disagreement_score":0.75422204,"about_ca_system_score_codex":0.0026315588,"about_ca_system_score_gemma":0.0074945497,"threshold_uncertainty_score":0.3505724},"labels":[],"label_agreement":null},{"id":"W6980799941","doi":"","title":"Credit repair for survivors of modern slavery and human trafficking","year":2022,"lang":"en","type":"other","venue":"UNU Collections (United Nations University)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Human trafficking; Financial sector; Credit crunch; Debt; Government (linguistics)","score_opus":0.025212338900149414,"score_gpt":0.2777655466348463,"score_spread":0.2525532077346969,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6980799941","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.19536993,0.0044072648,0.0024916606,0.28622228,0.008992462,0.0012360709,0.003484894,0.00057193753,0.4972235],"genre_scores_gemma":[0.41363075,0.006479588,0.004620611,0.029181153,0.0010385676,0.0011525393,0.0020465604,0.00025065395,0.5415996],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.997948,0.00084195146,0.00007290996,0.00006787226,0.0004063157,0.00066295546],"domain_scores_gemma":[0.991434,0.002511844,0.00043949948,0.00028305556,0.002562836,0.0027687934],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0057179937,0.00034274947,0.00021851086,0.00095344364,0.010684519,0.0031264976,0.0010000993,0.0031010378,0.06930399],"category_scores_gemma":[0.017820915,0.00016340346,0.0002809461,0.0007420081,0.001366494,0.0039077103,0.0054785865,0.0023733715,0.0057926485],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000101168225,0.0002640873,0.0066676023,0.0003653266,0.0000045751044,0.0005742841,0.04722149,0.0001975631,0.00034122076,0.011115337,0.7751824,0.15796494],"study_design_scores_gemma":[0.00000867865,0.0001014831,0.0048100897,0.0004196497,0.0000027825536,0.00016474124,0.1244977,0.00006806252,0.00021491102,0.0021285724,0.86756605,0.000017307719],"about_ca_topic_score_codex":0.025315454,"about_ca_topic_score_gemma":0.09589072,"teacher_disagreement_score":0.06930399,"about_ca_system_score_codex":0.0034509941,"about_ca_system_score_gemma":0.010961231,"threshold_uncertainty_score":0.23184496},"labels":[],"label_agreement":null},{"id":"W6981475138","doi":"","title":"El marketing digital y los emprendimientos en el sector de artesanías en la región Tacna, Perú","year":2024,"lang":"en","type":"article","venue":"Dialnet (Universidad de la Rioja)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Craft; Purchasing; The Internet; E-commerce; Clothing","score_opus":0.00982829444486833,"score_gpt":0.3061886526824386,"score_spread":0.2963603582375703,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6981475138","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99553585,0.000120770164,0.000038107337,0.00020787724,0.0000014793767,0.000016331112,0.000032462747,0.0000047654685,0.0040423363],"genre_scores_gemma":[0.9978752,0.00033479003,0.00010021436,0.000033526852,0.0000036135036,0.000019665202,0.00003290724,0.0000014866208,0.0015986713],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9996972,0.00013267004,0.000011088936,0.000035167577,0.00005566365,0.000068278554],"domain_scores_gemma":[0.99860364,0.0005832891,0.00038368648,0.00006699321,0.00023580891,0.00012653759],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006512729,0.00018505946,0.0001297519,0.00062317116,0.000968481,0.0011314992,0.00022231374,0.00040915635,0.0024614283],"category_scores_gemma":[0.002662547,0.00012050626,0.00010042935,0.00064276916,0.0008070601,0.00062938087,0.0013032033,0.00034671804,0.0002257577],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00018820478,0.0007138323,0.70606565,0.00030777327,0.000026602667,0.0034756481,0.19798052,0.0005095277,0.0076697962,0.0013579528,0.0018148298,0.07988967],"study_design_scores_gemma":[0.000014836996,0.00042361722,0.81179845,0.00012255767,0.000022906952,0.00044914806,0.15969723,0.0005190029,0.00076562684,0.00019306823,0.025978066,0.000015456633],"about_ca_topic_score_codex":0.026446898,"about_ca_topic_score_gemma":0.05387777,"teacher_disagreement_score":0.026446898,"about_ca_system_score_codex":0.0011841084,"about_ca_system_score_gemma":0.00087245647,"threshold_uncertainty_score":0.05258596},"labels":[],"label_agreement":null},{"id":"W6981765487","doi":"","title":"FAIRNESS IN CLASSROOM ASSESSMENT: CONCEPTUAL AND EMPIRICAL INVESTIGATIONS","year":2021,"lang":"en","type":"dissertation","venue":"QSpace (Queen's University Library)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Set (abstract data type); Work (physics); Reliability (semiconductor); Quality (philosophy); Subconscious; Limiting","score_opus":0.020941052767542188,"score_gpt":0.29154497184692624,"score_spread":0.270603919079384,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6981765487","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.86151457,0.021585187,0.035051923,0.011331529,0.0002089193,0.0003406753,0.000033171793,0.000027881526,0.0699062],"genre_scores_gemma":[0.99505866,0.0018686712,0.0025094955,0.00023466209,0.000041551317,0.000077290264,0.0000062829017,0.0000042552274,0.00019914012],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","domain_scores_codex":[0.9647624,0.02223461,0.0017793353,0.0023516521,0.0074170795,0.0014549281],"domain_scores_gemma":[0.80371034,0.16396073,0.016320417,0.004164495,0.009218226,0.0026257476],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.046601713,0.00037236835,0.0007137675,0.0058302046,0.0059885276,0.0077661234,0.002270069,0.0019621714,0.0016304913],"category_scores_gemma":[0.10369295,0.0005319752,0.00044845341,0.005847124,0.021643566,0.012050349,0.0072957086,0.0040763454,0.00009353784],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010896536,0.0009824729,0.14164664,0.00090588274,0.00005304676,0.00029311999,0.19502953,0.0014787904,0.00042674586,0.49428996,0.0008093665,0.16397545],"study_design_scores_gemma":[0.00009503224,0.00032467738,0.20176648,0.0062377034,0.00009372215,0.0007798062,0.33500382,0.013880397,0.0016012256,0.4010162,0.038993068,0.00020786763],"about_ca_topic_score_codex":0.009222467,"about_ca_topic_score_gemma":0.0073685697,"teacher_disagreement_score":0.046601713,"about_ca_system_score_codex":0.011291448,"about_ca_system_score_gemma":0.009753391,"threshold_uncertainty_score":0.24645638},"labels":[],"label_agreement":null},{"id":"W6991109319","doi":"","title":"Exploring K–12 Teachers’ Assessment Literacy and Self-efficacy in China","year":2024,"lang":"en","type":"article","venue":"DOAJ (DOAJ: Directory of Open Access Journals)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Literacy; China; Educational assessment; Quantitative assessment; Professional development; Adult literacy","score_opus":0.3368514475856944,"score_gpt":0.5943787217653435,"score_spread":0.25752727417964905,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6991109319","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9992962,0.00001643953,0.000022304965,0.000030235105,7.50005e-7,0.000004511357,0.000013614001,8.8569357e-7,0.00061498507],"genre_scores_gemma":[0.9997063,0.000019775227,0.000032498727,0.000009258569,5.77516e-7,0.0000066687853,0.000023317272,5.437801e-7,0.00020100297],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9989779,0.00022315698,0.00011684558,0.00013162721,0.00025932153,0.00029116482],"domain_scores_gemma":[0.9973205,0.000619771,0.0006058178,0.00014052712,0.00067392376,0.0006395097],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002342731,0.00027102695,0.00037891755,0.0020360423,0.0016102055,0.0011005265,0.00037698256,0.00025653077,0.0012152229],"category_scores_gemma":[0.0035658588,0.00023633875,0.00025842641,0.0026398306,0.0010455551,0.0007450748,0.0011541332,0.00039066176,0.0001303101],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000033057935,0.00012082086,0.9615499,0.000034964156,0.000017285436,0.00013818838,0.026246043,0.00012493842,0.00036720184,0.00034211914,0.00015583873,0.010869575],"study_design_scores_gemma":[0.00000455044,0.00006014523,0.98595536,0.000018103068,0.0000073934784,0.000030300227,0.012886522,0.00035083358,0.00011913413,0.000062482664,0.0004979334,0.000007279367],"about_ca_topic_score_codex":0.112729795,"about_ca_topic_score_gemma":0.1416224,"teacher_disagreement_score":0.112729795,"about_ca_system_score_codex":0.0022790073,"about_ca_system_score_gemma":0.00472674,"threshold_uncertainty_score":0.22414726},"labels":[],"label_agreement":null},{"id":"W6991573789","doi":"","title":"Grade Scaling: Issues and Approaches","year":2003,"lang":"en","type":"article","venue":"Carleton University's Institutional Repository (MacOdrum Library, Carleton University)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Carleton University","funders":"","keywords":"Context (archaeology); Set (abstract data type); Class (philosophy); Test (biology); Axiom; Scaling","score_opus":0.03188456343583341,"score_gpt":0.2327190848528795,"score_spread":0.2008345214170461,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6991573789","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.007215154,0.010703378,0.799336,0.079407185,0.0039805113,0.0009176005,0.00026997493,0.00068625814,0.09748399],"genre_scores_gemma":[0.26298162,0.008553,0.69196415,0.010116242,0.005070255,0.0029845044,0.00025209438,0.00074079965,0.017337328],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.831256,0.10067697,0.013680581,0.01561506,0.036995474,0.0017760241],"domain_scores_gemma":[0.76172984,0.13865276,0.011029959,0.028189484,0.057790134,0.0026078124],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.10352613,0.0023115946,0.002449333,0.012710687,0.0077608665,0.022298947,0.011687242,0.008517812,0.0075128633],"category_scores_gemma":[0.26837045,0.001774611,0.0021617222,0.015288627,0.04003422,0.021014242,0.011236727,0.015941624,0.0029053534],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00001912583,0.00004989811,0.001345565,0.0003397031,0.00002958746,0.000040834584,0.003081839,0.0009486502,0.00011246097,0.89954287,0.0068535325,0.08763593],"study_design_scores_gemma":[0.000021013222,0.00005798054,0.0013820687,0.001119331,0.000028625685,0.00015664288,0.00314095,0.0045462227,0.00041929862,0.9167475,0.07229045,0.000089911184],"about_ca_topic_score_codex":0.0070413193,"about_ca_topic_score_gemma":0.0049513206,"teacher_disagreement_score":0.10352613,"about_ca_system_score_codex":0.012167797,"about_ca_system_score_gemma":0.008165454,"threshold_uncertainty_score":0.547505},"labels":[],"label_agreement":null},{"id":"W6991650725","doi":"","title":"Impacts of pre/post examination metacognition prompts on study strategies and predicting grades","year":2023,"lang":"en","type":"article","venue":"Scholarship@Western (Western University)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Metacognition; Cognition; Class (philosophy); Inclusion (mineral); Academic achievement; Qualitative property","score_opus":0.13614975146700337,"score_gpt":0.3905274174875319,"score_spread":0.2543776660205285,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6991650725","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9993055,0.00002564735,0.00013227966,0.000025855406,0.0000038962858,0.000016817217,0.000035482866,0.000009242815,0.00044526462],"genre_scores_gemma":[0.9989281,0.000031799267,0.00051672757,0.000007907564,0.000002997351,0.000032248754,0.00006314144,0.0000035054015,0.00041342308],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9965951,0.0013827808,0.00036205008,0.00040338156,0.0008915992,0.0003651116],"domain_scores_gemma":[0.90657955,0.064622305,0.015732704,0.0030501655,0.0046824072,0.0053329472],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0054780976,0.00042961823,0.00031703722,0.0011247285,0.00043526362,0.0018345191,0.0006818044,0.00046066343,0.0018742979],"category_scores_gemma":[0.050826643,0.00026688952,0.00038087287,0.0007093854,0.00044288504,0.00084229914,0.001245291,0.00088580494,0.00034943226],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00090667716,0.0010867034,0.9488549,0.00007306229,0.0000505079,0.00010918689,0.003658463,0.00046041748,0.0020093587,0.00006700865,0.00014003037,0.042583596],"study_design_scores_gemma":[0.0000064067262,0.0010509292,0.9948257,0.000029516113,0.000018491439,0.000038413094,0.001997686,0.0006931047,0.0010255452,0.00005442862,0.0002476646,0.000012143879],"about_ca_topic_score_codex":0.0026724264,"about_ca_topic_score_gemma":0.0055369446,"teacher_disagreement_score":0.0054780976,"about_ca_system_score_codex":0.00070432544,"about_ca_system_score_gemma":0.0012395055,"threshold_uncertainty_score":0.028971314},"labels":[],"label_agreement":null},{"id":"W6992297165","doi":"","title":"La motivation scolaire des élèves du secondaire est-elle plus élevée lorsque ces derniers participent à un programme particulier de plein air?","year":2023,"lang":"fr","type":"other","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Context (archaeology); General interest; Decorum","score_opus":0.036960269624157195,"score_gpt":0.3020176555506169,"score_spread":0.26505738592645967,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6992297165","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9948525,0.00014554622,0.000242075,0.00020313768,0.000011113477,0.00000968805,0.000058719295,0.0000046865025,0.004472602],"genre_scores_gemma":[0.9955753,0.00010910067,0.00017120622,0.000040504572,0.0000050726,0.000016412121,0.00006279253,0.0000032411183,0.004016354],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99937844,0.00014548247,0.00001388645,0.00012120973,0.00012979386,0.00021120813],"domain_scores_gemma":[0.9977841,0.0003530993,0.00058309024,0.00007331044,0.0003447971,0.00086164713],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010144699,0.00018128841,0.0002963476,0.0004328142,0.0009644613,0.0014715736,0.0003083898,0.00038472112,0.0054660463],"category_scores_gemma":[0.0024251437,0.00015034691,0.00023623422,0.00042118446,0.00095197896,0.0004999221,0.0007810348,0.00059825357,0.00045318293],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003161465,0.0002597594,0.8955798,0.0002014253,0.00009958247,0.00016147037,0.043313663,0.0003126709,0.005338795,0.0023810386,0.00086332107,0.051172297],"study_design_scores_gemma":[0.0000021814094,0.00006434443,0.9914814,0.000021699881,0.000006575336,0.000010127729,0.0067659104,0.00004781978,0.00011766453,0.000079144025,0.0013953607,0.000007711019],"about_ca_topic_score_codex":0.09254313,"about_ca_topic_score_gemma":0.23576112,"teacher_disagreement_score":0.09254313,"about_ca_system_score_codex":0.0019740786,"about_ca_system_score_gemma":0.0028730936,"threshold_uncertainty_score":0.18400896},"labels":[],"label_agreement":null},{"id":"W6995956337","doi":"","title":"Public knowledge and perceptions of large-scale assessments","year":2016,"lang":"en","type":"article","venue":"IslandScholar (University of Prince Edward Island)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Center for Makroøkologi, Evolution og Klima","keywords":"Nucleofection; Gestational period; Diafiltration; TSG101; Articular cartilage damage; Hyporeflexia; Dysgeusia; Tubulopathy","score_opus":0.022389491914067885,"score_gpt":0.3044506025167043,"score_spread":0.28206111060263644,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6995956337","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9946585,0.00007253442,0.00018105327,0.00062434876,0.0000075080998,0.000019125053,0.000015815625,0.000006289618,0.004414791],"genre_scores_gemma":[0.99944824,0.00007149547,0.0000611279,0.000060124617,0.0000045124175,0.0000056310523,0.000008190506,0.0000011344242,0.00033938512],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99448544,0.0021565729,0.00035786143,0.00021495698,0.002092212,0.0006929102],"domain_scores_gemma":[0.95628625,0.021035992,0.009306024,0.0015519634,0.0074821156,0.004337638],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0085112825,0.00019307708,0.0002736408,0.0012052791,0.0013458387,0.0026785324,0.0004277152,0.0007405046,0.002954319],"category_scores_gemma":[0.031936463,0.00020691275,0.00026609935,0.00066464266,0.0019611379,0.0015696244,0.0017773431,0.0014178109,0.00022146643],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025893343,0.00073931087,0.7120521,0.0002508842,0.000052997828,0.0010296768,0.21230768,0.00058849115,0.003223353,0.001492831,0.0015601326,0.06644354],"study_design_scores_gemma":[0.000019864194,0.0007611831,0.6142517,0.0004003588,0.000042053307,0.0004099197,0.370691,0.0015088987,0.0011722302,0.001061492,0.009591021,0.0000903216],"about_ca_topic_score_codex":0.025184253,"about_ca_topic_score_gemma":0.02260173,"teacher_disagreement_score":0.025184253,"about_ca_system_score_codex":0.0024394381,"about_ca_system_score_gemma":0.0026575981,"threshold_uncertainty_score":0.050075293},"labels":[],"label_agreement":null},{"id":"W6996631828","doi":"","title":"In the service of the stakeholder: a critical, mixed-method program of research in high-stakes language assessment","year":2011,"lang":"en","type":"dissertation","venue":"eScholarship@McGill (McGill)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Test (biology); Certification; Stakeholder; Language assessment; Language proficiency; Perception; Task (project management); Service (business); Field (mathematics)","score_opus":0.10398658210226995,"score_gpt":0.4408162889804222,"score_spread":0.3368297068781522,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6996631828","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.72539556,0.0025178012,0.09320697,0.0030436283,0.00057110854,0.16621543,0.00040711937,0.00025052886,0.008391839],"genre_scores_gemma":[0.55371094,0.0008746502,0.2674043,0.004028167,0.00022634714,0.16977584,0.00022531209,0.00013598656,0.0036184923],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.71671164,0.24829571,0.0075279353,0.008726214,0.014683908,0.004054577],"domain_scores_gemma":[0.6529102,0.26944923,0.012775324,0.027043125,0.03515228,0.0026699186],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.26738977,0.0014679758,0.0019154643,0.004812097,0.010191752,0.0073087844,0.0060189464,0.004186808,0.0027897616],"category_scores_gemma":[0.21460053,0.0016227654,0.0017686043,0.004777394,0.0064588157,0.0056895767,0.006369501,0.0032131027,0.0005877544],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0032835095,0.020762967,0.030371217,0.00865541,0.0010515857,0.0014567971,0.6217349,0.0021346775,0.015677197,0.022235684,0.0038864634,0.2687496],"study_design_scores_gemma":[0.00864992,0.04755348,0.06582902,0.010800281,0.001825159,0.0011838546,0.66571677,0.011129646,0.0425793,0.03169959,0.11227705,0.0007558915],"about_ca_topic_score_codex":0.008924136,"about_ca_topic_score_gemma":0.028000843,"teacher_disagreement_score":0.26738977,"about_ca_system_score_codex":0.0125015145,"about_ca_system_score_gemma":0.023975177,"threshold_uncertainty_score":0.90343887},"labels":[],"label_agreement":null},{"id":"W6996941080","doi":"","title":"A study of the reliability and validity of the standardized exams used in grade 10 science in a Winnipeg school division","year":2009,"lang":"en","type":"dissertation","venue":"Mspace (University of Manitoba)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Reliability (semiconductor); Test (biology); Affect (linguistics); Statistical analysis; Quality (philosophy); Standardized test; Validity","score_opus":0.03187281653173227,"score_gpt":0.3007936059981488,"score_spread":0.2689207894664165,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W6996941080","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9980855,0.00014462901,0.00029759182,0.00005430021,0.000020478548,0.00009602943,0.00010574183,0.000008430653,0.0011873231],"genre_scores_gemma":[0.99714416,0.00014880004,0.0013594462,0.000041642452,0.00000990423,0.000081882696,0.00030183967,0.0000072286066,0.00090511964],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99419045,0.0023889004,0.0004717762,0.00066479744,0.0018426819,0.00044133127],"domain_scores_gemma":[0.96931714,0.0074213874,0.0057511027,0.0017243241,0.014272027,0.0015140495],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0105240205,0.0004325851,0.00037990915,0.0023409596,0.0014134242,0.0011655056,0.0011787298,0.00024602938,0.00074205373],"category_scores_gemma":[0.04117876,0.0004574127,0.00021572142,0.0022538258,0.0010837787,0.0003890833,0.001052539,0.00044500944,0.00026404217],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000085518994,0.00009283796,0.9740794,0.000045453635,0.000070152,0.00006382448,0.00533174,0.00007706717,0.00092387217,0.00010669383,0.00030699832,0.018816397],"study_design_scores_gemma":[0.00001218875,0.000104817234,0.9958807,0.000026554368,0.000014414411,0.00003010224,0.0022837135,0.00017433865,0.00034668043,0.000016072803,0.0011054348,0.0000050525086],"about_ca_topic_score_codex":0.4236651,"about_ca_topic_score_gemma":0.65176064,"teacher_disagreement_score":0.98947597,"about_ca_system_score_codex":0.003993742,"about_ca_system_score_gemma":0.0055556647,"threshold_uncertainty_score":0.84239817},"labels":[],"label_agreement":null},{"id":"W7000495802","doi":"","title":"Frequent, low-stakes assessments: Balance and benefits","year":2025,"lang":"en","type":"article","venue":"Scholarship@Western (Western University)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Workload; Stakeholder; Isolation (microbiology); Perception; Online assessment; Balance (ability); Contradiction; Stakeholder engagement","score_opus":0.10167408059832438,"score_gpt":0.3821524828414491,"score_spread":0.2804784022431247,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7000495802","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.74804455,0.0039583137,0.053581256,0.025076892,0.0005862395,0.0039956984,0.0011374254,0.0016199843,0.16199966],"genre_scores_gemma":[0.94992304,0.00092312647,0.04009508,0.0011345871,0.00017058008,0.0011916122,0.00024812273,0.00017974147,0.0061340407],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.8996478,0.050579876,0.0048028636,0.0043958747,0.037386365,0.0031872517],"domain_scores_gemma":[0.78871095,0.12231946,0.014563741,0.018190939,0.04478362,0.0114312405],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.066110075,0.00065481826,0.00077727117,0.003182591,0.0026153452,0.007859655,0.0019652357,0.0012123713,0.005155926],"category_scores_gemma":[0.20282625,0.000520387,0.0005719237,0.0022100685,0.0024626532,0.005297519,0.0055876435,0.0024320995,0.0012632097],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00076765293,0.0013251083,0.07767178,0.0013052851,0.000098641794,0.0001895022,0.016805075,0.00050207746,0.002661687,0.006759632,0.008380921,0.8835326],"study_design_scores_gemma":[0.00045387776,0.005058826,0.7070542,0.008912742,0.00042715276,0.0012488401,0.060282595,0.0064013735,0.009070939,0.041390717,0.1592406,0.00045804237],"about_ca_topic_score_codex":0.018248476,"about_ca_topic_score_gemma":0.07032646,"teacher_disagreement_score":0.066110075,"about_ca_system_score_codex":0.007983401,"about_ca_system_score_gemma":0.013991505,"threshold_uncertainty_score":0.34962767},"labels":[],"label_agreement":null},{"id":"W7001130225","doi":"","title":"Intensive training and practice (ITaP): Impact and possibilities for primary trainee teachers and schools","year":2024,"lang":"en","type":"article","venue":"Edge Hill University Research Information Repository (Edge Hill University)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Education and Early Childhood Development","funders":"","keywords":"Curriculum; Control (management); Focus (optics); Training (meteorology); Focus group","score_opus":0.06463478474217471,"score_gpt":0.3576662179976658,"score_spread":0.2930314332554911,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7001130225","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.4538929,0.009480422,0.018121986,0.08501188,0.0010248317,0.0005827374,0.00019452284,0.00092949125,0.43076128],"genre_scores_gemma":[0.9624831,0.004038447,0.01053813,0.0023899218,0.00023181917,0.00021825923,0.0000950323,0.000080858415,0.019924529],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9892783,0.0055658445,0.0002584564,0.00037236116,0.0034678448,0.0010571609],"domain_scores_gemma":[0.97971135,0.01282224,0.00090212363,0.00084958324,0.0017492076,0.003965533],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008501397,0.00021995296,0.0002875619,0.0011542217,0.002190439,0.005218365,0.00089665526,0.0011815942,0.012524971],"category_scores_gemma":[0.022948196,0.00023099383,0.00029524186,0.0007360412,0.0027118253,0.00374006,0.008682891,0.0017328135,0.0010985023],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013132284,0.00069012394,0.008615771,0.0005032933,0.000008050814,0.00019416699,0.019441066,0.0001662012,0.0009046787,0.008537085,0.013014538,0.9477938],"study_design_scores_gemma":[0.00020666287,0.0047207107,0.18787621,0.0055812174,0.00005882072,0.002290539,0.19863081,0.0014671247,0.0047246288,0.052111402,0.5421828,0.0001490952],"about_ca_topic_score_codex":0.0029875124,"about_ca_topic_score_gemma":0.00647532,"teacher_disagreement_score":0.012524971,"about_ca_system_score_codex":0.0018896988,"about_ca_system_score_gemma":0.007278455,"threshold_uncertainty_score":0.0449602},"labels":[],"label_agreement":null},{"id":"W7006674247","doi":"","title":"Using \"assessment for learning\" practices with pre-university level students of English as a Second Language: a mixed methods study of teacher and student performance and beliefs","year":2011,"lang":"en","type":"dissertation","venue":"eScholarship@McGill (McGill)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Class (philosophy); Control (management); Data collection; Exploratory research; Language acquisition; Action research; English language; Note-taking; Teaching method","score_opus":0.05408613286330487,"score_gpt":0.40666346692551686,"score_spread":0.352577334062212,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7006674247","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9984505,0.00007957896,0.00052720594,0.00004379459,0.000005152953,0.00026529556,0.000020308265,0.00000682328,0.0006012884],"genre_scores_gemma":[0.99334514,0.00026983328,0.0032676745,0.00014383288,0.000013797655,0.0011003976,0.00007428878,0.000010471196,0.0017746099],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.9881235,0.006903178,0.0008319931,0.0012244387,0.0019949507,0.0009219448],"domain_scores_gemma":[0.9771399,0.014436672,0.0030218111,0.0018384178,0.002405231,0.0011578944],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0145508805,0.000852615,0.0016073617,0.0018863739,0.0043671792,0.0037669097,0.0020962588,0.0015726665,0.0015619871],"category_scores_gemma":[0.026049033,0.0008774268,0.00078137795,0.0013322498,0.0030216444,0.0023362415,0.002976692,0.0022917117,0.0005775674],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00087627454,0.020434182,0.11726194,0.00056405214,0.00017276323,0.00081055745,0.75085354,0.00026798047,0.010439685,0.0011749922,0.00045110402,0.09669292],"study_design_scores_gemma":[0.00036542106,0.030249069,0.27620837,0.00042860312,0.00017397628,0.0013186176,0.6645237,0.0012857094,0.012825016,0.0015168702,0.010893271,0.00021130826],"about_ca_topic_score_codex":0.0029128762,"about_ca_topic_score_gemma":0.006543501,"teacher_disagreement_score":0.0145508805,"about_ca_system_score_codex":0.002142395,"about_ca_system_score_gemma":0.002661948,"threshold_uncertainty_score":0.07695335},"labels":[],"label_agreement":null},{"id":"W7010134099","doi":"","title":"Gormley - Scott Aitchison - Thursday, May 12, 2022","year":2022,"lang":"en","type":"other","venue":"Bulletin of Miscellaneous Information (Royal Gardens Kew)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Yesterday; Joins; Field (mathematics); Work (physics)","score_opus":0.00968297778947116,"score_gpt":0.2375199158444829,"score_spread":0.22783693805501173,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7010134099","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.004755749,0.0016306618,0.00034070737,0.03549985,0.010849198,0.00021669744,0.0030182134,0.001360032,0.9423288],"genre_scores_gemma":[0.0024759157,0.00019293108,0.000050233415,0.00063744845,0.00012694731,0.000016572112,0.00016565643,0.000071011396,0.9962633],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99957067,0.0000474377,0.000010615646,0.000057534005,0.00022190614,0.000091831214],"domain_scores_gemma":[0.9984444,0.00012075209,0.000035976052,0.00005470428,0.0006897693,0.00065451476],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00073067815,0.0005253006,0.00035724216,0.00070313027,0.003525026,0.0027505986,0.00045019563,0.00127494,0.58362985],"category_scores_gemma":[0.003128127,0.00022736397,0.00016290051,0.0007449949,0.00045533717,0.0013822404,0.001333791,0.0015117703,0.251147],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000016168819,0.000013910294,0.00014046248,0.000011698817,2.800951e-7,0.000026335447,0.00007275452,0.0000036768945,0.000046136076,0.00018632333,0.99021775,0.009264483],"study_design_scores_gemma":[0.000004404354,0.000016828815,0.0013280722,0.000026051013,5.880105e-7,0.000022127686,0.0005744857,0.000019078476,0.00006605237,0.00009291721,0.99784553,0.0000037508644],"about_ca_topic_score_codex":0.042843573,"about_ca_topic_score_gemma":0.18160684,"teacher_disagreement_score":0.58362985,"about_ca_system_score_codex":0.0012288105,"about_ca_system_score_gemma":0.001837884,"threshold_uncertainty_score":0.5939015},"labels":[],"label_agreement":null},{"id":"W7015669281","doi":"","title":"Thematic Working Group 5: Formative assessment supported by technology.","year":2023,"lang":"en","type":"article","venue":"IPIR – Repository of the Institute for Educational Research (Institute for Educational Research, Belgrade, Serbia)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Universitetet i Oslo; University of Mumbai; Victoria University of Wellington; Tel Aviv University; Victoria University; Curtin University of Technology; Tata Trusts; Griffith University; University of North Texas; University of Wollongong; Al Akhawayn University in Ifrane; Itä-Suomen Yliopisto; Université de Sherbrooke; Vrije Universiteit Brussel; King's College London; Dublin City University; Universiteit van Amsterdam; Monash University; Université Laval; West Virginia University; University of Canterbury; Tata Institute of Social Sciences; Manchester Metropolitan University; University of Otago; Arizona State University; Nova Southeastern University; Kasetsart University","keywords":"Formative assessment; Summative assessment; Accountability; Thematic analysis; Focus group; Knowledge survey; Peer assessment; Work (physics); Educational assessment; Assessment for learning","score_opus":0.15973400638312366,"score_gpt":0.4819537601001392,"score_spread":0.3222197537170155,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7015669281","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006976503,0.1177817,0.22986495,0.0705392,0.041841444,0.20059308,0.025874963,0.0035591633,0.30296892],"genre_scores_gemma":[0.05955035,0.09695717,0.32097018,0.032576274,0.007932447,0.32053792,0.04127478,0.0032730883,0.116927795],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.86074877,0.079547875,0.021346875,0.0068886825,0.02597946,0.0054883766],"domain_scores_gemma":[0.8399866,0.052747652,0.011709371,0.02707268,0.05835882,0.010124845],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.16503158,0.00323128,0.0036310495,0.013039979,0.004701243,0.01128535,0.010674131,0.009491256,0.06852026],"category_scores_gemma":[0.16843908,0.00142326,0.0059962496,0.010425936,0.007701071,0.011690227,0.023546474,0.007751784,0.026043676],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00058735494,0.00042664283,0.0011628252,0.11438177,0.00039874954,0.00030375566,0.022111813,0.0010064075,0.0047170273,0.07611039,0.17751838,0.60127485],"study_design_scores_gemma":[0.00019222025,0.0003408812,0.0023390134,0.08672817,0.0001905931,0.000408663,0.0046486463,0.00035794976,0.002272419,0.032309197,0.8701359,0.00007635704],"about_ca_topic_score_codex":0.007233634,"about_ca_topic_score_gemma":0.0040679486,"teacher_disagreement_score":0.16503158,"about_ca_system_score_codex":0.01640965,"about_ca_system_score_gemma":0.08818494,"threshold_uncertainty_score":0.87278086},"labels":[],"label_agreement":null},{"id":"W7017400211","doi":"","title":"Assessment for learning in a chinese university context: a mixed methods case study on english as a foreign language speaking ability","year":2012,"lang":"en","type":"dissertation","venue":"eScholarship@McGill (McGill)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McGill University","funders":"","keywords":"Perception; Foreign language; English as a foreign language; English language; Multimethodology; Qualitative research; Selection (genetic algorithm); China; Second language","score_opus":0.028748098564853525,"score_gpt":0.38507770390510826,"score_spread":0.3563296053402547,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7017400211","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9969292,0.00036607965,0.00071767083,0.00025922296,0.000010519306,0.00048248307,0.00002073662,0.0000034844024,0.0012105142],"genre_scores_gemma":[0.9908723,0.0013095594,0.0049148565,0.00031970008,0.000021370377,0.0010259748,0.000045161167,0.00000826839,0.0014827844],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.991755,0.0051030014,0.00042194844,0.0005147156,0.0010686566,0.0011366497],"domain_scores_gemma":[0.9930211,0.0040192576,0.0006474507,0.00036202377,0.00096532906,0.0009848455],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013540535,0.00082141644,0.0010740904,0.0018960409,0.007935816,0.0027036746,0.0016980619,0.0018006475,0.0013842039],"category_scores_gemma":[0.009486748,0.0005089544,0.00095976837,0.0023214666,0.002118514,0.0020282606,0.0033734257,0.0015227115,0.00018999945],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00043600533,0.0127139455,0.105659135,0.0011668201,0.00015961778,0.015694948,0.71499145,0.0008769715,0.005695235,0.0026404222,0.0012764095,0.13868901],"study_design_scores_gemma":[0.00019430148,0.006055692,0.0816035,0.0005937596,0.00019822785,0.0038662234,0.88793457,0.0020909181,0.004498243,0.0007692765,0.012043113,0.0001521638],"about_ca_topic_score_codex":0.01691607,"about_ca_topic_score_gemma":0.03778853,"teacher_disagreement_score":0.01691607,"about_ca_system_score_codex":0.0058345404,"about_ca_system_score_gemma":0.007975735,"threshold_uncertainty_score":0.07161003},"labels":[],"label_agreement":null},{"id":"W7018513866","doi":"","title":"Does self-assessment with specific criteria enhance graduate level ESL students' writing?","year":2007,"lang":"en","type":"dissertation","venue":"eScholarship@McGill (McGill)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Control (management); English as a second language; Graduate students; Qualitative research; Second language; Language proficiency; Note-taking","score_opus":0.039696675660746555,"score_gpt":0.3751141077246522,"score_spread":0.3354174320639056,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7018513866","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9967784,0.00021903506,0.0003714295,0.00028710623,0.000027640306,0.00006196743,0.000013635319,0.000048263737,0.0021924467],"genre_scores_gemma":[0.99517894,0.0003327474,0.0031128253,0.00012017915,0.000032691656,0.00005594801,0.000036526602,0.000007940687,0.0011221255],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99782276,0.0010953634,0.00020208114,0.00014422405,0.0006509103,0.00008462274],"domain_scores_gemma":[0.97117597,0.017094139,0.0048731323,0.0016198835,0.0027499162,0.002486894],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0043654856,0.00019673111,0.00042144133,0.0006682369,0.00020991091,0.00074273505,0.0003577532,0.00036887295,0.0020072726],"category_scores_gemma":[0.040571928,0.000109695146,0.00023373344,0.00033581626,0.00030255457,0.000629269,0.00058454985,0.0003658407,0.0006514803],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0008858663,0.0075229476,0.27100593,0.00050819956,0.000081046775,0.00018056176,0.005470882,0.00022167873,0.0071105985,0.00010267241,0.0018636279,0.7050458],"study_design_scores_gemma":[0.0002767724,0.012392296,0.968424,0.00027630376,0.00008962455,0.00057757756,0.004462567,0.0010792299,0.0069290306,0.00045679472,0.0049895085,0.000046278237],"about_ca_topic_score_codex":0.00031709435,"about_ca_topic_score_gemma":0.0011575972,"teacher_disagreement_score":0.0043654856,"about_ca_system_score_codex":0.00018270077,"about_ca_system_score_gemma":0.0005775988,"threshold_uncertainty_score":0.023087204},"labels":[],"label_agreement":null},{"id":"W7018553199","doi":"","title":"Dineren onder vrienden (en rivalen). Literaire prijzen, netwerken en consecratiestrategieën","year":2008,"lang":"nl","type":"article","venue":"Open Repository and Bibliography (University of Liège)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Francophone University Association","funders":"","keywords":"Government (linguistics); Set (abstract data type); Identification (biology); Context (archaeology); Perspective (graphical)","score_opus":0.028881407520693146,"score_gpt":0.2748239915696272,"score_spread":0.24594258404893407,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7018553199","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.037315316,0.028856087,0.002558042,0.043450646,0.011841054,0.000107664164,0.001173741,0.00055827416,0.8741391],"genre_scores_gemma":[0.1430271,0.01130531,0.0033067293,0.002158702,0.0008864657,0.000074725525,0.00077510864,0.00048054414,0.83798534],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.99614847,0.0012839653,0.00019575976,0.00029891386,0.0016060683,0.00046675061],"domain_scores_gemma":[0.99388313,0.0012663775,0.0004960149,0.00039703824,0.0019550829,0.0020025338],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0037766295,0.0004079943,0.0007059311,0.0027222408,0.004147555,0.015173229,0.00086911937,0.001655885,0.16648622],"category_scores_gemma":[0.017269501,0.00030423165,0.00022774823,0.0027677207,0.00165238,0.008521691,0.0065872846,0.002813426,0.051301837],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00010281891,0.00021538824,0.0035502783,0.0007066411,0.000012844135,0.00037115728,0.027108507,0.00011462492,0.0011620643,0.06633442,0.37565812,0.52466315],"study_design_scores_gemma":[0.0000028316601,0.000017502618,0.0020027517,0.0002911306,0.0000038647477,0.00010024665,0.009057956,0.00002765536,0.00022560405,0.0026725202,0.9855875,0.000010394574],"about_ca_topic_score_codex":0.0066957236,"about_ca_topic_score_gemma":0.02395191,"teacher_disagreement_score":0.16648622,"about_ca_system_score_codex":0.0025945825,"about_ca_system_score_gemma":0.006084753,"threshold_uncertainty_score":0.5569519},"labels":[],"label_agreement":null},{"id":"W7019173226","doi":"","title":"Exploring Feedback Literacy in the Undergraduate Medical Education Context","year":2024,"lang":"en","type":"dissertation","venue":"MacSphere (McMaster University)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"McMaster University","funders":"McMaster University","keywords":"Context (archaeology); Literacy; Psychological intervention; Peer feedback; Health literacy; Higher education; Active learning (machine learning)","score_opus":0.04418322156107731,"score_gpt":0.3121943755882959,"score_spread":0.2680111540272186,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7019173226","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9708594,0.0047343457,0.0027570631,0.0052904896,0.00009439019,0.00016799934,0.00006265016,0.0000224843,0.016011143],"genre_scores_gemma":[0.99278766,0.0030724253,0.0019355325,0.0009864115,0.000039453993,0.000107852626,0.000031705287,0.000008059594,0.001030997],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.987608,0.007135728,0.0005762619,0.0005659568,0.003028677,0.001085314],"domain_scores_gemma":[0.9635247,0.025465393,0.0041775936,0.0004953316,0.003680104,0.002656833],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.010196342,0.00035474598,0.00063961616,0.0025588328,0.0019230228,0.0062559783,0.0006013202,0.001111987,0.002641894],"category_scores_gemma":[0.03671467,0.00031282302,0.0006377089,0.0013406913,0.0024163614,0.003342208,0.003706605,0.002234405,0.00032108647],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00025302713,0.0028008912,0.26833576,0.0057887947,0.00019676656,0.0019553073,0.36678177,0.00046408994,0.004209081,0.0114912605,0.0041267294,0.33359656],"study_design_scores_gemma":[0.00008861412,0.0038830081,0.4234878,0.012866198,0.00030477438,0.0024606644,0.4513446,0.0013522425,0.00480263,0.012171978,0.087019086,0.00021835172],"about_ca_topic_score_codex":0.001902292,"about_ca_topic_score_gemma":0.0040388987,"teacher_disagreement_score":0.010196342,"about_ca_system_score_codex":0.0031029019,"about_ca_system_score_gemma":0.0073386845,"threshold_uncertainty_score":0.053924084},"labels":[],"label_agreement":null},{"id":"W7019427849","doi":"","title":"Guiding students Towards Success in Calculus via a Focused Assessment Approach","year":2023,"lang":"en","type":"article","venue":"York University Digital Library (York University)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"York University","funders":"","keywords":"Calculus (dental); Curriculum","score_opus":0.038946072673093725,"score_gpt":0.2679864002203329,"score_spread":0.22904032754723916,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7019427849","genre_codex":"empirical","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9366037,0.00019784301,0.034684084,0.0011459545,0.00012764256,0.0014652691,0.00015906946,0.0010122855,0.024604036],"genre_scores_gemma":[0.9243241,0.00035465293,0.06239126,0.0002448216,0.0000268689,0.0009265887,0.00019837229,0.00006822521,0.011465026],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9949285,0.002372685,0.0002448129,0.00042895912,0.0015603467,0.00046477668],"domain_scores_gemma":[0.98035,0.009175612,0.0014170756,0.00079443,0.0044401027,0.0038227234],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0069012525,0.0011850941,0.00077021285,0.0023081473,0.0012448558,0.0045297,0.0013318083,0.0011329105,0.005310069],"category_scores_gemma":[0.03507594,0.000341783,0.00045940353,0.0009100756,0.00044846884,0.0020507064,0.0032182217,0.0015548111,0.002159031],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001212204,0.015385975,0.048509613,0.00047778824,0.000100241916,0.00020266582,0.017628692,0.0049299346,0.011583784,0.0037854637,0.014270668,0.88191295],"study_design_scores_gemma":[0.0019241881,0.05337391,0.4551529,0.0033077786,0.0010680201,0.0011673894,0.06588691,0.10873869,0.09807139,0.0892433,0.12047139,0.0015942283],"about_ca_topic_score_codex":0.0014135211,"about_ca_topic_score_gemma":0.004610811,"teacher_disagreement_score":0.0069012525,"about_ca_system_score_codex":0.0010256759,"about_ca_system_score_gemma":0.004283764,"threshold_uncertainty_score":0.036497712},"labels":[],"label_agreement":null},{"id":"W7023926164","doi":"","title":"The Poverty Police: Police-Proxy University Services and Homelessness","year":2024,"lang":"en","type":"article","venue":"DOAJ (DOAJ: Directory of Open Access Journals)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Poverty; Pipeline (software); Vulnerability (computing); Public health; Community service","score_opus":0.13373077805529454,"score_gpt":0.5308291729785508,"score_spread":0.39709839492325627,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7023926164","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.74970293,0.02481362,0.0014622991,0.16342503,0.0011772718,0.00028111134,0.00017935534,0.000048392078,0.058910012],"genre_scores_gemma":[0.9859816,0.007071332,0.00038071742,0.0037009337,0.00009993006,0.000097321645,0.000033468994,0.000012707881,0.0026220558],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.964178,0.027149482,0.0017920559,0.0005834253,0.0044276933,0.0018694355],"domain_scores_gemma":[0.96576494,0.017459579,0.0075445813,0.00081943185,0.005568089,0.002843424],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0219722,0.00020739765,0.00043015278,0.0022422278,0.007803481,0.0077487547,0.0008631504,0.0012223189,0.0035108712],"category_scores_gemma":[0.070447475,0.00034087378,0.00020896,0.0033423083,0.008241088,0.0038779303,0.008625185,0.0020657738,0.00020281458],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000043292097,0.000056209683,0.043263394,0.0012173292,0.000031211286,0.000659019,0.8613146,0.000059645125,0.00022116092,0.013481393,0.01682191,0.06283086],"study_design_scores_gemma":[0.0000059465374,0.00005487036,0.01972088,0.0013467608,0.000017289285,0.00023030167,0.9306104,0.000036664827,0.00015229924,0.0010720855,0.046734165,0.000018321392],"about_ca_topic_score_codex":0.061082378,"about_ca_topic_score_gemma":0.1392491,"teacher_disagreement_score":0.061082378,"about_ca_system_score_codex":0.00811157,"about_ca_system_score_gemma":0.023153337,"threshold_uncertainty_score":0.12145364},"labels":[],"label_agreement":null},{"id":"W7026718776","doi":"","title":"An Argument-Based Approach to the Validity of Interpretation and Use of Chinese High School Students' Grades across Educational Contexts","year":2021,"lang":"en","type":"dissertation","venue":"QSpace (Queen's University Library)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Grading (engineering); Interpretation (philosophy); China; Argument (complex analysis); External validity; Predictive validity; Internal validity; Test validity; Globalization; Empirical research","score_opus":0.013832816171119582,"score_gpt":0.2983439730504333,"score_spread":0.2845111568793137,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7026718776","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18565834,0.0035321717,0.44621983,0.07022641,0.0014658937,0.00482388,0.0006122695,0.000145432,0.2873157],"genre_scores_gemma":[0.9243473,0.0006685337,0.067204416,0.0023117021,0.00014801737,0.0030641512,0.00019688868,0.00005084653,0.0020082176],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.76100564,0.18934837,0.012651815,0.009529013,0.023957694,0.0035074137],"domain_scores_gemma":[0.6267049,0.2967709,0.019841999,0.025811382,0.029354544,0.0015163348],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.22575344,0.0015160511,0.0017917627,0.018674612,0.011306764,0.019033935,0.006342509,0.006040492,0.002739278],"category_scores_gemma":[0.30323365,0.001101958,0.0019221589,0.011242721,0.09035398,0.019524634,0.014402317,0.0068971068,0.00028472472],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00005761545,0.000059998063,0.0060264184,0.00050758803,0.00012335002,0.00036124612,0.13497834,0.000536036,0.00029531028,0.83749133,0.0013564602,0.018206332],"study_design_scores_gemma":[0.00015087372,0.00012005162,0.0072156177,0.0035735264,0.00024403124,0.00026744907,0.114612095,0.006261551,0.0019399691,0.8186093,0.04687789,0.00012768709],"about_ca_topic_score_codex":0.012654834,"about_ca_topic_score_gemma":0.00894636,"teacher_disagreement_score":0.22575344,"about_ca_system_score_codex":0.025399884,"about_ca_system_score_gemma":0.023927765,"threshold_uncertainty_score":0.95478386},"labels":[],"label_agreement":null},{"id":"W7034584056","doi":"","title":"Tunique aux couleurs multiples: Deux siècles de présence juive au Canada","year":2021,"lang":"fr","type":"article","venue":"Project Muse (Johns Hopkins University)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Context (archaeology); Meaning (existential); Narrative; Identity (music)","score_opus":0.030327235380401725,"score_gpt":0.2794713260612569,"score_spread":0.2491440906808552,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7034584056","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96487224,0.0010121984,0.0012841487,0.0037055204,0.00031420687,0.000079091056,0.00066378334,0.00008834342,0.027980361],"genre_scores_gemma":[0.9450998,0.00054674566,0.0012793571,0.00042578872,0.00005124656,0.000065355845,0.00021470022,0.000047509042,0.05226957],"study_design_codex":"qualitative","study_design_gemma":"not_applicable","domain_scores_codex":[0.99818426,0.00030505104,0.000058505422,0.0002513501,0.00050181104,0.0006989523],"domain_scores_gemma":[0.9960735,0.00080160185,0.00026450024,0.0001043825,0.0014422153,0.0013137665],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0014797928,0.0006857161,0.0006838943,0.001302738,0.011465668,0.0038706022,0.0011480056,0.0020304585,0.0096311],"category_scores_gemma":[0.006018781,0.0004825318,0.0006202405,0.0020883179,0.0030021556,0.0014759528,0.0031822477,0.0036010307,0.00055927417],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00252317,0.0006989512,0.27659467,0.00062247756,0.00031746898,0.010652009,0.45438772,0.0031343913,0.013469149,0.020562604,0.027123865,0.18991353],"study_design_scores_gemma":[0.00009057411,0.00031525726,0.43721542,0.0004032494,0.00008179763,0.00068648136,0.35146803,0.0014018182,0.0036385274,0.0007613973,0.20377317,0.00016433185],"about_ca_topic_score_codex":0.96508396,"about_ca_topic_score_gemma":0.9893063,"teacher_disagreement_score":0.039434373,"about_ca_system_score_codex":0.039434373,"about_ca_system_score_gemma":0.031169977,"threshold_uncertainty_score":0.28611773},"labels":[],"label_agreement":null},{"id":"W7036622043","doi":"","title":"Chatting with Bill and Ian","year":2021,"lang":"en","type":"other","venue":"Bulletin of Miscellaneous Information (Royal Gardens Kew)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Check-in; Soul; The Internet; Ticket; Launched","score_opus":0.009140975278899111,"score_gpt":0.22650067570483357,"score_spread":0.21735970042593444,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7036622043","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.001871487,0.005847764,0.0032362712,0.05767906,0.03230482,0.0001986457,0.0013972006,0.0053438214,0.89212084],"genre_scores_gemma":[0.004568589,0.001595189,0.000923824,0.015941786,0.0018028225,0.00010803264,0.0005727921,0.0011107671,0.9733762],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99892765,0.00025042027,0.00004876376,0.0001820002,0.00038282122,0.0002083779],"domain_scores_gemma":[0.9967938,0.0005826427,0.00016980756,0.00025639124,0.00097219885,0.0012250608],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0010103398,0.001253076,0.00076648884,0.0011957319,0.0035219388,0.0044177994,0.0013649688,0.002464179,0.44733602],"category_scores_gemma":[0.008811925,0.0004593705,0.00046916897,0.0008378261,0.000968361,0.0058918195,0.003857142,0.0046891873,0.3983718],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000011521789,0.000011680751,0.000047345275,0.00002668648,7.946312e-7,0.000052848052,0.0002345871,0.0000075771363,0.0000662242,0.0010489997,0.98256576,0.0159259],"study_design_scores_gemma":[0.000002465995,0.0000051886564,0.0001339684,0.000054078795,9.5279444e-7,0.000100678546,0.0006977864,0.000026772706,0.00004791655,0.0004961485,0.9984269,0.000007118452],"about_ca_topic_score_codex":0.0034599197,"about_ca_topic_score_gemma":0.007859319,"teacher_disagreement_score":0.552664,"about_ca_system_score_codex":0.001163475,"about_ca_system_score_gemma":0.0015410555,"threshold_uncertainty_score":0.7883081},"labels":[],"label_agreement":null},{"id":"W7037814327","doi":"","title":"Estudo geofísico da transição continente-oceano e das anomalias-J na parte distal do sistema rifte ibéria-newfoundland : paleorreconstrução e implicações para a evolução tectônica","year":2021,"lang":"pt","type":"article","venue":"Repositório Digital Institucional da UFPR (Universidade Federal do Paraná)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Deformation (meteorology); Work (physics); Filter (signal processing)","score_opus":0.037345793831580286,"score_gpt":0.3083338666166812,"score_spread":0.27098807278510095,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7037814327","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99805117,0.00003058575,0.000035896715,0.000056347893,0.0000010177852,0.0000041528583,0.00014310646,0.000002403073,0.0016751749],"genre_scores_gemma":[0.9987754,0.00004873606,0.00008566718,0.000006126957,5.196339e-7,0.0000035676314,0.00008131376,0.0000011885376,0.000997511],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9997125,0.000057705,0.000025134286,0.00004496415,0.00007665784,0.00008297888],"domain_scores_gemma":[0.9982072,0.0004958291,0.00044701438,0.0000873321,0.0005512331,0.0002113297],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00071417645,0.000120864395,0.00015337186,0.0013107798,0.0008547051,0.0010898104,0.00034622918,0.0002020462,0.002458573],"category_scores_gemma":[0.0036925825,0.00011174767,0.00014296103,0.0020607763,0.0010775102,0.00043834987,0.0012190435,0.00028426823,0.00018793535],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000042442443,0.000015636157,0.97822887,0.000019310284,0.000012498074,0.00015482528,0.009369575,0.00018004703,0.00083951885,0.00017640152,0.00015697304,0.010803883],"study_design_scores_gemma":[7.153241e-7,0.000014832657,0.98708355,0.000008456602,0.0000067335804,0.000032604523,0.011860345,0.00010437109,0.00019735201,0.000026147523,0.00066247117,0.0000024450194],"about_ca_topic_score_codex":0.49416775,"about_ca_topic_score_gemma":0.70233095,"teacher_disagreement_score":0.49416775,"about_ca_system_score_codex":0.0023268347,"about_ca_system_score_gemma":0.004131915,"threshold_uncertainty_score":0.98258275},"labels":[],"label_agreement":null},{"id":"W7043557011","doi":"","title":"Towards a Situated View of Assessment Literacy for Higher Education","year":2022,"lang":"en","type":"dissertation","venue":"University Library (University of Saskatchewan)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Situated; Higher education; Sample (material); Thematic analysis; Literacy; Relation (database); Situated learning; Term (time)","score_opus":0.013788561541878961,"score_gpt":0.2838788324900515,"score_spread":0.27009027094817256,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7043557011","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22243194,0.01972,0.20252167,0.11932782,0.0008805317,0.0004759501,0.00015625803,0.00027319216,0.43421268],"genre_scores_gemma":[0.9689274,0.0025943776,0.021646515,0.0021628186,0.00010350043,0.000121754354,0.000044419012,0.000047066806,0.0043521337],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9806387,0.014704873,0.000590515,0.0010784427,0.001656935,0.0013305933],"domain_scores_gemma":[0.98051274,0.012949699,0.0014402673,0.0016193809,0.0015301389,0.0019477565],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.022572977,0.00060040393,0.00065741583,0.0062027294,0.0076467493,0.023273697,0.00228578,0.003988075,0.0028565314],"category_scores_gemma":[0.017007083,0.0005466544,0.00075278373,0.004172445,0.059101995,0.020102797,0.0152572375,0.0062246625,0.00043576577],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000021456575,0.00004197225,0.004644651,0.00039127833,0.000015743273,0.0005429425,0.31963682,0.00042459252,0.000597071,0.65240437,0.00098567,0.020293416],"study_design_scores_gemma":[0.00002103435,0.0000860645,0.00808537,0.0024942155,0.000044919947,0.0007560261,0.3652993,0.0013878269,0.00074496225,0.48155782,0.13946603,0.000056431552],"about_ca_topic_score_codex":0.031190187,"about_ca_topic_score_gemma":0.037719272,"teacher_disagreement_score":0.031190187,"about_ca_system_score_codex":0.017973589,"about_ca_system_score_gemma":0.018920975,"threshold_uncertainty_score":0.13040811},"labels":[],"label_agreement":null},{"id":"W7071929433","doi":"","title":"Unpacking 'the Next Black Box': Investigating the Cognitive and Affective Underpinnings of Student Self-Assessment","year":2021,"lang":"en","type":"dissertation","venue":"QSpace (Queen's University Library)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Queen's University","funders":"","keywords":"Unpacking; Session (web analytics); Cognition; Centrality; Class (philosophy); TRACE (psycholinguistics); Process (computing); Empirical research; Protocol analysis","score_opus":0.017294814971463176,"score_gpt":0.28373958965874113,"score_spread":0.26644477468727795,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7071929433","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9316649,0.0007894342,0.047644857,0.0042293384,0.000071232804,0.00012348098,0.000059631595,0.00010136182,0.0153157795],"genre_scores_gemma":[0.99271506,0.00016956282,0.0062988517,0.00022467002,0.000012581895,0.00006467313,0.000014423069,0.000027781605,0.00047240237],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.98852044,0.008198185,0.00032628994,0.0010547831,0.0015080301,0.00039227452],"domain_scores_gemma":[0.9498998,0.040173277,0.0030812356,0.0036352186,0.0022111803,0.0009992571],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.015404195,0.00030530058,0.00043787292,0.0014481635,0.0017684865,0.00868916,0.0009259096,0.001036764,0.0017490825],"category_scores_gemma":[0.043670636,0.0003332934,0.0003516293,0.0010319228,0.012591385,0.0077785305,0.0051526865,0.0025686608,0.00029950752],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014017419,0.0002376117,0.09712147,0.00077344355,0.00006794134,0.00021448298,0.69705194,0.0009786981,0.008181788,0.049120523,0.0007837706,0.1453281],"study_design_scores_gemma":[0.00003562258,0.0007185771,0.21953768,0.00172856,0.00008353439,0.00059013406,0.4993193,0.011148354,0.009764659,0.21823825,0.03855768,0.0002777589],"about_ca_topic_score_codex":0.0018690936,"about_ca_topic_score_gemma":0.0027083715,"teacher_disagreement_score":0.015404195,"about_ca_system_score_codex":0.0015577518,"about_ca_system_score_gemma":0.0022535073,"threshold_uncertainty_score":0.08146614},"labels":[],"label_agreement":null},{"id":"W7073581443","doi":"","title":"Acute and sublethal toxicity of novaluron, a novel chitin synthesis inhibitor, to Leptinotarsa decemlineata (Coleoptera: Chrysomelidae)","year":2011,"lang":"en","type":"article","venue":"The Atrium (University of Guelph)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":5,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Agriculture and Agri-Food Canada","keywords":"Leptinotarsa; Novaluron; Colorado potato beetle; Larva; PEST analysis; Insect growth regulator","score_opus":0.03697645924542412,"score_gpt":0.2620231421321643,"score_spread":0.2250466828867402,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7073581443","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99875367,0.0005802598,0.00015869124,0.00001319403,0.000004305352,0.000010197189,0.00011493159,0.000011012108,0.00035373613],"genre_scores_gemma":[0.9971028,0.0006645598,0.0004513416,0.000034285567,0.000004677461,0.000016970453,0.00041273987,0.000003980924,0.0013085454],"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.99992394,0.000012299219,0.000009864649,0.00001711291,0.00001912686,0.000017626826],"domain_scores_gemma":[0.9998709,0.000022858027,0.00004647534,0.000009787334,0.000019187652,0.00003076482],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000092448194,0.00039847757,0.00022580785,0.00017305717,0.000112929,0.00018622505,0.00019403899,0.00028321322,0.000713993],"category_scores_gemma":[0.00011351774,0.00015980417,0.00019576408,0.000101688776,0.00012780805,0.00012903947,0.00016067569,0.00032305683,0.0001167175],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0002371085,0.000044861536,0.0007974559,0.00005367436,0.000010857185,0.000031981082,0.000019477478,0.00005799399,0.99765366,0.0000072449334,0.000016144362,0.00106953],"study_design_scores_gemma":[0.00006209917,0.009358252,0.06064901,0.000014904639,0.00007149071,0.0003208991,0.00009272891,0.0007284108,0.9275829,0.000013943755,0.0010933073,0.000011950886],"about_ca_topic_score_codex":0.0016314834,"about_ca_topic_score_gemma":0.0036682684,"teacher_disagreement_score":0.0016314834,"about_ca_system_score_codex":0.00019727848,"about_ca_system_score_gemma":0.00012935152,"threshold_uncertainty_score":0.0032439828},"labels":[],"label_agreement":null},{"id":"W7095385706","doi":"","title":"Canadian Society for the Study of Education","year":2013,"lang":"en","type":"article","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Government (linguistics); Higher education; Work (physics)","score_opus":0.031446218296256094,"score_gpt":0.36755614502329503,"score_spread":0.33610992672703893,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7095385706","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0008629851,0.033416465,0.0020347114,0.026705265,0.011794219,0.00027076236,0.020199668,0.0005407927,0.9041753],"genre_scores_gemma":[0.049062327,0.08831619,0.009127996,0.006951879,0.0015087107,0.001230461,0.015778346,0.0007796428,0.8272444],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99496424,0.0005160843,0.0005458134,0.0006230971,0.0025267089,0.0008240188],"domain_scores_gemma":[0.98588574,0.0020172256,0.0005829444,0.0016738067,0.007779957,0.0020603496],"candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0030885688,0.001235934,0.0022513277,0.0043253023,0.004385995,0.007599221,0.002352315,0.002755061,0.38959774],"category_scores_gemma":[0.012955677,0.00056427094,0.0007900748,0.009134852,0.0036423458,0.002963471,0.00326376,0.003731979,0.119012505],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000063925145,0.000048459282,0.0012486227,0.0012814081,0.000034790486,0.0002869988,0.0007561588,0.0001553127,0.00016496601,0.06828826,0.78248084,0.14519018],"study_design_scores_gemma":[0.000010170813,0.0000063208895,0.0021935108,0.00044304214,0.0000077130135,0.00006529007,0.0003676125,0.00004910502,0.000016781443,0.0030063982,0.99382085,0.000013195845],"about_ca_topic_score_codex":0.6726633,"about_ca_topic_score_gemma":0.63561535,"teacher_disagreement_score":0.6726633,"about_ca_system_score_codex":0.014085409,"about_ca_system_score_gemma":0.08829957,"threshold_uncertainty_score":0.8706647},"labels":[],"label_agreement":null},{"id":"W7095589736","doi":"","title":"Knowledge and Skills Related to the Development and Use of Teacher-Made Tests","year":2016,"lang":"en","type":"article","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Competence (human resources); Test (biology); Recall; Standardized test; Knowledge level; Quarter (Canadian coin)","score_opus":0.033680102457859705,"score_gpt":0.3461971084290518,"score_spread":0.31251700597119214,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7095589736","genre_codex":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.36773565,0.6040742,0.0046982565,0.0010326558,0.0002030852,0.000230172,0.0016036546,0.0000623734,0.020360062],"genre_scores_gemma":[0.7533569,0.24038292,0.0039565424,0.00025037018,0.000052987176,0.00014640165,0.0007575711,0.000019768142,0.0010765459],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9889402,0.0025517447,0.0027765955,0.00087355,0.0046315687,0.00022633585],"domain_scores_gemma":[0.89135444,0.07809069,0.021478524,0.0018380836,0.0066821584,0.0005561765],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007944271,0.00027710685,0.00087009295,0.004759119,0.00029074706,0.001758181,0.0008211765,0.00042583526,0.0015068164],"category_scores_gemma":[0.06753275,0.000312142,0.0008487732,0.004381232,0.0010057229,0.0016649021,0.0009454952,0.00064348255,0.00020377195],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013660057,0.00013596346,0.28552672,0.036954332,0.0012599354,0.00062773674,0.010673051,0.0007404284,0.0017100804,0.0006986686,0.0011926473,0.6603438],"study_design_scores_gemma":[0.000024703704,0.0004256696,0.9035113,0.034836996,0.002213138,0.0029135935,0.007870069,0.00019866072,0.0038475615,0.00052614027,0.04357081,0.00006133211],"about_ca_topic_score_codex":0.0076121963,"about_ca_topic_score_gemma":0.016467048,"teacher_disagreement_score":0.007944271,"about_ca_system_score_codex":0.0010076934,"about_ca_system_score_gemma":0.0037010182,"threshold_uncertainty_score":0.042013824},"labels":[],"label_agreement":null},{"id":"W7096392813","doi":"","title":"Toronto","year":2005,"lang":"en","type":"article","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Confidentiality; Expectancy theory; Inflation (cosmology); Function (biology); Anonymity","score_opus":0.025201443647737347,"score_gpt":0.37703904011560563,"score_spread":0.3518375964678683,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7096392813","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.011438698,0.0014501935,0.004045117,0.0025777223,0.00088326563,0.0002178724,0.015476455,0.0010860411,0.9628246],"genre_scores_gemma":[0.08054199,0.0020206827,0.0048313416,0.0012051028,0.00018298443,0.00020872599,0.01207904,0.0005100238,0.8984201],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99925834,0.00008467921,0.00003888509,0.00027682065,0.00022553447,0.00011585176],"domain_scores_gemma":[0.9987072,0.00021603754,0.00008958757,0.00017523441,0.0005807575,0.00023125693],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0005816962,0.00080706243,0.0005201299,0.0013074664,0.0024956448,0.00381876,0.0010296156,0.001078602,0.53854525],"category_scores_gemma":[0.0031007505,0.0004010438,0.0004812713,0.0019151835,0.00046572642,0.0014450516,0.001640155,0.0011043414,0.225953],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00035322848,0.00019217956,0.023876898,0.0005703067,0.00004624913,0.0012636606,0.0025283762,0.00094815326,0.0011764922,0.06793053,0.48046756,0.42064643],"study_design_scores_gemma":[0.000029226534,0.000050216633,0.012946039,0.00016566741,0.000020123685,0.00032567434,0.00088737643,0.0007963856,0.00034748088,0.004922042,0.9794881,0.00002163887],"about_ca_topic_score_codex":0.055697184,"about_ca_topic_score_gemma":0.08098915,"teacher_disagreement_score":0.9443028,"about_ca_system_score_codex":0.0023572338,"about_ca_system_score_gemma":0.0025285243,"threshold_uncertainty_score":0},"labels":[],"label_agreement":null},{"id":"W7096394374","doi":"","title":"Learning","year":2016,"lang":"en","type":"article","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Curriculum; Space (punctuation); Key (lock); Philosophy of education; Affect (linguistics); Formative assessment","score_opus":0.027973769974527177,"score_gpt":0.356247329041961,"score_spread":0.32827355906743383,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7096394374","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.003342065,0.0027354418,0.01785856,0.016421208,0.002107363,0.0001577745,0.0008565033,0.0010136853,0.95550734],"genre_scores_gemma":[0.08116454,0.0046780095,0.023164151,0.011163184,0.0010324259,0.00048480305,0.0025807004,0.0007398136,0.8749923],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.99708706,0.00088662404,0.00014222614,0.00068870286,0.00082191057,0.00037341387],"domain_scores_gemma":[0.99760675,0.0004883422,0.00014600277,0.00064619107,0.00061224616,0.00050039036],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00233184,0.0007650134,0.0005504395,0.001405806,0.002510514,0.009477586,0.0023992565,0.002535783,0.20838909],"category_scores_gemma":[0.007501359,0.00027412645,0.0006603172,0.0013628309,0.002517418,0.009504922,0.008701392,0.0028263598,0.12428322],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000058411322,0.00009947335,0.0012584873,0.00027634055,0.000014678029,0.00016309488,0.0024773702,0.00032999954,0.00030436466,0.44254762,0.23357065,0.31889942],"study_design_scores_gemma":[0.00000618,0.000019030003,0.00028849815,0.0001620311,0.000002973794,0.000115736126,0.0006458137,0.00013967139,0.00014648399,0.05247271,0.94599205,0.000008855059],"about_ca_topic_score_codex":0.0019289587,"about_ca_topic_score_gemma":0.0030730725,"teacher_disagreement_score":0.7916109,"about_ca_system_score_codex":0.0027246184,"about_ca_system_score_gemma":0.0036517163,"threshold_uncertainty_score":0},"labels":[],"label_agreement":null},{"id":"W7096583644","doi":"","title":"Washback in language assessment","year":2013,"lang":"en","type":"article","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Test (biology); Language assessment; Quarter (Canadian coin); Language proficiency; English language; Criterion-referenced test","score_opus":0.01766615138195563,"score_gpt":0.37841698802956336,"score_spread":0.3607508366476077,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7096583644","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18288586,0.14679392,0.32338,0.046913005,0.006011463,0.0010978143,0.00014780379,0.0022490022,0.2905211],"genre_scores_gemma":[0.7875956,0.027596384,0.12303045,0.009984356,0.0010482492,0.00095503364,0.00013012167,0.0006579176,0.04900188],"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.96785283,0.021738911,0.0014646223,0.0015329551,0.0066541205,0.0007566059],"domain_scores_gemma":[0.94081116,0.045608703,0.0025623061,0.003939903,0.006059125,0.0010188608],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02308274,0.0008487614,0.001030927,0.0028800033,0.0019930322,0.0065675187,0.002342419,0.003050953,0.01049219],"category_scores_gemma":[0.08064187,0.00051414536,0.0005270771,0.0015010878,0.0062373183,0.011687093,0.009040352,0.0037610573,0.0024132242],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00035644567,0.00030350414,0.0033709323,0.0014561594,0.000029398809,0.00026884646,0.016451817,0.0005035806,0.001687339,0.0563143,0.006010887,0.91324675],"study_design_scores_gemma":[0.0002085793,0.0023037344,0.013890105,0.010562237,0.00014117273,0.003496392,0.03356005,0.003943577,0.011466475,0.32603747,0.59406567,0.00032441883],"about_ca_topic_score_codex":0.0014729699,"about_ca_topic_score_gemma":0.0015766968,"teacher_disagreement_score":0.02308274,"about_ca_system_score_codex":0.0033509093,"about_ca_system_score_gemma":0.0026976948,"threshold_uncertainty_score":0.12207472},"labels":[],"label_agreement":null},{"id":"W7097327432","doi":"","title":"Perceptions of Assessment","year":2015,"lang":"en","type":"article","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Windsor; Permission; Perception; Legislation","score_opus":0.07329582133251847,"score_gpt":0.43890915689663546,"score_spread":0.365613335564117,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7097327432","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.77061754,0.0020744011,0.0024148996,0.002835254,0.00016075312,0.0002700885,0.0007864856,0.000108978566,0.22073154],"genre_scores_gemma":[0.9915787,0.00052158046,0.00037448146,0.00013395063,0.000014460227,0.000046062312,0.00018660913,0.00001531841,0.007128854],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.9902429,0.0038042748,0.00056557765,0.00044301053,0.0044649257,0.00047922586],"domain_scores_gemma":[0.9600398,0.020452425,0.0041047796,0.0021306186,0.008244494,0.0050279293],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0076101287,0.00026301155,0.0003763791,0.00228866,0.0014097798,0.005001591,0.00052870007,0.00045471845,0.014880926],"category_scores_gemma":[0.063139014,0.00015445407,0.0002940006,0.0016559054,0.0013914561,0.0029645448,0.0024006274,0.000990757,0.0013374303],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00033156291,0.0008981201,0.47617108,0.00067031954,0.00014411449,0.00024052615,0.19263399,0.00057004497,0.0006876744,0.01935316,0.029630512,0.27866885],"study_design_scores_gemma":[0.000050196588,0.0005882332,0.6274449,0.000590438,0.00006186574,0.00040818588,0.19633628,0.0012571972,0.0004955501,0.011769478,0.16086188,0.00013584562],"about_ca_topic_score_codex":0.01017034,"about_ca_topic_score_gemma":0.009995383,"teacher_disagreement_score":0.014880926,"about_ca_system_score_codex":0.0023973717,"about_ca_system_score_gemma":0.0020344772,"threshold_uncertainty_score":0.04978168},"labels":[],"label_agreement":null},{"id":"W7097468103","doi":"","title":"Differential Bundle Functioning on Mathematics and Science Achievement Tests: A Small Step Toward Understanding Differential Performance","year":2000,"lang":"en","type":"article","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Grading (engineering); Test (biology); Student achievement; Achievement test; Standardized test; Selection (genetic algorithm); Academic achievement; Subject (documents)","score_opus":0.07533882156350026,"score_gpt":0.3092023842523159,"score_spread":0.23386356268881564,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7097468103","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.62885106,0.040669393,0.056862306,0.10528767,0.00156149,0.0012897616,0.004813929,0.00069354166,0.15997078],"genre_scores_gemma":[0.9108846,0.012158563,0.06004979,0.007186453,0.00037257926,0.00029762654,0.0014396522,0.00009758831,0.00751306],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99725145,0.00052463094,0.00021538058,0.00032994314,0.0013580828,0.0003204247],"domain_scores_gemma":[0.9889697,0.0035545363,0.0010125246,0.0013307551,0.004417015,0.00071551296],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0063149533,0.0010192484,0.0010371582,0.007876691,0.0026099489,0.0052848174,0.0028377871,0.0016864849,0.0033106946],"category_scores_gemma":[0.009940425,0.00037501025,0.0006707579,0.0046827914,0.007091991,0.007851185,0.0048567676,0.0046758116,0.0005270158],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00019389352,0.0006021939,0.46808943,0.0015731909,0.00020336655,0.0010237041,0.026069028,0.0008455653,0.0029086566,0.08208955,0.024535593,0.39186582],"study_design_scores_gemma":[0.000031908276,0.0005200173,0.7920351,0.0016733212,0.00021065913,0.00087803864,0.023729557,0.00384878,0.0015970604,0.061435737,0.1139262,0.00011358574],"about_ca_topic_score_codex":0.28781295,"about_ca_topic_score_gemma":0.39640284,"teacher_disagreement_score":0.28781295,"about_ca_system_score_codex":0.0075479452,"about_ca_system_score_gemma":0.011668662,"threshold_uncertainty_score":0.5722754},"labels":[],"label_agreement":null},{"id":"W7099236764","doi":"","title":"Principles for Fair Student Assessment Practices for Education in Canada The Principles for Fair Student Assessment Practices for Education in Canada contains a set of","year":2011,"lang":"en","type":"article","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Set (abstract data type); Process (computing); Standards-based assessment; Commission; Construct (python library); Educational assessment; Curriculum; Professional association; Best practice","score_opus":0.13526576797902734,"score_gpt":0.4662201732620031,"score_spread":0.33095440528297576,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7099236764","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.017931571,0.00837131,0.3328731,0.14415014,0.0046377988,0.017144896,0.0026679211,0.0035519786,0.46867126],"genre_scores_gemma":[0.1804556,0.0057151723,0.6520829,0.024795393,0.0005958837,0.007904815,0.0013776902,0.0006909854,0.12638153],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.81301725,0.038602985,0.013763868,0.004828095,0.11705817,0.012729577],"domain_scores_gemma":[0.7419177,0.030130079,0.0051385225,0.012025561,0.1919862,0.018801833],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.11240142,0.0010689802,0.0016699735,0.0066309096,0.017971309,0.01606543,0.007778195,0.007198571,0.0062480704],"category_scores_gemma":[0.16129199,0.00188941,0.0022402583,0.006745917,0.014824725,0.0039788047,0.009292542,0.011392688,0.0034083365],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013913192,0.00051393907,0.008338837,0.0012490834,0.00008708535,0.00064922584,0.023651427,0.006484577,0.0020743867,0.35754967,0.31637934,0.2828833],"study_design_scores_gemma":[0.00010895823,0.00012732508,0.024459679,0.0029497272,0.00007391618,0.00040675479,0.007486508,0.004791957,0.0015274405,0.053353745,0.90430754,0.00040646957],"about_ca_topic_score_codex":0.9324673,"about_ca_topic_score_gemma":0.94874746,"teacher_disagreement_score":0.11240142,"about_ca_system_score_codex":0.098976046,"about_ca_system_score_gemma":0.49669334,"threshold_uncertainty_score":0.71812487},"labels":[],"label_agreement":null},{"id":"W7099448534","doi":"","title":"Development Canada.","year":2003,"lang":"en","type":"article","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Human resources; Government (linguistics); Human development (humanity); Human Development Report; Work (physics); Development aid","score_opus":0.027569301283668142,"score_gpt":0.3112024190526638,"score_spread":0.2836331177689957,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7099448534","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0026262377,0.004458509,0.001117256,0.015372294,0.0010726254,0.00027863274,0.105298065,0.0012781147,0.8684983],"genre_scores_gemma":[0.00869769,0.0018010341,0.0015466725,0.0013719236,0.000024817366,0.00008106736,0.015661234,0.00019496054,0.97062063],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9982388,0.000107597094,0.000056815952,0.00017867595,0.0010877021,0.00033044655],"domain_scores_gemma":[0.9953382,0.0002065,0.00007672313,0.00016636186,0.0033774655,0.0008347178],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001095042,0.00085325056,0.00046662183,0.00189151,0.0031189185,0.0030442758,0.0013696242,0.0011141202,0.25439203],"category_scores_gemma":[0.0031451478,0.0005731529,0.0002742556,0.0035549137,0.00046658315,0.0008746218,0.0012745188,0.0015298628,0.0583498],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000079917896,0.000037467194,0.0015698043,0.0001700834,0.0000070524893,0.000107103726,0.0002225425,0.00011651551,0.00029160106,0.009115093,0.904696,0.08358693],"study_design_scores_gemma":[0.000010759245,0.0000074596514,0.0034935074,0.000057143858,0.000003638818,0.00003817402,0.00018766274,0.000069389476,0.000119567805,0.00035737312,0.99564916,0.000006052208],"about_ca_topic_score_codex":0.92949677,"about_ca_topic_score_gemma":0.97069126,"teacher_disagreement_score":0.745608,"about_ca_system_score_codex":0.021801408,"about_ca_system_score_gemma":0.07488388,"threshold_uncertainty_score":0.8510261},"labels":[],"label_agreement":null},{"id":"W7099739439","doi":"","title":"from members of the project team. Special thanks are due to the following people for their advice and intellectual","year":2010,"lang":"en","type":"article","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Advice (programming); Corporate governance; Section (typography); Identification (biology); Key (lock); Point (geometry)","score_opus":0.021261052201838267,"score_gpt":0.31628644087335356,"score_spread":0.2950253886715153,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7099739439","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.28327435,0.0068472163,0.09393939,0.19295403,0.029733822,0.03287689,0.013509769,0.004781222,0.3420833],"genre_scores_gemma":[0.25951564,0.0016059302,0.057970818,0.020632496,0.0013169951,0.014706255,0.0031635535,0.001384628,0.63970363],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.97919786,0.008682722,0.001209244,0.0021079676,0.0068693096,0.0019329933],"domain_scores_gemma":[0.9357206,0.0024512557,0.0015413386,0.0025216478,0.028013928,0.02975116],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01479542,0.0010479485,0.00070702523,0.0017266563,0.0065399464,0.00471948,0.0015723574,0.0012760406,0.0822339],"category_scores_gemma":[0.037708987,0.0008119978,0.00060442876,0.0012771569,0.0017181361,0.002279209,0.007388098,0.004494169,0.0349389],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0005788651,0.0005781628,0.00975552,0.0005331921,0.000032665463,0.001183585,0.05237364,0.0003932971,0.00788053,0.005214668,0.6038101,0.31766585],"study_design_scores_gemma":[0.000115643816,0.00020877237,0.008666109,0.0003346467,0.00002779292,0.00047908255,0.04605478,0.00047986628,0.00166056,0.0016782973,0.94021714,0.00007732236],"about_ca_topic_score_codex":0.016776836,"about_ca_topic_score_gemma":0.03500574,"teacher_disagreement_score":0.9177661,"about_ca_system_score_codex":0.0051279846,"about_ca_system_score_gemma":0.021289159,"threshold_uncertainty_score":0.2750998},"labels":[],"label_agreement":null},{"id":"W7100101866","doi":"","title":"THE UNIVERSITY OF WESTERN ONTARIO FACULTY OF GRADUATE STUDIES CERTIFICATE OF EXAMINATION Advisor Examining Board","year":2000,"lang":"en","type":"article","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Certificate; Graduate students; Graduate research; Higher education; Editorial board","score_opus":0.2949934286798181,"score_gpt":0.37382672880350487,"score_spread":0.07883330012368678,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7100101866","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.07469394,0.0013542204,0.0016054711,0.062614515,0.008365714,0.001542711,0.0062593804,0.00083953084,0.84272444],"genre_scores_gemma":[0.033348132,0.00034573404,0.0008732681,0.0010539709,0.00019674895,0.00010776143,0.00073331175,0.00007273598,0.96326834],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9949174,0.0004107544,0.00024388992,0.00033003784,0.0028785234,0.0012194661],"domain_scores_gemma":[0.9244695,0.0015932282,0.0013820085,0.0018295409,0.04397966,0.02674614],"candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004166349,0.00037717182,0.00067912217,0.0028767718,0.009734647,0.0050374777,0.0014734196,0.002067543,0.1773647],"category_scores_gemma":[0.017102439,0.00065041345,0.00035235682,0.0015222968,0.0015694697,0.0011457255,0.0027290545,0.0016682731,0.03818349],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009408946,0.00014251974,0.018210301,0.00009262817,0.0000060655193,0.0001804397,0.00094753964,0.00008906435,0.00073538383,0.0029251047,0.90931076,0.067266166],"study_design_scores_gemma":[0.00004150571,0.000088241875,0.1274639,0.00018452675,0.000011063677,0.00010202768,0.0033532982,0.0003335232,0.000446114,0.00046845805,0.8674749,0.000032510456],"about_ca_topic_score_codex":0.6676925,"about_ca_topic_score_gemma":0.92349017,"teacher_disagreement_score":0.8226353,"about_ca_system_score_codex":0.01988136,"about_ca_system_score_gemma":0.13016899,"threshold_uncertainty_score":0.66852903},"labels":[],"label_agreement":null},{"id":"W7100226999","doi":"","title":"Paper Presented at the Symposium entitled “Improving Large-Scale Assessment in Education ” at the Annual Meeting of the Canadian Society for the Study of Education","year":2013,"lang":"en","type":"article","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Research council; Standardized test; Educational assessment; Government (linguistics); National education","score_opus":0.011477720456780673,"score_gpt":0.323893062274081,"score_spread":0.3124153418173003,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7100226999","genre_codex":"editorial","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.005006457,0.026296841,0.0033678506,0.31199756,0.4745318,0.0008327302,0.0040660407,0.00029893668,0.17360172],"genre_scores_gemma":[0.03865048,0.028633539,0.0035259544,0.04463505,0.09429921,0.00036731022,0.003091884,0.00067322847,0.78612334],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.99711454,0.0006648827,0.00013170687,0.00040398407,0.0013443033,0.0003405878],"domain_scores_gemma":[0.988727,0.0017952,0.00016491114,0.00028422385,0.007384154,0.0016445717],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005568824,0.00095927285,0.0011721094,0.001672489,0.004083254,0.0037596405,0.0018559917,0.0021277445,0.13221945],"category_scores_gemma":[0.010525659,0.00030117977,0.00054587855,0.0016343326,0.001506739,0.00221415,0.0020302343,0.0030556342,0.017809676],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000865016,0.000044248118,0.00030785834,0.0001529589,0.000011219859,0.000043778262,0.00030895337,0.00003315849,0.0002685898,0.0007226008,0.975049,0.022971068],"study_design_scores_gemma":[0.00003546442,0.000044874596,0.0057973056,0.0002571657,0.000020269898,0.000053423475,0.00076509983,0.00009222557,0.00027071545,0.0009946455,0.99164283,0.000025951667],"about_ca_topic_score_codex":0.14810695,"about_ca_topic_score_gemma":0.42957243,"teacher_disagreement_score":0.14810695,"about_ca_system_score_codex":0.008138381,"about_ca_system_score_gemma":0.012138487,"threshold_uncertainty_score":0.44231814},"labels":[],"label_agreement":null},{"id":"W7102398008","doi":"10.65005/154230723836949059","title":"Students′ Perceptions of Skills Transfer in a First-Year Seminar","year":2023,"lang":"en","type":"article","venue":"Journal of The First-Year Experience & Students in Transition","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Perception; Academic skills; Study skills; Skills management; Transfer of training; Life skills","score_opus":0.014708777745636491,"score_gpt":0.353956143502827,"score_spread":0.3392473657571905,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7102398008","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9990761,0.00004106566,0.00007763949,0.000082195846,0.000007839844,0.00001247121,0.000006517434,0.0000060872635,0.00068996585],"genre_scores_gemma":[0.99935657,0.000051027477,0.000082274775,0.000046564848,0.0000050467174,0.000011718961,0.000011643166,0.0000019861898,0.00043332943],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.99760854,0.00074471167,0.00016334886,0.00013815198,0.0008582965,0.00048689355],"domain_scores_gemma":[0.9868444,0.0041827755,0.0026207524,0.00033859437,0.0014169302,0.0045964094],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0042007756,0.00041529915,0.00042959693,0.00065852393,0.00101191,0.0023881078,0.00061109563,0.00087281695,0.0033829168],"category_scores_gemma":[0.016213235,0.0002605131,0.00062753964,0.00028524856,0.00082317815,0.0009019425,0.0015306226,0.0016964823,0.00051875424],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0010150579,0.008701565,0.7865758,0.0003041215,0.00017205116,0.0011132883,0.09937941,0.00065483584,0.016389025,0.00042897355,0.0011003743,0.084165625],"study_design_scores_gemma":[0.00007191248,0.004842136,0.86961776,0.00010032068,0.00007600725,0.00043287658,0.11769937,0.00074633415,0.0036083993,0.00026497126,0.0024617838,0.00007813675],"about_ca_topic_score_codex":0.0015981543,"about_ca_topic_score_gemma":0.0018764,"teacher_disagreement_score":0.0042007756,"about_ca_system_score_codex":0.0006402654,"about_ca_system_score_gemma":0.0008297627,"threshold_uncertainty_score":0.022216082},"labels":[],"label_agreement":null},{"id":"W7103494908","doi":"","title":"A Collaborative &amp; Systematic Approach To Implementing An Effective Standards-Based Grading And Reporting System: A Change Leadership Plan","year":2017,"lang":"","type":"article","venue":"Digital Commons - NLU (National Louis University)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Grading (engineering); Action plan; General partnership; Best practice; Program evaluation; Quarter (Canadian coin); Plan (archaeology); Standardized test","score_opus":0.16643018346009017,"score_gpt":0.3582139314163848,"score_spread":0.19178374795629463,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7103494908","genre_codex":"methods","genre_gemma":"methods","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"methods","genre_consensus":"methods","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.33878452,0.0056311334,0.45410648,0.045796633,0.0011345111,0.12231026,0.00048079173,0.0014188342,0.03033688],"genre_scores_gemma":[0.44761276,0.0009184622,0.5208681,0.0032384659,0.000114872986,0.02510353,0.00016895318,0.000047600748,0.0019272248],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.6635686,0.27527156,0.018074958,0.011321597,0.027635338,0.004128067],"domain_scores_gemma":[0.7785261,0.11010043,0.034499228,0.02615709,0.04271674,0.008000378],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.238076,0.00099285,0.0012385307,0.008549277,0.008830679,0.008906234,0.0047240243,0.0021378705,0.0013977988],"category_scores_gemma":[0.1676683,0.0013181871,0.0015752052,0.004433548,0.0058246683,0.0080113495,0.008874639,0.0027889446,0.00042424272],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00032810503,0.0050040884,0.051257327,0.0057290713,0.0004785515,0.00043820098,0.10871332,0.0022935034,0.0026959602,0.01721579,0.008755219,0.79709095],"study_design_scores_gemma":[0.003189879,0.020357708,0.09352075,0.021007169,0.0017388084,0.0013828579,0.55883896,0.043030538,0.019689448,0.06507325,0.17107338,0.0010973171],"about_ca_topic_score_codex":0.008152199,"about_ca_topic_score_gemma":0.023412911,"teacher_disagreement_score":0.238076,"about_ca_system_score_codex":0.014149614,"about_ca_system_score_gemma":0.07641795,"threshold_uncertainty_score":0.93958795},"labels":[],"label_agreement":null},{"id":"W7103756966","doi":"10.5206/cjsotlrcacea.2025.1.19788","title":"Student Reflections on Mindfully Reframing Feedback for Growth in Academic, Personal, and Professional Settings","year":2025,"lang":"fr","type":"article","venue":"The Canadian Journal for the Scholarship of Teaching and Learning","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":true,"route_about_ca":false,"ca_institutions":"Western University","funders":"Schulich School of Medicine and Dentistry; Social Sciences and Humanities Research Council of Canada","keywords":"Cognitive reframing; Mindfulness; Thematic analysis; Literacy; Focus group; Professional development; Meaning (existential); Metacognition; Adult literacy","score_opus":0.06407297731461939,"score_gpt":0.4286397605762346,"score_spread":0.3645667832616152,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7103756966","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9722315,0.0006228832,0.006213682,0.008178109,0.0004967848,0.00019601702,0.00012596711,0.00031753714,0.011617502],"genre_scores_gemma":[0.98829067,0.0005875618,0.0032396377,0.0013937309,0.000090638576,0.000079618236,0.000051032748,0.00011928417,0.0061479514],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99184567,0.0051618167,0.0002716142,0.0002913659,0.0015136254,0.0009159116],"domain_scores_gemma":[0.9827372,0.010767512,0.0009073918,0.0008829182,0.0025946212,0.0021103618],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009856546,0.00088014407,0.0007223024,0.00084920437,0.0053124344,0.004269888,0.001393706,0.0021703958,0.0026590163],"category_scores_gemma":[0.027926698,0.00044555403,0.0007510079,0.0006209047,0.003798443,0.0020282045,0.0041825557,0.0052486886,0.0010143806],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0003163273,0.0009019192,0.0075809592,0.00033253594,0.000026847434,0.0018070383,0.88064635,0.00033480482,0.011359694,0.0017125828,0.008856791,0.08612417],"study_design_scores_gemma":[0.000070696915,0.002963058,0.029349798,0.00074941164,0.00006919271,0.0040151696,0.7794898,0.0016603625,0.023426695,0.00333912,0.15459213,0.0002745649],"about_ca_topic_score_codex":0.0026465445,"about_ca_topic_score_gemma":0.005967839,"teacher_disagreement_score":0.009856546,"about_ca_system_score_codex":0.0019607441,"about_ca_system_score_gemma":0.0025276213,"threshold_uncertainty_score":0.052127063},"labels":[],"label_agreement":null},{"id":"W7106788186","doi":"10.1108/978-1-68123-046-720251012","title":"Student Assessment in A Blended Learning Environment","year":2015,"lang":"en","type":"book-chapter","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Mount Royal University","funders":"","keywords":"Blended learning; Experiential learning; Student engagement; Electronic learning; Test (biology); Process (computing); Online assessment","score_opus":0.05432146798584401,"score_gpt":0.36860370754773575,"score_spread":0.3142822395618917,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7106788186","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.035912298,0.015609221,0.46159738,0.0024362234,0.0017235645,0.00023424698,0.0001433016,0.001981263,0.48036256],"genre_scores_gemma":[0.30448607,0.013257706,0.13549723,0.00057931355,0.00058241957,0.00035325266,0.00030933664,0.00040444726,0.5445302],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99897635,0.00024334865,0.00005695991,0.00007141186,0.00060937845,0.0000426704],"domain_scores_gemma":[0.9989201,0.00047040687,0.00005324479,0.00007255627,0.0003496621,0.00013411819],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0010139766,0.00060704234,0.0004730539,0.00072513736,0.00039067518,0.00281339,0.0009654582,0.00072951755,0.006760136],"category_scores_gemma":[0.0037698024,0.00017686028,0.0002994333,0.00078639097,0.0005293604,0.0020786142,0.0018258587,0.0012697441,0.0025549692],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000047934715,0.00014173225,0.00064761937,0.0001705647,0.000008531025,0.000066327855,0.00083330425,0.003546087,0.0020477078,0.035757236,0.019748555,0.9369844],"study_design_scores_gemma":[0.000043307136,0.000474482,0.0100714825,0.0016182974,0.0000427157,0.0012305747,0.0016745552,0.07016945,0.010995547,0.30746064,0.59612334,0.00009569144],"about_ca_topic_score_codex":0.0006811867,"about_ca_topic_score_gemma":0.0012212988,"teacher_disagreement_score":0.006760136,"about_ca_system_score_codex":0.0008549552,"about_ca_system_score_gemma":0.00093121576,"threshold_uncertainty_score":0.022614956},"labels":[],"label_agreement":null},{"id":"W7106822041","doi":"10.1108/978-1-68123-046-720251004","title":"Empowering Learners to Engage in Authentic Online Assessment","year":2015,"lang":"en","type":"book-chapter","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Online assessment; Qualitative research; Process (computing); The Internet; Context (archaeology); Work (physics)","score_opus":0.09050856878806421,"score_gpt":0.42984025083243166,"score_spread":0.3393316820443675,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7106822041","genre_codex":"other","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":"other","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.022063637,0.008591247,0.14259043,0.008232398,0.0013943267,0.00016336003,0.0000688271,0.00093276,0.81596303],"genre_scores_gemma":[0.18303244,0.012720634,0.06478815,0.0024999003,0.00085901504,0.00038133652,0.00016391634,0.00029562935,0.735259],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.99905616,0.00041240844,0.000022866556,0.00005955903,0.00038225262,0.00006665971],"domain_scores_gemma":[0.9985815,0.0008585579,0.00006904126,0.0000991678,0.00017875299,0.00021286638],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00132085,0.00043571737,0.00019379324,0.0003093586,0.0006138977,0.0028885014,0.0006280063,0.0008406038,0.011578127],"category_scores_gemma":[0.0035782496,0.00012291239,0.00019977178,0.0002381506,0.0012065851,0.00271575,0.0035216708,0.002056196,0.0043981452],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000022544764,0.000211664,0.0005422025,0.00029525856,0.0000054913917,0.00014744869,0.015315586,0.00037462846,0.0026469482,0.11611434,0.06137211,0.80295175],"study_design_scores_gemma":[0.0000065329345,0.00005394104,0.0010981244,0.00066126895,0.0000058524893,0.00046221694,0.0039299196,0.00089522,0.0024836021,0.096845925,0.8935415,0.000015970096],"about_ca_topic_score_codex":0.00021904425,"about_ca_topic_score_gemma":0.000873138,"teacher_disagreement_score":0.011578127,"about_ca_system_score_codex":0.00040335252,"about_ca_system_score_gemma":0.0010664363,"threshold_uncertainty_score":0.038732648},"labels":[],"label_agreement":null},{"id":"W7111684596","doi":"","title":"Redefining Neuro-Inclusive, Stakeholder-Informed Language Assessment in UK Higher Education","year":2025,"lang":"en","type":"book-chapter","venue":"Pure (Coventry University)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Centre for Global Health Research","funders":"","keywords":"Formative assessment; Higher education; Equity (law); Accreditation; Quality (philosophy); Best practice; Educational assessment; Resource (disambiguation); Discourse analysis; Scope (computer science)","score_opus":0.03523103187095834,"score_gpt":0.31009817115500404,"score_spread":0.2748671392840457,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7111684596","genre_codex":"review","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.04037845,0.43174016,0.14693192,0.23072982,0.004696203,0.0014833759,0.00042602437,0.00038822604,0.1432258],"genre_scores_gemma":[0.5620503,0.16856141,0.2071926,0.034464784,0.00084838836,0.0035562238,0.00041666036,0.0002594899,0.022650208],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.91597027,0.070304,0.004267752,0.0012603841,0.007408844,0.00078877265],"domain_scores_gemma":[0.9192247,0.07185021,0.002094565,0.0019717624,0.0041928524,0.00066598057],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.07064581,0.0006503202,0.0007947296,0.0029952016,0.0021312432,0.011464316,0.0017614765,0.0030962494,0.0027548622],"category_scores_gemma":[0.0672727,0.000597691,0.00055900903,0.0034146283,0.010746314,0.011991296,0.008674744,0.0038008452,0.0005231894],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000050273247,0.000029308023,0.00119066,0.0140453335,0.000052157884,0.00037054875,0.09876241,0.00092902913,0.00091243564,0.30692133,0.023132257,0.55360425],"study_design_scores_gemma":[0.000032936387,0.0001618933,0.0017147654,0.03717388,0.00006537676,0.00068886625,0.044142894,0.0006946592,0.0016966241,0.19257279,0.7209794,0.000076049706],"about_ca_topic_score_codex":0.007658203,"about_ca_topic_score_gemma":0.019021217,"teacher_disagreement_score":0.07064581,"about_ca_system_score_codex":0.012323104,"about_ca_system_score_gemma":0.023787385,"threshold_uncertainty_score":0.3736152},"labels":[],"label_agreement":null},{"id":"W7115402523","doi":"","title":"Teacher-Led Learning Circles for Formative Assessment:Full Report of International Research Findings","year":2024,"lang":"en","type":"book","venue":"Edinburgh Research Explorer (University of Edinburgh)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Toronto; Queen's University","funders":"Ministère de l’Éducation, Gouvernement de l’Ontario; Jacobs Foundation; Queen's University; University of South Florida; American Educational Research Association","keywords":"Formative assessment; Qualitative research; Experiential learning; Research methodology","score_opus":0.1450135143569837,"score_gpt":0.4418710255656071,"score_spread":0.29685751120862336,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7115402523","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.2829872,0.029447734,0.06875269,0.011818025,0.0025347152,0.0063591055,0.0049067833,0.004750998,0.58844274],"genre_scores_gemma":[0.7106338,0.03229289,0.080368415,0.0025553613,0.0005937629,0.005692073,0.008837887,0.0027184447,0.15630737],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9778086,0.009357403,0.0015121826,0.0011062616,0.00911455,0.0011009686],"domain_scores_gemma":[0.90299666,0.042896137,0.0040205005,0.0118160285,0.033170328,0.0051003494],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.027940085,0.00083142164,0.00054760143,0.00315278,0.0015307917,0.005644453,0.0025430794,0.00092948455,0.016885774],"category_scores_gemma":[0.05823886,0.00042431024,0.00052741583,0.0050400314,0.0010877672,0.005106173,0.004154085,0.002006311,0.009180728],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000193311,0.0011481935,0.015671285,0.0011428917,0.000024635352,0.00022639628,0.00846115,0.00026632205,0.0027162877,0.0021511677,0.032900497,0.9350978],"study_design_scores_gemma":[0.0001489067,0.004045414,0.19552824,0.007471198,0.00016922945,0.005092068,0.03988246,0.0017154405,0.03944991,0.003022441,0.7031724,0.00030233458],"about_ca_topic_score_codex":0.0035768799,"about_ca_topic_score_gemma":0.004389997,"teacher_disagreement_score":0.027940085,"about_ca_system_score_codex":0.0022682953,"about_ca_system_score_gemma":0.009278514,"threshold_uncertainty_score":0.14776301},"labels":[],"label_agreement":null},{"id":"W7116078021","doi":"10.20343/teachlearninqu.13.61","title":"Structured Flexibility in Assessment: Students’ Perceptions of the Impact of Different Elements of Choice on Their Decision Making, Engagement, and Learning Experiences","year":2025,"lang":"en","type":"article","venue":"Teaching & Learning Inquiry The ISSOTL Journal","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"MacEwan University","funders":"","keywords":"Flexibility (engineering); Autonomy; Perception; Quality (philosophy); Process (computing); Scholarship; Higher education","score_opus":0.051035545615166655,"score_gpt":0.4602103792120843,"score_spread":0.40917483359691764,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7116078021","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9977399,0.00003400091,0.0011314442,0.00009467243,0.0000074340464,0.00003619016,0.000007103154,0.000009829191,0.00093938643],"genre_scores_gemma":[0.9988341,0.00003086192,0.0008013397,0.0000353975,0.0000026989276,0.000035566252,0.000011174993,0.0000029113705,0.00024592236],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.98882246,0.006169407,0.0008343925,0.0005932498,0.0027101766,0.00087022793],"domain_scores_gemma":[0.97078043,0.019004436,0.0033855475,0.0013940515,0.0016415416,0.0037939048],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011444636,0.00043912968,0.0005857467,0.00086383166,0.0010287149,0.004974317,0.00060888554,0.0010235689,0.0022023993],"category_scores_gemma":[0.040936437,0.00028874184,0.000877702,0.0004781206,0.002457329,0.0021002146,0.003914736,0.0020484251,0.0002839968],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0014956477,0.003737656,0.44901997,0.00052605016,0.00023596887,0.0009978147,0.38572514,0.0032779535,0.02918199,0.0030381482,0.0010725008,0.1216912],"study_design_scores_gemma":[0.00034273605,0.009799762,0.5618851,0.0005253946,0.0001847639,0.0014703323,0.37005058,0.0119917225,0.011975883,0.013432301,0.017664112,0.0006773211],"about_ca_topic_score_codex":0.0007125818,"about_ca_topic_score_gemma":0.0008489823,"teacher_disagreement_score":0.011444636,"about_ca_system_score_codex":0.00094777026,"about_ca_system_score_gemma":0.001311453,"threshold_uncertainty_score":0.060525775},"labels":[],"label_agreement":null},{"id":"W7116316694","doi":"10.1016/j.ijedudev.2025.103476","title":"Exploring effective teacher certificate requirements to benefit student achievement: Evidence from a global perspective","year":2025,"lang":"en","type":"article","venue":"International Journal of Educational Development","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Certification; Licensure; Certificate; Perspective (graphical); Test (biology); Professional certification (computer technology)","score_opus":0.20509403059623602,"score_gpt":0.46798326171927596,"score_spread":0.26288923112303997,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7116316694","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.94754136,0.0041881027,0.0014585028,0.0040699868,0.00007616002,0.00014305848,0.00026496252,0.00004231661,0.042215623],"genre_scores_gemma":[0.9972486,0.0010375871,0.00054798316,0.0003590325,0.00001622495,0.000043243843,0.000071514274,0.000012819603,0.000662985],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98702675,0.00751735,0.00063457503,0.00076267973,0.002759293,0.0012994143],"domain_scores_gemma":[0.9047524,0.06689568,0.016085045,0.0035300185,0.0050779018,0.0036589159],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0134509895,0.0003833967,0.000879763,0.0014230825,0.0011018557,0.0028684037,0.0013327618,0.0011714413,0.0067244223],"category_scores_gemma":[0.05968014,0.0002483975,0.00074197486,0.002563887,0.002428808,0.0020984386,0.0035032954,0.0017249984,0.0007414144],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0031728935,0.0065091946,0.3827725,0.005478798,0.0010616806,0.00046571312,0.014663608,0.0027785078,0.0010214319,0.015699547,0.005513542,0.5608626],"study_design_scores_gemma":[0.0013207376,0.005705903,0.9184339,0.0048306547,0.0015350961,0.00041600532,0.022595575,0.0011926439,0.0026207906,0.009693547,0.031555664,0.00009952186],"about_ca_topic_score_codex":0.0066889278,"about_ca_topic_score_gemma":0.017195748,"teacher_disagreement_score":0.0134509895,"about_ca_system_score_codex":0.0018972434,"about_ca_system_score_gemma":0.008342301,"threshold_uncertainty_score":0.071136534},"labels":[],"label_agreement":null},{"id":"W7117361401","doi":"10.51798/sijis.v6i4.1177","title":"Validation of tests using an argument-based approach: a review based on the PRISMA model","year":2025,"lang":"","type":"article","venue":"Sapienza International Journal of Interdisciplinary Studies","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Barrie Urology Group","funders":"","keywords":"Relevance (law); Empirical research; Reliability (semiconductor); Quality (philosophy); Process (computing); Test (biology)","score_opus":0.11653760396115638,"score_gpt":0.45201481181218167,"score_spread":0.3354772078510253,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7117361401","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.006493872,0.6862894,0.1844069,0.019993883,0.0048750443,0.08336186,0.005761581,0.00086006976,0.007957399],"genre_scores_gemma":[0.084833376,0.2603994,0.47283036,0.0059920736,0.000508732,0.1704865,0.0041404692,0.00021982266,0.00058938446],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.50519377,0.27272782,0.15619774,0.011461353,0.052483615,0.0019357024],"domain_scores_gemma":[0.3996008,0.45477298,0.053270537,0.023981882,0.06646436,0.0019094357],"candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.40662575,0.0034289,0.012263475,0.03527448,0.0040023816,0.0076925308,0.0116479155,0.0055019534,0.004237104],"category_scores_gemma":[0.5448468,0.0031198855,0.026921004,0.027556475,0.0076816585,0.0113866525,0.009854433,0.0065086,0.0010149732],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00035574625,0.00007279768,0.0018314319,0.8265684,0.010666263,0.00022939019,0.0027163366,0.001597733,0.0004654027,0.012564598,0.0054938453,0.13743807],"study_design_scores_gemma":[0.0010305324,0.0004157268,0.0042857546,0.8623978,0.031983525,0.0005380941,0.0017253802,0.0028532986,0.0015019339,0.020523245,0.07245172,0.00029301993],"about_ca_topic_score_codex":0.0059396583,"about_ca_topic_score_gemma":0.011926428,"teacher_disagreement_score":0.59337425,"about_ca_system_score_codex":0.013852369,"about_ca_system_score_gemma":0.068572864,"threshold_uncertainty_score":0.73173606},"labels":[],"label_agreement":null},{"id":"W7124146263","doi":"10.31986/issn.2995-8288_vol3iss2.4","title":"“The Being of Being Creative” in Assessment: Learning from the Creative and Performing Arts","year":2025,"lang":"","type":"article","venue":"Turning toward being :","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Athabasca University","funders":"","keywords":"Foregrounding; Formative assessment; Creativity; Performing arts; Experiential learning; Memorization; Narrative; Value (mathematics); Quality (philosophy)","score_opus":0.02363586033746035,"score_gpt":0.33832485041748234,"score_spread":0.314688990080022,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7124146263","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.22658432,0.01439806,0.256989,0.12702215,0.0016288386,0.0005276836,0.00006592834,0.00026854343,0.37251547],"genre_scores_gemma":[0.96276444,0.004076843,0.023397025,0.0030531818,0.00018372163,0.00024257824,0.000027211698,0.000082248334,0.00617286],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9677811,0.027768506,0.0005860907,0.00088090653,0.0023458032,0.0006376083],"domain_scores_gemma":[0.9727137,0.021860043,0.00095709926,0.0017235266,0.0014351166,0.0013105472],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02163447,0.0005109001,0.00043041573,0.0015971396,0.0065910895,0.01867852,0.0014772451,0.003194365,0.001930101],"category_scores_gemma":[0.037243918,0.00038311278,0.0004551894,0.0015341793,0.048193693,0.020036733,0.011414755,0.006283337,0.0005185454],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00003881088,0.00006853137,0.0020220606,0.00037758064,0.0000096731,0.000417707,0.5360394,0.00027021466,0.000691211,0.3780772,0.003037297,0.07895025],"study_design_scores_gemma":[0.000028518461,0.0001610309,0.0024597875,0.0022772911,0.00003090953,0.0013180107,0.3340122,0.0013312529,0.0024342355,0.39866203,0.25720498,0.000079748475],"about_ca_topic_score_codex":0.0017659662,"about_ca_topic_score_gemma":0.002385528,"teacher_disagreement_score":0.02163447,"about_ca_system_score_codex":0.003792484,"about_ca_system_score_gemma":0.006513224,"threshold_uncertainty_score":0.11441541},"labels":[],"label_agreement":null},{"id":"W7125351318","doi":"","title":"A Comparative Study of Student Perspectives on Technical Writing Feedback Quality: Evaluating LLMs, SLMs, and Humans in Computer Science Topics","year":2025,"lang":"","type":"article","venue":"ArXiv.org","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"","funders":"Division of Undergraduate Education; Natural Sciences and Engineering Research Council of Canada; University of Toronto","keywords":"CLARITY; Technical writing; Perspective (graphical); Preference; Course (navigation); Scalability; Quality (philosophy); Peer feedback","score_opus":0.17140721702955675,"score_gpt":0.5004576099750087,"score_spread":0.3290503929454519,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7125351318","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99874157,0.000052459844,0.00047849695,0.0000851073,0.0000074682484,0.000014648388,0.000014829726,0.000009956102,0.0005954684],"genre_scores_gemma":[0.9991234,0.000061577564,0.00043414877,0.00005832493,0.000008428008,0.000028983895,0.000022950988,0.0000082717215,0.00025391797],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.98285896,0.009921047,0.0011430687,0.0008233512,0.004320545,0.00093302375],"domain_scores_gemma":[0.8997066,0.063903645,0.0139048975,0.0016304519,0.015257333,0.005597118],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.017590243,0.00042924692,0.00063959695,0.0023107952,0.0010934841,0.0032131195,0.0004920048,0.0008023695,0.0014664626],"category_scores_gemma":[0.07966901,0.0003016401,0.00051368785,0.0011835458,0.0014995764,0.0014968929,0.0022403882,0.0011500178,0.0003004324],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0011373105,0.001254437,0.4117295,0.0005287578,0.00015485953,0.0005262716,0.48266402,0.0004128666,0.013999763,0.00051721226,0.0010329133,0.086042084],"study_design_scores_gemma":[0.00009926449,0.0059564067,0.49967244,0.00045086717,0.00013604281,0.00069478934,0.4741456,0.0031406665,0.00899986,0.00058714114,0.005919386,0.00019751798],"about_ca_topic_score_codex":0.00085108937,"about_ca_topic_score_gemma":0.0011024724,"teacher_disagreement_score":0.017590243,"about_ca_system_score_codex":0.0011080106,"about_ca_system_score_gemma":0.0010936299,"threshold_uncertainty_score":0.093027174},"labels":[],"label_agreement":null},{"id":"W7127392540","doi":"10.1109/ccece64018.2025.11364447","title":"Automated Grading of Scratch Card Based Immediate Feedback Assessment Technique (IFAT)","year":2025,"lang":"","type":"article","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Trent University","funders":"","keywords":"Scratch; Grading (engineering); Process (computing); Automation; Usability","score_opus":0.018134071906542287,"score_gpt":0.36203799488045996,"score_spread":0.3439039229739177,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7127392540","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.18195984,0.0004123528,0.77879065,0.00011916261,0.00037262563,0.0022782222,0.0028955191,0.022271093,0.010900424],"genre_scores_gemma":[0.31945714,0.00023371814,0.6645302,0.00009275553,0.00006394314,0.0013750448,0.0025287676,0.0009950822,0.010723264],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9951448,0.00097175705,0.00047624475,0.0008727063,0.0023168419,0.00021761778],"domain_scores_gemma":[0.9793397,0.0041600335,0.0016369271,0.0025010325,0.011923649,0.00043860535],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0034240477,0.0010871497,0.0008739392,0.0030738264,0.00049457944,0.0015284066,0.0013752903,0.00063497125,0.008876648],"category_scores_gemma":[0.016504692,0.00028230605,0.00055351784,0.0012443886,0.0003413897,0.0008081383,0.0010677471,0.0005466317,0.0050211167],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00074213295,0.00033760347,0.017401287,0.0005600821,0.00006524669,0.0001608988,0.00043910393,0.0047879023,0.08863115,0.0012463729,0.0152559895,0.8703722],"study_design_scores_gemma":[0.00024664236,0.003094934,0.18158537,0.00037520126,0.00022715692,0.0017139774,0.0007327822,0.35186338,0.38293278,0.004564836,0.0721081,0.00055489026],"about_ca_topic_score_codex":0.0017980977,"about_ca_topic_score_gemma":0.0023978997,"teacher_disagreement_score":0.008876648,"about_ca_system_score_codex":0.00042555406,"about_ca_system_score_gemma":0.00085152214,"threshold_uncertainty_score":0.029695332},"labels":[],"label_agreement":null},{"id":"W7130683390","doi":"10.1109/swc65939.2025.00073","title":"Can Question Validation Criteria Improve the Quality of LLM-Generated Multiple-Choice Questions?","year":2025,"lang":"","type":"article","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta; Athabasca University","funders":"Alberta Innovates; Natural Sciences and Engineering Research Council of Canada; Athabasca University","keywords":"Formative assessment; Quality (philosophy); Set (abstract data type); Subject-matter expert; Quality assurance; Key (lock); Subject (documents)","score_opus":0.05532363522220222,"score_gpt":0.43079302854945173,"score_spread":0.3754693933272495,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7130683390","genre_codex":"methods","genre_gemma":"empirical","domain_codex":null,"domain_gemma":"methods","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":"methods","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.3904373,0.0014323061,0.5840762,0.0026731903,0.00045274143,0.0031876627,0.000542837,0.009663574,0.007534124],"genre_scores_gemma":[0.64814276,0.0002254965,0.3478896,0.0004952854,0.00008614398,0.0011456666,0.00054607115,0.00055377284,0.0009152147],"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","domain_scores_codex":[0.89285827,0.08104622,0.006499467,0.0065891445,0.011875774,0.0011310792],"domain_scores_gemma":[0.36630517,0.51358086,0.0303577,0.030090913,0.057770524,0.0018948002],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.09528947,0.0015503863,0.0010918301,0.0025469675,0.00063096377,0.0033990606,0.0024112733,0.0020194664,0.0031125292],"category_scores_gemma":[0.4845497,0.0005711771,0.00082448527,0.0013650728,0.0013127208,0.004907543,0.002859982,0.0014345379,0.0014226075],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.002139217,0.0012667307,0.04507375,0.0026536954,0.00018427879,0.00020847376,0.009968588,0.006527586,0.053058043,0.0027751685,0.0044667143,0.8716777],"study_design_scores_gemma":[0.0015436395,0.0104855085,0.24129282,0.004423055,0.00072439265,0.0017902666,0.008951049,0.32951322,0.31465077,0.025710182,0.059971828,0.0009432566],"about_ca_topic_score_codex":0.0012183168,"about_ca_topic_score_gemma":0.0012721997,"teacher_disagreement_score":0.90471053,"about_ca_system_score_codex":0.0014571436,"about_ca_system_score_gemma":0.0017507608,"threshold_uncertainty_score":0.5039449},"labels":[],"label_agreement":null},{"id":"W7130688282","doi":"10.1109/swc65939.2025.00060","title":"Automated Grading: Methods, Implementations, and Opportunities in Higher Education","year":2025,"lang":"","type":"article","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Athabasca University; University of Alberta","funders":"Innovation Fund; Government of Alberta","keywords":"Grading (engineering); Workflow; Automation; Higher education","score_opus":0.17804031274985058,"score_gpt":0.5101519021792482,"score_spread":0.33211158942939767,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7130688282","genre_codex":"methods","genre_gemma":"review","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.019734709,0.023592135,0.9285154,0.00850421,0.0008908251,0.0005662899,0.00023981449,0.004044817,0.013911805],"genre_scores_gemma":[0.16394696,0.010777548,0.81820834,0.00069096097,0.00061565416,0.00043143524,0.00032521036,0.00058405567,0.0044199256],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.95581186,0.025832906,0.002672649,0.0033303872,0.011456163,0.00089609146],"domain_scores_gemma":[0.8926159,0.056736797,0.0069325254,0.01743194,0.023236537,0.0030462763],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.05202021,0.0014922397,0.0011574273,0.0060225795,0.001511248,0.007889289,0.0039644404,0.0029885806,0.004420193],"category_scores_gemma":[0.07196784,0.0015051034,0.0008837613,0.0069802497,0.003366741,0.00935768,0.0029466387,0.0039682155,0.0044147973],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013656823,0.00034155094,0.0071516307,0.00076204183,0.000053243224,0.00006151456,0.0008299578,0.0033433093,0.002196189,0.029388355,0.0070464853,0.9486891],"study_design_scores_gemma":[0.00026300474,0.0014018359,0.025422588,0.005347912,0.00018436753,0.001399006,0.0024638453,0.14809345,0.02627988,0.4776094,0.31082875,0.00070596614],"about_ca_topic_score_codex":0.0027231497,"about_ca_topic_score_gemma":0.0024051447,"teacher_disagreement_score":0.05202021,"about_ca_system_score_codex":0.0027955435,"about_ca_system_score_gemma":0.003667653,"threshold_uncertainty_score":0.27511245},"labels":[],"label_agreement":null},{"id":"W7132913430","doi":"","title":"Conflicts and challenges of testing: Differences between novice and experienced teachers&apos; preparation practices for large-scale assessments","year":2008,"lang":"","type":"dissertation","venue":"TSpace","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Set (abstract data type); Test (biology); Sample (material); Educational measurement","score_opus":0.22750643072695254,"score_gpt":0.5093735031714349,"score_spread":0.2818670724444824,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7132913430","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99889237,0.00004353474,0.00006899673,0.00013004821,0.000002860661,0.000009409707,0.000010272949,0.0000029250498,0.0008395807],"genre_scores_gemma":[0.99938476,0.000037605736,0.00011088817,0.00003365021,0.000001885514,0.00000644744,0.000013485478,0.000001966219,0.00040927995],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.9954021,0.0014504154,0.00040258683,0.00026583087,0.0017055112,0.00077347737],"domain_scores_gemma":[0.9720408,0.010426032,0.007362336,0.00086984993,0.00465217,0.004648837],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0043886784,0.00014611286,0.00022409008,0.0006672579,0.002157069,0.0022403542,0.0007029501,0.00046329995,0.0011738541],"category_scores_gemma":[0.03551702,0.0003236962,0.00016918428,0.0006057356,0.0019281649,0.00072907866,0.0016431639,0.00069494697,0.00019584884],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00013426752,0.0001660779,0.71496695,0.000051340554,0.00001268108,0.0005609963,0.25083545,0.00010275404,0.0017942135,0.00015873855,0.0006811164,0.030535487],"study_design_scores_gemma":[0.0000083351015,0.00014192819,0.827725,0.000043189204,0.0000053964086,0.00023513866,0.1691379,0.00021941512,0.00030838526,0.00012795464,0.0020269863,0.000020264199],"about_ca_topic_score_codex":0.19408312,"about_ca_topic_score_gemma":0.39626,"teacher_disagreement_score":0.19408312,"about_ca_system_score_codex":0.0042110225,"about_ca_system_score_gemma":0.0065206173,"threshold_uncertainty_score":0.38590688},"labels":[],"label_agreement":null},{"id":"W7132923481","doi":"","title":"Exploring Perspective-taking in Peer Assessment","year":2023,"lang":"","type":"dissertation","venue":"TSpace","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Canadian Association for the Study of Adult Education","funders":"","keywords":"Peer assessment; Rubric; Peer feedback; Operationalization; Judgement; Peer group; Peer evaluation; Peer review","score_opus":0.2197275793622576,"score_gpt":0.5054941032321677,"score_spread":0.2857665238699101,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7132923481","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.89147115,0.0013165184,0.053478777,0.0030010978,0.00015942205,0.00047278753,0.000040884013,0.00006407475,0.049995307],"genre_scores_gemma":[0.9894956,0.0004906198,0.008073203,0.0001534438,0.000029615385,0.00014216456,0.000020471178,0.000019591756,0.0015754255],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.93626255,0.052835215,0.00090373517,0.0019256207,0.0064680735,0.0016048049],"domain_scores_gemma":[0.9273435,0.056986354,0.004812155,0.0028568911,0.0054550967,0.0025460583],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.030976519,0.000971428,0.00067580387,0.002432479,0.0041843457,0.009609203,0.0019503188,0.0014601023,0.0021557584],"category_scores_gemma":[0.057275206,0.0005933597,0.0010197399,0.0016202327,0.00970021,0.0064686267,0.008954819,0.0032340644,0.00026936305],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00009618626,0.00024154279,0.008916139,0.00035018206,0.00007129173,0.001108026,0.92991894,0.000381287,0.004345022,0.015313912,0.00037021676,0.038887307],"study_design_scores_gemma":[0.000093419585,0.00089748204,0.026872916,0.00085751317,0.00013031471,0.0019572848,0.87613755,0.0036465328,0.0071515553,0.040350094,0.041721478,0.00018385243],"about_ca_topic_score_codex":0.001669727,"about_ca_topic_score_gemma":0.0023202247,"teacher_disagreement_score":0.030976519,"about_ca_system_score_codex":0.0035183362,"about_ca_system_score_gemma":0.0031607237,"threshold_uncertainty_score":0.16382146},"labels":[],"label_agreement":null},{"id":"W7132932718","doi":"","title":"Large scale performance-based assessment: Dentification of individual student gaps with implications for teacher content knowledge","year":2004,"lang":"","type":"dissertation","venue":"TSpace","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Nature versus nurture; Literacy; Population; Construct (python library); Scale (ratio); Pace; Knowledge acquisition; Task (project management); Interpretation (philosophy)","score_opus":0.06807253949039363,"score_gpt":0.436790008042412,"score_spread":0.36871746855201837,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7132932718","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95125985,0.00021376621,0.028875075,0.0003503197,0.00003366716,0.0006370387,0.00028836992,0.00033552552,0.01800645],"genre_scores_gemma":[0.98302704,0.00010401861,0.0133864265,0.00002701213,0.000011803203,0.00024940158,0.00020187392,0.000031592972,0.0029608419],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9943944,0.0024776189,0.00038962305,0.0004171694,0.0021902393,0.00013090139],"domain_scores_gemma":[0.97307116,0.015995221,0.0022859431,0.0017808417,0.006287671,0.0005792311],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005777074,0.00039707302,0.00032495311,0.0014964938,0.0005341916,0.0011393343,0.00045461784,0.00043479522,0.0023127187],"category_scores_gemma":[0.032362543,0.00009761445,0.00021944602,0.0009950494,0.0005304825,0.0013722138,0.0012899787,0.00047401944,0.00054558105],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00085893564,0.0016494214,0.31483963,0.00041870502,0.00011290119,0.00032424825,0.01989856,0.004554114,0.02073054,0.0021328628,0.0048375763,0.6296424],"study_design_scores_gemma":[0.00007787357,0.00469784,0.8842244,0.00029719408,0.00013504713,0.0009184728,0.023222025,0.032370135,0.032569427,0.0049863383,0.016350292,0.00015080717],"about_ca_topic_score_codex":0.0017078765,"about_ca_topic_score_gemma":0.004025423,"teacher_disagreement_score":0.005777074,"about_ca_system_score_codex":0.00062411925,"about_ca_system_score_gemma":0.0011020536,"threshold_uncertainty_score":0.030552447},"labels":[],"label_agreement":null},{"id":"W7132982053","doi":"","title":"Reforming Language Teaching through Learner Portfolio Assessment: The Complexity of Practitioners’ Experiences","year":2022,"lang":"","type":"dissertation","venue":"TSpace","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"Social Sciences and Humanities Research Council of Canada; University of Toronto","keywords":"Authentic assessment; Data collection; Agency (philosophy); Exploratory factor analysis; Metacognition; Language assessment; Language education; Portfolio; Self-assessment; Qualitative research","score_opus":0.06834876892462345,"score_gpt":0.4694674329827249,"score_spread":0.4011186640581015,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7132982053","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9856009,0.000925575,0.006508387,0.003595243,0.0000415064,0.00008119524,0.000016359265,0.00002875533,0.0032021184],"genre_scores_gemma":[0.994476,0.0006296791,0.00322916,0.0004433727,0.000020647001,0.00009110354,0.0000156938,0.000022005865,0.0010722465],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9521356,0.03922188,0.001175774,0.0017227213,0.0033626356,0.0023813308],"domain_scores_gemma":[0.9495623,0.03972887,0.0027762183,0.0015799509,0.0035510827,0.0028015517],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03521839,0.00045581226,0.0008530652,0.002380547,0.0059630526,0.00883956,0.002077048,0.0024138787,0.0016600958],"category_scores_gemma":[0.052670106,0.0007936909,0.00040134502,0.0020108703,0.0074872933,0.008029317,0.009534938,0.002930331,0.00029836607],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023227434,0.00005658638,0.004753573,0.000111298345,0.000007227821,0.0005710712,0.97501004,0.00006468268,0.0007873256,0.0011072934,0.00023435644,0.017273376],"study_design_scores_gemma":[0.000009215945,0.00015831369,0.0020495162,0.00022033656,0.000008911648,0.0007369927,0.984452,0.00031631364,0.00040530815,0.00088202907,0.01074013,0.000020906606],"about_ca_topic_score_codex":0.0032516643,"about_ca_topic_score_gemma":0.006853365,"teacher_disagreement_score":0.03521839,"about_ca_system_score_codex":0.005057606,"about_ca_system_score_gemma":0.0069026845,"threshold_uncertainty_score":0.18625486},"labels":[],"label_agreement":null},{"id":"W7133013582","doi":"","title":"Teaching methodologies and assessment strategies of Ontario grade 9 mathematics teachers","year":2004,"lang":"","type":"dissertation","venue":"TSpace","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Teaching method; Evaluation methods; Alternative assessment; Connected Mathematics; Program evaluation","score_opus":0.1199004617813298,"score_gpt":0.4912382694024263,"score_spread":0.3713378076210965,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7133013582","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9921747,0.0010530122,0.00062349986,0.00018153031,0.000008297327,0.00004237959,0.000119025855,0.000024548486,0.005772943],"genre_scores_gemma":[0.99058527,0.0017042846,0.002650813,0.000055874887,0.000005048735,0.00005692011,0.00019092242,0.000011518367,0.004739251],"study_design_codex":"observational","study_design_gemma":"qualitative","domain_scores_codex":[0.99700767,0.00048734664,0.00025592564,0.0001901963,0.0018125023,0.00024646867],"domain_scores_gemma":[0.99083495,0.002388201,0.0026539173,0.00020439828,0.00323763,0.0006808625],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015424136,0.00023938288,0.00023152346,0.0019108597,0.001060301,0.0015157337,0.0004919825,0.00027141222,0.0009556317],"category_scores_gemma":[0.011541823,0.00027983054,0.00017633845,0.0016207419,0.0006261909,0.00051623216,0.0007054482,0.00030201938,0.0002517279],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00012181832,0.00019007576,0.63764155,0.0006096141,0.000043652934,0.00045193668,0.091170184,0.00023035124,0.013254876,0.0003848803,0.0011947742,0.25470626],"study_design_scores_gemma":[0.000007087406,0.00017442537,0.95486856,0.00018874074,0.000031696043,0.00026417614,0.026572848,0.00021526871,0.002012512,0.00013034101,0.015505652,0.000028634688],"about_ca_topic_score_codex":0.31061366,"about_ca_topic_score_gemma":0.6822204,"teacher_disagreement_score":0.68938637,"about_ca_system_score_codex":0.0049391524,"about_ca_system_score_gemma":0.009115024,"threshold_uncertainty_score":0.6176114},"labels":[],"label_agreement":null},{"id":"W7133083716","doi":"","title":"Teachers Navigating Their Experiences of &quot;Going Gradeless&quot; in Ontario, Canada","year":2020,"lang":"","type":"dissertation","venue":"TSpace","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Rubric; Curriculum; Qualitative research; National curriculum; Process (computing); Task (project management); Hidden curriculum; Politics; Conceptual framework","score_opus":0.030177475987947074,"score_gpt":0.3594132025837606,"score_spread":0.3292357265958135,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7133083716","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97076786,0.0009777234,0.0008064323,0.006293911,0.00009577429,0.00012655898,0.0002794943,0.00005325032,0.020599002],"genre_scores_gemma":[0.9840656,0.0006372072,0.00039682334,0.00084371446,0.000008833476,0.00005226342,0.00009519887,0.000041376625,0.013859104],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.99385095,0.0017017496,0.00023858799,0.00049826456,0.0015509191,0.002159468],"domain_scores_gemma":[0.99001724,0.0020056537,0.00085964106,0.0002574269,0.0030483694,0.0038117415],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0029608533,0.0004340246,0.0007235304,0.0012462301,0.033892512,0.005674566,0.002582304,0.0016317058,0.004077437],"category_scores_gemma":[0.0071913023,0.0006943799,0.00033630742,0.0028078558,0.016215235,0.0020306672,0.0047220006,0.002536414,0.00038068337],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000023262488,0.000012245968,0.005659455,0.00006877366,0.000002592517,0.0007406519,0.9870417,0.00003768374,0.00068915903,0.00068933424,0.0016474116,0.003387737],"study_design_scores_gemma":[0.0000020692223,0.000019833671,0.007273387,0.00007721972,0.0000043594478,0.00008628477,0.9622551,0.000044720593,0.00013159266,0.00008013592,0.030006407,0.000018953237],"about_ca_topic_score_codex":0.9857216,"about_ca_topic_score_gemma":0.99479055,"teacher_disagreement_score":0.09769749,"about_ca_system_score_codex":0.09769749,"about_ca_system_score_gemma":0.11851012,"threshold_uncertainty_score":0.70884824},"labels":[],"label_agreement":null},{"id":"W7140392809","doi":"10.1333/s00897050976a","title":"The Art of Good Grading—A Training Seminar for Graduate Students","year":2005,"lang":"en","type":"article","venue":"The Chemical Educator","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Cheating; Grading (engineering); Graduate students; Task (project management); Orientation (vector space)","score_opus":0.08500414879889394,"score_gpt":0.41575166508023165,"score_spread":0.3307475162813377,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7140392809","genre_codex":"commentary","genre_gemma":"other","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"other","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.034736883,0.011303049,0.3116641,0.3224392,0.053499173,0.0014848595,0.00037028536,0.011500884,0.2530016],"genre_scores_gemma":[0.2648855,0.0076221917,0.41385782,0.059517764,0.02853657,0.0018407224,0.00058788486,0.003029328,0.22012235],"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","domain_scores_codex":[0.9931271,0.0033173347,0.0003404106,0.00051934447,0.00227325,0.00042259772],"domain_scores_gemma":[0.9735246,0.008447659,0.00186317,0.0041835536,0.0047652847,0.007215884],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.018947804,0.00095734774,0.00071030814,0.0014323592,0.0041928682,0.0061007733,0.002707309,0.0030335244,0.017952006],"category_scores_gemma":[0.03880625,0.00074672716,0.0006868541,0.0007226852,0.0042707766,0.0070052217,0.0064069405,0.008564422,0.012185548],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0000967627,0.0005413235,0.00072310737,0.000161254,0.000014509124,0.0002749146,0.0044494625,0.00042059706,0.0033804353,0.019028543,0.62601143,0.34489775],"study_design_scores_gemma":[0.000059601767,0.0004991861,0.0024280953,0.00046287235,0.000012151312,0.0010934487,0.005427238,0.0009436496,0.0016975297,0.07215277,0.91512585,0.00009771347],"about_ca_topic_score_codex":0.0003890425,"about_ca_topic_score_gemma":0.0011597561,"teacher_disagreement_score":0.018947804,"about_ca_system_score_codex":0.0014257744,"about_ca_system_score_gemma":0.0034136323,"threshold_uncertainty_score":0.10020679},"labels":[],"label_agreement":null},{"id":"W7155756298","doi":"","title":"Assessing Core Competencies in British Columbia","year":2021,"lang":"en","type":"dissertation","venue":"KU ScholarWorks (The University of Kansas)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"CLARITY; Curriculum; Social skills; Skills management; Life skills; Core competency; Plan (archaeology); Academic skills","score_opus":0.027029602601231065,"score_gpt":0.2932933160606973,"score_spread":0.26626371345946626,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7155756298","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.96655697,0.00026065097,0.00036408796,0.0003207912,0.000018601815,0.0001359181,0.0007101568,0.000066241504,0.031566564],"genre_scores_gemma":[0.9757134,0.00037555676,0.0025005082,0.00020613088,0.0000015959758,0.00013513185,0.0009850747,0.000018037194,0.020064527],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9993573,0.00008499311,0.000041648593,0.00007793162,0.00029296306,0.00014514387],"domain_scores_gemma":[0.9971028,0.00025862776,0.00012007365,0.00007402083,0.0019383933,0.0005060591],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00077066134,0.00026749072,0.00019267047,0.002266219,0.0019432174,0.0010751821,0.00060990197,0.0002569099,0.003960979],"category_scores_gemma":[0.0033001692,0.00017142126,0.00009517692,0.0018663015,0.00048448044,0.0003328444,0.0009662506,0.0004902696,0.000762153],"study_design_candidate":"observational","study_design_consensus":"observational","about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0001421294,0.00048561432,0.6331489,0.00029417925,0.000020878335,0.0008292205,0.022835182,0.0008991931,0.005654388,0.0017324255,0.019402666,0.31455517],"study_design_scores_gemma":[0.000011714314,0.00011737814,0.95362,0.00019095391,0.000009849381,0.00019056424,0.017900923,0.0008071942,0.0026750185,0.00031674423,0.024127038,0.000032587366],"about_ca_topic_score_codex":0.91499627,"about_ca_topic_score_gemma":0.9769379,"teacher_disagreement_score":0.08500373,"about_ca_system_score_codex":0.012235154,"about_ca_system_score_gemma":0.020092,"threshold_uncertainty_score":0.17100865},"labels":[],"label_agreement":null},{"id":"W7160501424","doi":"10.66281/70130/8718","title":"Global perspectives on School-Based Assessment (SBA): A systematic review of international practices and challenges","year":2025,"lang":"","type":"article","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Formative assessment; Consistency (knowledge bases); Foundation (evidence); Nexus (standard); Policy analysis; Systematic review; Key (lock)","score_opus":0.048523417659662615,"score_gpt":0.4380889449965813,"score_spread":0.3895655273369187,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7160501424","genre_codex":"review","genre_gemma":"review","domain_codex":null,"domain_gemma":"evaluation","model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"review","genre_consensus":"review","domain_candidate":"evaluation","domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.0009478609,0.99452907,0.00084734964,0.0022722308,0.00025627096,0.00015135221,0.00019872992,0.0000110182145,0.000786079],"genre_scores_gemma":[0.01851705,0.97529083,0.0033428706,0.0018518463,0.00012077955,0.000525797,0.00025109923,0.000017995697,0.00008174053],"study_design_codex":"systematic_review","study_design_gemma":"systematic_review","domain_scores_codex":[0.9310697,0.035421122,0.021170752,0.0031100924,0.008277211,0.00095109537],"domain_scores_gemma":[0.7450858,0.21057373,0.017996524,0.00531454,0.019529112,0.0015003693],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.08498364,0.0013551693,0.005030339,0.017713077,0.0012250632,0.006191578,0.0022274442,0.0022894572,0.0022429875],"category_scores_gemma":[0.2059374,0.0012668322,0.004144844,0.0262703,0.0037051083,0.006349027,0.004469515,0.003113272,0.00035461935],"study_design_candidate":"systematic_review","study_design_consensus":"systematic_review","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000120966324,0.00004062477,0.0022182015,0.64000803,0.002864249,0.0001279859,0.004085503,0.00038284596,0.00029175897,0.006031638,0.005777599,0.33805057],"study_design_scores_gemma":[0.00004483678,0.00010915488,0.0030383484,0.9104209,0.005085535,0.0002269245,0.0024344716,0.00008697832,0.0001866196,0.0017909443,0.07653565,0.000039722046],"about_ca_topic_score_codex":0.014287292,"about_ca_topic_score_gemma":0.034952912,"teacher_disagreement_score":0.91501635,"about_ca_system_score_codex":0.005787653,"about_ca_system_score_gemma":0.044524603,"threshold_uncertainty_score":0.4494418},"labels":[],"label_agreement":null},{"id":"W7161986211","doi":"10.82308/37465","title":"Does self-assessment with specific criteria enhance graduate level ESL students' writing?","year":2007,"lang":"en","type":"dissertation","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Control (management); English as a second language; Graduate students; Qualitative research; Second language; Language proficiency; Note-taking","score_opus":0.04555487175482572,"score_gpt":0.43876116485543487,"score_spread":0.39320629310060917,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7161986211","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99696726,0.00021760254,0.00046162884,0.00023903819,0.000026406116,0.000064246495,0.000010338693,0.00004651429,0.0019670425],"genre_scores_gemma":[0.9947712,0.00034657167,0.003631668,0.0001036285,0.000034001056,0.00005862531,0.000032020394,0.000007927765,0.0010142664],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99797386,0.0010265495,0.00018998215,0.00013811047,0.00059415045,0.00007741778],"domain_scores_gemma":[0.97292715,0.016258769,0.0045095114,0.0016360438,0.0024505504,0.0022179603],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0040799202,0.00019530693,0.0004266127,0.0006185713,0.00020785931,0.00072538236,0.00033754826,0.00035752254,0.0016707098],"category_scores_gemma":[0.037210904,0.00010437833,0.00024385423,0.00032368698,0.00030704588,0.00063200406,0.0005614004,0.00035775304,0.00057714095],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00097187364,0.008824487,0.24719295,0.00054125115,0.00009352039,0.00019528033,0.005517609,0.00026077547,0.008669695,0.00011958007,0.0014966223,0.7261163],"study_design_scores_gemma":[0.00031328524,0.016041499,0.96178895,0.00029304312,0.000114323346,0.0006650515,0.00480256,0.001390905,0.008780405,0.0005827369,0.005175827,0.000051492723],"about_ca_topic_score_codex":0.00025895078,"about_ca_topic_score_gemma":0.0009380557,"teacher_disagreement_score":0.0040799202,"about_ca_system_score_codex":0.00016667503,"about_ca_system_score_gemma":0.0005248937,"threshold_uncertainty_score":0.021576941},"labels":[],"label_agreement":null},{"id":"W7161994237","doi":"10.82308/45504","title":"In the service of the stakeholder: a critical, mixed-method program of research in high-stakes language assessment","year":2011,"lang":"en","type":"dissertation","venue":"","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Test (biology); Certification; Stakeholder; Language assessment; Language proficiency; Perception; Task (project management); Service (business); Field (mathematics)","score_opus":0.15716927244799214,"score_gpt":0.5265548475892885,"score_spread":0.36938557514129633,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W7161994237","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.62807786,0.0022029213,0.11935065,0.0034474325,0.00075519807,0.23662506,0.00048100005,0.00035943394,0.008700529],"genre_scores_gemma":[0.4364684,0.00068724377,0.31826755,0.004304061,0.0002558714,0.23638472,0.00023207851,0.00018103172,0.0032190862],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.70566124,0.25595105,0.00819006,0.010740578,0.015017879,0.004439199],"domain_scores_gemma":[0.6178423,0.290166,0.011949773,0.033269506,0.04359033,0.0031822298],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.28886968,0.0017204864,0.0021857282,0.005000775,0.011708946,0.0075238897,0.006277825,0.004879502,0.0030941968],"category_scores_gemma":[0.24347037,0.0020158342,0.0022337905,0.0047628446,0.0073684934,0.005815657,0.00728259,0.0041656625,0.00077838113],"study_design_candidate":"qualitative","study_design_consensus":"qualitative","about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.0039245733,0.021554824,0.022792183,0.0087627545,0.001146924,0.0016018794,0.63496447,0.0025422068,0.016936308,0.0225236,0.0048155272,0.25843492],"study_design_scores_gemma":[0.012878198,0.060431857,0.05506828,0.012292091,0.002316079,0.0014257646,0.6123653,0.012885004,0.044955067,0.044264674,0.14013174,0.0009859336],"about_ca_topic_score_codex":0.008573334,"about_ca_topic_score_gemma":0.025452606,"teacher_disagreement_score":0.28886968,"about_ca_system_score_codex":0.01341889,"about_ca_system_score_gemma":0.026757693,"threshold_uncertainty_score":0.87695026},"labels":[],"label_agreement":null},{"id":"W761528972","doi":"10.71781/5733","title":"Noticeability of corrective feedback, L2 development and learner beliefs","year":2012,"lang":"en","type":"dissertation","venue":"Open MIND","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Corrective feedback; Psychology; Cognitive psychology; Mathematics education","score_opus":0.058032085151739826,"score_gpt":0.3894859929590068,"score_spread":0.331453907807267,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W761528972","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9959287,0.00013476993,0.0006025408,0.00008416156,0.00001519336,0.00018108178,0.000047595382,0.000032513057,0.0029734066],"genre_scores_gemma":[0.99167573,0.00015443473,0.0018052143,0.000090357775,0.000014854244,0.00071683445,0.00007559639,0.000027906692,0.005439007],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9933549,0.0027624427,0.00043603152,0.0008673267,0.0021065378,0.00047279388],"domain_scores_gemma":[0.92246765,0.059004173,0.008909487,0.0033874572,0.0035095224,0.0027217036],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007692848,0.00051542436,0.00075657445,0.0006211453,0.00069177087,0.002256713,0.0009549864,0.0010680188,0.007874523],"category_scores_gemma":[0.056034934,0.0005335766,0.00047268,0.00036261548,0.001282684,0.0013453222,0.001587315,0.0016646595,0.00066189485],"study_design_candidate":"observational","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.02469469,0.03348774,0.29734978,0.0041600727,0.0005839573,0.0006719552,0.18261497,0.0029910207,0.07012071,0.003018599,0.0022982827,0.3780082],"study_design_scores_gemma":[0.0023626909,0.04250085,0.8737961,0.00083515194,0.00057697436,0.00028708318,0.03307897,0.0036498678,0.028746719,0.0026234374,0.011215799,0.0003263655],"about_ca_topic_score_codex":0.0051971283,"about_ca_topic_score_gemma":0.0042558378,"teacher_disagreement_score":0.007874523,"about_ca_system_score_codex":0.0012639968,"about_ca_system_score_gemma":0.0018643964,"threshold_uncertainty_score":0.040684104},"labels":[],"label_agreement":null},{"id":"W783986","doi":"10.1023/a:1013022527681","title":"Accountability Testing Without Accountability?","year":2001,"lang":"en","type":"article","venue":"Interchange","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Institute for Christian Studies; University of Toronto","funders":"","keywords":"Philosophy of education; Political science; Higher education; Law","score_opus":0.1549698558271588,"score_gpt":0.41791797016587584,"score_spread":0.262948114338717,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W783986","genre_codex":"commentary","genre_gemma":"commentary","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"commentary","genre_consensus":"commentary","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.03234332,0.0035615612,0.11492183,0.44389623,0.006639825,0.0001495436,0.0003615421,0.0012232282,0.39690298],"genre_scores_gemma":[0.88171226,0.0012872998,0.03297119,0.038667545,0.0034767354,0.00046523908,0.00021484829,0.00055044185,0.040654466],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","domain_scores_codex":[0.8461111,0.09861588,0.007444676,0.0067005767,0.03449662,0.0066310945],"domain_scores_gemma":[0.6678064,0.20199496,0.022262756,0.05011442,0.048097506,0.00972399],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.10234571,0.0011886152,0.0020976567,0.0054993085,0.00784235,0.018470207,0.0044418275,0.010574954,0.017869396],"category_scores_gemma":[0.3818811,0.0010494221,0.0010645504,0.0045953663,0.02831837,0.043350473,0.012251363,0.0129645625,0.0044974554],"study_design_candidate":"not_applicable","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.00014982454,0.000121487916,0.006403451,0.00009187818,0.00003038548,0.000138633,0.0036758196,0.00023144079,0.00013438408,0.8316755,0.038508046,0.11883914],"study_design_scores_gemma":[0.00007200664,0.00010811085,0.0034074208,0.00038182852,0.00005228034,0.00039343117,0.0044114026,0.0025509552,0.0013882926,0.9311149,0.056044564,0.000074673175],"about_ca_topic_score_codex":0.010629238,"about_ca_topic_score_gemma":0.006635796,"teacher_disagreement_score":0.10234571,"about_ca_system_score_codex":0.008729068,"about_ca_system_score_gemma":0.01528117,"threshold_uncertainty_score":0.5412623},"labels":[],"label_agreement":null},{"id":"W870701221","doi":"","title":"Improving effectiveness of learning through class activity assessment : a case study","year":2010,"lang":"en","type":"book-chapter","venue":"Sunway Institutional Repository (Sunway University)","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"route_ca_aff":false,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"","funders":"","keywords":"Matriculation; Class (philosophy); Mathematics education; Curriculum; TRIPS architecture; Creativity; Process (computing); Pedagogy; Psychology; Computer science","score_opus":0.022662941449848477,"score_gpt":0.29380806370281526,"score_spread":0.2711451222529668,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W870701221","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99031013,0.00017857396,0.003706116,0.0005469141,0.000020770816,0.0006178551,0.000049302158,0.00006601355,0.0045043565],"genre_scores_gemma":[0.9875832,0.00042251495,0.008692596,0.00014366055,0.000029340828,0.0004014866,0.000058674457,0.00003453474,0.0026339039],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.9813255,0.012890695,0.0009768645,0.00090462784,0.0022013853,0.001700986],"domain_scores_gemma":[0.9624141,0.025599018,0.002296645,0.0024668605,0.0042159585,0.0030074706],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.013712566,0.00092559867,0.0008634503,0.0026617746,0.0037040398,0.0031692958,0.0025798539,0.0032004535,0.0016015971],"category_scores_gemma":[0.030826787,0.00047663538,0.00090492,0.0019200789,0.0020552275,0.002450474,0.0030546582,0.0023656117,0.00063860504],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.001557184,0.055714983,0.1046947,0.001600047,0.00018621676,0.018593695,0.38780504,0.004543463,0.011523419,0.003339687,0.004258442,0.40618306],"study_design_scores_gemma":[0.0014975347,0.061812233,0.2441242,0.001809024,0.00069540425,0.022990696,0.48439226,0.028688103,0.06931463,0.004384906,0.07947096,0.00082013936],"about_ca_topic_score_codex":0.0035350919,"about_ca_topic_score_gemma":0.0061022337,"teacher_disagreement_score":0.013712566,"about_ca_system_score_codex":0.0030040601,"about_ca_system_score_gemma":0.001634047,"threshold_uncertainty_score":0.0725199},"labels":[],"label_agreement":null},{"id":"W98146743","doi":"10.1007/978-94-007-5902-2_16","title":"Authentic Assessment, Teacher Judgment and Moderation in a Context of High Accountability","year":2014,"lang":"en","type":"book-chapter","venue":"˜The œenabling power of assessment","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":11,"is_retracted":false,"has_abstract":false,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"University of Calgary","funders":"","keywords":"Accountability; Moderation; Context (archaeology); Psychology; Political science; Social psychology; History; Law; Archaeology","score_opus":0.030514511894305606,"score_gpt":0.3371362410140897,"score_spread":0.3066217291197841,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W98146743","genre_codex":"other","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":null,"domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.12354502,0.007053472,0.13539247,0.025618276,0.00064935954,0.000118486765,0.000035650934,0.00023894936,0.7073483],"genre_scores_gemma":[0.96821827,0.0005697161,0.011522584,0.00035023037,0.00011568818,0.00007053785,0.0000062919416,0.000033697535,0.019113095],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.9901704,0.007484361,0.00017839746,0.00048747903,0.001307246,0.00037208784],"domain_scores_gemma":[0.979192,0.017388906,0.0008824905,0.0010531155,0.0008370102,0.00064637384],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0072234534,0.0002965019,0.00031883226,0.0005222517,0.0024748563,0.005714492,0.00080714514,0.001278123,0.0026911101],"category_scores_gemma":[0.019354569,0.00026612674,0.00016777925,0.00065162184,0.015337785,0.005361432,0.004488892,0.003631386,0.00027236642],"study_design_candidate":"qualitative","study_design_consensus":null,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_system_candidate":false,"about_ca_system_consensus":false,"study_design_scores_codex":[0.000024888759,0.00003582064,0.001882605,0.000064019274,0.0000054805373,0.00022038246,0.04114895,0.0006338598,0.00049733365,0.9019363,0.0030834242,0.050466973],"study_design_scores_gemma":[0.000008654786,0.0000371893,0.0028024907,0.00011132691,0.0000050626018,0.00021517472,0.009483095,0.0013493791,0.00082036323,0.93799525,0.0471523,0.000019594843],"about_ca_topic_score_codex":0.0015625843,"about_ca_topic_score_gemma":0.0035964688,"teacher_disagreement_score":0.0072234534,"about_ca_system_score_codex":0.0019683,"about_ca_system_score_gemma":0.003277575,"threshold_uncertainty_score":0.03820175},"labels":[],"label_agreement":null}]}