{"meta":{"query_hash":"09153c5ce259","filters":{"venue":"Assessment & Evaluation in Higher Education"},"cohort_total":44,"direct_labels_cover":1,"predictions_cover":44,"exported":44,"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/09153c5ce259","api":"https://metacan.xera.ac/api/v1/cohort?venue=Assessment+%26+Evaluation+in+Higher+Education"},"results":[{"id":"W1841123149","doi":"10.1080/02602938.2015.1044421","title":"Whose feedback? A multilevel analysis of student completion of end-of-term teaching evaluations","year":2015,"lang":"en","type":"article","venue":"Assessment & Evaluation in Higher Education","topic":"Evaluation of Teaching Practices","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 British Columbia","funders":"","keywords":"Respondent; Set (abstract data type); Psychology; Quality (philosophy); Quality assurance; Term (time); Higher education; Medical education; Multilevel model; Course evaluation; Mathematics education; Computer science; Medicine; Political science","score_opus":0.4085236037266901,"score_gpt":0.6050658361994158,"score_spread":0.19654223247272568,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1841123149","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":[0.99621576,0.00011516596,0.0015971243,0.00021551957,0.00001310112,0.000106851214,0.0010398044,0.0000271951,0.000669511],"genre_scores_gemma":[0.9980082,0.000028072951,0.00081653404,0.000020120699,0.0000064901465,0.000124607,0.0005643633,0.000010108864,0.00042155414],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.97528195,0.015476569,0.0018826401,0.0018857738,0.0037501054,0.0017230005],"domain_scores_gemma":[0.90415686,0.055501994,0.01886938,0.007856843,0.010113886,0.0035010234],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.020877354,0.00033931652,0.0010283402,0.00233775,0.000936223,0.0019974236,0.001572585,0.0007430412,0.0026639781],"category_scores_gemma":[0.085343644,0.000278128,0.002051787,0.0025351332,0.00065948075,0.0011244789,0.0020161096,0.0017743296,0.00044180008],"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":[0.00028939766,0.00013925832,0.98460454,0.00005595503,0.0009758554,0.000023459872,0.0025770336,0.00031713204,0.00014384859,0.00019013401,0.00045318177,0.010230174],"study_design_scores_gemma":[0.000013972709,0.00041100025,0.995083,0.00003963386,0.00017346526,0.000018086615,0.0014211927,0.0020502298,0.00018499476,0.00012737367,0.00045991366,0.000017111332],"about_ca_topic_score_codex":0.03324432,"about_ca_topic_score_gemma":0.03204249,"teacher_disagreement_score":0.97912264,"about_ca_system_score_codex":0.0018737537,"about_ca_system_score_gemma":0.0019083685,"threshold_uncertainty_score":0.11041129},"labels":[],"label_agreement":null},{"id":"W1904991648","doi":"10.1080/02602938.2015.1089977","title":"New assessment process in an introductory undergraduate physics laboratory: an exploration on collaborative learning","year":2015,"lang":"en","type":"article","venue":"Assessment & Evaluation in Higher Education","topic":"Innovative Teaching Methods","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":"York University","funders":"","keywords":"Grading (engineering); Session (web analytics); Peer assessment; Process (computing); Peer evaluation; Mathematics education; Incentive; Class (philosophy); Task (project management); Higher education; Medical education; Psychology; Computer science; Engineering","score_opus":0.24140766209384704,"score_gpt":0.5511415627937231,"score_spread":0.30973390069987605,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1904991648","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.89305687,0.00014136347,0.09896616,0.00060402177,0.00009888857,0.0020412921,0.000025290678,0.00039203462,0.0046741557],"genre_scores_gemma":[0.78365934,0.00014417684,0.2128383,0.00018251978,0.000046126974,0.0009497676,0.000046410085,0.00004388256,0.0020893186],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98166764,0.010496169,0.001002628,0.0015845153,0.0045712553,0.0006777408],"domain_scores_gemma":[0.9418216,0.039745286,0.0031705261,0.0059842807,0.005993882,0.0032844532],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.022486404,0.00062182057,0.00070034125,0.0012018547,0.001506688,0.0035734382,0.0024817276,0.0013981728,0.0010334817],"category_scores_gemma":[0.04666671,0.00045629917,0.0008338256,0.00061143265,0.0013430958,0.0030280997,0.0029699283,0.0017562053,0.0003155052],"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":[0.0016549833,0.025664791,0.039566454,0.00096595753,0.00014547839,0.0012559831,0.06146255,0.014882097,0.050533827,0.008355608,0.002366227,0.7931461],"study_design_scores_gemma":[0.0038936203,0.09862238,0.18536638,0.0014898076,0.0009048455,0.0075355517,0.040948957,0.29705295,0.19706479,0.045883436,0.119580485,0.0016567791],"about_ca_topic_score_codex":0.00079436204,"about_ca_topic_score_gemma":0.0012441706,"teacher_disagreement_score":0.022486404,"about_ca_system_score_codex":0.001579421,"about_ca_system_score_gemma":0.0029729765,"threshold_uncertainty_score":0.11892086},"labels":[],"label_agreement":null},{"id":"W1963676041","doi":"10.1080/02602930600760884","title":"Reflections on using journals in higher education: a focus group discussion with faculty","year":2006,"lang":"en","type":"article","venue":"Assessment & Evaluation in Higher Education","topic":"Reflective Practices in Education","field":"Social Sciences","cited_by":61,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":true,"route_ca_venue":false,"route_about_ca":false,"ca_institutions":"Lakehead University","funders":"Lakehead University","keywords":"Journaling file system; Reflective writing; Focus group; Higher education; Psychology; Journal writing; Medical education; Writing process; Pedagogy; Experiential learning; Professional writing; Narrative; Mathematics education; Teaching method; Sociology; Medicine; Computer science; Political science","score_opus":0.26059440791254546,"score_gpt":0.5788218747837022,"score_spread":0.3182274668711567,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1963676041","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9184005,0.0013421478,0.012499956,0.05502221,0.0021545538,0.0011365238,0.000095607145,0.0002200033,0.009128376],"genre_scores_gemma":[0.966624,0.0015394553,0.007183969,0.0146353785,0.0010911006,0.0009663565,0.00007876634,0.00014158875,0.007739332],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9577824,0.033317372,0.0012931084,0.0016255308,0.0026192863,0.0033622058],"domain_scores_gemma":[0.8692414,0.10631721,0.004001014,0.0030276647,0.0098580355,0.007554649],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.056263737,0.0013235152,0.0010101353,0.0020800964,0.02398037,0.0069490224,0.0038692805,0.006599896,0.0038093224],"category_scores_gemma":[0.09814709,0.0012215031,0.0010588978,0.0020033666,0.009669481,0.0074411775,0.008930984,0.00873582,0.0008339221],"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":[0.00016129404,0.00052040594,0.003425835,0.00022663196,0.0000159881,0.0013733037,0.9561818,0.00012810533,0.0044312547,0.0011669236,0.0035228531,0.028845605],"study_design_scores_gemma":[0.00007032228,0.00092127017,0.0044285203,0.00031503398,0.0000454971,0.0008331119,0.9472795,0.00042140085,0.006354407,0.0012014151,0.03803539,0.000094101604],"about_ca_topic_score_codex":0.004098308,"about_ca_topic_score_gemma":0.0044728853,"teacher_disagreement_score":0.056263737,"about_ca_system_score_codex":0.0081612645,"about_ca_system_score_gemma":0.008041308,"threshold_uncertainty_score":0.2975546},"labels":[],"label_agreement":null},{"id":"W1964857994","doi":"10.1080/02602938.2013.845647","title":"Student personality differences are related to their responses on instructor evaluation forms","year":2013,"lang":"en","type":"article","venue":"Assessment & Evaluation in Higher Education","topic":"Communication in Education and Healthcare","field":"Psychology","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":"Cape Breton University","funders":"","keywords":"Agreeableness; Conscientiousness; Neuroticism; Psychology; Extraversion and introversion; Big Five personality traits; Personality; Hierarchical structure of the Big Five; Openness to experience; Regression analysis; Social psychology; Statistics; Mathematics","score_opus":0.22323133286836125,"score_gpt":0.5409676873858742,"score_spread":0.3177363545175129,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1964857994","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":[0.99976367,0.000009620561,0.000030052743,0.0000067473516,0.0000015772182,0.000002011334,0.000012359573,0.0000012261465,0.00017268928],"genre_scores_gemma":[0.9997334,0.000011734073,0.000045103123,0.000006309476,0.00000208922,0.00000392196,0.0000416344,0.0000010134073,0.00015465163],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99901843,0.00030067007,0.0001065055,0.00008800722,0.00032470372,0.0001617335],"domain_scores_gemma":[0.99114156,0.0034332073,0.0027551036,0.00046086177,0.0008216995,0.0013874428],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.001230748,0.00015528413,0.00023380031,0.0006565436,0.00027602364,0.0006468352,0.00013344584,0.00027643002,0.002280262],"category_scores_gemma":[0.011267997,0.00016234584,0.00022596915,0.00041213812,0.0002907809,0.0002620154,0.00056221645,0.0005072677,0.0004181116],"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":[0.000097619326,0.000081114165,0.9943039,0.0000041829544,0.000017775208,0.000036740537,0.0005718517,0.000044187014,0.00042618063,0.000018627812,0.000054531793,0.0043431907],"study_design_scores_gemma":[0.0000037531179,0.00016834807,0.99877256,0.0000026658042,0.000003583098,0.00009623731,0.0005020534,0.00017093885,0.00014687444,0.000036212277,0.00009336388,0.0000033443469],"about_ca_topic_score_codex":0.00056098175,"about_ca_topic_score_gemma":0.00087641255,"teacher_disagreement_score":0.9987692,"about_ca_system_score_codex":0.00017329973,"about_ca_system_score_gemma":0.00015309513,"threshold_uncertainty_score":0.007628262},"labels":[],"label_agreement":null},{"id":"W1977788398","doi":"10.1080/02602930903337612","title":"Student satisfaction with Canadian music programmes: the application of the American Customer Satisfaction Model in higher education","year":2010,"lang":"en","type":"article","venue":"Assessment & Evaluation in Higher Education","topic":"Customer Service Quality and Loyalty","field":"Business, Management and Accounting","cited_by":66,"is_retracted":false,"has_abstract":true,"route_ca_aff":true,"route_ca_fund":false,"route_ca_venue":false,"route_about_ca":true,"ca_institutions":"Lakehead University","funders":"","keywords":"Loyalty; Customer satisfaction; Psychology; Higher education; Word of mouth; Marketing; Quality (philosophy); Minor (academic); Social psychology; Advertising; Business; Political science","score_opus":0.04703466291038546,"score_gpt":0.3601511729886637,"score_spread":0.3131165100782783,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1977788398","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9733698,0.00023122541,0.002432952,0.00088742434,0.000018505894,0.000085728105,0.00027301454,0.00002346362,0.022677993],"genre_scores_gemma":[0.99884546,0.00012574422,0.00048096888,0.00003793431,0.0000036524427,0.000017794093,0.00009105255,0.0000018166286,0.000395601],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99837047,0.00046769812,0.000047092704,0.00007368847,0.0007950359,0.0002459768],"domain_scores_gemma":[0.9968882,0.0009918109,0.00040103236,0.00010404572,0.0012606804,0.0003541688],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0020850375,0.00026610948,0.00024446158,0.0015498667,0.0014142212,0.0021715735,0.0006614894,0.00045966986,0.0023484642],"category_scores_gemma":[0.005898127,0.00013145605,0.0004605552,0.003720724,0.0011896499,0.0006516333,0.0009068599,0.0006664959,0.00017276057],"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":[0.00017709639,0.00022393488,0.89670163,0.00009677151,0.000071276285,0.00012727473,0.004278403,0.004925924,0.00035990932,0.014303691,0.0034010177,0.07533322],"study_design_scores_gemma":[0.0000191513,0.00025073864,0.9483789,0.000080806654,0.00007110213,0.0001235416,0.009968613,0.03228401,0.0002913597,0.0032325499,0.0052412474,0.000058075493],"about_ca_topic_score_codex":0.7251483,"about_ca_topic_score_gemma":0.7174302,"teacher_disagreement_score":0.27485168,"about_ca_system_score_codex":0.009051645,"about_ca_system_score_gemma":0.010935584,"threshold_uncertainty_score":0.5529406},"labels":[],"label_agreement":null},{"id":"W1981924652","doi":"10.1080/02602938.2011.630977","title":"Assessing the psychometric properties of Kember and Leung’s Reflection Questionnaire","year":2011,"lang":"en","type":"article","venue":"Assessment & Evaluation in Higher Education","topic":"Reflective Practices in Education","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":true,"ca_institutions":"Western University","funders":"","keywords":"Psychology; Reflective thinking; Confirmatory factor analysis; Test (biology); Construct validity; Critical thinking; Reflection (computer programming); Construct (python library); Nurse education; Reliability (semiconductor); Reflective practice; Medical education; Psychometrics; Pedagogy; Medicine; Structural equation modeling; Clinical psychology","score_opus":0.3077723684892498,"score_gpt":0.5370573176723951,"score_spread":0.22928494918314524,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1981924652","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":[0.97967315,0.0002860959,0.009840693,0.00057895406,0.000055547443,0.0024475746,0.00051890366,0.0000889219,0.006510119],"genre_scores_gemma":[0.97194076,0.00028462202,0.02243051,0.00015146131,0.000016824317,0.0033924207,0.000665171,0.000022558792,0.001095563],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99103093,0.003401393,0.0016298335,0.0003634244,0.0032374088,0.0003369512],"domain_scores_gemma":[0.9378501,0.03424353,0.006602659,0.003475596,0.016202245,0.0016257549],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01963224,0.00022910313,0.0006400842,0.0018055986,0.00066218514,0.00078685867,0.0009113881,0.000546781,0.0020020315],"category_scores_gemma":[0.068943314,0.00031291283,0.0010657669,0.0013483512,0.00078291935,0.0012437861,0.0013553131,0.000746008,0.000401808],"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":[0.0006751726,0.0012459964,0.6959161,0.00061379623,0.00038193594,0.00023796887,0.010864074,0.002312733,0.003968236,0.0015306531,0.0049528955,0.27730054],"study_design_scores_gemma":[0.0001798683,0.0015958025,0.9758478,0.00024761035,0.00010149958,0.00031610197,0.0044057146,0.005755456,0.0020712283,0.0011787488,0.008208105,0.0000920096],"about_ca_topic_score_codex":0.0029362484,"about_ca_topic_score_gemma":0.0036128706,"teacher_disagreement_score":0.9803678,"about_ca_system_score_codex":0.0011888043,"about_ca_system_score_gemma":0.002806801,"threshold_uncertainty_score":0.1038264},"labels":[],"label_agreement":null},{"id":"W1996403924","doi":"10.1080/02602930701772788","title":"An investigation into electronic‐source plagiarism in a first‐year essay assignment","year":2008,"lang":"en","type":"article","venue":"Assessment & Evaluation in Higher Education","topic":"Academic integrity and plagiarism","field":"Social Sciences","cited_by":40,"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":"Inyuvesi Yakwazulu-Natali","keywords":"Acknowledgement; Ignorance; The Internet; Quarter (Canadian coin); Perception; Psychology; Electronic publishing; Sociology; Pedagogy; Mathematics education; Public relations; Political science; Computer science; World Wide Web; History; Law","score_opus":0.049372582319956566,"score_gpt":0.3927665071328492,"score_spread":0.34339392481289266,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W1996403924","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99548894,0.00009932536,0.0008872179,0.00018387043,0.000019702831,0.00010024873,0.000023788281,0.0000126654195,0.0031841714],"genre_scores_gemma":[0.9938167,0.00019861861,0.0010600886,0.00007551326,0.000032799977,0.000063698826,0.000038725557,0.000011561828,0.0047023054],"study_design_codex":"qualitative","study_design_gemma":"observational","domain_scores_codex":[0.9941005,0.002805967,0.00067060767,0.00041976545,0.0016242672,0.00037880937],"domain_scores_gemma":[0.9481672,0.030105187,0.010450049,0.00216407,0.0074228905,0.0016905436],"candidate_categories":["research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0073806266,0.0003936298,0.0003717221,0.0039820187,0.0041306186,0.0037143202,0.0009842681,0.0010663478,0.002985952],"category_scores_gemma":[0.044726487,0.00034212266,0.0002519613,0.00197562,0.0018048966,0.0019820281,0.002630787,0.001283344,0.0006044558],"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":[0.00047704304,0.0021501214,0.23100817,0.00077443215,0.000046800094,0.0071850433,0.59395707,0.00039087297,0.01636963,0.0025323075,0.0010484874,0.14405996],"study_design_scores_gemma":[0.000050674214,0.0033734967,0.51764536,0.0006777658,0.000060332324,0.0056518475,0.40092734,0.0018514084,0.023471868,0.0021183912,0.04403744,0.0001340354],"about_ca_topic_score_codex":0.0011143772,"about_ca_topic_score_gemma":0.0024919345,"teacher_disagreement_score":0.9989337,"about_ca_system_score_codex":0.0015817047,"about_ca_system_score_gemma":0.0017698525,"threshold_uncertainty_score":0.039032936},"labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low"},{"model":"gpt","categories":["research_integrity"],"domain":null,"study_design":"design_other","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high"}],"label_agreement":"split"},{"id":"W2029621922","doi":"10.1080/02602930802563094","title":"Web‐based student feedback: comparing teaching‐award and research‐award recipients","year":2009,"lang":"en","type":"article","venue":"Assessment & Evaluation in Higher Education","topic":"Evaluation of Teaching Practices","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":"Helpfulness; CLARITY; Psychology; Credibility; Competence (human resources); Medical education; Personality; Mathematics education; Pedagogy; Social psychology; Medicine; Political science","score_opus":0.3379119990917349,"score_gpt":0.600605115458447,"score_spread":0.26269311636671205,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2029621922","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":[0.9974107,0.000067842826,0.00048495375,0.00011431507,0.000029853365,0.00006675371,0.00026099294,0.00004067161,0.0015237919],"genre_scores_gemma":[0.9968502,0.000079274374,0.00074952864,0.000082719984,0.000046277702,0.0001523669,0.00030403904,0.000022534901,0.0017131596],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98986393,0.0051938877,0.0010471134,0.00053257373,0.0029540828,0.00040843664],"domain_scores_gemma":[0.9083785,0.050030615,0.0153959785,0.0032777898,0.016183011,0.00673423],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.014029254,0.00028339363,0.0007190788,0.0023296745,0.0005350186,0.0012935343,0.00039673742,0.000536554,0.0039837095],"category_scores_gemma":[0.060871452,0.00014655868,0.00033482016,0.0012513513,0.00032046565,0.00096042466,0.0014511193,0.0005837915,0.0017534607],"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":[0.0020522922,0.0013802078,0.82393277,0.0003029083,0.00015767234,0.00015356841,0.00944861,0.00039786147,0.0036547948,0.00011181304,0.0027527786,0.1556547],"study_design_scores_gemma":[0.0000931054,0.0020832578,0.9786926,0.00006940948,0.000051509567,0.00023914284,0.008646264,0.0023301118,0.00365019,0.0001677178,0.0039185663,0.000058134992],"about_ca_topic_score_codex":0.0005416785,"about_ca_topic_score_gemma":0.0008723306,"teacher_disagreement_score":0.98597074,"about_ca_system_score_codex":0.0004035183,"about_ca_system_score_gemma":0.00039626454,"threshold_uncertainty_score":0.07419467},"labels":[],"label_agreement":null},{"id":"W2043118965","doi":"10.1080/02602930802082228","title":"What do students consider useful about student ratings?","year":2008,"lang":"en","type":"article","venue":"Assessment & Evaluation in Higher Education","topic":"Evaluation of Teaching Practices","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":"University of Calgary","funders":"","keywords":"Psychology; Ranking (information retrieval); Reliability (semiconductor); Applied psychology; Variance (accounting); Higher education; Mathematics education; Computer science","score_opus":0.27636819001779894,"score_gpt":0.581646382299723,"score_spread":0.30527819228192404,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2043118965","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":[0.9845085,0.0009594153,0.0052299737,0.0021015566,0.00010605362,0.00007971986,0.00018641661,0.000089960115,0.0067383377],"genre_scores_gemma":[0.9977029,0.00030823218,0.0013944311,0.00011653852,0.000046070232,0.000027740156,0.0000771337,0.000010730805,0.00031619295],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.98039985,0.011523619,0.0013101506,0.00050111435,0.0057303854,0.00053491973],"domain_scores_gemma":[0.84727836,0.09588954,0.028059915,0.004567943,0.019917304,0.0042869863],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.02094046,0.00028372643,0.0006141414,0.0012488449,0.00037790963,0.0029977218,0.00034247592,0.00061272335,0.0015866616],"category_scores_gemma":[0.16341832,0.00014251324,0.00054467376,0.0011450889,0.00080480304,0.0012680292,0.0007527528,0.0010317095,0.0004645758],"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":[0.00046376282,0.00027928775,0.78285754,0.000360326,0.00022025824,0.000096444935,0.0106120845,0.0005039925,0.0020249153,0.00084310106,0.0031978893,0.19854042],"study_design_scores_gemma":[0.000074497424,0.0011124818,0.9558374,0.0006370799,0.00024186153,0.00056674273,0.019432746,0.005509044,0.0039825104,0.0025157586,0.009959844,0.00013001714],"about_ca_topic_score_codex":0.001041697,"about_ca_topic_score_gemma":0.0020680241,"teacher_disagreement_score":0.9790595,"about_ca_system_score_codex":0.0007374444,"about_ca_system_score_gemma":0.00074029394,"threshold_uncertainty_score":0.11074507},"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":"W2060845473","doi":"10.1080/02602930701772754","title":"Telling the second half of the story: linking academic development to student experience of learning","year":2008,"lang":"en","type":"article","venue":"Assessment & Evaluation in Higher Education","topic":"Evaluation of Teaching Practices","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":"McGill University","funders":"","keywords":"Psychology; Value (mathematics); Higher education; Pedagogy; Mathematics education; Computer science; Political science","score_opus":0.258701240075958,"score_gpt":0.5317956474131663,"score_spread":0.2730944073372083,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2060845473","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98523176,0.00025227314,0.005601594,0.0011871689,0.00004092652,0.00013415412,0.00007029331,0.000044029304,0.007437947],"genre_scores_gemma":[0.9945728,0.00023142286,0.0035562643,0.00021123445,0.000019395065,0.00015841548,0.00006693911,0.00002331491,0.0011602466],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.978564,0.015969757,0.00067400467,0.0007448629,0.0033758585,0.0006714244],"domain_scores_gemma":[0.82982814,0.13740368,0.017229239,0.0048640086,0.0059319898,0.004742852],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014434177,0.00068897894,0.0006313713,0.0015167443,0.0016061295,0.0068629654,0.0010871979,0.0014715063,0.0027300462],"category_scores_gemma":[0.08456207,0.0005729148,0.000553516,0.0010151153,0.003666768,0.0047328635,0.0056733983,0.0030065803,0.0006110679],"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":[0.0010526672,0.0011040083,0.149579,0.0009288573,0.00031640654,0.0010459061,0.6933205,0.0008127511,0.007641045,0.004147832,0.003015597,0.13703546],"study_design_scores_gemma":[0.00008512446,0.005096195,0.42335275,0.0010099593,0.00040093507,0.0022698266,0.51851964,0.0037363772,0.019814098,0.0064960117,0.018884525,0.00033451535],"about_ca_topic_score_codex":0.00080142694,"about_ca_topic_score_gemma":0.0011264082,"teacher_disagreement_score":0.014434177,"about_ca_system_score_codex":0.001068749,"about_ca_system_score_gemma":0.0010108324,"threshold_uncertainty_score":0.076336145},"labels":[],"label_agreement":null},{"id":"W2071016044","doi":"10.1080/02602930500260688","title":"Ratings of university teacher instruction: how much do student and course characteristics really matter?","year":2005,"lang":"en","type":"article","venue":"Assessment & Evaluation in Higher Education","topic":"Evaluation of Teaching Practices","field":"Social Sciences","cited_by":119,"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":"Psychology; Mathematics education; Class (philosophy); Higher education; Student teacher; Medical education; Teacher education; Medicine; Computer science","score_opus":0.0842783477103564,"score_gpt":0.4658851886852968,"score_spread":0.3816068409749404,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2071016044","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":[0.99796593,0.00010199672,0.0002626708,0.0000663306,0.000008861657,0.000016338829,0.00011139006,0.000011117235,0.0014554212],"genre_scores_gemma":[0.99939036,0.000041556104,0.00011965435,0.000012596691,0.0000060664274,0.000008065058,0.00011863095,0.000003827654,0.00029925987],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99603575,0.0010587864,0.00028993297,0.00029078778,0.0020405327,0.00028419856],"domain_scores_gemma":[0.9579069,0.017007135,0.011484104,0.0013578844,0.007795135,0.0044488064],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.004460477,0.00012949419,0.00041346863,0.0006609833,0.00028531003,0.0010140308,0.00030654893,0.0002828578,0.0016550865],"category_scores_gemma":[0.031437047,0.00011531837,0.00034446415,0.0006898554,0.0004103364,0.00040214925,0.00042359086,0.00048583662,0.0002902339],"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":[0.0002585873,0.0000871731,0.97946155,0.000031165964,0.0000925525,0.000017392587,0.00092029956,0.00010639722,0.0006670676,0.000030592644,0.00035241764,0.017974902],"study_design_scores_gemma":[0.000005267381,0.00013061105,0.9986745,0.0000071822783,0.000012989535,0.000014066845,0.0005465814,0.00018755061,0.00019755769,0.000014016121,0.00020472596,0.0000049567057],"about_ca_topic_score_codex":0.009899129,"about_ca_topic_score_gemma":0.025798721,"teacher_disagreement_score":0.99553955,"about_ca_system_score_codex":0.000728387,"about_ca_system_score_gemma":0.0006239179,"threshold_uncertainty_score":0.023589551},"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":"W2087036401","doi":"10.1080/02602930902862842","title":"Bases of competence: an instrument for self and institutional assessment","year":2009,"lang":"en","type":"article","venue":"Assessment & Evaluation in Higher Education","topic":"Higher Education and Employability","field":"Social Sciences","cited_by":48,"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 Guelph","funders":"","keywords":"Competence (human resources); Psychology; Self-assessment; Medical education; Pedagogy; Mathematics education; Social psychology; Medicine","score_opus":0.1171535369150104,"score_gpt":0.4856852979474642,"score_spread":0.3685317610324538,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2087036401","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.7949075,0.0008085796,0.08239364,0.0017587343,0.00056321325,0.020298237,0.016603656,0.0021338912,0.08053258],"genre_scores_gemma":[0.75041586,0.0007408781,0.18825342,0.0006282962,0.0001455382,0.034148913,0.010315448,0.00034384936,0.015007782],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99466527,0.001958822,0.00092146895,0.00022649906,0.0018547159,0.00037328817],"domain_scores_gemma":[0.9895839,0.0034057875,0.0021127583,0.0010075999,0.0029102992,0.0009796515],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0085129,0.0005558997,0.0005718766,0.0047289054,0.0006154722,0.0013644483,0.00094788405,0.00075335,0.0045187473],"category_scores_gemma":[0.020205157,0.00042263884,0.001164129,0.001524848,0.0005676984,0.002056202,0.0027961885,0.0016458139,0.0019644315],"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":[0.0011912519,0.0034870037,0.33349815,0.00049769116,0.00026072338,0.0002531521,0.004803053,0.003560602,0.008576911,0.013173275,0.041984726,0.58871347],"study_design_scores_gemma":[0.00042591715,0.0034796987,0.8458755,0.00043929895,0.000106002895,0.0010693345,0.004465781,0.017701324,0.00629847,0.014373969,0.10543954,0.00032523953],"about_ca_topic_score_codex":0.0011801881,"about_ca_topic_score_gemma":0.0014888268,"teacher_disagreement_score":0.0085129,"about_ca_system_score_codex":0.0009293806,"about_ca_system_score_gemma":0.0022795897,"threshold_uncertainty_score":0.045021057},"labels":[],"label_agreement":null},{"id":"W2119158672","doi":"10.1080/02602938.2012.693906","title":"Interpreting differences between the United States and New Zealand university students’ engagement scores as measured by the NSSE and AUSSE","year":2012,"lang":"en","type":"article","venue":"Assessment & Evaluation in Higher Education","topic":"Higher Education Research Studies","field":"Social Sciences","cited_by":6,"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 Auckland; National Center For Environmental Assessment; University of Victoria","keywords":"Student engagement; Constructive; Psychology; Scale (ratio); Medical education; Mathematics education; Medicine; Geography; Computer science; Process (computing)","score_opus":0.13220037945104948,"score_gpt":0.4711410347303959,"score_spread":0.33894065527934647,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2119158672","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.98841465,0.000113657574,0.0012789947,0.00044417527,0.00006021342,0.000104089384,0.00067818904,0.000013920312,0.008892181],"genre_scores_gemma":[0.9968405,0.00009404282,0.000999356,0.000100448706,0.000013014627,0.0002327438,0.00072140904,0.000015465468,0.0009829337],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99394107,0.002167213,0.0009185527,0.00048354175,0.0018948395,0.000594899],"domain_scores_gemma":[0.98571056,0.0041835117,0.003523522,0.00085984165,0.004699304,0.0010232918],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008629145,0.00041407763,0.00046847633,0.0027151713,0.00081497524,0.0016224147,0.0005704141,0.00037130067,0.0029160674],"category_scores_gemma":[0.04276112,0.00023298475,0.00079187297,0.0031279365,0.0014332632,0.0014585019,0.0026541285,0.0009500758,0.00055359246],"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":[0.00022436243,0.00006741331,0.9570097,0.00011585272,0.00024185535,0.00006839229,0.01676114,0.00014631182,0.0012432401,0.00072665914,0.0015950295,0.021800056],"study_design_scores_gemma":[0.000006878203,0.000085726875,0.98757,0.000033812976,0.000026656184,0.000025083378,0.009573718,0.00027836818,0.00029005454,0.00023605702,0.0018592866,0.000014328871],"about_ca_topic_score_codex":0.10648619,"about_ca_topic_score_gemma":0.14649084,"teacher_disagreement_score":0.10648619,"about_ca_system_score_codex":0.0012680087,"about_ca_system_score_gemma":0.0013348941,"threshold_uncertainty_score":0.21173275},"labels":[],"label_agreement":null},{"id":"W2401839864","doi":"10.1080/02602938.2016.1188057","title":"Impact assessment of a department-wide science education initiative using students’ perceptions of teaching and learning experiences","year":2016,"lang":"en","type":"article","venue":"Assessment & Evaluation in Higher Education","topic":"Evaluation of Teaching Practices","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":"Helpfulness; Context (archaeology); Psychology; Perception; Medical education; Preference; Science education; Class (philosophy); Teaching method; Mathematics education; Medicine; Computer science","score_opus":0.1817612835993253,"score_gpt":0.5919669342211382,"score_spread":0.4102056506218129,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2401839864","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9991955,0.0000127380745,0.00017315465,0.000021318818,0.000002110426,0.000091900016,0.000018574752,0.000010665912,0.00047390405],"genre_scores_gemma":[0.9983981,0.000024660216,0.0011325442,0.000017202541,0.00000491074,0.00012274615,0.000049828643,0.0000027253882,0.00024732345],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9925332,0.0031643522,0.00067770877,0.00046270492,0.0021885252,0.0009734457],"domain_scores_gemma":[0.9671747,0.014094642,0.00578646,0.0013320114,0.005929116,0.00568302],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014069598,0.00062093546,0.0006325657,0.0015516676,0.0009678385,0.0015345899,0.0009910356,0.00057133095,0.0015653513],"category_scores_gemma":[0.023510236,0.00037504348,0.0009052861,0.00089624774,0.0006484338,0.00096018816,0.00208388,0.0009538325,0.00024514267],"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":[0.0021188066,0.016812125,0.80650955,0.00039894646,0.00030970815,0.00033448145,0.027972892,0.0013072881,0.015748769,0.00016897853,0.00085552153,0.12746298],"study_design_scores_gemma":[0.00013577472,0.016426973,0.95535386,0.00004195672,0.000110557055,0.00010697667,0.01687939,0.0013621789,0.008185788,0.00006711977,0.0012657195,0.000063714484],"about_ca_topic_score_codex":0.0013304714,"about_ca_topic_score_gemma":0.004195481,"teacher_disagreement_score":0.014069598,"about_ca_system_score_codex":0.0014455622,"about_ca_system_score_gemma":0.0014491569,"threshold_uncertainty_score":0.074408054},"labels":[],"label_agreement":null},{"id":"W2705397363","doi":"10.1080/02602938.2017.1343799","title":"Comparing student, instructor, classroom and institutional data to evaluate a seven-year department-wide science education initiative","year":2017,"lang":"en","type":"article","venue":"Assessment & Evaluation in Higher Education","topic":"Evaluation of Teaching Practices","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":"Helpfulness; Enthusiasm; Graduation (instrument); Psychology; Medical education; Perception; Class (philosophy); Class size; Higher education; Mathematics education; Medicine; Social psychology; Computer science; Political science","score_opus":0.41775580264030054,"score_gpt":0.5790085889658491,"score_spread":0.16125278632554851,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2705397363","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9984003,0.000031900254,0.00037030855,0.000016494956,0.000005311033,0.00009458361,0.00038384733,0.000015845688,0.00068144634],"genre_scores_gemma":[0.9956053,0.000025105684,0.001592179,0.00003181162,0.000008206742,0.0002576605,0.002106697,0.000012453499,0.0003606687],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9891339,0.004601044,0.0009858941,0.00074965425,0.0040267557,0.0005027803],"domain_scores_gemma":[0.9291316,0.033901908,0.01005639,0.0045433827,0.018225,0.0041417233],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014585161,0.000298452,0.0004975164,0.0034637756,0.0006277595,0.0011858129,0.00078041165,0.0005234161,0.0009860703],"category_scores_gemma":[0.037801094,0.00017209552,0.00059676374,0.0027788577,0.00046770304,0.0009979188,0.0014505128,0.00077823957,0.00031403624],"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":[0.0007688439,0.0023171257,0.9590907,0.000117159085,0.00018950825,0.000053001124,0.0032729493,0.00039011284,0.0017649587,0.00014125103,0.0005275604,0.031366903],"study_design_scores_gemma":[0.00004979512,0.0031787013,0.988644,0.000024436484,0.000064997126,0.000046509507,0.0029435775,0.00082711846,0.0024712041,0.00004434038,0.0016831992,0.000022049699],"about_ca_topic_score_codex":0.0029199242,"about_ca_topic_score_gemma":0.007628412,"teacher_disagreement_score":0.014585161,"about_ca_system_score_codex":0.0011165412,"about_ca_system_score_gemma":0.0011017973,"threshold_uncertainty_score":0.07713467},"labels":[],"label_agreement":null},{"id":"W2762181356","doi":"10.1080/02602938.2017.1380161","title":"Team dynamics feedback for post-secondary student learning teams","year":2017,"lang":"en","type":"article","venue":"Assessment & Evaluation in Higher Education","topic":"Team Dynamics and Performance","field":"Psychology","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 Ottawa; University of Calgary","funders":"","keywords":"Psychology; Team composition; Team effectiveness; Context (archaeology); Medical education; Health care; Teamwork; Suite; Perception; Applied psychology; Knowledge management; Computer science; Medicine; Social psychology","score_opus":0.04679159502534595,"score_gpt":0.4609525818626039,"score_spread":0.41416098683725794,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2762181356","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.95629674,0.00020409146,0.013861903,0.001484581,0.00032887197,0.0012709665,0.0010487544,0.0019384621,0.023565643],"genre_scores_gemma":[0.9711964,0.0002165822,0.018955989,0.00021886223,0.00008679559,0.0008233617,0.0008275583,0.00021039406,0.0074640173],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.99118656,0.0042712763,0.00056833477,0.00061451754,0.0027927423,0.00056653627],"domain_scores_gemma":[0.93675464,0.028144302,0.0049099023,0.002848733,0.016553555,0.010788772],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.009998021,0.0006774983,0.0006041402,0.0025786515,0.0013929072,0.0022700864,0.0009670772,0.00076177827,0.015082316],"category_scores_gemma":[0.07527458,0.00028529888,0.0005038677,0.0009335104,0.00028057588,0.0012768655,0.002816407,0.0011351228,0.004045016],"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":[0.0019749897,0.008563548,0.19576442,0.0006929667,0.000060106882,0.00044562228,0.030485317,0.0024321,0.00557741,0.00065159256,0.027616708,0.72573525],"study_design_scores_gemma":[0.0008967706,0.017149447,0.76877594,0.0019284262,0.00013445948,0.00070371357,0.053626403,0.030281581,0.017559743,0.0043266825,0.10420496,0.00041193597],"about_ca_topic_score_codex":0.0022103018,"about_ca_topic_score_gemma":0.004037535,"teacher_disagreement_score":0.015082316,"about_ca_system_score_codex":0.0014978703,"about_ca_system_score_gemma":0.0024618276,"threshold_uncertainty_score":0.05287522},"labels":[],"label_agreement":null},{"id":"W2771690381","doi":"10.1080/02602938.2017.1412397","title":"Taking stock and effecting change: curriculum evaluation through a review of course syllabi","year":2017,"lang":"en","type":"review","venue":"Assessment & Evaluation in Higher Education","topic":"Evaluation of Teaching Practices","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":true,"ca_institutions":"University of Windsor","funders":"University of Windsor","keywords":"Syllabus; Curriculum; Experiential learning; Unit (ring theory); Higher education; Medical education; Discipline; Psychology; Course evaluation; Reading (process); Pedagogy; Mathematics education; Political science; Medicine","score_opus":0.6459460384304073,"score_gpt":0.6783012568282019,"score_spread":0.03235521839779454,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2771690381","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":[0.026571902,0.9557816,0.0030563502,0.0020915992,0.00056275673,0.0033182758,0.00027612518,0.000039435796,0.008302045],"genre_scores_gemma":[0.15664677,0.82014614,0.018213818,0.00087970984,0.00021718664,0.0023382944,0.0002660534,0.000029115894,0.0012627922],"study_design_codex":"design_other","study_design_gemma":"qualitative","domain_scores_codex":[0.94838923,0.02921098,0.0059587657,0.0014490162,0.014553391,0.00043866053],"domain_scores_gemma":[0.9299582,0.038847752,0.008844489,0.0017819217,0.019623032,0.00094460865],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.06048958,0.0008359665,0.0024741408,0.005582212,0.0007945396,0.0029317234,0.0017526271,0.0008942713,0.0014259802],"category_scores_gemma":[0.11623778,0.00037853376,0.0015675649,0.005793475,0.0009114631,0.0020069554,0.0013537363,0.000840044,0.0003217376],"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":[0.00021259135,0.00020017043,0.0017189784,0.043124527,0.0007294984,0.000041354644,0.0012495974,0.00015616101,0.00035140236,0.0006997891,0.002162723,0.94935316],"study_design_scores_gemma":[0.0011021919,0.008687585,0.055024832,0.47495124,0.019042963,0.0010244754,0.010383815,0.0012276968,0.008236929,0.0036823757,0.41627282,0.00036310675],"about_ca_topic_score_codex":0.0057720966,"about_ca_topic_score_gemma":0.020370709,"teacher_disagreement_score":0.06048958,"about_ca_system_score_codex":0.0049769464,"about_ca_system_score_gemma":0.014836311,"threshold_uncertainty_score":0.3199033},"labels":[],"label_agreement":null},{"id":"W2962316688","doi":"10.1080/02602938.2019.1637819","title":"Voices at the gate: Faculty members’ and students’ differing perspectives on the purposes of the PhD comprehensive examination","year":2019,"lang":"en","type":"article","venue":"Assessment & Evaluation in Higher Education","topic":"Doctoral Education Challenges and Solutions","field":"Health Professions","cited_by":15,"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":"Gatekeeping; Psychology; Medical education; Final examination; Empirical examination; Identity (music); Function (biology); Higher education; Affect (linguistics); Pedagogy; Perspective (graphical); Mathematics education; Medicine; Political science","score_opus":0.3458290584160393,"score_gpt":0.5752187854825841,"score_spread":0.2293897270665448,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2962316688","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":[0.939609,0.0012737621,0.0029758294,0.036603797,0.00063511665,0.00006144213,0.000027785167,0.00004511806,0.018768236],"genre_scores_gemma":[0.99457633,0.00033709363,0.0004904719,0.002389429,0.00010538934,0.000023819479,0.000009242568,0.000023182738,0.0020449585],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.92602974,0.051836014,0.0022169375,0.0017958084,0.010443503,0.0076780217],"domain_scores_gemma":[0.9199824,0.03997831,0.006082173,0.0020001368,0.011150262,0.020806665],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.04212815,0.00036551978,0.0006129208,0.0018705238,0.019699462,0.016480437,0.0022207438,0.0043731607,0.0022572363],"category_scores_gemma":[0.097961865,0.0005729355,0.00064806617,0.001410061,0.017125564,0.0075896364,0.01293384,0.0074139186,0.00041400146],"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":[0.0000699735,0.00006153236,0.0108856885,0.0000598118,0.000017076136,0.0011327591,0.9534557,0.00008387009,0.0010478948,0.009817946,0.003859527,0.019508302],"study_design_scores_gemma":[0.000008817871,0.00006657244,0.0045941225,0.000110737616,0.00000934645,0.0003764614,0.97467154,0.00016658408,0.00035121563,0.0014970666,0.018091874,0.000055676475],"about_ca_topic_score_codex":0.018803246,"about_ca_topic_score_gemma":0.022639299,"teacher_disagreement_score":0.95787185,"about_ca_system_score_codex":0.0109338155,"about_ca_system_score_gemma":0.017884206,"threshold_uncertainty_score":0.22279757},"labels":[],"label_agreement":null},{"id":"W2983876144","doi":"10.1080/02602938.2019.1689381","title":"The effects of perceived professor competence, warmth and gender on students’ likelihood to register for a course","year":2019,"lang":"en","type":"article","venue":"Assessment & Evaluation in Higher Education","topic":"Communication in Education and Healthcare","field":"Psychology","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","funders":"","keywords":"Vignette; Psychology; Gender bias; Competence (human resources); Social psychology; Developmental psychology","score_opus":0.10712911187854181,"score_gpt":0.527350665480816,"score_spread":0.4202215536022742,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W2983876144","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99953413,0.000027027352,0.000032951288,0.000029069264,0.0000027631697,0.0000044936983,0.000008456936,9.200263e-7,0.0003602159],"genre_scores_gemma":[0.99964476,0.000026471731,0.000057992755,0.000014189675,0.0000029999103,0.0000046164982,0.000017108949,6.688759e-7,0.00023121302],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9981748,0.0006551401,0.00012031468,0.00015847058,0.0005763133,0.00031507105],"domain_scores_gemma":[0.9867192,0.005070775,0.003881169,0.00045252644,0.00085443835,0.003021856],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0031037398,0.00020396535,0.0002881017,0.00058243965,0.00058237853,0.0013074391,0.00028981,0.00047174847,0.0034116583],"category_scores_gemma":[0.01405271,0.00016789942,0.00053333404,0.00028316703,0.00072112214,0.00035602614,0.00055416074,0.0008348604,0.00039250604],"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":[0.00037045,0.00065145787,0.98847336,0.000018271407,0.000053036863,0.00008510256,0.002031794,0.00007931992,0.0013974586,0.00009998112,0.00008603792,0.006653697],"study_design_scores_gemma":[0.0000065323893,0.0003061109,0.99722314,0.0000060160824,0.000011536342,0.000041780568,0.0018068685,0.00015699488,0.00024951968,0.000051442905,0.0001325179,0.000007548349],"about_ca_topic_score_codex":0.004020444,"about_ca_topic_score_gemma":0.010998659,"teacher_disagreement_score":0.004020444,"about_ca_system_score_codex":0.0008104228,"about_ca_system_score_gemma":0.0009439704,"threshold_uncertainty_score":0.016414285},"labels":[],"label_agreement":null},{"id":"W3008488197","doi":"10.1080/02602938.2020.1727412","title":"Team dynamics feedback for post-secondary student learning teams: introducing the “Bare CARE” assessment and report","year":2020,"lang":"en","type":"article","venue":"Assessment & Evaluation in Higher Education","topic":"Team Dynamics and Performance","field":"Psychology","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 Calgary","funders":"","keywords":"Formative assessment; Teamwork; Psychology; Experiential learning; Medical education; Health care; Sample (material); Applied psychology; Pedagogy; Medicine","score_opus":0.03439414168239335,"score_gpt":0.42985498815841316,"score_spread":0.3954608464760198,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3008488197","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.8683149,0.00062218943,0.09078515,0.0062911888,0.0013474944,0.0077033597,0.001693105,0.0027094085,0.020533243],"genre_scores_gemma":[0.79349095,0.0008493706,0.1900488,0.0009117146,0.00038761654,0.007133409,0.0011586398,0.000282135,0.005737349],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.98304373,0.007900061,0.0027087585,0.00070557743,0.004893054,0.00074877316],"domain_scores_gemma":[0.94224334,0.020251706,0.006487817,0.0028965548,0.023295125,0.004825449],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.017678449,0.0006011033,0.0006219933,0.0025937657,0.0007135386,0.0021833729,0.0009986802,0.00084571715,0.0026491308],"category_scores_gemma":[0.06883165,0.00027130562,0.0007998983,0.0008884967,0.0005513429,0.0015168822,0.0026712003,0.0016183547,0.0012347967],"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":[0.0006561689,0.0027143187,0.23041812,0.000701721,0.00007820641,0.00031778705,0.011395201,0.0015741829,0.0069008362,0.0011555111,0.017849589,0.7262384],"study_design_scores_gemma":[0.00036258556,0.009413494,0.8396772,0.0018793655,0.00013015048,0.0012178718,0.014662319,0.022877488,0.023162376,0.005661656,0.08037706,0.00057844387],"about_ca_topic_score_codex":0.0017538329,"about_ca_topic_score_gemma":0.0039493437,"teacher_disagreement_score":0.017678449,"about_ca_system_score_codex":0.0009586959,"about_ca_system_score_gemma":0.00284208,"threshold_uncertainty_score":0.0934937},"labels":[],"label_agreement":null},{"id":"W3049736335","doi":"10.1080/02602938.2020.1805410","title":"Are students gender-neutral in their assessment of online teaching staff?","year":2020,"lang":"en","type":"article","venue":"Assessment & Evaluation in Higher Education","topic":"Evaluation of Teaching Practices","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":"","keywords":"Workload; Psychology; Construct (python library); Quality (philosophy); Promotion (chess); Medical education; Course evaluation; Higher education; Computer science; Medicine","score_opus":0.37231232978525863,"score_gpt":0.5823678399594441,"score_spread":0.21005551017418544,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3049736335","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99349326,0.00030780045,0.0012888152,0.0008482797,0.000094565716,0.000034402146,0.00009270491,0.000015272763,0.0038249898],"genre_scores_gemma":[0.9987356,0.00010533709,0.0002665523,0.00029301518,0.000017476232,0.000030895797,0.000044129036,0.000006247033,0.00050077983],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99100167,0.0030969006,0.0007761532,0.00087916217,0.003462554,0.0007834911],"domain_scores_gemma":[0.9711277,0.009232206,0.010585468,0.0015909821,0.0049445806,0.002519157],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.011887787,0.00021748635,0.0003875306,0.0008850827,0.00056236837,0.0021348402,0.00046799224,0.00041084288,0.0022855154],"category_scores_gemma":[0.049985483,0.00018718156,0.000372999,0.0004952503,0.0010536811,0.0011049617,0.00090917427,0.0005160204,0.00085514947],"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":[0.0005359582,0.00021257573,0.88316107,0.00010196072,0.000086937005,0.00026657173,0.019585336,0.000079618796,0.003257644,0.0006307025,0.0012978053,0.090783894],"study_design_scores_gemma":[0.000028719174,0.0006124178,0.9557297,0.00016122838,0.00005053854,0.0008136897,0.032135695,0.00048585597,0.0028322435,0.0013478963,0.005738434,0.000063476524],"about_ca_topic_score_codex":0.001750766,"about_ca_topic_score_gemma":0.0032256395,"teacher_disagreement_score":0.011887787,"about_ca_system_score_codex":0.000812918,"about_ca_system_score_gemma":0.00093344453,"threshold_uncertainty_score":0.06286937},"labels":[],"label_agreement":null},{"id":"W3092685673","doi":"10.1080/02602938.2020.1826900","title":"When academic integrity rules should not apply: a survey of academic staff","year":2020,"lang":"en","type":"article","venue":"Assessment & Evaluation in Higher Education","topic":"Academic integrity and plagiarism","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":"Centre for Social Innovation","funders":"","keywords":"Academic integrity; Ambiguity; Public relations; Compliance (psychology); Ideology; Psychology; Multinational corporation; Welfare; Social psychology; Action (physics); Political science; Law","score_opus":0.29559258214728357,"score_gpt":0.4864898433562915,"score_spread":0.1908972612090079,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3092685673","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":[0.99806875,0.00013410003,0.00017191694,0.0007042134,0.000009681451,0.000012161016,0.000024357883,0.0000034728637,0.0008714043],"genre_scores_gemma":[0.9994155,0.00012295843,0.00012539612,0.00019379197,0.0000073788847,0.000010810168,0.000013602426,0.0000021321835,0.0001084343],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9778085,0.011658942,0.0030257308,0.0007508805,0.004184206,0.0025718282],"domain_scores_gemma":[0.9113723,0.028118886,0.0423546,0.002798359,0.009880358,0.005475562],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.02192045,0.00013448462,0.0003883759,0.0017590984,0.0026949418,0.0028205966,0.000784192,0.0012463115,0.0013807577],"category_scores_gemma":[0.07865191,0.0003726093,0.00022571851,0.002171869,0.002415743,0.0024669594,0.0021789053,0.0012085888,0.00045030293],"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":[0.000105890016,0.00010932595,0.8922543,0.0001164367,0.000019943694,0.00043369134,0.08586438,0.000054121763,0.0005364362,0.00042722805,0.0010440988,0.019034155],"study_design_scores_gemma":[0.000008829489,0.00032307697,0.482633,0.00025875765,0.000020001478,0.0009777714,0.5081089,0.00029843938,0.0005603677,0.000579363,0.006179746,0.000051806215],"about_ca_topic_score_codex":0.0071388744,"about_ca_topic_score_gemma":0.0082339905,"teacher_disagreement_score":0.99875367,"about_ca_system_score_codex":0.0019030119,"about_ca_system_score_gemma":0.0041104467,"threshold_uncertainty_score":0.115927815},"labels":[],"label_agreement":null},{"id":"W3095117930","doi":"10.1080/02602938.2020.1836123","title":"University students’ negative emotions in a computer-based examination: the roles of trait test-emotion, prior test-taking methods and gender","year":2020,"lang":"en","type":"article","venue":"Assessment & Evaluation in Higher Education","topic":"Education, Achievement, and Giftedness","field":"Psychology","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":"McGill University; Concordia University; McGill University Health Centre; University of Alberta","funders":"","keywords":"Test anxiety; Psychology; Test (biology); Trait; Anxiety; Social psychology; Computer science","score_opus":0.15587259605893805,"score_gpt":0.4787915717209989,"score_spread":0.32291897566206085,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3095117930","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9995441,0.00002100373,0.00005037174,0.000029115528,0.0000034339519,0.000002164059,0.0000053218355,0.0000011556416,0.0003434216],"genre_scores_gemma":[0.99979216,0.000014642947,0.000028138504,0.000015821797,0.0000022953552,0.0000028557847,0.000007959159,8.045399e-7,0.00013542906],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9991499,0.00029913135,0.0000613114,0.00008534728,0.00024927402,0.00015500598],"domain_scores_gemma":[0.9944442,0.001868088,0.0016444459,0.00029535976,0.0005168565,0.001230969],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0015341822,0.0001965112,0.00036094725,0.0003610162,0.0005016049,0.0023634073,0.00022013905,0.00032768832,0.0011466853],"category_scores_gemma":[0.007733211,0.00013249704,0.00023712151,0.00024356005,0.00090721156,0.00048221293,0.001003424,0.0009153137,0.00020253727],"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":[0.00045146147,0.000709976,0.96061784,0.000038009017,0.000053664426,0.00017986228,0.0133230435,0.00010949965,0.006533122,0.00018476542,0.0002215813,0.01757703],"study_design_scores_gemma":[0.000004532323,0.00022413401,0.991147,0.00001043288,0.000012724725,0.00008552926,0.007267547,0.00018198695,0.0007256902,0.00008784013,0.00023905997,0.0000135570035],"about_ca_topic_score_codex":0.0009847638,"about_ca_topic_score_gemma":0.001734905,"teacher_disagreement_score":0.0023634073,"about_ca_system_score_codex":0.00035217748,"about_ca_system_score_gemma":0.00025780723,"threshold_uncertainty_score":0.008113623},"labels":[],"label_agreement":null},{"id":"W3162164515","doi":"10.1080/02602938.2021.1921105","title":"Fitted: the impact of academics’ attire on students’ evaluations and intentions","year":2021,"lang":"en","type":"article","venue":"Assessment & Evaluation in Higher Education","topic":"Communication in Education and Healthcare","field":"Psychology","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":"University of Victoria","funders":"","keywords":"Psychology; Higher education; Pedagogy; Mathematics education; Medical education; Medicine; Political science","score_opus":0.2935359884430912,"score_gpt":0.625609991914194,"score_spread":0.3320740034711028,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3162164515","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":[0.9968618,0.000042295524,0.00028692436,0.00016384388,0.000026331356,0.00002397216,0.00005669139,0.000012564904,0.0025255186],"genre_scores_gemma":[0.997888,0.00001851494,0.00024651934,0.000055587454,0.000009319748,0.000034643843,0.000051718267,0.000005223524,0.0016904814],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9959708,0.002043633,0.0002666347,0.00049273355,0.00087451085,0.00035164243],"domain_scores_gemma":[0.9447308,0.030481089,0.009718904,0.0049222438,0.003477335,0.0066694887],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0075293505,0.0003221698,0.00043868367,0.00040071268,0.00073148246,0.0021421022,0.0006032461,0.00066962,0.014631501],"category_scores_gemma":[0.03736225,0.00017421262,0.0007882437,0.00030560463,0.0011213388,0.0011145566,0.00161284,0.0018320106,0.0014430432],"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":[0.0038870901,0.0070033846,0.8639232,0.00037707284,0.00042850475,0.00011798702,0.009733646,0.00059064216,0.007107535,0.0013427079,0.0019930543,0.10349518],"study_design_scores_gemma":[0.000039164133,0.0017670058,0.9920219,0.00005924666,0.00008917486,0.00002299863,0.002660228,0.00063751824,0.0015154652,0.00041175055,0.0007544237,0.000021119427],"about_ca_topic_score_codex":0.0019261827,"about_ca_topic_score_gemma":0.0037382108,"teacher_disagreement_score":0.9924706,"about_ca_system_score_codex":0.00071597035,"about_ca_system_score_gemma":0.0012210849,"threshold_uncertainty_score":0.048947275},"labels":[],"label_agreement":null},{"id":"W3172383618","doi":"10.1080/02602938.2021.1912286","title":"Student satisfaction with use of an online peer feedback system","year":2021,"lang":"en","type":"article","venue":"Assessment & Evaluation in Higher Education","topic":"Team Dynamics and Performance","field":"Psychology","cited_by":26,"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; University of Ottawa","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Teamwork; Peer feedback; Psychology; Team composition; Higher education; Social loafing; Curriculum; Knowledge management; Medical education; Computer science; Mathematics education; Pedagogy; Social psychology; Political science","score_opus":0.12416158612870165,"score_gpt":0.45557304381090247,"score_spread":0.3314114576822008,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3172383618","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9980369,0.000028913362,0.00039610968,0.0001668629,0.000011333957,0.000016550364,0.000083085375,0.00002088311,0.0012393979],"genre_scores_gemma":[0.99897975,0.00002755178,0.0002502996,0.000040087943,0.000006966014,0.000013513325,0.00006870845,0.000007429285,0.0006057101],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9922512,0.0031126328,0.0008289196,0.00045087998,0.0025263499,0.00082995184],"domain_scores_gemma":[0.9365042,0.025011439,0.01534041,0.0035551244,0.012588952,0.0069997706],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007217225,0.00018956662,0.0004774425,0.000812727,0.0005765381,0.0027816829,0.0005208493,0.0005304795,0.006482892],"category_scores_gemma":[0.050832212,0.00014736317,0.0005777431,0.0009396891,0.0005350197,0.00094358367,0.0012426109,0.0012936883,0.001103096],"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":[0.00026817655,0.0016517515,0.9043657,0.00009918323,0.00009954779,0.00009054002,0.0055175046,0.00029093833,0.0010702946,0.00014321598,0.0008673836,0.08553559],"study_design_scores_gemma":[0.000014288317,0.0018315664,0.9845073,0.000036380003,0.000057277786,0.00013656281,0.0074080955,0.0014999291,0.0016254147,0.00012195127,0.0027222924,0.00003885809],"about_ca_topic_score_codex":0.0016057672,"about_ca_topic_score_gemma":0.0016275235,"teacher_disagreement_score":0.007217225,"about_ca_system_score_codex":0.00050819863,"about_ca_system_score_gemma":0.0010286572,"threshold_uncertainty_score":0.038168788},"labels":[],"label_agreement":null},{"id":"W3184059431","doi":"10.1080/02602938.2021.1956428","title":"Patterns of special consideration requests at a UK university: reasons given and associations with demographic factors","year":2021,"lang":"en","type":"article","venue":"Assessment & Evaluation in Higher Education","topic":"Medical Education and Admissions","field":"Medicine","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; Quarter (Canadian coin); Mental health; Control (management); Medical education; Medicine; Psychiatry","score_opus":0.06568450014595346,"score_gpt":0.3824971704876142,"score_spread":0.3168126703416608,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W3184059431","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9981894,0.00036074064,0.00009753508,0.00043337204,0.000015911965,0.000022222051,0.00013614357,0.000009441805,0.0007351455],"genre_scores_gemma":[0.99921465,0.00023970983,0.000083374674,0.00005603503,0.0000143274865,0.000010601092,0.000077051845,0.0000050172766,0.00029924035],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9937551,0.0019318578,0.0015299518,0.00045344117,0.00127447,0.0010551931],"domain_scores_gemma":[0.9594618,0.007833737,0.023761945,0.00086923386,0.0030384848,0.005034764],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0023408162,0.0003152496,0.00048299608,0.0027089808,0.0009808438,0.0018782279,0.00073820655,0.00087074406,0.0057718153],"category_scores_gemma":[0.0258049,0.0004737265,0.0005319486,0.0024332856,0.0010337249,0.0013673297,0.0025279545,0.0013578417,0.0012491602],"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":[0.0000878688,0.00004361964,0.9934505,0.000035234392,0.000013719325,0.00021799465,0.0017972977,0.000030877047,0.00015455275,0.000028682482,0.00032849007,0.0038110819],"study_design_scores_gemma":[0.0000017962592,0.00010457333,0.9918933,0.000054116597,0.0000040040327,0.00052940956,0.006815098,0.00010391461,0.000060454047,0.000032744556,0.00038262314,0.000018027196],"about_ca_topic_score_codex":0.010442612,"about_ca_topic_score_gemma":0.016963962,"teacher_disagreement_score":0.010442612,"about_ca_system_score_codex":0.0012057245,"about_ca_system_score_gemma":0.0014194747,"threshold_uncertainty_score":0.020763636},"labels":[],"label_agreement":null},{"id":"W4200173019","doi":"10.1080/02602938.2021.2009439","title":"Does a classroom-based curriculum offer authentic assessments? A strategy to uncover their prevalence and incorporate opportunities for authenticity","year":2021,"lang":"en","type":"article","venue":"Assessment & Evaluation in Higher Education","topic":"Innovations in Medical Education","field":"Medicine","cited_by":12,"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 Guelph","funders":"Social Sciences and Humanities Research Council of Canada","keywords":"Authentic assessment; Syllabus; Curriculum; Capstone; Judgement; Psychology; Context (archaeology); Medical education; Summative assessment; Authentic learning; Mathematics education; Curriculum development; Pedagogy; Formative assessment; Medicine; Computer science","score_opus":0.10888072822505045,"score_gpt":0.42622515487460516,"score_spread":0.3173444266495547,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4200173019","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.92813236,0.001491352,0.04962098,0.0059753293,0.00017519308,0.00081807765,0.0001632861,0.0002577872,0.013365715],"genre_scores_gemma":[0.97410077,0.00033088622,0.0238912,0.00047619216,0.00003250337,0.00040880137,0.00005256502,0.0000194642,0.0006876267],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.9753294,0.014073884,0.0020900923,0.0017584747,0.0058629434,0.00088523584],"domain_scores_gemma":[0.8632114,0.06531549,0.021901874,0.017205238,0.025839046,0.0065270583],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.027528211,0.00027537072,0.0005884024,0.0028546331,0.0016807512,0.0035665939,0.0009867902,0.0011021469,0.0014674222],"category_scores_gemma":[0.12950678,0.0003696985,0.00036025967,0.0018588348,0.0020989268,0.0049088933,0.003966535,0.001562821,0.000601044],"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":[0.0002717622,0.0011487439,0.34348947,0.0011248268,0.00007655615,0.0002688316,0.018772483,0.0007263661,0.008526114,0.012104636,0.0028855135,0.6106047],"study_design_scores_gemma":[0.00014492276,0.006251362,0.8085252,0.003943045,0.00018784075,0.002225472,0.03950875,0.007951699,0.020564383,0.024000501,0.08636685,0.00032998028],"about_ca_topic_score_codex":0.0012086269,"about_ca_topic_score_gemma":0.0042279866,"teacher_disagreement_score":0.027528211,"about_ca_system_score_codex":0.001898656,"about_ca_system_score_gemma":0.0076447995,"threshold_uncertainty_score":0.14558482},"labels":[],"label_agreement":null},{"id":"W4366159769","doi":"10.1080/02602938.2023.2199181","title":"Students’ online evaluation of teaching and system continuance usage intention: new directions from a multidisciplinary perspective","year":2023,"lang":"en","type":"article","venue":"Assessment & Evaluation in Higher Education","topic":"Online and Blended Learning","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":"National Science and Technology Council","keywords":"Helpfulness; CLARITY; Set (abstract data type); Continuance; Psychology; Perspective (graphical); Higher education; Medical education; Knowledge management; Computer science; Social psychology; Political science","score_opus":0.10627568801785903,"score_gpt":0.5058444972128289,"score_spread":0.39956880919496984,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4366159769","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":[0.997832,0.0000661938,0.00047179253,0.00010523456,0.000004078033,0.000011736152,0.000019608733,0.0000066726866,0.0014826949],"genre_scores_gemma":[0.99950945,0.000028192264,0.00017606106,0.000013314937,0.000003303381,0.000008682259,0.00001841171,0.0000020932587,0.00024046573],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.996759,0.0014423906,0.00033191725,0.00021379012,0.001010865,0.00024216031],"domain_scores_gemma":[0.97159475,0.014513516,0.0059300307,0.0016926352,0.0039178403,0.002351223],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.005793571,0.0001902498,0.00028886244,0.0012940691,0.00040958385,0.0027498363,0.0003140416,0.00044653623,0.0021329965],"category_scores_gemma":[0.021709546,0.00012616273,0.0004158966,0.0009176754,0.0005812412,0.002183345,0.00095429475,0.00088718894,0.00029750713],"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":[0.00009560314,0.0007758444,0.9486361,0.00005557073,0.000057056168,0.000044237717,0.010741717,0.00012207637,0.000867513,0.00042412052,0.00012473676,0.03805546],"study_design_scores_gemma":[0.0000026100697,0.00043471306,0.9852064,0.00003967495,0.00002086337,0.000044412653,0.011371586,0.0012807682,0.0007222982,0.00028862752,0.0005711806,0.000016861868],"about_ca_topic_score_codex":0.0011388639,"about_ca_topic_score_gemma":0.0016411163,"teacher_disagreement_score":0.9942064,"about_ca_system_score_codex":0.00043413736,"about_ca_system_score_gemma":0.0005187579,"threshold_uncertainty_score":0.030639708},"labels":[],"label_agreement":null},{"id":"W4386923563","doi":"10.1080/02602938.2023.2259632","title":"Are assessment accommodations cheating? A critical policy analysis","year":2023,"lang":"en","type":"article","venue":"Assessment & Evaluation in Higher Education","topic":"Disability Education and Employment","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":"University of Calgary; Ontario Tech University","funders":"","keywords":"Cheating; Accommodation; Psychology; Context (archaeology); Realm; Inclusion (mineral); Public relations; Reasonable accommodation; Social psychology; Political science; Law","score_opus":0.21021702937233872,"score_gpt":0.577718254142636,"score_spread":0.3675012247702973,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4386923563","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":[0.009013811,0.006522301,0.0064658904,0.9552861,0.0021242923,0.00042921645,0.00012394332,0.000040748717,0.019993728],"genre_scores_gemma":[0.5758887,0.007793363,0.012273871,0.38860318,0.0062131495,0.0023000597,0.000074531345,0.000146567,0.00670652],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"qualitative","domain_scores_codex":[0.6471175,0.22779028,0.020230213,0.0148670385,0.058245152,0.031749826],"domain_scores_gemma":[0.124196164,0.78394717,0.029950112,0.011694336,0.041733965,0.008478215],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.38403842,0.0017825357,0.004917326,0.0060221944,0.014608165,0.033029288,0.006491344,0.05479307,0.014987804],"category_scores_gemma":[0.63713425,0.0022399195,0.003275004,0.0051587396,0.05042214,0.049372736,0.011138487,0.054625213,0.0012681071],"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":[0.0008712984,0.00038686348,0.00405345,0.0018203615,0.00040265667,0.0005138769,0.0070157195,0.0026487478,0.0003986687,0.8659046,0.06914967,0.046834078],"study_design_scores_gemma":[0.00049004355,0.00039040178,0.0033479126,0.009618383,0.0005028343,0.00027102313,0.018748553,0.005553403,0.0016228276,0.8281285,0.13091768,0.00040842063],"about_ca_topic_score_codex":0.012630359,"about_ca_topic_score_gemma":0.0068032867,"teacher_disagreement_score":0.38403842,"about_ca_system_score_codex":0.036289815,"about_ca_system_score_gemma":0.09006676,"threshold_uncertainty_score":0.75959027},"labels":[],"label_agreement":null},{"id":"W4387267871","doi":"10.1080/02602938.2023.2263668","title":"Flexible assessment: some benefits and costs for students and instructors","year":2023,"lang":"en","type":"article","venue":"Assessment & Evaluation in Higher Education","topic":"Evaluation of Teaching Practices","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":"Grading (engineering); Workload; Flexibility (engineering); Rigour; Formative assessment; Psychology; Medical education; Mathematics education; Pedagogy; Computer science; Engineering; Management; Medicine","score_opus":0.27421430645693995,"score_gpt":0.5825374862958459,"score_spread":0.30832317983890595,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4387267871","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":[0.704805,0.013062258,0.032766268,0.1666551,0.0010207961,0.00082772184,0.00019936885,0.0006431419,0.08002033],"genre_scores_gemma":[0.9651903,0.0022017101,0.024056967,0.0023639572,0.00035622934,0.00032192675,0.00005629963,0.000067929235,0.005384697],"study_design_codex":"design_other","study_design_gemma":"observational","domain_scores_codex":[0.96304905,0.019741325,0.0027125133,0.0007811934,0.011925138,0.0017907907],"domain_scores_gemma":[0.8602651,0.09183064,0.0078240745,0.00897613,0.020503024,0.010601115],"candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.029309288,0.00090905296,0.000654372,0.0017576716,0.0039931885,0.007141,0.001892878,0.002754075,0.008429941],"category_scores_gemma":[0.081479676,0.00046333837,0.0013273029,0.0015635549,0.002083285,0.00713257,0.0048486064,0.0033266624,0.0009084131],"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":[0.0008825122,0.0008954997,0.041270744,0.0007183256,0.00008761794,0.00082210364,0.005728545,0.0010825689,0.0018636943,0.0154020265,0.009237903,0.9220086],"study_design_scores_gemma":[0.00082767784,0.012903314,0.46704108,0.008536581,0.00097272045,0.011936744,0.1362881,0.02215533,0.013599675,0.1237906,0.20063357,0.0013146851],"about_ca_topic_score_codex":0.0035523844,"about_ca_topic_score_gemma":0.010363119,"teacher_disagreement_score":0.9706907,"about_ca_system_score_codex":0.0044035255,"about_ca_system_score_gemma":0.006262987,"threshold_uncertainty_score":0.1550042},"labels":[],"label_agreement":null},{"id":"W4391679980","doi":"10.1080/02602938.2024.2312918","title":"Decolonizing academic integrity: knowledge caretaking as ethical practice","year":2024,"lang":"en","type":"article","venue":"Assessment & Evaluation in Higher Education","topic":"African cultural and philosophical studies","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":"University of Calgary","funders":"National Natural Science Foundation of China","keywords":"Academic integrity; Psychology; Pedagogy; Higher education; Engineering ethics; Medical education; Social psychology; Medicine; Political science","score_opus":0.27405782341470886,"score_gpt":0.5728610453092766,"score_spread":0.29880322189456776,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4391679980","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":[0.08152392,0.013186064,0.17656209,0.49893257,0.0025135488,0.00058712804,0.000023832752,0.00024514875,0.22642577],"genre_scores_gemma":[0.95047206,0.0021611867,0.024638047,0.015574186,0.00041453383,0.00036060778,0.000009446094,0.00008203861,0.006287855],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8600167,0.11131283,0.0040619466,0.0053574457,0.014346636,0.0049045095],"domain_scores_gemma":[0.84613264,0.09543493,0.013909941,0.02361241,0.014094148,0.00681594],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.11781231,0.0007580959,0.001272018,0.0029982962,0.022385282,0.024472306,0.0040373164,0.012001797,0.002491963],"category_scores_gemma":[0.12069203,0.0006035083,0.0009185055,0.0017965578,0.20816478,0.029017285,0.030353388,0.017274367,0.0006277753],"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":[0.0000146529665,0.000047366262,0.0007182184,0.00020124202,0.000015104612,0.0002897982,0.15519074,0.00029977923,0.00034070728,0.81598735,0.0029321408,0.023962878],"study_design_scores_gemma":[0.00002086106,0.00008596431,0.00040286884,0.0014109984,0.00001452985,0.00045949995,0.10006216,0.00059204834,0.001016845,0.80359906,0.092270315,0.0000649427],"about_ca_topic_score_codex":0.0038046318,"about_ca_topic_score_gemma":0.0038539243,"teacher_disagreement_score":0.9879982,"about_ca_system_score_codex":0.012514949,"about_ca_system_score_gemma":0.03409447,"threshold_uncertainty_score":0.6230585},"labels":[],"label_agreement":null},{"id":"W4396978195","doi":"10.1080/02602938.2024.2350682","title":"Conflict management styles assessment and feedback for student self-awareness and team development","year":2024,"lang":"en","type":"article","venue":"Assessment & Evaluation in Higher Education","topic":"Conflict Management and Negotiation","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 Windsor; University of Ottawa; University of Winnipeg; University of Calgary","funders":"","keywords":"Psychology; Conflict management; Applied psychology; Medical education; Political science; Medicine","score_opus":0.09251670516487259,"score_gpt":0.48036438080568167,"score_spread":0.3878476756408091,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4396978195","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.9653122,0.00015976011,0.018655043,0.0004251482,0.00012453002,0.003156807,0.0009299943,0.0006483812,0.010588222],"genre_scores_gemma":[0.9465724,0.0002646719,0.04455413,0.00012967929,0.000039248305,0.0037854533,0.0010072135,0.00009068038,0.0035564501],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.9900147,0.004646109,0.0014709036,0.00045269015,0.0028788461,0.00053679745],"domain_scores_gemma":[0.962055,0.014114755,0.004973072,0.0022276936,0.012975492,0.0036539815],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.014093007,0.0007214707,0.0009182614,0.0036535196,0.0010074127,0.0015286156,0.0008190938,0.0006400583,0.0057144267],"category_scores_gemma":[0.048523534,0.00027773264,0.0012471244,0.001439842,0.00038016512,0.0010560694,0.0016225011,0.0013599292,0.0017568776],"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":[0.00089230813,0.0063497145,0.48712313,0.00046071503,0.00010372967,0.00021322668,0.008028223,0.0016022365,0.0054607093,0.0006778334,0.008428114,0.48066002],"study_design_scores_gemma":[0.00031184734,0.008088662,0.9251306,0.00042400236,0.00012228667,0.0006210454,0.009526385,0.019177971,0.016945228,0.0019610608,0.017442834,0.0002480315],"about_ca_topic_score_codex":0.0008315021,"about_ca_topic_score_gemma":0.0018030532,"teacher_disagreement_score":0.014093007,"about_ca_system_score_codex":0.000717095,"about_ca_system_score_gemma":0.0017779936,"threshold_uncertainty_score":0.07453185},"labels":[],"label_agreement":null},{"id":"W4402198693","doi":"10.1080/02602938.2024.2388699","title":"‘There was very little room for me to be me’: the lived tensions between assessment standardisation and student diversity","year":2024,"lang":"en","type":"article","venue":"Assessment & Evaluation in Higher Education","topic":"Higher Education Learning Practices","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":"Ontario Tech University","funders":"Curtin University of Technology","keywords":"Diversity (politics); Pedagogy; Psychology; Higher education; Lived experience; Sociology; Mathematics education; Political science","score_opus":0.19275646327551255,"score_gpt":0.5260661712831748,"score_spread":0.33330970800766224,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402198693","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.97300434,0.00067727023,0.0031535453,0.013633876,0.00015582897,0.000020729536,0.000016377064,0.000029669034,0.009308444],"genre_scores_gemma":[0.9979292,0.00013652122,0.00037269475,0.00054373784,0.00002020575,0.0000111067575,0.000005222539,0.000014173769,0.0009670047],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.97012836,0.02293287,0.0006595258,0.0014881683,0.0029728317,0.0018182194],"domain_scores_gemma":[0.9748497,0.013020729,0.002481102,0.0019952934,0.0022236954,0.005429442],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.016614588,0.00046089228,0.00088487315,0.0014778966,0.019192247,0.012977988,0.002243805,0.0031186263,0.0016131948],"category_scores_gemma":[0.03971044,0.0007471894,0.00045358675,0.0010092686,0.048475314,0.011938105,0.017837007,0.009724039,0.00032898263],"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":[0.000016492855,0.000016353555,0.0018654158,0.000018047127,0.0000038943167,0.00031194108,0.9898453,0.000022026712,0.00023826721,0.004141364,0.00035973944,0.0031612061],"study_design_scores_gemma":[0.000005340992,0.00006157017,0.0022974196,0.00008887988,0.000006424845,0.00061383116,0.9777591,0.000121962774,0.0002755313,0.0047023916,0.014021962,0.000045511097],"about_ca_topic_score_codex":0.006808419,"about_ca_topic_score_gemma":0.0067940233,"teacher_disagreement_score":0.019192247,"about_ca_system_score_codex":0.005573444,"about_ca_system_score_gemma":0.0052230684,"threshold_uncertainty_score":0.08786738},"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":"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":"W4402918453","doi":"10.1080/02602938.2024.2404634","title":"Authentic assessment: from panacea to criticality","year":2024,"lang":"en","type":"article","venue":"Assessment & Evaluation in Higher Education","topic":"Innovations in Medical Education","field":"Medicine","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":"Ontario Tech University","funders":"","keywords":"Panacea (medicine); Psychology; Criticality; Pedagogy; Mathematics education","score_opus":0.0740774940749726,"score_gpt":0.5029731262640805,"score_spread":0.4288956321891079,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4402918453","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":[0.028627101,0.028327143,0.4808098,0.22010694,0.0042007663,0.0009275786,0.00007508133,0.0006242976,0.23630123],"genre_scores_gemma":[0.77876973,0.0147041725,0.16514185,0.020504354,0.0024086053,0.00116122,0.00008195785,0.00049594906,0.016732149],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.8767447,0.095091864,0.004644988,0.0049313568,0.016636783,0.0019502853],"domain_scores_gemma":[0.87339664,0.09313231,0.0062650642,0.012318803,0.010162989,0.0047242255],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.07924443,0.0013155807,0.001180137,0.004889369,0.00797521,0.027772624,0.0030914873,0.0064468747,0.0043903682],"category_scores_gemma":[0.10614947,0.0007937427,0.000796336,0.0022373344,0.094726734,0.033995368,0.030690491,0.014679757,0.001384595],"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":[0.000058747508,0.00005069952,0.00091762043,0.00080154365,0.000023634107,0.00021604342,0.059518084,0.0005338469,0.0007957805,0.85422695,0.0063692993,0.07648761],"study_design_scores_gemma":[0.00002309272,0.000091456895,0.00040642158,0.0021373637,0.000015920601,0.00060029945,0.017991945,0.00095087755,0.0010289764,0.82248175,0.15420242,0.00006942787],"about_ca_topic_score_codex":0.0012100034,"about_ca_topic_score_gemma":0.0011819723,"teacher_disagreement_score":0.07924443,"about_ca_system_score_codex":0.007918889,"about_ca_system_score_gemma":0.012950329,"threshold_uncertainty_score":0.41908962},"labels":[],"label_agreement":null},{"id":"W4404012066","doi":"10.1080/02602938.2024.2419604","title":"The paradox of inclusive assessment","year":2024,"lang":"en","type":"article","venue":"Assessment & Evaluation in Higher Education","topic":"Higher Education Learning Practices","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":"Ontario Tech University","funders":"","keywords":"Psychology; Pedagogy; Higher education; Mathematics education; Evaluation methods; Political science","score_opus":0.07941909821958311,"score_gpt":0.5416770865350428,"score_spread":0.46225798831545967,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4404012066","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":[0.047987346,0.012896507,0.12849441,0.41674292,0.0024934788,0.00017104429,0.00010716389,0.00044235366,0.3906649],"genre_scores_gemma":[0.90595216,0.00435082,0.03309485,0.036899056,0.0015717493,0.00037870108,0.00006476115,0.00032036752,0.017367506],"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","domain_scores_codex":[0.9167755,0.04763058,0.0034033647,0.0060438057,0.02395742,0.0021893347],"domain_scores_gemma":[0.8757449,0.08321344,0.0043310067,0.013109665,0.018145742,0.0054552252],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.06645908,0.0006022941,0.0012829485,0.0032727958,0.007865715,0.017553654,0.0019661167,0.005525949,0.00450645],"category_scores_gemma":[0.1127488,0.00061352394,0.00085353275,0.0021967764,0.047373556,0.025606366,0.02001418,0.013671913,0.0013211658],"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":[0.00003843328,0.000034842513,0.0011653026,0.00013169822,0.000014987181,0.00009630655,0.007024622,0.00035987832,0.00017605079,0.9435461,0.0069542667,0.040457446],"study_design_scores_gemma":[0.000023508035,0.000033244407,0.00065650087,0.000265296,0.000009090526,0.0001879724,0.0023724644,0.0007728204,0.0002436114,0.92542464,0.06997424,0.000036572234],"about_ca_topic_score_codex":0.0026354252,"about_ca_topic_score_gemma":0.002251212,"teacher_disagreement_score":0.06645908,"about_ca_system_score_codex":0.0074121435,"about_ca_system_score_gemma":0.010478857,"threshold_uncertainty_score":0.3514734},"labels":[],"label_agreement":null},{"id":"W4407793778","doi":"10.1080/02602938.2025.2467647","title":"Self-assessment design in a digital world: centring student agency","year":2025,"lang":"en","type":"article","venue":"Assessment & Evaluation in Higher Education","topic":"Innovative Teaching and Learning Methods","field":"Psychology","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":"Ontario Tech University","funders":"","keywords":"Centring; Agency (philosophy); Pedagogy; Psychology; Higher education; Mathematics education; Sociology; Engineering; Political science; Social science","score_opus":0.10112696830078945,"score_gpt":0.5256117004833262,"score_spread":0.42448473218253674,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4407793778","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":[0.3363683,0.00087877666,0.5232602,0.0081599625,0.00041020953,0.0023388788,0.00010064051,0.0010463459,0.12743676],"genre_scores_gemma":[0.81883115,0.0003357687,0.16786571,0.00084544567,0.00005443293,0.001625047,0.00006764255,0.000118023934,0.010256763],"study_design_codex":"design_other","study_design_gemma":"not_applicable","domain_scores_codex":[0.9755425,0.019115722,0.0010572821,0.00151007,0.0022508046,0.0005236885],"domain_scores_gemma":[0.97820014,0.0119617935,0.0015328466,0.002966472,0.0030144174,0.0023244193],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.016618937,0.0005049991,0.00045753308,0.0013141512,0.0017562348,0.008709989,0.0014250475,0.001172135,0.0073638246],"category_scores_gemma":[0.034020808,0.00036025778,0.00055605924,0.00066754344,0.005350207,0.0050971527,0.0064940476,0.0015751281,0.0013447829],"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":[0.0007836929,0.0017960736,0.023425456,0.0011974543,0.00012679926,0.0005809627,0.11118752,0.0063627865,0.009112575,0.33064833,0.006901024,0.5078774],"study_design_scores_gemma":[0.0010899237,0.0040174196,0.018265119,0.0021472261,0.00026759983,0.0014957789,0.06291333,0.045731645,0.021090059,0.4918567,0.35076475,0.00036058598],"about_ca_topic_score_codex":0.0003938905,"about_ca_topic_score_gemma":0.00060674903,"teacher_disagreement_score":0.016618937,"about_ca_system_score_codex":0.0021679169,"about_ca_system_score_gemma":0.0029322517,"threshold_uncertainty_score":0.08789039},"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":"W4411690222","doi":"10.1080/02602938.2025.2523598","title":"Open book assessment: performance and student perceptions in a UK veterinary programme","year":2025,"lang":"en","type":"article","venue":"Assessment & Evaluation in Higher Education","topic":"Innovations in Medical Education","field":"Medicine","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":"Perception; Psychology; Medical education; Pedagogy; Medicine","score_opus":0.08350136233889723,"score_gpt":0.5151767344608628,"score_spread":0.43167537212196555,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4411690222","genre_codex":"empirical","genre_gemma":"empirical","domain_codex":null,"domain_gemma":null,"model_version":"metacan-v3-hybrid-931329e0061c","genre_candidate":"empirical","genre_consensus":"empirical","domain_candidate":null,"domain_consensus":null,"prediction_status":"machine_predicted_unvalidated","genre_scores_codex":[0.99855417,0.000101650796,0.000070490125,0.00037105486,0.000016601034,0.000016480124,0.000014623421,0.000005427032,0.0008495118],"genre_scores_gemma":[0.9990514,0.00010934178,0.000101997175,0.00009795157,0.000008282484,0.000010518982,0.000013292599,0.0000031584552,0.00060406554],"study_design_codex":"observational","study_design_gemma":"observational","domain_scores_codex":[0.99126184,0.003066969,0.0006581003,0.00052643276,0.0033008591,0.0011857882],"domain_scores_gemma":[0.97571665,0.005637377,0.0063127074,0.0004035991,0.0041622748,0.007767289],"candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0072421613,0.00031178063,0.00050459465,0.0012813916,0.0017077032,0.0054520434,0.000721907,0.0008971765,0.0028149677],"category_scores_gemma":[0.02639368,0.00034273902,0.00052281626,0.0009403393,0.0023637523,0.0017597903,0.0035992314,0.0020560394,0.0007635109],"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":[0.0007058503,0.0037534593,0.6903182,0.00045716335,0.000079827594,0.0017830164,0.2065351,0.00041099562,0.0034657477,0.0004685879,0.003487855,0.08853424],"study_design_scores_gemma":[0.00003134965,0.007148416,0.6821506,0.00036069466,0.000039016424,0.0013515374,0.2977913,0.000882698,0.0017712496,0.00035371262,0.007956406,0.00016303312],"about_ca_topic_score_codex":0.0053004217,"about_ca_topic_score_gemma":0.006071828,"teacher_disagreement_score":0.0072421613,"about_ca_system_score_codex":0.0020537456,"about_ca_system_score_gemma":0.0018902879,"threshold_uncertainty_score":0.038300633},"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":"W4416613148","doi":"10.1080/02602938.2025.2587246","title":"What should we be assessing exactly? Higher education staff narratives on gen AI integration of assessment in a postplagiarism era","year":2025,"lang":"en","type":"article","venue":"Assessment & Evaluation in Higher Education","topic":"Academic integrity and plagiarism","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":"Calgary Laboratory Services; Brock University; University of Calgary","funders":"","keywords":"Higher education; Narrative; Qualitative research; Professional development; Semi-structured interview; Focus group; Educational assessment","score_opus":0.11281127226536691,"score_gpt":0.49540280718684077,"score_spread":0.38259153492147385,"validation_status":"score_only:v0-immature-baseline","prediction":{"id":"W4416613148","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":[0.83311456,0.002384093,0.01826515,0.11382619,0.00054437644,0.00013044493,0.00007812225,0.00012505955,0.03153202],"genre_scores_gemma":[0.9936836,0.00034595846,0.0013613048,0.0022725759,0.00003635046,0.000035520934,0.000010537184,0.000025655037,0.0022284915],"study_design_codex":"qualitative","study_design_gemma":"qualitative","domain_scores_codex":[0.9396603,0.048255596,0.0021830217,0.0019523418,0.004668076,0.0032807041],"domain_scores_gemma":[0.89935464,0.07342859,0.007970442,0.0031821746,0.008671414,0.007392831],"candidate_categories":["metaresearch","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.05306284,0.0006265362,0.00062993175,0.0015951305,0.018732905,0.011245144,0.0018385086,0.0042322725,0.0014310014],"category_scores_gemma":[0.08082472,0.0006648882,0.00030733377,0.0014158727,0.03369857,0.012013602,0.013041342,0.0095569305,0.0003556586],"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":[0.000017520515,0.000014802179,0.0016269144,0.000058255147,0.0000019900972,0.00036632287,0.9755494,0.000054606622,0.00030465526,0.016139742,0.0010776911,0.0047881096],"study_design_scores_gemma":[0.000004135424,0.00003951368,0.001401852,0.00033406937,0.0000044561684,0.00033069198,0.9397187,0.00027320298,0.00086276274,0.008071923,0.048927065,0.000031621556],"about_ca_topic_score_codex":0.008130379,"about_ca_topic_score_gemma":0.009514097,"teacher_disagreement_score":0.9957677,"about_ca_system_score_codex":0.015550612,"about_ca_system_score_gemma":0.011905431,"threshold_uncertainty_score":0.28062648},"labels":[],"label_agreement":null}]}